Model monitoring methods, devices, chip systems, storage media, and software products

Abstract

This application provides a model monitoring method, apparatus, chip system, storage medium, and program product, relating to the field of communication technology. The method includes: a terminal device receiving M signals for positioning from M access network devices; and determining whether a first model can be used for positioning based on a first quantity and N, where N is the number of signals sent by the access network devices required for the first model to be positioned, and the first quantity is the number of devices among the M access network devices that can be used for positioning, determined based on a first indicator and / or a second indicator. The first indicator indicates whether the positioning results output by the first model using first measurement data corresponding to any N signals from the M signals are consistent; the second indicator includes at least two of the following: signal quality, direct path measurement quality, timing measurement quality, and consistency quality. In this way, the terminal device can monitor the performance of the first model used for positioning without relying on tags, and it is applicable to a wide range of scenarios.

Description

Technical Field

[0001] This application relates to the field of communication technology, and in particular to model monitoring methods, devices, chip systems, storage media and program products. Background Technology

[0002] Currently, terminal devices can perform positioning based on positioning models. The performance of the positioning model is a key factor affecting the accuracy of positioning results; therefore, performance monitoring of positioning models has received widespread attention. In one possible implementation, the network side can obtain the actual position of the positioning reference unit (PRU) (such as a tag), as well as the position of the PRU output by the positioning model. The performance of the positioning model can then be evaluated based on this actual position and the position output by the positioning model.

[0003] However, this approach relies on the actual location of the PRU. In some scenarios, the network side may not be able to obtain the actual location of the PRU, thus making it impossible to evaluate model performance. Summary of the Invention

[0004] This application provides a model monitoring method, device, chip system, storage medium, and program product, which are applied in the field of communication technology. The terminal device can effectively evaluate the performance of the positioning model without relying on tags, making the method applicable to scenarios where tags are scarce or difficult to obtain.

[0005] Firstly, this application proposes a model monitoring method. The method includes: receiving M signals from M access network devices, the M signals being used for positioning; determining whether a first model can be used for positioning based on a first quantity and N, where N is the number of signals sent by the access network devices required for the first model to perform positioning; wherein the first quantity is the number of access network devices among the M that can be used for positioning, the first quantity being determined based on a first indicator and / or a second indicator corresponding to each of the M access network devices, the first indicator indicating the consistency between the positioning results output by the first model based on first measurement data of any N signals among the M signals, and the second indicator including at least two of the following: signal quality, direct path measurement quality, timing measurement quality, or consistency quality; consistency quality indicating the consistency between the second measurement data of each signal among the M signals and the second measurement data of the training data, and timing measurement quality indicating whether the time difference of arrival is within a first range.

[0006] In one possible implementation, the method is executed by a terminal device. The terminal device can be the terminal equipment itself, or a component applied in the terminal equipment (e.g., a chip, chip system, circuit, software and / or hardware module, etc.).

[0007] Among them, the M signals can be, for example, positioning signals such as DL-PRS, other reference signals, or communication signals. For access network device i among the M access network devices, access network device i sends signal i (i.e., signal i) to the terminal device; correspondingly, the terminal device receives signal i from access network device i, where i is an integer greater than or equal to 1 and less than or equal to M.

[0008] The first metric can be understood as an indicator reflecting the stability of the output parameters of the first model, aiming to evaluate the consistency among multiple positioning results calculated by the first model based on different signal combinations. The second metric can be understood as a multi-dimensional quality standard used to individually evaluate the signals transmitted by each access network device.

[0009] The model monitoring method proposed in this application determines the availability of a first model by comparing the number of available signals with the minimum number of signals N required by the positioning model. This method not only evaluates the model's own performance but also makes comprehensive decisions based on the real-time positioning environment of the terminal, thereby significantly improving the comprehensiveness and reliability of the model monitoring results. Furthermore, since the model reliability assessment can be completed without relying on external labels, this method has stronger scene adaptability and is suitable for application scenarios in label-free or weakly labeled environments.

[0010] In one possible implementation, the second measurement data includes one or more of the following: Doppler shift, signal strength, carrier phase, or multipath delay.

[0011] It should be understood that consistency quality can be interpreted as an indicator used to evaluate the consistency between the signal measurement environment and the model training environment. Therefore, consistency quality can be determined by the consistency between some evaluation indicators obtained from signal measurement (second measurement data) and some evaluation indicators of training data (second measurement data).

[0012] In this way, the consistency quality index can be used to quantitatively evaluate the consistency between the signal measurement environment and the model training environment.

[0013] In one possible implementation, the consistency quality is determined based on one or more of the following metrics: Doppler shift quality, signal strength quality, carrier phase quality, or multipath delay quality; wherein, Doppler shift quality is used to indicate the consistency of the Doppler shift of each of the M signals with the Doppler shift of the training data, signal strength quality is used to indicate the consistency of the signal strength of each of the M signals with the signal strength of the training data, carrier phase quality is used to indicate the consistency of the carrier phase of each of the M signals with the carrier phase of the training data, and multipath delay quality is used to indicate the consistency of the multipath delay of each of the M signals with the multipath delay of the training data.

[0014] In this way, by integrating multiple quality indicators such as Doppler frequency shift, signal strength, carrier phase or multipath delay, it is possible to comprehensively perceive changes in factors such as the motion state of the terminal device, signal propagation conditions, phase stability and multipath interference. This allows the consistency quality to reflect the consistency between the signal measurement environment and the model training environment, thereby reflecting the degree of adaptation between the first model and the current environment (signal measurement environment) of the terminal device. This allows the consistency quality to reflect whether the first model is suitable for positioning the terminal device.

[0015] In one possible implementation, the Doppler shift quality is calculated based on the standard deviation of the Doppler shift of each of the M signals and the standard deviation of the Doppler shift of the training data, and / or the average value of the Doppler shift of each of the M signals and the average value of the Doppler shift of the training data; the signal strength quality is calculated based on the standard deviation of the signal strength of each of the M signals and the standard deviation of the signal strength of the training data, and / or the average value of the signal strength of each of the M signals and the average value of the signal strength of the training data; the carrier phase quality is calculated based on the standard deviation of the carrier phase of each of the M signals and the standard deviation of the carrier phase of the training data, and / or the average value of the carrier phase of each of the M signals and the average value of the carrier phase of the training data; or, the multipath delay quality is calculated based on the standard deviation of the multipath delay of each of the M signals and the standard deviation of the multipath delay of the training data, and / or the average value of the multipath delay of each of the M signals and the average value of the multipath delay of the training data.

[0016] In this way, by comparing the standard deviation and mean of the measurement data and the training data respectively, the consistency between the current environment (signal measurement environment) of the terminal device and the model training environment can be reflected.

[0017] In one possible implementation, the first quantity is determined based on a first indicator and / or a second indicator corresponding to each of the M access network devices, including: the first quantity is determined based on a weighted average of the first indicator and the second indicator.

[0018] In this way, the terminal device combines the stability of the output parameters of the first model with the signal quality of a single access network device (i.e., the quality of the input parameters) to determine the model performance of the first model, resulting in high reliability of the model monitoring results.

[0019] In one possible implementation, the weighted average of the first and second indicators corresponding to the M access network devices that can be used for positioning is greater than or equal to a first threshold.

[0020] The first threshold can be understood as the minimum value required to determine whether a single access network device can be used for positioning. This threshold is used to assess whether the access network device meets reliability standards in terms of signal quality and model output stability. The first metric can be the same for all access network devices.

[0021] In this way, by setting a first threshold to evaluate access network devices, the accurate screening of available access network devices can be achieved, which can improve the reliability of model performance monitoring results.

[0022] In one possible implementation, determining whether a first model can be used for positioning based on a first quantity and N includes: determining that the first model cannot be used for positioning if the first quantity is less than N; and determining that the first model can be used for positioning if the first quantity is greater than or equal to N.

[0023] In this way, by comparing the number of available access network devices (i.e., the first number) with the minimum number required by the first model (i.e., N), it is possible to efficiently and accurately determine whether the first model can be used to locate terminal devices in the current environment.

[0024] In one possible implementation, if the first model cannot be used for positioning, first information is sent to the first network element, the first information indicating a first number of access network devices that can be used for positioning.

[0025] The first network element is, for example, an LMF (or LMF network element).

[0026] In this way, when the terminal device determines that the first model is unavailable, it sends the first information to the first network element, thereby enabling the first network element to obtain the specific number of access network devices that can be used for positioning.

[0027] In one possible implementation, if the first model can be used for positioning, second information is sent to the first network element. The second information is used to indicate the positioning result. The positioning result is obtained by inputting first measurement data of N signals out of M signals into the first model. The N signals are signals sent by the access network devices that can be used for positioning among the M access network devices.

[0028] The second information can be understood as the positioning result report sent by the terminal device to the first network element, including the positioning result output by the first model.

[0029] In this way, the first network element can determine that the first model can be used for positioning, and can also determine the positioning result.

[0030] In one possible implementation, the second information is also used to indicate the confidence level of the first model, which is determined based on the first quantity and M.

[0031] The confidence level of the first model can be understood as a quantitative assessment of the reliability of the positioning results output by the first model.

[0032] In this way, the confidence level of the first model enables the first network element to determine the reliability of the positioning result.

[0033] In one possible implementation, the confidence level is determined based on a first quantity and M, and a first index and / or a second index corresponding to each of the M access network devices.

[0034] It should be understood that, if the terminal device determines that the first model is available, the terminal device can calculate the confidence level of the first model.

[0035] Secondly, this application proposes a model monitoring method. The method includes: receiving a first request from a terminal device, the first request being used to request monitoring of whether a first model is valid, the first model being used for positioning, and the first model requiring signals sent by N access network devices for positioning, the signals being used for positioning, where N is a positive integer; based on the first request, sending third information to M access network devices respectively, the third information being used to instruct the sending of signals to the terminal device, where M is an integer greater than N; and receiving first information from the terminal device; wherein the first information is used to indicate which of the M access network devices can be used for positioning.

[0036] In one possible implementation, the method is performed by a core network device. The core network device can be the core network equipment itself, or a component applied within the core network equipment (e.g., a chip, chip system, circuitry, software, and / or hardware module, etc.). For example, a core network device is an LMF (Low-Level Function).

[0037] In one possible implementation, a fourth message is sent to each of the M access network devices. The fourth message is used to indicate the order in which the M access network devices send signals to the terminal device. The first message includes a bit map, where each bit in the bit map is used to indicate whether one of the M access network devices can be used for positioning. The order in which the bits in the bit map indicate whether the M access network devices can be used for positioning is the same as the order indicated by the third message.

[0038] Thirdly, this application provides a communication device that can be used to execute the model monitoring method of the first or second aspect. The communication device can be a terminal device or a core network device, or a component (e.g., a chip, a chip system, or a circuit, such as a circuit or chip responsible for communication functions in a terminal device (e.g., a modem chip, also known as a baseband chip, or a system-on-chip (SoC) chip or system-in-package (SIP) chip containing a modem core)) in the terminal device or a device that can be used in conjunction with a terminal device or a core network device. It can also be a logic module or software that can implement all or part of the functions of a terminal device or a core network device.

[0039] In one possible implementation, the communication device may include modules or units that perform the methods / operations / steps / actions described in the first or second aspect. These modules or units may be hardware circuits, software, or a combination of hardware circuits and software.

[0040] Fourthly, this application provides another communication device, including a processor and a memory, wherein the memory is used to store computer-executable instructions, and the processor is used to run the computer-executable instructions stored in the memory to perform the methods described in the first aspect or any possible implementation of the first aspect, or the second aspect or any possible implementation of the second aspect.

[0041] Fifthly, this application provides a computer-readable storage medium storing a computer program or instructions that, when executed on a computer, cause the computer to perform the methods described in the first aspect or any possible implementation thereof, or the second aspect or any possible implementation thereof.

[0042] Sixthly, this application provides a computer program product including a computer program, which, when run, causes the computer to perform the methods described in the first aspect or any possible implementation of the first aspect, or the second aspect or any possible implementation of the second aspect.

[0043] Seventhly, this application provides a chip or chip system including at least one processor and a communication interface. The communication interface and the at least one processor are interconnected via a circuit. The at least one processor is used to run computer programs or instructions to perform the methods described in the first aspect or any possible implementation of the first aspect, or the second aspect or any possible implementation of the second aspect. The communication interface in the chip can be an input / output interface, pins, or circuits, etc.

