Used to evaluate consistency in AI / ML localization and relative TRP location information of GDOP.
By providing relative spatial domain information in the wireless communication network to assist the AI/ML model of user equipment in positioning, the problems of positioning consistency and GDOP are solved, and more efficient and accurate user equipment positioning is achieved.
Patent Information
- Application Number
- CN202610616024.2
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Priority Date
- 2025-05-09
- Filing Date
- 2026-05-07
- Publication Date
- 2026-11-10
AI Technical Summary
In wireless communication networks, existing technologies struggle to effectively utilize artificial intelligence or machine learning for user equipment positioning, particularly in ensuring positioning consistency and geometrical accuracy decay (GDOP).
By providing relative spatial domain information, such as relative position, relative distance, and relative angle, it assists the AI/ML model of user equipment in localization, ensures consistency between training and inference, and selects the Transmitter Receiving Point (TRP) with the best geometric accuracy, thereby reducing signaling overhead and processing costs.
It improves the accuracy and consistency of user equipment positioning, reduces signaling and processing overhead, and optimizes the performance and positioning quality of AI/ML models.
Smart Images

Figure CN123075352A_ABST
Abstract
Description
Technical Field
[0001] The exemplary and non-limiting embodiments generally relate to user equipment location, and more specifically to the location of user equipment in a wireless network based on artificial intelligence or machine learning. Background Technology
[0002] In wireless communication networks, communication devices can access the network via access network nodes. Summary of the Invention
[0003] The subject matter of the independent claims is provided in several respects. Several other aspects are provided in the subject matter of the dependent claims. Attached Figure Description
[0004] The foregoing aspects and other features are explained in the following description in conjunction with the accompanying drawings, wherein:
[0005] Figure 1 This is a block diagram of one possible and non-limiting example system in which exemplary embodiments may be practiced;
[0006] Figure 2 Signaling flows according to one or more example embodiments of this disclosure are shown;
[0007] Figure 3 A flowchart is shown according to one or more example embodiments of the present disclosure;
[0008] Figure 4 A flowchart is shown according to one or more example embodiments of the present disclosure;
[0009] Figure 5 A flowchart illustrating one or more example embodiments according to this disclosure is shown; and
[0010] Figure 6 A flowchart is shown according to one or more example embodiments of the present disclosure. Detailed Implementation
[0011] Go to Figure 1 This figure illustrates a block diagram of one possible and non-limiting example in which the example can be practiced. User equipment (UE) 110, radio access network (RAN) node 170, and (multiple) network elements 190 are shown. Examples of network devices, network equipment, or network entities may be understood to include, for example, at least a portion of a transmit and receive point (TRP), a cell, a base station (gNB), or a node. Figure 1In the example, UE 110 wirelessly communicates with wireless network 100. UE 110 can be a wireless device capable of accessing wireless network 100. UE 110 may include one or more processors 120, one or more memories 125, and one or more transceivers 130 interconnected via one or more buses 127. Each of the one or more transceivers 130 may include a receiver (Rx) 132 and a transmitter (Tx) 133. The one or more buses 127 may be an address bus, a data bus, or a control bus, and may include any interconnection mechanism, such as a series of lines on a motherboard or integrated circuit, fiber optic cable, or other optical communication device. The one or more transceivers 130 may be connected to one or more antennas 128. The one or more memories 125 may include computer program code 123. UE 110 may include module 140, which includes one or both of portions 140-1 and / or 140-2, which may be implemented in various ways. Module 140 may be implemented in hardware as module 140-1, such as as a portion of one or more processors 120. Module 140-1 can also be implemented as an integrated circuit or via other hardware, such as a programmable gate array. In another example, module 140 can be implemented as module 140-2, which is implemented as computer program code 123 and executed by one or more processors 120. For example, one or more memories 125 and computer program code 123 can be configured, together with one or more processors 120, to cause UE 110 to perform one or more operations as described herein. UE 110 can communicate with RAN node 170 via wireless link 111.