[0044] In one possible implementation, the chip or chip system described above in this application further includes at least one memory storing instructions. The memory can be an internal storage unit of the chip, such as a register or cache, or it can be a storage unit of the chip itself (e.g., read-only memory, random access memory, etc.).

[0045] It should be understood that the second to seventh aspects of this application correspond to the technical solutions of the first aspect of this application, and the beneficial effects achieved by each aspect and the corresponding feasible implementation are similar, and will not be repeated here. Attached Figure Description

[0046] Figure 1 A schematic diagram of the communication system 100 provided in an embodiment of this application;

[0047] Figure 2 A schematic flowchart of the model monitoring method 200 provided in the embodiments of this application;

[0048] Figure 3 A flowchart illustrating the model availability determination method 300 provided in this application embodiment;

[0049] Figure 4 A flowchart illustrating the method 400 for determining a valid status code provided in this application embodiment;

[0050] Figure 5 A schematic diagram illustrating the determination of a valid status code sequence provided in an embodiment of this application;

[0051] Figure 6 A schematic diagram illustrating the process of determining the availability of a first model based on a valid status code sequence, provided in an embodiment of this application;

[0052] Figure 7 A schematic diagram illustrating the process of determining the unavailability of the first model based on a valid status code sequence, provided in an embodiment of this application;

[0053] Figure 8 A flowchart illustrating the positioning method 800 provided in an embodiment of this application;

[0054] Figure 9Schematic block diagram of a model monitoring device provided by an embodiment of the present application;

[0055] Figure 10 Schematic block diagram of another model monitoring device provided by an embodiment of the present application. Detailed implementation manners

[0056] Next, the technical solutions in the present application will be described in conjunction with the accompanying drawings.

[0057] For the convenience of understanding the embodiments of the present application, the following points are first explained:

[0058] First, in some embodiments provided by the present application, terms such as "first" and "second" are used to distinguish identical or similar items with basically the same functions and effects. For example, the first value and the second value are only used to distinguish different values, and do not limit their order. Those skilled in the art can understand that terms such as "first" and "second" do not limit the quantity and execution order, and the terms "first" and "second" do not necessarily limit being different.

[0059] It should be noted that in the embodiments of the present application, words such as "exemplarily" or "for example" are used to represent examples, illustrations or explanations. Any embodiment or design solution described as "exemplarily" or "for example" in the present application should not be construed as being more preferred or more advantageous than other embodiments or design solutions. Exactly speaking, using words such as "exemplarily" or "for example" aims to present relevant concepts in a specific manner.

[0060] In the embodiments of the present application, "at least one" means one or more, and "a plurality" means two or more. "And / or" describes the association relationship of associated objects, indicating that there can be three relationships. For example, A and / or B can represent: A exists alone, A and B exist simultaneously, and B exists alone, where A and B can be singular or plural. The character " / " generally represents that the front and rear associated objects are in an "or" relationship. "At least one (item)" or its similar expression refers to any combination of these items, including any combination of single item (item) or plural items (items). For example, at least one (item) of a, b, or c can represent: a, b, c, a - b, a - c, b - c, or a - b - c, where a, b, c can be single or multiple.

[0061] Second, for the convenience of understanding, multiple examples of information or indication information are provided herein, such as the first indication information, the second indication information, etc. The order of transmission and the names of these information are all examples and should not constitute any limitation to the present application.

[0062] Third, in the embodiments of this application, "instruction" can include direct instruction and indirect instruction, as well as explicit instruction and implicit instruction. The information indicated by a certain piece of information (hereinafter referred to as instruction information) is called the information to be instructed. In the specific implementation process, there are many ways to indicate the information to be instructed, such as, but not limited to, directly indicating the information to be instructed, such as the information to be instructed itself or its index. It can also indirectly indicate the information to be instructed by indicating other information, where there is a correlation between the other information and the information to be instructed; or it can only indicate a part of the information to be instructed, while the other parts of the information to be indicated are known or pre-agreed upon. For example, the instruction of specific information can be achieved by using a pre-agreed (e.g., protocol predefined) arrangement order of various pieces of information, thereby reducing the instruction overhead to a certain extent. This application does not limit the specific method of instruction.

[0063] Fourth, in the embodiments of this application, descriptions such as "when," "under the circumstances," "if," and "if" all refer to the fact that the device (e.g., network device or terminal device) will make corresponding processing under certain objective circumstances. They are not time limits, nor do they require the device (e.g., network device or terminal device) to make a judgment action when implementing it, nor do they imply any other limitations.

[0064] Fifth, the predefined terms in this application can be understood as: definition, pre-defined, storage, pre-storage, pre-negotiation, pre-configuration, solidification, or pre-firing.

[0065] Sixth, the technical solutions of the embodiments of this application can be applied to various communication systems, such as: Long Term Evolution (LTE) system, LTE Frequency Division Duplex (FDD) system, LTE Time Division Duplex (TDD) system, Universal Mobile Telecommunication System (UMTS), Worldwide Interoperability for Microwave Access (WiMAX) system, 5th Generation (5G) system or New Radio (NR) system, and future evolution communication systems, such as 6th Generation (6G) system, etc.

[0066] Seventh, the terminal equipment in the embodiments of this application may also be referred to as: user equipment (UE), mobile station (MS), mobile terminal (MT), access terminal, user unit, user station, mobile station, mobile station, remote station, remote terminal, mobile device, user terminal, terminal, wireless communication equipment, user agent or user device, etc.

[0067] The terminal devices in this application embodiment may include handheld devices with communication functions, vehicle-mounted devices, etc. For example, some electronic devices include: mobile phones, tablets, PDAs, laptops, mobile internet devices (MIDs), wearable devices, virtual reality (VR) devices, augmented reality (AR) devices, wireless terminals in industrial control, wireless terminals in self-driving, wireless terminals in remote medical surgery, wireless terminals in smart grids, wireless terminals in transportation safety, wireless terminals in smart cities, wireless terminals in smart homes, cellular phones, cordless phones, session initiation protocol (SIP) phones, wireless local loop (WLL) stations, personal digital assistants (PDAs), handheld devices with wireless communication capabilities, computing devices or other processing devices connected to wireless modems, in-vehicle devices, wearable devices, terminal devices in 5G networks, or future evolution of public land mobile communication networks. Terminal devices in a network (PLMN), etc., are not limited to this in the embodiments of this application.

[0068] By way of example and not limitation, in this embodiment, the electronic device can also be a wearable device. Wearable devices, also known as wearable smart devices, are a general term for devices that utilize wearable technology to intelligently design and develop everyday wearables, such as glasses, gloves, watches, clothing, and shoes. Wearable devices are portable devices that are worn directly on the body or integrated into the user's clothing or accessories. Wearable devices are not merely hardware devices, but also achieve powerful functions through software support, data interaction, and cloud interaction. Broadly speaking, wearable smart devices include those that are feature-rich, large in size, and can achieve complete or partial functions without relying on a smartphone, such as smartwatches or smart glasses, as well as those that focus on a specific type of application function and require the use of other devices such as smartphones, such as various smart bracelets and smart jewelry for vital sign monitoring.

[0069] Furthermore, in this embodiment of the application, the electronic device can also be a terminal device in the Internet of Things (IoT) system. IoT is an important part of the future development of information technology. Its main technical feature is to connect objects to the network through communication technology, thereby realizing an intelligent network of human-machine interconnection and object-to-object interconnection.

[0070] Eighth, the network devices in the embodiments of this application may include access network devices.

[0071] Access network equipment can be any device with wireless transceiver capabilities. Access network equipment includes, but is not limited to: evolved Node B (eNB), radio network controller (RNC), Node B (NB), base station controller (BSC), base transceiver station (BTS), home base station (e.g., home evolved Node B, or home Node B, HNB), baseband unit (BBU), access point (AP), wireless relay node, wireless backhaul node, transmission point (TP), or transmission and reception point (TRP) in a wireless fidelity (WiFi) system. It can also be a 5G base station (next-generation Node B, gNB) in a 5G system, such as NR, or a transmission point (TRP or TP), one or a group of antenna panels (including multiple antenna panels) of a base station in a 5G system, or a network node constituting a gNB or transmission point, such as a baseband unit (BBU) or a distributed unit (DU).

[0072] In some deployments, a gNB may include a centralized unit (CU) and a dedicated unit (DU). A gNB may also include an active antenna unit (AAU). The CU implements some of the gNB's functions, and the DU implements others. For example, the CU can handle non-real-time protocols and services, such as implementing the functions of the radio resource control (RRC) layer, the service data adaptation protocol (SDAP) layer, and / or the packet data convergence protocol (PDCP) layer. The DU can handle physical layer protocols and real-time services, such as implementing the functions of the radio link control (RLC) layer, the media access control (MAC) layer, and the physical (PHY) layer. A DU can connect to only one CU or to multiple CUs, while a CU can connect to multiple DUs. Communication between CUs and DUs can be achieved via the F1 interface. The AAU can implement some physical layer processing functions, radio frequency processing, and active antenna-related functions. Since the information from the RRC layer is ultimately delivered to the PHY layer and thus becomes PHY layer information, or is transformed from PHY layer information, in this architecture, higher-level signaling, such as RRC layer signaling, can also be considered as being sent by the DU, or by the DU+AAU.

[0073] It is understood that access network equipment can be one or more of the following: CU nodes, DU nodes, and AAU nodes. Furthermore, a CU can be classified as an access network device in the radio access network (RAN) or as an access network device in the core network (CN); this application does not limit this classification.

[0074] The network device in this application embodiment may further include core network device. The core network device in this application embodiment may be the core network device in a 4G system, the core network device in a 5G system, or the core network device in a future communication system. This application embodiment does not limit this.

[0075] To facilitate a clear description of the technical solutions in the embodiments of this application, some terms and technologies involved in the embodiments of this application will be briefly introduced below:

[0076] 1. Doppler frequency shift

[0077] Doppler shift refers to the phenomenon where the frequency of the wireless signal received by the receiver deviates from the frequency of the wireless signal transmitted by the transmitter due to the relative motion between the transmitter (such as a base station) and the receiver (such as a terminal device).

[0078] 2. Carrier phase

[0079] Carrier phase describes the phase state of a carrier signal at a given moment in wireless communication. During wireless communication, the information to be transmitted is modulated onto a high-frequency carrier wave, which is typically represented as a sine wave.

[0080] For example, assume the carrier is ,in That is, the carrier phase (f is the carrier frequency, t is the time). (This is the initial phase). This parameter reflects the precise position of the sine wave within one period: a phase of 0 corresponds to the start of the waveform. Corresponding to the peak, Corresponding to the midpoint of the waveform, Corresponding to the trough, after completing a full cycle, the phase returns to its original position. It is equivalent to phase 0.

[0081] 3. Multipath delay

[0082] Multipath delay refers to the time difference that occurs when a wireless signal is transmitted from the transmitter to the receiver via different paths such as direct transmission, reflection, or scattering, and the signals from each path arrive at the receiver at different times due to their different propagation distances.

[0083] To facilitate understanding of the embodiments of this application, the following is combined with... Figure 1 The communication system applicable to the embodiments of this application will be described in detail.

[0084] Figure 1 A schematic diagram of a communication system 100 applying an embodiment of this application is shown. The communication system 100 includes an access network and a core network.

[0085] The access network includes at least one access network device, such as Figure 1 The access network devices 110, 120, and 130 are shown; the access network also includes at least one terminal device, such as... Figure 1 The terminal device 140 shown.

[0086] In this context, core network equipment in the core network can connect to access network equipment wirelessly or via wired means, while terminal equipment, when within the coverage area of ​​access network equipment, can connect to access network equipment wirelessly.

[0087] In some possible scenarios, the terminal device may be within the coverage area of ​​multiple access network devices, enabling the terminal device to receive signals from multiple access network devices.

[0088] For example, such as Figure 1 As shown, within the coverage area of ​​access network devices 110, 120, and 130, terminal device 140 can communicate with access network devices 110, 120, and 130 via wireless links. For example, terminal device 140 can receive downlink signals from access network devices 110, 120, and 130 respectively.

[0089] It should be understood that Figure 1 The various communication devices shown can be configured with multiple antennas, which may include at least one transmitting antenna for transmitting signals and at least one receiving antenna for receiving signals. Additionally, Figure 1 The various communication devices illustrated may also include transmitter chains and receiver chains, which, as will be understood by those skilled in the art, can all include multiple components (e.g., processors, modulators, multiplexers, demodulators, demultiplexers, or antennas) related to signal transmission and reception. Therefore, access network equipment and terminal equipment can communicate via multi-antenna technology.

[0090] It should also be noted that terminal device 140 can also communicate with core network equipment through access network equipment 110, access network equipment 120, or access network equipment 130. For example, if terminal device 140 establishes a wireless communication connection with access network equipment 110, then terminal device 140 can communicate with core network equipment through access network equipment 110.

[0091] The core network's main functions are to provide user connections, manage users, and carry out service provision, serving as the interface to external networks. User connection establishment includes functions such as mobility management (MM), call management (CM), switching / routing, and recording notifications (which, in conjunction with intelligent network services, establishes connections to peripheral intelligent network devices).

[0092] It's understandable that the core network of a 4G network is an evolved packet core (EPC) network. The EPC network is the core network of a 4G mobile communication network. It falls under the core network category and possesses traditional mobile network capabilities such as user subscription data storage, mobility management, and data exchange, while providing users with an ultra-high-speed internet experience. The core network of a 5G network is the 5G Core (which can be abbreviated as 5GC). 5GC will use general-purpose network function virtualization equipment to replace the dedicated communication equipment of the 4G network.

[0093] It should be noted that, Figure 1 The core network in the network architecture shown can be obtained by merging EPC and 5GC. That is, the core network in this network architecture can include network elements from both EPC and 5GC. For example, the core network in this network architecture can include location management function (LMF) network elements, access and mobility management function (AMF) network elements, mobility management entity (MME) network elements, serving gate way (SGW) network elements, packet data network gate way (PGW) network elements, session management function (SMF) network elements, user plane function (UPF) network elements, unified data management (UDM) network elements, and home subscriber server (HSS) network elements, etc.

[0094] In some embodiments of this application, the core network in this network architecture may include fused network elements derived from network elements in EPC and 5GC. Examples include SMF+PGW-C, UPF+PGW-U, UDM+HSS, etc. Here, PGW-C is the control plane node of the PGW network element, and PGW-U is the user plane node of the PGW network element.

[0095] Each network element in the core network can also be called a functional entity. It can be a network element implemented on dedicated hardware, a software instance running on dedicated hardware, or an instance of virtualized function on an appropriate platform.

[0096] It should be understood that all network element names in this application are merely examples. In future communications, such as 6G, they may be referred to by other names, or in future communications, such as 6G, the network elements involved in this application may be replaced by other entities or devices with the same function, etc., and this application does not limit them in any way. This is a unified explanation here and will not be repeated hereafter. Optionally, the various network elements in the embodiments of this application may be communication devices, or chips or chip systems that can be used in the communication devices, etc., and this application does not limit them in any way.

[0097] Understandable Figure 1 The core network in the network architecture shown may also include other devices, network elements, network entities, or network subsystems, such as policy control function (PCF) network elements, which are not limited in this application. It should be noted that this application does not limit the distribution of each network element in the core network; the specific distribution method can be found in relevant technical documents, which will not be elaborated here.

[0098] It should be understood that Figure 1 This is merely an illustration and does not limit the specific architecture of the applicable system. The communication system 100 may also include other network devices, such as wireless relay devices and wireless backhaul devices. Figure 1 The components are not shown in the diagram. This application does not limit the number or specific form of the core network equipment, access network equipment, and terminal equipment included in the communication system 100.

[0099] Optionally, the communication system 100 may also include other network entities such as a network controller and a mobility management entity, but the embodiments of this application are not limited thereto.

[0100] It should be noted that in the following embodiments of this application, the information interaction between the terminal device and the core network device can be achieved through the access network device. In order to make the description more concise, the access network device in the information interaction process between the terminal device and the core network device will not be described in the following text.

[0101] With the increasing number of terminal devices, higher demands are being placed on the real-time performance and accuracy of location services. Currently, the methods for locating terminal devices include the following three:

[0102] Method (1): The terminal device achieves positioning or assisted positioning through artificial intelligence (AI) / machine learning (ML).

[0103] Method (2): The terminal device provides auxiliary information to the LMF, and the LMF determines the location of the terminal device based on the auxiliary information.

[0104] Method (3): The access network device (such as gNB) provides auxiliary information to the LMF, and the LMF determines the location of the terminal device based on the auxiliary information.

[0105] In method (1), the performance of the positioning model (AI model or ML model) deployed in the terminal device is crucial to the positioning accuracy. Therefore, monitoring the performance of the positioning model is of great significance.

[0106] Monitoring of localization models is mainly divided into two methods: labeled (truth-dependent) monitoring and unlabeled monitoring.

[0107] Among them, the tag-based monitoring method relies on ground truth tags, that is, the actual location information of the terminal device or the accurate reference location. The accurate reference location is, for example, the accurate location of the deployed positioning reference unit (PRU).

[0108] However, due to the fact that terminal devices are usually mobile and the wireless measurement environment is dynamically changing, and the deployment cost of PRUs is high, it is often difficult to obtain high-precision ground truth labels. Using unreliable labels for monitoring can introduce errors and distort the model evaluation results. Therefore, in practical applications, label-free monitoring methods are widely used.

[0109] When using label-free monitoring to monitor the performance of a localization model, one possible implementation is as follows:

[0110] S10, the terminal device sends relative displacement information (referred to as relative information 1) obtained by it based on its built-in sensors (such as an inertial measurement unit) to the network device. Correspondingly, the network device receives relative information 1 from the terminal device.

[0111] For example, relative information 1 could be the relative displacement information of the terminal device between its position at time 1 and its position at time 2.

[0112] S20. The network device obtains the positioning results (i.e., relative information 2) of the positioning model at the same time. Based on the position of the terminal device at time 1 and the position of the terminal device at time 2, the relative information 2 between the two positions can be determined. The relative information 2 is the relative displacement information between the two positions.

[0113] Finally, the network device compares relative information 1 with relative information 2, and evaluates the performance of the positioning model by quantifying the difference between the two.

[0114] However, this monitoring method relies on the error between relative information 1 and relative information 2, and can only reflect the accuracy of the positioning model's output. The positioning model's output is not only affected by its performance but also by various factors such as the model's input parameters. Therefore, this approach is prone to evaluation errors.

[0115] Furthermore, this method relies on the truth benchmark provided by the terminal device, namely relative information 1. However, the acquisition of relative information 1 is susceptible to various factors such as sensor errors and environmental interference, which can lead to deviations in the reference benchmark. This can further cause misjudgments, that is, misjudging correct positioning results as incorrect, or misjudging incorrect results as correct, ultimately affecting the reliability of the model evaluation.

[0116] In view of this, embodiments of this application provide a model monitoring method. The method assesses whether a positioning model can be used for positioning by evaluating the quality of its input parameters and / or the stability of its output parameters.

[0117] For example, the terminal device receives M signals for positioning from M access network devices and performs signal measurements to obtain measurement data for the M signals.

[0118] The terminal device arbitrarily selects N measurement data from the measurement data of M signals (N is the minimum number of signals required for the first model to complete the positioning, that is, the first model depends on the measurement data of at least N signals to output the positioning result), and inputs them into the first model respectively. The first model can output multiple positioning results. By analyzing the consistency between these positioning results, the first index can be obtained.

[0119] Furthermore, the terminal device performs a quality assessment on the measurement data of each of the M signals to obtain a second index, which indicates the quality of the input parameters of the positioning model. The second index may include, for example, signal quality, direct trajectory measurement quality, timing measurement quality, or consistency quality.

[0120] The terminal device can determine the number of access network devices that can be used for positioning based on a first indicator and / or a second indicator, i.e., the first number, which means that the signals sent by a first number of access network devices out of M access network devices can be used for positioning through the positioning model. Finally, the terminal device determines whether the first model can be used for positioning based on the first number and N.

[0121] In this method, the first indicator reflects the stability of the positioning model's output parameters, while the second indicator reflects the quality of the parameters input to the positioning model. This ensures that the determined first quantity reflects the number of signals available for accurate positioning using the positioning model in the current positioning scenario. Essentially, it filters from M signals in the current positioning scenario to select those suitable for positioning the terminal device using the positioning model. This approach considers not only the model's performance but also the current positioning scenario of the terminal device, enabling a more comprehensive and reliable determination of whether the positioning model can be used to locate the terminal device, thus improving the reliability of the model monitoring results.

[0122] Below, in conjunction with Figures 2 to 8 This application provides a detailed description of the model monitoring method according to its embodiments. The specific forms and quantities of the devices shown are merely examples and should not be construed as limiting the implementation of the methods provided in this application.

[0123] The method implementation subject provided in this application embodiment can be a terminal device or an access network device.

[0124] The terminal device can be the terminal equipment itself, a chip, chip system, or processor that supports the model monitoring method of the terminal equipment, or a logic module or software that can implement all or part of the terminal equipment. The access network device can be the access network equipment (such as a base station) itself, a chip, chip system, or processor that supports the model monitoring method of the access network equipment, or a logic module or software that can implement all or part of the access network equipment. This application does not specifically limit these limitations.

[0125] The following describes the model monitoring method of this application embodiment in detail, taking terminal equipment and access network equipment as the main execution entities. The access network equipment described below can also be replaced with other access network devices, such as components in the access network equipment or base stations, etc. The terminal equipment can also be replaced with other terminal devices, such as components in the terminal equipment, etc. This application embodiment does not specifically limit this.

[0126] Figure 2 This is a flowchart illustrating the model monitoring method 200 provided in an embodiment of this application. Method 200 is applicable to the communication system employing architecture 100, and can also be applied to other systems. The system to which method 200 is applicable may include at least one terminal device and multiple access network devices.

[0127] like Figure 2 As shown, method 200 includes the following steps:

[0128] S201. M access network devices send signals to the terminal device respectively; correspondingly, the terminal device receives M signals from the M access network devices, and the M signals are used for positioning.

[0129] Among them, M signals are signals that can be used to determine the location of the terminal device. The M signals can be the same signal or different signals. The M signals can be, for example, positioning signals such as DL-PRS, other reference signals, or communication signals. This application embodiment does not limit the type of signals.

[0130] For access network device i among M access network devices, access network device i sends signal i (i.e., signal i) to the terminal device; correspondingly, the terminal device receives signal i from access network device i, where i is an integer greater than or equal to 1 and less than or equal to M.

[0131] For example, suppose there are three base stations around the terminal device (i.e., M=3, namely base station A, base station B, and base station C). These three base stations can send signals (such as DL-PRS) to the terminal device based on the instructions of the core network side (such as LMF). The terminal device can receive DL-PRS from the three base stations.

[0132] S202. The terminal device determines whether the first model can be used for positioning based on the first quantity and N, where N is the number of signals sent by the access network device required for the first model to perform positioning.

[0133] Wherein, the first quantity is the number of access network devices among the M access network devices that can be used for positioning. The first quantity is determined based on a first indicator and / or a second indicator corresponding to each of the M access network devices. The first indicator is used to indicate the consistency between the positioning results output by the first model based on the first measurement data of any N signals among the M signals. The second indicator includes at least two of the following:

[0134] Signal quality, direct path measurement quality, timing measurement quality, or consistency quality; consistency quality is used to indicate the consistency between the second measurement data of each of the M signals and the second measurement data of the training data; timing measurement quality is used to indicate whether the arrival time difference is within a first range.

[0135] The first model can also be called a localization model, AI model, localization AI model, ML model, etc. The name of the first model is not specifically limited in this application embodiment.

[0136] The first quantity can be understood as the total number of access network devices that, after multi-dimensional evaluation, are determined to have reliable signals and can provide effective input parameters for the positioning model out of the M access network devices that transmit positioning signals. Alternatively, the first quantity can also be understood as the number of signals that can be used for positioning out of the M signals.