[0012] In this example, RAN node 170 is a base station that provides access to wireless network 100 by wireless devices such as UE 110. For example, RAN node 170 could be a base station for 5G (also known as New Radio (NR)). In 5G, RAN node 170 could be an NG-RAN node, which is defined as a base station (gNB) for 5G / NR or a Next Generation Evolution Node B (ng-eNB), such as an LTE base station. A gNB is a node that provides NR user plane and control plane protocol termination to the UE and is connected to the fifth-generation core network (5GC) (such as, for example, multiple network elements 190) via an NG interface. An ng-eNB is a node that provides Evolved Universal Terrestrial Radio Access (E-UTRA) user plane and control plane protocol termination to the UE and is connected to the 5GC via a Next Generation (NG) interface. An NG-RAN node can include multiple gNBs, and a gNB can also include a central unit (CU) (gNB-CU) 196 and multiple distributed units (DUs) (gNB-DU), where DU 195 is shown. Note that a DU may include or be coupled to and control a Radio Unit (RU). A gNB-CU is a logical node that carries the Radio Resource Control (RRC), Service Data Adaptive Protocol (SDAP), and Packet Data Convergence Protocol (PDCP) protocols of a gNB, or the RRC and PDCP protocols of an en-gNB that control the operation of one or more gNB-DUs. The gNB-CU terminates the F1 interface connected to the gNB-DU. The F1 interface is shown as reference numeral 198, but reference numeral 198 also shows the link between remote and centralized elements of RAN node 170, such as between gNB-CU 196 and gNB-DU 195. A gNB-DU is a logical node that carries the Radio Link Control (RLC), Media Access Control (MAC), and Physical (PHY) layers of a gNB or en-gNB, and its operation is partially controlled by the gNB-CU. A gNB-CU supports one or more cells. A cell is supported by only one gNB-DU. The gNB-DU terminates the F1 interface 198 connected to the gNB-CU. Note that DU 195 is considered to include transceiver 160, for example, as part of the RU; however, some examples of this may have transceiver 160 as part of a separate RU, for example, controlled by and connected to DU 195. RAN node 170 may also be an eNB (evolved NodeB) base station, a Long Term Evolution (LTE) base station, or any other suitable base station or node.
[0013] RAN node 170 includes one or more processors 152, one or more memories 155, one or more network interfaces (N / WI / F) 161, and one or more transceivers 160 interconnected via one or more buses 157. Each of the one or more transceivers 160 includes Rx 162 and Tx 163. The one or more transceivers 160 are connected to one or more antennas 158. The one or more memories 155 include computer program code 153. CU 196 may include one or more processors 152, memories 155, and network interfaces 161. Note that DU 195 may also include its own one or more memories and processors, and / or other hardware, but these are not shown.
[0014] RAN node 170 includes module 150, which includes one or both of portions 150-1 and / or 150-2, and can be implemented in various ways. Module 150 can be implemented in hardware as module 150-1, such as as part of one or more processors 152. Module 150-1 can also be implemented as an integrated circuit or by other hardware, such as a programmable gate array. In another example, module 150 can be implemented as module 150-2, which is implemented as computer program code 153 and executed by one or more processors 152. For example, one or more memories 155 and computer program code 153 are configured, together with one or more processors 152, to cause RAN node 170 to perform one or more operations as described herein. Note that the functionality of module 150 can be distributed, such as being distributed between DU 195 and CU 196, or implemented only in DU 195.
[0015] One or more network interfaces 161 communicate over a network, such as via links 176 and 131. Two or more gNBs 170 may communicate using, for example, link 176. Link 176 may be wireless, wired, or both, and may implement, for example, an Xn interface for 5G, an X2 interface for LTE, or other suitable interfaces for other standards.
[0016] One or more buses 157 may be address buses, data buses, or control buses, and may include any interconnection mechanism, such as a series of lines on a motherboard or integrated circuit, optical fiber or other optical communication equipment, wireless channels, etc. For example, one or more transceivers 160 may be implemented as a Remote Radio Unit (RRH) 195 for LTE or a DU 195 for gNB implementation for 5G, while other elements of the RAN node 170 may be physically located different from the RRH / DU. One or more buses 157 may be partially implemented as, for example, fiber optic cables or other suitable network connections to connect other elements of the RAN node 170 (e.g., CU or gNB-CU) to the RRH / DU 195. Reference numeral 198 also indicates these suitable network links(s).
[0017] Note that the description in this article indicates that a "cell" performs functions, but it should be clear that the equipment forming the cell can perform these functions. A cell constitutes part of a base station. That is, each base station can have multiple cells. For example, for a single carrier frequency and associated bandwidth, there can be three cells, each covering one-third of a 360-degree area, such that the coverage area of a single base station is approximately elliptical or circular. Furthermore, each cell can correspond to a single carrier, and a base station can use multiple carriers. Therefore, if each carrier has three 120-degree cells and two carriers, the base station has a total of six cells.