[0137] For example, suppose there are 4 base stations around the terminal device (i.e., M=4), all of which send DL-PRS to the terminal device, and the first model requires signals from at least 3 base stations (i.e., N=3) to complete the positioning. The process for determining the first number is as follows:

[0138] The terminal equipment sequentially evaluates the second metric of the four base stations, including signal quality, direct beam distance measurement quality, timing measurement quality, and consistency quality. It is assumed that one of the base stations, located behind a tall building, experiences severe signal reflection interference, resulting in its direct beam distance measurement quality failing to meet the standard.

[0139] Then, the terminal device randomly selects 3 signals from the 4 base stations (i.e., 4 combinations) and inputs them into the first model to obtain 4 sets of positioning results. Based on these results, the first index is calculated, namely the consistency between the positioning results.

[0140] By analyzing the first and second indicators, the terminal device determines that one base station cannot be used for positioning because its signal quality is substandard. Therefore, the first quantity is set to 3. Since the first quantity equals N, the terminal device determines that the first model is suitable for positioning under the current conditions.

[0141] The first model can be understood as a model deployed in the terminal device to determine the location of the terminal device. This model takes the first measurement data of the positioning signals emitted by at least N access network devices as input, analyzes and processes it based on a preset algorithm (such as triangulation), and finally outputs the location information of the terminal device, such as coordinates.

[0142] The first measurement data of the signal can be understood as the data (or parameters) obtained by the terminal device based on the signal received from the access network device, and the first measurement data of the signal includes the parameters that the positioning model needs to rely on when determining the location of the terminal device.

[0143] For example, the terminal device determines the positioning result based on the first model, for example, through direct position determination (DPD) or a two-step method.

[0144] DPD can be understood as a method that determines the location information (such as coordinates) of a terminal device based on received signals. The first measurement data of each of the M signals can be replaced with the signal sequence of each of the M signals.

[0145] The two-step method can be understood as a way to determine the location information (such as coordinates) of the terminal device based on the parameter 'a' obtained from the measurement of each signal. The parameter 'a' may include, but is not limited to, one or more of the following: time of arrival (TOA), angle of arrival (AOA), time difference of arrival (TDOA), received signal strength (RSS), frequency difference of arrival (FDOA), and difference of received signal strength (DRSS). The first measurement data of each of the M signals may include, for example, parameter 'a'.

[0146] The second measurement data of the signal can be understood as data (or parameters) obtained by the terminal device based on the signal received from the access network device, and the second measurement data of the signal includes parameters that need to be used to determine the consistency quality. The second measurement data may differ from the first measurement data.

[0147] For example, the second measurement data may include one or more of the following: Doppler frequency shift, signal strength, carrier phase, or multipath delay.

[0148] Training data can be understood as the data used to train the first model. Training data also includes the second measurement data.

[0149] The second measurement data of each of the M signals, along with the second measurement data of the training data, can be used to determine the consistency quality. This consistency quality indicates whether there are changes in the second measurement data caused by factors such as the movement of the terminal device or changes in the environment.

[0150] The first indicator can be understood as an indicator reflecting the stability of the output parameters of the first model. Its purpose is to evaluate the consistency between multiple positioning results calculated by the first model based on different signal combinations. If the differences between multiple positioning results are small, it indicates that the output parameters of the first model are stable and reliable in the current environment. If the differences between multiple positioning results are significant, it indicates that the first model may be affected by factors such as signal interference or environmental incompatibility, resulting in a lower reliability of its output parameters.

[0151] For example, the first metric can be the variance of the positioning results corresponding to multiple signal combinations. The smaller the variance, the more stable the output parameters of the first model; the larger the variance, the greater the fluctuation of the output parameters of the first model.

[0152] For example, given M signals transmitted by M access network devices, the first measurement data of any N signals can be used as a set of first measurement data, for example, a total of x sets of first measurement data. Each of the x sets of first measurement data is input into a first model, resulting in one positioning result, for a total of x positioning results. The first indicator can be, for example, the variance among the x positioning results, or it can be the standard deviation or other indicators that can characterize the differences between the x positioning results. x is a positive integer.

[0153] The second indicator can be understood as a multi-dimensional quality standard used to individually evaluate the signal transmitted by each access network device.

[0154] The calculation process and measurement significance of the first and second indicators are shown in Table 1.

[0155] Table 1

[0156]

[0157]

[0158] The model monitoring method provided in this application, on the input side, involves a terminal device evaluating the signals sent by the access network device using a second indicator (signal quality, direct path measurement quality, timing measurement quality, or consistency quality, etc.) to determine the quality of the input parameters of the first model. On the output side, the terminal device determines the operational stability of the first model using a first indicator (i.e., the consistency between positioning results generated based on different signal combinations). Furthermore, it further determines the actual number of effective access network devices that can be used for positioning (i.e., the first number) based on the first indicator and / or the second indicator.

[0159] The minimum number of signals N required for a terminal device to perform positioning based on a first quantity and a first model can be used to determine whether the first model can be used for positioning. In this method, the performance of the first model is determined based on the quality of its input parameters and / or the stability of its output parameters. The first quantity reflects the number of signals that can be used for accurate positioning using the positioning model in the current positioning scenario. Essentially, it filters signals from M signals in the current positioning scenario that can be used to position the terminal device using the positioning model. This method not only considers the model's performance but also the current positioning scenario of the terminal device, enabling a more comprehensive and reliable determination of whether the positioning model can be used to position the terminal device, thus improving the reliability of the model monitoring results.

[0160] Furthermore, this method can determine the reliability of the localization model without relying on labels, which significantly broadens its applicable scenarios and further enhances its practicality and flexibility.

[0161] Based on the above embodiments, the second indicator, including consistency quality, is calculated based on the second measurement data of each of the M signals and the second measurement data of the training data.

[0162] For example, the consistency quality ε of signal i among M signals. i , ε i It is calculated based on the second measurement data of signal i and the second measurement data of training data.

[0163] The second measurement data includes one or more of the following: Doppler frequency shift, signal strength, carrier phase, or multipath delay.

[0164] It should be understood that consistency quality can be interpreted as an indicator used to evaluate the consistency between the signal measurement environment and the model training environment. Therefore, consistency quality can be determined by the consistency between some evaluation indicators obtained from signal measurement (second measurement data) and some evaluation indicators of training data (second measurement data).

[0165] If the second measurement data of the signal measurement is small in difference from the second measurement data of the training phase (i.e., training data), it indicates that the signal propagation environment remains stable and the first model is still in the adaptation state. At this time, the first measurement data of the signal has high reliability. If there is a significant difference between the two, it indicates that the environment may have changed significantly (such as the addition of obstacles or the terminal device entering a high-speed movement state). Such changes are likely to cause the first model to fail, thereby affecting the positioning accuracy.

[0166] The specific calculation of consistency quality can be determined based on one or more signal characteristic parameters such as Doppler frequency shift, signal strength, carrier phase or multipath delay, thereby realizing a multi-dimensional judgment of environmental consistency.

[0167] In this way, by using consistency quality indicators to integrate multi-dimensional signal characteristics such as Doppler frequency shift, signal strength, carrier phase or multipath delay, a quantitative evaluation of the consistency between the signal measurement environment and the model training environment can be achieved.

[0168] Consistency quality is achieved by comparing the feature differences between the second measurement data received in real time and the second measurement data during the training phase, thereby enabling a quantitative assessment of environmental consistency.

[0169] Specifically, the indicator is determined based on one or more of the following: Doppler shift quality, signal strength quality, carrier phase quality, or multipath delay quality.

[0170] Among them, Doppler shift quality is used to indicate the consistency between the Doppler shift of each of the M signals and the Doppler shift of the training data; signal strength quality is used to indicate the consistency between the signal strength of each of the M signals and the signal strength of the training data; carrier phase quality is used to indicate the consistency between the carrier phase of each of the M signals and the carrier phase of the training data; and multipath delay quality is used to indicate the consistency between the multipath delay of each of the M signals and the multipath delay of the training data.

[0171] Doppler shift quality can be understood as an indicator used to assess whether the relative motion state between the terminal device and the access network device matches the model training expectations. By determining the difference between the Doppler shift of each signal and the baseline data during the training phase (i.e., the Doppler shift of the training data), it is determined whether the motion state of the terminal device (such as stationary, walking, or high-speed movement) is within the adaptation range of the first model. If the difference is small, it indicates that the motion state is stable and the signal is reliable; if the difference is significant, it indicates that the motion state exceeds expectations and may cause positioning errors.

[0172] Signal strength quality can be understood as an indicator used to monitor the stability of the signal propagation environment. By determining the difference between the signal strength of each signal and the baseline data during the training phase (i.e., the signal strength of the training data), it is assessed whether the signal attenuation is within the expected range. If the difference is small, it indicates that the environment is stable, without significant obstruction or interference, and the first measurement data of the signal is reliable; if the difference is significant, it may be due to signal distortion caused by environmental changes, which in turn introduces positioning errors.

[0173] Carrier phase quality can be understood as an indicator used to evaluate the reliability of signal phase measurements. By determining the difference between the carrier phase of each signal and the reference data during the training phase (i.e., the carrier phase of the training data), it is determined whether the phase data is affected by noise or multipath interference. If the difference is small, it indicates that the phase measurement accuracy is high and can provide reliable data for high-precision positioning; if the difference is significant, it indicates that the phase data is distorted, which will directly affect the accuracy of the positioning results.

[0174] Multipath delay quality can be understood as an indicator used to assess whether the degree of multipath interference in the current scene meets the model training expectations. By determining the difference between the multipath delay of each signal (such as the arrival time difference of signals along different propagation paths) and the baseline data during the training phase (i.e., the multipath delay of the training data), it is determined whether the signal is subject to excessive reflection or refraction interference. If the difference is small, it indicates that the multipath effect is within the expected range and the signal can effectively reflect the true distance; if the difference is large, it indicates severe multipath interference, which can easily cause positioning calculation errors.

[0175] The measurement significance of Doppler frequency shift quality, signal strength quality, carrier phase quality, or multipath delay quality is shown in Table 2.

[0176] Table 2

[0177]

[0178] In this way, by integrating multiple quality indicators such as Doppler frequency shift, signal strength, carrier phase or multipath delay, it is possible to comprehensively perceive changes in factors such as the motion state of terminal equipment, signal propagation conditions, phase stability and multipath interference, thereby achieving accurate identification and early prediction of environmental anomalies and model adaptation risks.

[0179] Based on the above embodiments, several indicators used to determine consistency quality satisfy any one or more of the following items 1 to 4:

[0180] Item 1: Doppler shift quality is calculated based on the standard deviation of the Doppler shift of each of the M signals and the standard deviation of the Doppler shift of the training data, and / or the average value of the Doppler shift of each of the M signals and the average value of the Doppler shift of the training data.

[0181] Item 2: Signal strength quality is calculated based on the standard deviation of the signal strength of each of the M signals and the standard deviation of the signal strength of the training data, and / or the average of the signal strength of each of the M signals and the average of the signal strength of the training data.

[0182] Item 3: Carrier phase quality is calculated based on the standard deviation of the carrier phase of each of the M signals and the standard deviation of the carrier phase of the training data, and / or the average value of the carrier phase of each of the M signals and the average value of the carrier phase of the training data.

[0183] Item 4: Multipath delay quality is calculated based on the standard deviation of the multipath delay of each signal in the M signals and the standard deviation of the multipath delay of the training data, and / or the average value of the multipath delay of each signal in the M signals and the average value of the multipath delay of the training data.

[0184] As an example and not a limitation, for signal i among M signals, the Doppler frequency shift quality, signal strength quality, carrier phase quality, and multipath delay quality corresponding to signal i can be calculated, for example, in the following way.

[0185] For the first item above, the Doppler frequency shift quality C corresponding to signal i among the M signals is... DF Doppler frequency shift quality C DF Satisfy the following formula:

[0186] (Formula 1)

[0187] in, and These are weighting coefficients, all of which are greater than 0, and can be preset parameters; It is the default quality benchmark for Doppler frequency shift quality, and can be a preset value; It is the average value of the Doppler frequency shift of signal i. It is the average value of the Doppler shift in the training data; It is the standard deviation of the Doppler frequency shift of signal i; It is the standard deviation of the Doppler shift in the training data.

[0188] In this way, the terminal device can calculate the Doppler frequency shift quality corresponding to signal i. For each of the M signals, the Doppler frequency shift quality corresponding to that signal can be obtained in a similar manner.

[0189] Regarding the second item above, the signal strength quality C corresponding to signal i among the M signals... RSCP Signal strength quality C RSCP Satisfy the following formula:

[0190] (Formula 2)

[0191] in, It is a weighting coefficient, and A value greater than 0 indicates a preset parameter. This is the default quality benchmark for signal strength, and can be a preset value; It is the standard deviation of the signal strength of signal i; It is the standard deviation of the signal strength in the training data.

[0192] In this way, the terminal device can calculate the signal strength quality corresponding to signal i. For each of the M signals, the signal strength quality corresponding to that signal can be obtained in a similar manner.

[0193] Regarding the third item above, the carrier phase quality C corresponding to signal i among the M signals... RSRPP Carrier phase quality C RSRPP Satisfy the following formula:

[0194] (Formula 3)

[0195] in, and These are weighting coefficients, all of which are greater than 0, and can be preset parameters; It is the default quality benchmark for carrier phase quality, and can be a preset value; It is the standard deviation of the carrier phase of signal i; It is the standard deviation of the carrier phase in the training data; It is the autocorrelation coefficient of the signal sequence.

[0196] In this way, the terminal device can calculate the carrier phase quality corresponding to signal i. For each of the M signals, the carrier phase quality can be obtained in a similar manner.

[0197] Regarding the fourth item above, the multipath delay quality C corresponding to signal i among the M signals... τ Multipath delay quality C τ Satisfy the following formula:

[0198] (Formula 4)

[0199] in, and These are weighting coefficients, all of which are greater than 0, and can be preset parameters; It is the default quality benchmark for multipath delay quality, and can be preset parameters; It is the maximum value of the multipath delay of signal i. It is the average value of the multipath delay of signal i; It is the standard deviation of multipath delay in the training data; It is the standard deviation of the multipath delay of signal i.

[0200] In this way, the terminal device can calculate the multipath delay quality corresponding to signal i. For each of the M signals, the multipath delay quality corresponding to that signal can be obtained in a similar manner.

[0201] Furthermore, based on the Doppler frequency shift quality C of signal i DF Signal strength quality C RSCP Carrier phase quality C RSRPP and multipath delay quality C τ The terminal device can determine the consistency quality ε of signal i. i .

[0202] For example, ε i Satisfy the following formula:

[0203] (Formula 5)

[0204] Where α1, α2, α3 and α4 are weighting coefficients, which can be preset values ​​and are all greater than 0, and ε is a constant.

[0205] In this way, the terminal device can calculate the consistency quality corresponding to signal i. For each of the M signals, the consistency quality can be obtained in a similar manner.

[0206] Based on the above embodiments, the terminal device can determine the first quantity based on the first indicator and / or the second indicator. Specifically, the first quantity is determined based on the first indicator and / or the second indicator corresponding to each of the M access network devices, including: the first quantity is determined based on the weighted average of the first indicator and the second indicator.

[0207] The first quantity can be determined in the following three ways:

[0208] The first method: Determined based on the first indicator.

[0209] This method determines the first quantity based on a first indicator (i.e., the consistency of the output results of the positioning model).

[0210] For example, the terminal device calculates the variance between x positioning results to obtain a first index. If the first index is less than a certain threshold, all M access network devices are determined to be reliable. In this case, the first quantity equals M. If the first index is greater than a certain threshold, all M access network devices are determined to be unreliable, and the first quantity becomes 0.

[0211] The second approach: Determined based on the second indicator.

[0212] This method determines the first quantity based on the second indicator (i.e., signal quality parameters) corresponding to the signals sent by each access network device.

[0213] For example, taking signal i from M signals as an example, the terminal device calculates a second index for signal i, namely at least two of the following: signal quality, direct path measurement quality, timing measurement quality, and consistency quality. Further, the terminal device can also calculate a weighted average of each index in the second index of signal i to obtain a parameter corresponding to signal i. If the parameter is greater than or equal to a threshold a, the access network device i that transmits signal i is marked as a reliable access network device; if the parameter is less than the threshold a, the access network device i that transmits signal i is marked as an unreliable access network device.

[0214] The first number is the total number of all access network devices marked as reliable.

[0215] The third approach: Determined based on the first and second indicators.

[0216] This method uses a weighted average of the first and second indicators to determine the first quantity.

[0217] For example, the terminal device assigns corresponding weights to the first indicator and each of the second indicators. The terminal device calculates the access network device i quality score Q for the transmitted signal i. i It satisfies the following formula:

[0218] (Formula 6)

[0219] in, , , and These are weighting coefficients, all of which are greater than 0, and can be preset parameters.

[0220] In this way, the terminal device combines the stability of the output parameters of the first model with the signal quality of a single access network device (i.e., the quality of the input parameters) to determine the model performance of the first model, resulting in high reliability of the model monitoring results.

[0221] Optionally, for , , and The first indicator It can reflect the reliability of the first model, weights It can be relatively large; consistency quality ε i It can reflect the degree of environmental change, weight It can be relatively large.

[0222] However, since the training data may reflect features such as noise interference in the real environment, and may also contain features of the NLOS scene, the weights... and weight The values ​​can be relatively small. This application does not limit the specific values ​​of each weight in its embodiments.

[0223] Using the above method, the terminal device can obtain the quality score of each of the M access network devices, for a total of M quality scores.

[0224] Among the M quality scores, the access network device to which the quality score is greater than or equal to the first threshold belongs is an access network device that can be used for positioning and can be marked as a reliable access network device (e.g., denoted as 1); the access network device to which the quality score is less than the first threshold belongs is an access network device that cannot be used for positioning and can be marked as an unreliable access network device (e.g., denoted as 0).

[0225] In this way, the terminal device can determine which of the M access network devices can be used for positioning, that is, determine the first number.

[0226] The first threshold can be understood as the minimum value required to determine whether a single access network device can be used for positioning. This threshold is used to evaluate whether the access network device meets the reliability standards in terms of signal quality and model output stability. If its weighted average sum (i.e., quality score) is greater than or equal to the first threshold, it indicates that the access network device meets the positioning requirements; conversely, if it is lower than the first threshold, it is usually considered an unusable access network device due to poor signal quality or insufficient model stability.

[0227] For example, assume the first threshold is Q'. The terminal device evaluates the quality scores of base station 1, base station 2, and base station 3: if the quality scores of base station 1 and base station 2 are both greater than or equal to Q', while the quality score of base station 3 is less than Q', then base station 1 and base station 2 meet the positioning requirements, and in this case, the first quantity is equal to 2.

[0228] In this way, by setting a first threshold to evaluate access network devices, the accurate screening of available access network devices can be achieved, which can improve the reliability of the positioning model performance monitoring results.

[0229] After determining the number of available access network devices (i.e., the first number), the terminal device compares it with the minimum number N of access network devices required for positioning to determine whether the first model can be used for positioning. Specifically, determining whether the first model can be used for positioning based on the first number and N includes: if the first number is less than N, determining that the first model cannot be used for positioning; if the first number is greater than or equal to N, determining that the first model can be used for positioning.

[0230] When the first quantity is less than N, it indicates that the number of available access network devices has not reached the minimum number of available access network devices required for the positioning model to complete the positioning. For example, suppose the positioning model needs signals from at least 3 base stations (i.e., N=3) to calculate the location of the terminal device, but only 2 available base stations are actually selected (i.e., the first quantity = 2). Due to insufficient input data, the positioning result may have a significant deviation, so the first model is determined to be unusable.

[0231] When the first quantity is greater than or equal to N, it indicates that the number of available access network devices meets or even exceeds the basic requirements of the positioning model. For example, assuming the positioning model requires at least 3 base stations (i.e., N=3) to calculate the terminal location, and 4 available base stations are actually selected (i.e., the first quantity = 4), it not only meets the basic requirements of positioning calculation, but also allows for redundancy verification based on the data from the redundant devices. By eliminating individual abnormal data, the positioning accuracy can be further improved. In this case, the first model is determined to be suitable for positioning.

[0232] In this way, by comparing the number of available access network devices (i.e., the first number) with the minimum number required by the positioning model (i.e., N), the positioning model is activated only when the available signal resources are greater than or equal to N, thereby effectively avoiding positioning failure or poor accuracy due to insufficient input data.

[0233] The following is combined Figure 3 The process by which the terminal device determines whether the first model is available (S202 implementation method) will be described in detail. Figure 3 This is a flowchart illustrating the model availability determination method 300 provided in an embodiment of this application. The specific steps are as follows:

[0234] S301. After receiving M signals from M access network devices, the terminal device can calculate a first index; and for each of the M signals, it can calculate a second index of that signal. For example, for signal i, it can calculate the second index of signal i.

[0235] The calculation process for the first and second indicators can be found above and will not be repeated here.

[0236] S302, The terminal device calculates the quality score Q of signal i based on the first indicator and the second indicator of signal i. i .

[0237] For example, the quality score Q of signal i i It can be the weighted average of the first and second indicators, for example, satisfying Formula 6 above.

[0238] It is understandable that the weights in Formula 6 can be dynamically adjusted according to the characteristics of the scene. For example, in urban scenes with strong multipath interference, the weight of the second indicator reflecting the anti-interference capability of a single signal is relatively high; while in open suburban scenes, the weight of the first indicator reflecting the consistency of the output results of multiple devices (multiple signals) is relatively high.

[0239] S303, Terminal equipment determines the quality score Q of signal i. i Is it greater than or equal to the first threshold Q'?

[0240] In Q i If the value is greater than or equal to Q', execute S304.

[0241] In Q i In the case of <Q', execute S305.

[0242] The first threshold Q' can be set according to the sensitivity of the first model to signal quality. For example, in scenarios with high positioning accuracy requirements, the value of Q' is relatively large; in scenarios with low positioning accuracy requirements, the value of Q' is relatively small.

[0243] S304. The terminal device determines that signal i (or access network device i) meets the positioning requirements, and access network device i can be used for positioning. Signal i is a valid signal for positioning based on the first model.

[0244] S305. The terminal device determines that signal i (or access network device i) does not meet the positioning requirements, access network device i cannot be used for positioning, and signal i cannot be used for positioning calculation, in order to reduce positioning errors caused by poor signal quality.

[0245] S306. After the terminal device traverses M signals and completes the judgments in S301-S305, it determines the total number of signals that meet the positioning requirements, which is the first number, or the actual number of access network devices that can participate in positioning.

[0246] S307. The terminal device determines whether the first quantity is greater than or equal to the number N of signals N sent by the access network device required for the first model to perform positioning.

[0247] If the first quantity is greater than or equal to N, execute S308.

[0248] If the first quantity is less than N, execute S309.

[0249] The value of N is related to the positioning dimension or the positioning algorithm used by the first model. For example, two-dimensional positioning requires at least 3 signals (i.e., N=3), while three-dimensional positioning may require 4 signals (i.e., N=4). In scenarios with redundant design, N can be set to 5 to enhance anti-interference capability.

[0250] S308. The terminal device determines that the first model is available because at this time there are enough available access network devices and their quality meets the standards. The first model can output a reliable positioning result based on the first measurement data of these signals.

[0251] S309. The terminal device determines that the first model is unavailable. Due to the insufficient number of available access network devices, the first model cannot complete the positioning calculation (e.g., the location is ambiguous due to missing data dimensions). In this case, it may be necessary to trigger alternative solutions, such as switching the positioning model or requesting more access network devices to send signals.

[0252] After the terminal device determines that the first model cannot be used for positioning because the first number is less than N, it can interact with the first network element. Specifically, when the first model cannot be used for positioning, it sends first information to the first network element. The first information indicates the first number of access network devices that can be used for positioning. Alternatively, it can be understood that the first information indicates the access network devices that cannot be used for positioning among the M access network devices.

[0253] The first network element can be understood as a network functional entity used to receive positioning status feedback from terminal devices and to coordinate resources to maintain positioning services, such as an LMF (Local Positioning Function). When a terminal cannot complete positioning using the first model, the first network element can receive first information from the terminal device and can also take remedial measures based on the first information, such as scheduling more access network devices, thereby helping to prevent positioning service interruption.

[0254] The first information can be understood as the location resource status report sent by the terminal device to the first network element when the first model is unavailable. It includes the number of currently available valid access network devices, providing a decision-making basis for the first network element to implement subsequent remedial strategies.

[0255] As an example and not a limitation, the first information may be, for example, a bitmap with M bits, where each of the M bits is used to indicate an access network device in the access network device.