[0018] Wireless network 100 may include one or more network elements 190, which may include core network functions and provide connectivity to other networks (such as telephone networks and / or data communication networks (e.g., the Internet)) via one or more links 181. Such core network functions for 5G may include (multiple) location management functions (multiple LMFs), (multiple) access and mobility management functions (multiple AMFs), and / or user plane functions (multiple UPFs), and / or (multiple) session management functions (multiple SMFs). Such core network functions for LTE may include mobility management entity (MME) / serving gateway (serving gateway SGW) functions. These are merely exemplary functions that may be supported by (multiple) network elements 190, and note that both 5G and LTE functions may be supported. RAN node 170 is coupled to network element 190 via link 131. Link 131 may be implemented as, for example, an NG interface for 5G, or an S1 interface for LTE, or other suitable interfaces for other standards. Network element 190 includes one or more processors 175 interconnected via one or more buses 185, one or more memories 171, and one or more network interfaces (N / WI / F) 180. The one or more memories 171 include computer program code 173. The one or more memories 171 and the computer program code 173 are configured, together with the one or more processors 175, to cause network element 190 to perform one or more operations.
[0019] Wireless network 100 can implement network virtualization, which is the process of combining hardware and software network resources and network functions into a single software-based management entity or virtual network. Network virtualization involves platform virtualization, often combined with resource virtualization. Network virtualization is classified into external virtualization and internal virtualization. External virtualization combines many networks or parts of networks into virtual units, while internal virtualization provides network-like functionality to software containers on a single system. Note that the virtualized entities created by network virtualization are still implemented to some extent using hardware (such as processors 152 or 175 and memory 155 and 171), and these virtualized entities also produce technical effects.
[0020] Computer-readable storage devices 125, 155, and 171 can be of any type suitable for the local technical environment and can be implemented using any suitable data storage technology, such as semiconductor-based memory devices, flash memory, magnetic memory devices and systems, optical memory devices and systems, non-transitory memory, transient memory, fixed memory, and removable memory. Computer-readable storage devices 125, 155, and 171 can be components for performing storage functions. Processors 120, 152, and 175 can be of any type suitable for the local technical environment and, as non-limiting examples, can include one or more of the following: general-purpose computers, special-purpose computers, microprocessors, digital signal processors (DSPs), and processors based on multi-core processor architectures. Processors 120, 152, and 175 can be components for performing functions, such as controlling UE 110, RAN node 170, and other functions described herein.
[0021] Generally speaking, various embodiments of UE 110 may include, but are not limited to, cellular phones, such as smartphones, tablets, personal digital assistants (PDAs) with wireless communication capabilities, portable computers with wireless communication capabilities, image capture devices (such as digital cameras with wireless communication capabilities), gaming devices with wireless communication capabilities, music storage and playback devices with wireless communication capabilities, internet devices (allowing wireless internet access and browsing), tablets with wireless communication capabilities, and portable units or terminals that combine these functions.
[0022] This embodiment particularly relates to systems and methods for using auxiliary data, such as spatial domain information, in conjunction with artificial intelligence or machine learning (AI / ML) localization. For example, one or more UE-side AI / ML models can be used with auxiliary data to determine the location or position of a communication device, such as a UE on a communication network. In some embodiments, the auxiliary data can be used to ensure consistency between the training and inference results of the UE's (multiple) AI / ML models. In one example, the auxiliary data can be used to ensure consistency between the training and inference of network (NW)-side conditions. In some embodiments, spatial domain information can include at least one of the following: location, distance, angle, power value, latitude coordinates, or longitude coordinates associated with a network node (such as a TRP).
[0023] In a non-limiting example of AI / ML-based positioning, auxiliary data or information can be provided to the UE from the Location Management Function (LMF) for AI / ML positioning. The AI / ML model on the UE side can use the auxiliary data provided by the LMF to estimate the UE's location. Auxiliary data may include, for example, the geographic coordinates of the TRP, the downlink positioning reference signal (DL-PRS) configuration of the candidate NR TRP, etc. See Table 1 for an example list of information that can be provided as auxiliary data. LMF Table 1: Auxiliary Data in NG-RAN
[0024] In some embodiments, auxiliary information (e.g., any information listed in Table 1) may be provided implicitly or explicitly by a network device (such as the LMF). In some cases, the UE may request the auxiliary information to be provided explicitly or implicitly. Alternatively, if provided implicitly, some information associated with the auxiliary information (e.g., relative auxiliary information) may be signaled by the LMF without disclosing actual information (such as the location of the TRP). This may be preferred in some network configurations to protect network privacy and security. In some embodiments, this information may be used to determine whether the associated auxiliary information is still valid or consistent between training and inference, as described below. In some cases, auxiliary information is not provided to the UE from the LMF. In such scenarios, when auxiliary information is not provided, the UE may assume that the auxiliary information is consistent between training and inference. In some cases, auxiliary information may be provided to the UE explicitly from the LMF.