[0256] In this bitmap, a bit of 1 for an access network device indicates that the device can be used for location tracking; a bit of 0 indicates that the device cannot be used for location tracking. For example, if M is 4, the four bits in the bitmap sequentially indicate access network device 1, access network device 2, access network device 3, and access network device 4. When the bitmap is 1100, it means that access network device 1 and access network device 2 can be used for location tracking, while access network device 3 and access network device 4 cannot.

[0257] Alternatively, when a bit corresponding to an access network device is 0, it can indicate that the access network device can be used for positioning; when a bit corresponding to an access network device is 1, it can indicate that the access network device cannot be used for positioning. This application does not impose specific limitations on this aspect.

[0258] In this way, when the terminal device determines that the first model is unavailable, it sends the first information to the first network element, thereby enabling the first network element to obtain the specific number of access network devices that can be used for positioning.

[0259] Once the terminal device determines that the first quantity is greater than or equal to N, meaning the first model can be used for positioning, it can also interact with the first network element. Specifically, when the first model can be used for positioning, it sends second information to the first network element. The second information indicates the positioning result, which is obtained by inputting first measurement data of N signals out of M signals into the first model. The N signals are signals sent by the access network devices that can be used for positioning among the M access network devices.

[0260] It is understood that if a first number of access network devices out of M access network devices can be used for positioning, and the first number is greater than or equal to N, then the terminal device can input the first measurement data of N signals into the first model. These N signals are signals emitted by the N access network devices out of the first number of access network devices.

[0261] For example, M is 4, and the M access network devices are access network device 1, access network device 2, access network device 3 and access network device 4, and they send signal 1, signal 2, signal 3 and signal 4 to the terminal device in sequence; where access network device 1, access network device 2 and access network device 3 can be used for positioning, the first measurement data of signal 1, the first measurement data of signal 2 and the first measurement data of signal 3 can be used to calculate the positioning result through the first model.

[0262] When N is 3, the first measurement data of signal 1, the first measurement data of signal 2, and the first measurement data of signal 3 can be input into the first model, and the first model can output the positioning result.

[0263] When N is 2, the first measurement data of any two of the first measurement data of signal 1, signal 2 and signal 3 can be input into the first model, and the first model can output the positioning result.

[0264] The second information can be understood as a location result report sent by the terminal device to the first network element, including the location result calculated by the first model, so that the first network element can schedule network resources or provide location services based on the information.

[0265] In this way, once the terminal device confirms that the positioning model is available, it will calculate the positioning result based on N signals that meet the positioning requirements, and send it to the first network element through the second information. This not only completes the positioning service request, but also outputs a highly reliable result to the network side.

[0266] Based on the information above, if the first model is unavailable, the terminal device may send first information to the LMF. This first information indicates a first number of access network devices that can be used for location, and / or, among the M access network devices, those that cannot be used for location. For example, the first information may be a bitmap of M bits.

[0267] This bitmap can also be referred to as a valid status code sequence.

[0268] The following is combined Figure 4 The process of determining a valid status code is explained in detail. Figure 4 A flowchart illustrating the method 400 for determining a valid status code provided in this application embodiment. The specific steps are as follows:

[0269] Process a (S301-S303): The quality score of each signal in the M signals is compared with the relative size of the first threshold.

[0270] Taking signal i out of M signals as an example, the terminal device will calculate the quality score Q of signal i. iCompare with the first threshold Q', and perform subsequent steps based on the comparison result.

[0271] In Q i If ≥Q', execute S401.

[0272] In Q i In the case of <Q', execute S402.

[0273] Process b (S401 and S402): Assigning valid status codes.

[0274] S401. The terminal device sets the valid status code of the access network device i that sends signal i to 1, indicating that the signal i sent by the access network device meets the positioning requirements, the first measurement data of signal i is valid, and can be used as a reliable input parameter for the first model. Or it can be understood as the access network device i being usable for positioning.

[0275] Setting the valid status code of access network device i to 1 can also be understood as setting the bit indicating access network device i to 1 in the bit diagram.

[0276] S402. The terminal device sets the valid status code of the access network device i that sends signal i to 0, indicating that the signal i sent by the access network device does not meet the positioning requirements, the first measurement data of signal i is invalid, and it needs to be excluded from the input parameters of the first model to avoid introducing positioning errors. Alternatively, it can be understood that the access network device i cannot be used for positioning.

[0277] Setting the valid status code of access network device i to 0 can also be understood as setting the bit indicating access network device i to 0 in the bit diagram.

[0278] Performing the above operation on each of the M access network devices will yield a valid status code for each access network device, resulting in a valid status code sequence of length M (i.e., the bit diagram mentioned above).

[0279] It should be understood that the above description uses "1" to indicate that the access network device can be used for positioning and "0" to indicate that the access network device cannot be used for positioning. In actual application scenarios, "0" can also indicate that the access network device can be used for positioning and "1" can indicate that the access network device cannot be used for positioning. This application embodiment does not specifically limit this.

[0280] In one possible implementation, the access network device ID list is pre-configured by the LMF, and the terminal device generates a valid status code sequence according to the order of the list.

[0281] The following is combined Figure 5 The process of determining a valid status code sequence is explained in detail. Figure 5This is a schematic diagram illustrating the determination of a valid status code sequence provided in an embodiment of this application.

[0282] like Figure 5 As shown in (a), the LMF sends a first request to all available access network devices (e.g., M=4) within the scene using protocols such as NR positioning protocol A (NRPPa). The first request is used to request the execution of the positioning service (i.e., sending a signal for positioning to the terminal device). The first request may also request each access network device to send information a to the LMF. Information a may include, for example, the device ID of the access network device (such as PCI or GCI) and signal configuration data (such as PRS configuration data).

[0283] Each access network device can then send information a to the LMF.

[0284] After receiving information 'a' from all access network devices, the LMF sorts the access network devices according to preset rules (such as PCI ascending order) and generates a list of device IDs for the access network devices, for example: [01, 02, 03, 04], so that the terminal device and the LMF have a consistent understanding of the order of the access network devices.

[0285] like Figure 5 As shown in (b), the LMF instructs each access network device to send a positioning signal (such as a DL-PRS) to the terminal device sequentially according to the access network device ID list [01, 02, 03, 04]. The terminal device performs channel measurements based on the DL-PRS of each access network device, obtains the first and second measurement data of each signal, calculates the quality score of the signal transmitted by each access network device, and compares the quality score with a first threshold, thereby assigning a valid status code to each access network device.

[0286] The terminal device combines the valid status codes of M access network devices into a valid status code sequence, such as 1100, according to the order of the access network device ID list pre-configured by the LMF. These 4 bits sequentially indicate the access network device with device ID 01, device ID 02, device ID 03, and device ID 04, respectively.

[0287] As an example rather than a limitation, such as Figure 5 As shown in (b), due to the obstacle between access network device 02 and the terminal device, the signal emitted by access network device 02 may not be usable for positioning. The valid status code of access network device 02 can be 0, while the valid status codes of the other access network devices are 1. Therefore, the generated valid status code sequence can be 1011. The terminal device sends the valid status code sequence (in bitmap form) to the LMF.

[0288] Since the LMF can determine the list of device IDs of access network devices, the LMF can directly map the specific device status based on the valid status code sequence: for example, the first bit 1 corresponds to device ID 01, indicating that the access network device with device ID 01 can be used for location (or is valid); the second bit 0 corresponds to device ID 02, indicating that the access network device with device ID 02 cannot be used for location (or is invalid).

[0289] In another possible implementation, the terminal device sends the device ID of each of the M access network devices and the valid status code of the access network device to the LMF, so that the LMF can determine whether each of the M access network devices can be used for positioning.

[0290] and Figure 5 The difference in the process shown is that LMF does not need to determine the order in which the M access network devices send signals to the terminal device.

[0291] After receiving signals from various access network devices (such as DL-PRS), the terminal device can also extract the device ID (such as PCI:10 and PCI:11) of the access network device from the data packet header; measure the signal and calculate the quality score Q. i This generates valid status codes for each access network device.

[0292] The terminal device maps the device ID of the access network device to a valid status code, forming a correspondence between the valid status code and the device ID. For example:

[0293] PCI: 10, valid status code: 0;

[0294] PCI: 11, Valid status code: 1;

[0295] PCI: 12, Valid status code: 0;

[0296] PCI: 13, Valid status code: 1.

[0297] In this way, the terminal device can report the correspondence between the device ID of each access network device and the valid status code of the access network device to the LMF, so that the LMF can determine whether each access network device can be used for positioning.

[0298] Alternatively, the terminal device may also report M (i.e., the total number of access network devices participating in the positioning) to the LMF, for example, [total number of access network devices M; PCI 10, valid status code 1; PCI 11, valid status code 1; ...].

[0299] The following is combined Figure 6 and Figure 7 The process of using valid status code sequences is explained.

[0300] Figure 6 This is a schematic diagram illustrating the process of determining the availability of a first model based on a valid status code sequence, as provided in an embodiment of this application.

[0301] like Figure 6 As shown, taking M=4 and the number of signals required for the positioning calculation of the first model as 3, i.e. N=3, the terminal device can filter out the valid signals sent by the access network devices corresponding to PCI 21, PCI 22 and PCI 23 through the valid status code sequence 1110, and meet the requirement of N. At this time, it can be determined that the first model is available, and the first measurement data of the signals sent by the access network devices corresponding to PCI 21, PCI 22 and PCI 23 can be used as the input of the first model.

[0302] Figure 7 This is a schematic diagram illustrating the process of determining that the first model is unavailable based on a valid status code sequence, as provided in an embodiment of this application.

[0303] like Figure 7 As shown, taking M=4 and the number of signals required for positioning calculation in the first model as 3 (i.e., N=3), the terminal device can filter out the valid signals sent by the access network devices corresponding to PCI 31 and PCI 32 through the valid status code sequence 1100. Since the requirement of N is not met, it can be determined that the first model is unusable. The terminal device can indicate the valid status code sequence 1100 to the LMF.

[0304] Upon receiving a valid status code sequence, LMF can accurately identify that the signals sent by the access network devices corresponding to PCI 33 and PCI 34 are invalid, meaning that the access network devices corresponding to PCI 33 and PCI 34 cannot be used for positioning.

[0305] In addition, the second information can also be used to indicate the confidence level of the first model, which can be used to indicate the reliability of the localization results output by the first model, and the confidence level can be determined based on the first quantity and M.

[0306] The confidence level of the first model can be understood as a quantitative assessment of the reliability of the positioning results output by the first model. It evaluates the sufficiency and stability of the model input data by calculating the relationship between the actual number of available access network devices (the first number) and the total number M of access network devices participating in the positioning, thereby reflecting the credibility of the positioning results.

[0307] For example, confidence level = coefficient 1 × first quantity / M.

[0308] The coefficient 1 can be a preset value.

[0309] The closer the first quantity is to M, the higher the confidence of the first model; the smaller the first quantity is, the lower the confidence of the first model.

[0310] In this way, the confidence level of the first model provides a quantitative reliability indicator for the location service.

[0311] Optionally, the confidence level is determined based on a first quantity and M, including: the confidence level is determined based on the first quantity and M, and a first indicator and / or a second indicator corresponding to each of the M access network devices.

[0312] For example, the confidence level of the first model satisfies the following formula:

[0313] (Formula 7)

[0314] Where λ1 and λ2 are weighting coefficients, and their sum is 1, which can be preset parameters; K is the number of effective access network devices, i.e., the first number; Q MAX It is the maximum quality score among M access network devices (M signals); Q i It is the quality score of signal i.

[0315] It should be understood that when the first model is determined to be available, the terminal device can calculate the confidence level of the first model.

[0316] In this way, confidence level can achieve multi-dimensional and accurate quantification of the reliability of positioning results.

[0317] Below, in conjunction with Figure 8 This section provides a more detailed explanation of the process for positioning terminal devices using the first model.

[0318] Figure 8 This is a flowchart illustrating the positioning method 800 provided in an embodiment of this application. Method 800 can be applied to... Figure 1 The communication system shown. Method 800 includes the following steps:

[0319] S801. The terminal device sends a first request to the LMF. The first request is used to request the monitoring of whether the first model is valid. The first model is used for positioning, and the positioning requires signals sent by N access network devices. Correspondingly, the LMF receives the first request from the terminal device.

[0320] Alternatively, the first request can also be understood as a location request, used to request location services.

[0321] The first request is used to request monitoring of whether the first model is effective, which can also be understood as: the terminal device requests monitoring of the performance of the first model.

[0322] Optionally, after receiving the first request, the LMF can determine whether a ground truth tag can be obtained in the current scenario; if a ground truth tag cannot be obtained, such as due to a lack of real location reference or a complex signal environment that makes the tag unreliable, the tagless monitoring method, namely S802-S811, is activated.

[0323] S802. Based on the first request, the LMF sends third information to each of the M access network devices. The third information is used to indicate the transmission signal, which is used for positioning. Correspondingly, each of the M access network devices receives the third information from the LMF.

[0324] For example, for access network device 1, LMF sends third information 1 to access network device 1. Third information 1 is used to instruct access network device 1 to send a signal for positioning. Correspondingly, access network device 1 receives third information 1 from LMF.

[0325] For access network device 2, LMF sends third information 2 to access network device 2. Third information 2 is used to instruct access network device 2 to send a signal for positioning. Correspondingly, access network device 2 receives third information 2 from LMF.

[0326] For access network device M, LMF sends third information M to access network device M. The third information M is used to instruct access network device M to send a signal for positioning. Correspondingly, access network device 1 receives the third information M from LMF.

[0327] It is understandable that the third piece of information can also be understood as a location request, used to request M access network devices to perform location services.

[0328] Optionally, the third information is also used to request device IDs and configuration data for location signals (such as PRS) from each of the M access network devices.

[0329] This can also be understood as the third information being used to request device identifiers (IDs) and resource configuration information (or service capability information) from each of the M access network devices.

[0330] The device ID of the access network device can also be replaced with a physical cell identifier (PCI) or a global cell identifier (GCI) to distinguish each access network device.

[0331] In addition, optionally, the LMF can also send a sixth message to the terminal device, which is used to indicate that the performance of the first model is monitored by a labelless monitoring method; correspondingly, the terminal device receives the sixth message from the LMF.

[0332] The sixth piece of information can also be referred to as the tagless monitoring method start command, etc.

[0333] This enables the terminal device to determine, based on the sixth piece of information, whether the first model can be used for positioning through tagless monitoring.

[0334] S803: Each of the M access network devices sends a fifth message to the LMF. The fifth message includes the device ID and signal configuration data (such as PRS configuration data). Correspondingly, the LMF receives the fifth message from the M access network devices.

[0335] The configuration data may include, but is not limited to, various parameters such as the PRS transmission time interval and measurement interval configuration. For the sake of brevity, they will not be listed here.

[0336] For example, for access network device 1, access network device 1 sends fifth information 1 to LMF. Fifth information 1 is used to indicate the device ID and signal configuration data (such as PRS configuration data) of access network device 1. Correspondingly, LMF receives fifth information 1 from access network device 1.

[0337] For access network device 2, access network device 2 sends fifth information 2 to LMF. Fifth information 2 is used to indicate the device ID and signal configuration data (such as PRS configuration data) of access network device 2. Correspondingly, LMF receives fifth information 2 from access network device 2.

[0338] For access network device M, access network device M sends fifth information M to LMF. Fifth information M is used to indicate the device ID and signal configuration data (such as PRS configuration data) of access network device M. Correspondingly, LMF receives fifth information M from access network device M.

[0339] Based on this, the LMF obtains the device ID and signal configuration data (such as PRS configuration data) of each of the M access network devices. Furthermore, the LMF can determine the order in which the M access network devices send signals to the terminal device.

[0340] For example, the LMF sorts the M access network devices according to preset rules to generate an ID sequence table. The ID sequence table is used to indicate the sorting order of the device IDs of the M access network devices, that is, the order in which the M access network devices send signals to the terminal device. For example, the LMF can sort them in ascending or descending order based on identifiers such as PCI or GCI.

[0341] S804 and LMF respectively send fourth information to M access network devices. The fourth information is used to indicate the order in which the M access network devices send signals to the terminal device (such as an ID sequence table). Correspondingly, the M access network devices respectively receive the fourth information from LMF.

[0342] For example, for access network device 1, LMF sends fourth information 1 to access network device 1. Fourth information 1 is used to indicate the order in which M access network devices send signals to the terminal device; correspondingly, access network device 1 receives fourth information 1 from LMF.

[0343] For access network device 2, LMF sends fourth information 2 to access network device 2. Fourth information 2 is used to indicate the order in which M access network devices send signals to the terminal device; correspondingly, access network device 2 receives fourth information 2 from LMF.

[0344] For access network device M, LMF sends fourth information M to access network device M. The fourth information M is used to indicate the order in which the M access network devices send signals to the terminal device. Correspondingly, access network device M receives the fourth information M from LMF.

[0345] S805, the M access network devices send signals to the terminal device in the order indicated by the fourth information; correspondingly, the terminal device receives M signals from the M access network devices, and the M signals are used for positioning.

[0346] Taking the order of the fourth information indication as: access network device 1, access network device 2, ..., access network device M as an example, access network device 1 sends signal 1 to the terminal device; correspondingly, the terminal device receives signal 1 from access network device 1.

[0347] Access network device 2 sends signal 2 to terminal device; correspondingly, terminal device receives signal 2 from access network device 2.

[0348] Access network device M sends signal M to terminal device; correspondingly, terminal device receives signal M from access network device M.

[0349] S806. After receiving M signals, the terminal device performs channel measurements on each signal, such as measuring parameters like the first and second measurement data of each signal, and calculates the first index and the second index of each signal.

[0350] It should be understood that the methods for calculating the first and second indicators can be referred to the description above, and will not be repeated here.

[0351] S807. The terminal device calculates the quality score of each signal based on the first indicator and the second indicator of each signal; and determines whether the access network device that sends the signal can be used for positioning based on the quality score of each signal and the first threshold, thereby obtaining a valid status code sequence.

[0352] The method for obtaining a valid status code can be found in the description above, and will not be repeated here.

[0353] S808: The terminal device determines the number of valid access network devices based on the valid status code sequence, and further determines whether the first model is available.

[0354] The method for determining whether the first model is usable can be referred to the description above, and will not be repeated here.

[0355] If the first model is unavailable, execute S809.

[0356] If the first model is available, execute S810-811.

[0357] S809. The terminal device sends a measurement report to the LMF, which includes a valid status code sequence. Correspondingly, the LMF receives the measurement report from the terminal device.

[0358] In addition, the measurement report may also include measurement data for each of the M signals (such as first measurement data and / or second measurement data).

[0359] It should be understood that the LMF can take remedial measures based on this measurement report (such as scheduling more access network devices to transmit PRS or switching to traditional positioning methods).

[0360] S810, the terminal device calculates the positioning result and the confidence level of the first model based on the first model.

[0361] The method for calculating the location results and the confidence level of the first model can be referred to the description above, and will not be repeated here.

[0362] S811, The terminal device sends the positioning result and the confidence level of the first model to the LMF. Correspondingly, the LMF receives the positioning result and the confidence level of the first model from the terminal device.

[0363] The following is combined Figure 9 and Figure 10 This application describes in detail the model monitoring device according to embodiments of the present application.

[0364] It should be noted that the module names involved in the embodiments of this application can all be defined as other names, as long as they can achieve the function of each module, and no specific restrictions are placed on the module names.

[0365] Figure 9 This is a schematic diagram of the structure of a model monitoring device 900 provided in an embodiment of this application. Figure 9 As shown, the device 900 includes a processing module 901 and a transceiver module 902.

[0366] In one possible implementation, the device 900 is used to perform the steps executed by the terminal device in the above method embodiments.

[0367] The transceiver module 902 is used to receive M signals from M access network devices, where the M signals are used for positioning. The processing module 901 is used to determine whether a first model can be used for positioning based on a first quantity and N, where N is the number of signals sent by the access network devices required for the first model to perform positioning; wherein, the first quantity is the number of access network devices among the M access network devices that can be used for positioning, and the first quantity is determined based on a first indicator and / or a second indicator corresponding to each of the M access network devices, the first indicator is used to indicate the consistency between the positioning results output by the first model based on the first measurement data of any N signals among the M signals, and the second indicator includes at least two of the following: signal quality, direct path measurement quality, timing measurement quality, or consistency quality; consistency quality is used to indicate the consistency between the second measurement data of each signal among the M signals and the second measurement data of the training data, and timing measurement quality is used to indicate whether the time difference of arrival is within a first range.

[0368] Optionally, the second measurement data may include one or more of the following: Doppler frequency shift, signal strength, carrier phase, or multipath delay.

[0369] Optionally, the consistency quality is determined based on one or more of the following metrics: Doppler shift quality, signal strength quality, carrier phase quality, or multipath delay quality; wherein, Doppler shift quality is used to indicate the consistency between the Doppler shift of each of the M signals and the Doppler shift of the training data, signal strength quality is used to indicate the consistency between the signal strength of each of the M signals and the signal strength of the training data, carrier phase quality is used to indicate the consistency between the carrier phase of each of the M signals and the carrier phase of the training data, and multipath delay quality is used to indicate the consistency between the multipath delay of each of the M signals and the multipath delay of the training data.

[0370] Optionally, the Doppler frequency shift quality is calculated based on the standard deviation of the Doppler frequency shift of each of the M signals and the standard deviation of the Doppler frequency shift of the training data, and / or the average value of the Doppler frequency shift of each of the M signals and the average value of the Doppler frequency shift of the training data; the signal strength quality is calculated based on the standard deviation of the signal strength of each of the M signals and the standard deviation of the signal strength of the training data, and / or the average value of the signal strength of each of the M signals and the average value of the signal strength of the training data; the carrier phase quality is calculated based on the standard deviation of the carrier phase of each of the M signals and the standard deviation of the carrier phase of the training data, and / or the average value of the carrier phase of each of the M signals and the average value of the carrier phase of the training data; or, the multipath delay quality is calculated based on the standard deviation of the multipath delay of each of the M signals and the standard deviation of the multipath delay of the training data, and / or the average value of the multipath delay of each of the M signals and the average value of the multipath delay of the training data.

[0371] Optionally, the first quantity is determined based on the first indicator and / or the second indicator corresponding to each of the M access network devices, including: the first quantity is determined based on the weighted average of the first indicator and the second indicator.

[0372] Optionally, the weighted average of the first and second indicators corresponding to the M access network devices that can be used for positioning is greater than or equal to the first threshold.

[0373] Optionally, the processing module 901 is further configured to: determine whether the first model can be used for positioning based on the first quantity and N, including: determining that the first model cannot be used for positioning when the first quantity is less than N; and determining that the first model can be used for positioning when the first quantity is greater than or equal to N.

[0374] Optionally, the transceiver module 902 is further configured to: send first information to the first network element when the first model cannot be used for positioning, the first information being used to indicate a first number of access network devices that can be used for positioning.

[0375] Optionally, the transceiver module 902 is further configured to: send second information to the first network element when the first model can be used for positioning, the second information being used to indicate the positioning result, the positioning result being obtained by inputting first measurement data of N signals out of M signals into the first model, the N signals being signals sent by the access network devices that can be used for positioning among the M access network devices.

[0376] Optionally, the second information is also used to indicate the confidence level of the first model, which is determined based on the first quantity and M.

[0377] Optionally, the confidence level is determined based on the first quantity and M, as well as the first index and / or second index corresponding to each of the M access network devices.

[0378] In one possible implementation, the device 900 is used to perform the steps executed by the access network device in the above method embodiments.

[0379] The transceiver module 902 is configured to: receive a first request from a terminal device, the first request being used to request monitoring whether a first model is valid, the first model being used for positioning, and the first model requiring signals sent by N access network devices for positioning, the signals being used for positioning, where N is a positive integer; based on the first request, send third information to M access network devices respectively, the third information being used to instruct the sending of signals to the terminal device, where M is an integer greater than N; and receive first information from the terminal device; wherein the first information is used to indicate which of the M access network devices can be used for positioning.

[0380] Optionally, a fourth message is sent to each of the M access network devices. The fourth message is used to indicate the order in which the M access network devices send signals to the terminal device. The first message includes a bit map, where each bit in the bit map is used to indicate whether one of the M access network devices can be used for positioning. The order in which the bits in the bit map indicate whether the M access network devices can be used for positioning is the same as the order indicated by the third message.

[0381] It should be understood that the device 900 here is embodied in the form of a functional module. The term "module" here can refer to application-specific integrated circuits (ASICs), electronic circuits, processors (e.g., shared processors, proprietary processors, or group processors, etc.) and memories for executing one or more software or firmware programs, integrated logic circuits, and / or other suitable components supporting the described functions. In an alternative example, those skilled in the art will understand that the device 900 can specifically be a terminal device or access network device as described in the above embodiments. The device 900 can be used to execute the various processes and / or steps corresponding to the terminal device or access network device in the above method embodiments; to avoid repetition, these will not be described again here.

[0382] The aforementioned device 900 has the function of implementing the corresponding steps performed by the terminal device or access network device in the above method; the above function can be implemented by hardware or by hardware executing corresponding software. The hardware or software includes one or more modules corresponding to the above function.

[0383] In the embodiments of this application, Figure 9The device 900 in the diagram can also be a chip. Correspondingly, the transceiver module 902 can be the transceiver circuit of the chip, which is not limited here.

[0384] Figure 10 A schematic diagram of the structure of the device 1000 provided in an embodiment of this application is shown. The device 1000 includes a processor 1001, a transceiver 1002, and a memory 1003. The processor 1001, transceiver 1002, and memory 1003 communicate with each other through an internal connection path. The memory 1003 is used to store instructions, and the processor 1001 is used to execute the instructions stored in the memory 1003 to control the transceiver 1002 to transmit and / or receive signals.

[0385] It should be understood that the device 1000 may specifically be a terminal device or an access network device as described in the above embodiments, and may be used to execute the various steps and / or processes corresponding to the terminal device or access network device in the above method embodiments. Optionally, the memory 1003 may include a read-only memory and a random access memory, and provide instructions and data to the processor. A portion of the memory may also include non-volatile random access memory. For example, the memory may also store device type information. The processor 1001 may be used to execute instructions stored in the memory, and when the processor 1001 executes instructions stored in the memory, the processor 1001 is used to execute the various steps and / or processes of the above method embodiments. The transceiver 1002 may include a transmitter and a receiver, the transmitter may be used to implement the various steps and / or processes corresponding to the transceiver for performing a transmitting action, and the receiver may be used to implement the various steps and / or processes corresponding to the transceiver for performing a receiving action.

[0386] It should be understood that, in the embodiments of this application, the processor may be a central processing unit (CPU), or it may be other general-purpose processors, digital signal processors (DSPs), application-specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. The general-purpose processor may be a microprocessor or any conventional processor, etc.

[0387] In implementation, each step of the above method can be completed by integrated logic circuits in the processor's hardware or by instructions in software. The steps of the method disclosed in the embodiments of this application can be directly manifested as execution by a hardware processor, or as a combination of hardware and software modules within the processor. The software modules can reside in random access memory, flash memory, read-only memory, programmable read-only memory, electrically erasable programmable memory, registers, or other mature storage media in the art. This storage medium is located in memory, and the processor executes the instructions in the memory, combining them with its hardware to complete the steps of the above method. To avoid repetition, detailed descriptions are omitted here.

[0388] The model monitoring method provided in this application can be applied to terminal devices or access network devices with communication functions. The specific device configuration of the terminal device or access network device can be referred to the above-mentioned descriptions, and will not be repeated here.

[0389] This application provides a terminal device, which includes a processor and a memory; the memory stores computer execution instructions; the processor executes the computer execution instructions stored in the memory, causing the terminal device to perform the above-described method.

[0390] This application provides a chip. The chip includes a processor, which is used to call a computer program in memory to execute the technical solutions in the above embodiments. Its implementation principle and technical effects are similar to those in the related embodiments described above, and will not be repeated here.

[0391] This application also provides a computer-readable storage medium. The computer-readable storage medium stores a computer program. When the computer program is executed by a processor, it implements the methods described above. The methods described in the above embodiments can be implemented wholly or partially by software, hardware, firmware, or any combination thereof. If implemented in software, the functionality can be stored as one or more instructions or code on or transmitted over the computer-readable medium. The computer-readable medium can include computer storage media and communication media, and can also include any medium that can transfer a computer program from one place to another. The storage medium can be any target medium accessible by a computer.

[0392] In one possible implementation, a computer-readable medium may include RAM, ROM, compact disc read-only memory (CD-ROM) or other optical disc storage, disk storage or other magnetic storage devices, or any other medium targeted to carry or to store the required program code in the form of instructions or data structures, and accessible by a computer. Furthermore, any connection is appropriately referred to as a computer-readable medium. For example, if software is transmitted from a website, server, or other remote source using coaxial cable, fiber optic cable, twisted pair, DSL, or wireless technologies such as infrared, radio, and microwave, then coaxial cable, fiber optic cable, twisted pair, DSL, or wireless technologies such as infrared, radio, and microwave are included in the definition of medium. As used herein, disks and optical discs include laser discs, Digital Versatile Discs (DVDs), floppy disks, and Blu-ray discs, where disks typically reproduce data magnetically, while optical discs optically reproduce data using lasers. Combinations of the above should also be included within the scope of computer-readable media.

[0393] This application provides a computer program product, which includes a computer program that, when run, causes a computer to perform the above-described method.

[0394] This application describes embodiments of methods, apparatus (systems), and computer program products according to embodiments of this application with reference to flowchart illustrations and / or block diagrams. It should be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processing unit of a general-purpose computer, special-purpose computer, embedded processor, or other programmable device to produce a machine, such that the instructions, which execute via the processing unit of the computer or other programmable data processing device, generate instructions for implementing the flowchart illustrations. Figure 1 One or more processes and / or boxes Figure 1 A device that provides the functions specified in one or more boxes.

[0395] The above detailed embodiments further illustrate the purpose, technical solution, and beneficial effects of the embodiments of this application. It should be understood that the above are merely specific embodiments of the embodiments of this application and are not intended to limit the protection scope of the embodiments of this application. Any modifications, equivalent substitutions, improvements, etc., made on the basis of the technical solutions of the embodiments of this application should be included within the protection scope of the embodiments of this application.

Claims

1. A model monitoring method, characterized in that, The method includes: Receive M signals from M access network devices, the M signals being used for positioning; Based on the first quantity and N, it is determined whether the first model can be used for positioning, where N is the number of signals sent by the access network device required for the first model to perform positioning. Wherein, the first quantity is the number of access network devices among the M access network devices that can be used for positioning. The first quantity is determined based on a first indicator and / or a second indicator corresponding to each of the M access network devices. The first indicator is used to indicate the consistency between the positioning results output by the first model based on the first measurement data of any N signals among the M signals. The second indicator includes at least two of the following: Signal quality, direct path measurement quality, timing measurement quality, or consistency quality; the consistency quality is used to indicate the consistency between the second measurement data of each of the M signals and the second measurement data of the training data, and the timing measurement quality is used to indicate whether the arrival time difference is within a first range.

2. The method according to claim 1, characterized in that, The second measurement data includes one or more of the following: Doppler shift, signal strength, carrier phase, or multipath delay.

3. The method according to claim 2, characterized in that, The consistency quality is determined based on one or more of the following metrics: Doppler frequency shift quality, signal strength quality, carrier phase quality, or multipath delay quality; Wherein, the Doppler frequency shift quality is used to indicate the consistency between the Doppler frequency shift of each of the M signals and the Doppler frequency shift of the training data; the signal strength quality is used to indicate the consistency between the signal strength of each of the M signals and the signal strength of the training data; the carrier phase quality is used to indicate the consistency between the carrier phase of each of the M signals and the carrier phase of the training data; and the multipath delay quality is used to indicate the consistency between the multipath delay of each of the M signals and the multipath delay of the training data.

4. The method according to claim 3, characterized in that, The Doppler shift quality is calculated based on the standard deviation of the Doppler shift of each of the M signals and the standard deviation of the Doppler shift of the training data, and / or the average value of the Doppler shift of each of the M signals and the average value of the Doppler shift of the training data; The signal strength quality is calculated based on the standard deviation of the signal strength of each of the M signals and the standard deviation of the signal strength of the training data, and / or the average signal strength of each of the M signals and the average signal strength of the training data; The carrier phase quality is calculated based on the standard deviation of the carrier phase of each of the M signals and the standard deviation of the carrier phase of the training data, and / or the average value of the carrier phase of each of the M signals and the average value of the carrier phase of the training data; or, The multipath delay quality is calculated based on the standard deviation of the multipath delay of each of the M signals and the standard deviation of the multipath delay of the training data, and / or the average value of the multipath delay of each of the M signals and the average value of the multipath delay of the training data.

5. The method according to claim 1, characterized in that, The first quantity is determined based on a first indicator and / or a second indicator corresponding to each of the M access network devices, including: The first quantity is determined based on the weighted average of the first indicator and the second indicator.

6. The method according to claim 5, characterized in that, The weighted average of the first indicator and the second indicator corresponding to the M access network devices that can be used for positioning is greater than or equal to the first threshold.

7. The method according to any one of claims 1 to 6, characterized in that, The step of determining whether the first model can be used for localization based on the first quantity and N includes: If the first quantity is less than N, it is determined that the first model cannot be used for localization; If the first quantity is greater than or equal to N, it is determined that the first model can be used for localization.

8. The method according to claim 7, characterized in that, The method further includes: If the first model cannot be used for positioning, first information is sent to the first network element, the first information being used to indicate the first number of access network devices that can be used for positioning.

9. The method according to claim 7, characterized in that, The method also includes When the first model can be used for positioning, second information is sent to the first network element. The second information is used to indicate the positioning result. The positioning result is obtained by inputting the first measurement data of N signals out of the M signals into the first model. The N signals are signals sent by the access network devices that can be used for positioning among the M access network devices.

10. The method according to claim 9, characterized in that, The second information is also used to indicate the confidence level of the first model, which is determined based on the first quantity and M.

11. The method according to claim 10, characterized in that, The confidence level is determined based on the first quantity and M, as well as the first indicator and / or the second indicator corresponding to each of the M access network devices.

12. A model monitoring method, characterized in that, The method includes: Receive a first request from a terminal device, the first request being used to request monitoring whether a first model is valid, the first model being used for positioning, and the first model requiring N signals sent by access network devices for positioning, the signals being used for positioning, where N is a positive integer; Based on the first request, third information is sent to M access network devices respectively, the third information being used to instruct the terminal device to send the signal, where M is an integer greater than N; The system receives first information from the terminal device; wherein the first information is used to indicate the access network devices among the M access network devices that can be used for positioning, and the number of access network devices among the M access network devices that can be used for positioning is a first quantity; the first quantity is determined based on a first indicator and / or a second indicator corresponding to each of the M access network devices; the first indicator is used to indicate the consistency between the positioning results output by the first model based on the first measurement data of any N signals among the M signals, and the second indicator includes at least two of the following: signal quality, direct path measurement quality, timing measurement quality, or consistency quality; the consistency quality is used to indicate the consistency between the second measurement data of each signal among the M signals and the second measurement data of the training data, and the timing measurement quality is used to indicate whether the time difference of arrival is within a first range.

13. The method according to claim 12, characterized in that, The method further includes: The fourth information is sent to each of the M access network devices, and the fourth information is used to indicate the order in which the M access network devices send the signal to the terminal device; The first information includes a bitmap, where each bit in the bitmap is used to indicate whether one of the M access network devices can be used for positioning, and the order in which the bits in the bitmap indicate whether the M access network devices can be used for positioning is the same as the order indicated by the third information.

14. A communication device, characterized in that, include: Processor and memory; The memory stores computer-executed instructions; The processor executes computer execution instructions stored in the memory, causing the apparatus to perform the method as described in any one of claims 1-13.

15. A chip system, characterized in that, It includes at least one processor and a communication interface, the communication interface and the at least one processor being interconnected via a line, the at least one processor being used to run a computer program or instructions to perform the method as described in any one of claims 1-13.

16. A computer-readable storage medium storing a computer program, characterized in that, When the computer program is executed by a processor, it implements the method as described in any one of claims 1-13.

17. A computer program product, characterized in that, Includes a computer program that, when run, causes a computer to perform the method as described in any one of claims 1-13.

Images