[0025] This disclosure illustrates a method for using auxiliary data with AI / ML localization, such as a UE-side AI / ML model for direct localization.
[0026] In some embodiments, network devices (such as LMF) may assist the UE in reasoning, detection, or data collection purposes to assess or ensure the general consistency of the content of TRP location or auxiliary data information.
[0027] In the first example, the NW can provide relative spatial domain information, such as relative position, relative distance, relative angle, relative coordinates, etc., for each TRP in the network via the LMF, regarding the corresponding reference spatial domain information. In some embodiments, the relative spatial domain information and / or reference spatial domain information can be associated with a corresponding ID. For example, for location information, auxiliary data including multiple data points (such as multiple geographic coordinates) can create an associated ID for each geographic coordinate. Alternatively, the associated ID can be created for each node or reference location with respect to its location data (e.g., an associated ID representing the geographic coordinates of the TRP). The relative position information for each TRP can be relative to a specific reference location. Furthermore, this specific reference location can be unknown to the UE, i.e., its actual location can be unknown to the UE. For example, the NW indicates [Associated ID for TRP#1: delta-Latitude=+100, delta-Longitude=-200 (in milliarcseconds); Associated ID for TRP#2=delta-Latitude=+200, delta-Longitude=+150]. Alternatively or concurrently, the network may indicate whether the reference location is always fixed, such as via a binary flag. In some cases, even if the reference location is fixed, the TRP location may change (which is visible to the UE via a change in the associated ID). In some embodiments, if the reference location is not always fixed, the network may use another ID or use it as part of the associated ID to indicate the reference location. For example, the network may indicate [Associated ID for reference location = ID#142954].
[0028] In the second example, the network can provide relative spatial domain information about each other between TRPs via the LMF, such as relative position, relative distance, relative angle, relative coordinates, etc. In some embodiments, the relative spatial domain information can be associated with an ID.
[0029] For example, for information #7 in Table 1, for three TRPs configured for DL-PRS transmission, the network can provide a (triangular) matrix with elements indicating the distance D between TRPs and the vector between TRPs (e.g., from the TRP in the first column to the TRP in the first row) together with the angle A about the reference axis, as follows:
[0030] In the provided example, the network does not need to disclose the actual TRP location in the network (which is crucial, for example, for security reasons), while also assisting the UE in checking the consistency of TRP locations between training and inference, as well as selecting TRPs in terms of geometric precision decay (GDOP) based on the relative location information of TRPs, or enabling the UE to directly train its AI / ML model (e.g., as input) using the relative location information of TRPs in a standardized manner.
[0031] The impact of the associated ID message transmitted from the LMF to the UE is that the size of the information sent by the signal is proportional to the number of TRPs represented by that associated ID.
[0032] In some embodiments, a method is provided to reduce the signaling overhead of associated ID updates, wherein the UE notifies the network of its interest in changes to the associated ID only when the difference between the associated ID and a previous associated ID exceeds a certain threshold, for example, based on the expected performance of its AI / ML model(s). This threshold can be set with respect to changes in distance, changes in angle, or combinations thereof. In some embodiments, the threshold can be configured by the network, or determined by the UE and indicated to the network.
[0033] While the provided example uses info#7, i.e., TRP location, for ease of illustration, this method is also applicable to other spatial domain information included in (UE-based) AI / ML positioning assistance data, such as info#16: TRP beam / antenna information (including azimuth, elevation, and relative power between PRS resources for each angle of each TRP). In this example, an association ID can be generated for a TRP, representing its specific reference spatial domain information on the network or its relative spatial domain information (e.g., azimuth, elevation, etc.) with respect to other TRPs on the network.
[0034] In some cases, the LMF or UE may initiate a session for positioning. For AI / ML positioning, the session may involve the UE performing measurements it collects from reference signals (e.g., DL PRS) transmitted by the network to perform one or more of the following: inference using location information from (multiple) UE-side AI / ML models, where the UE uses the collected measurements as input to its AI / ML models; performance monitoring of (multiple) UE-side AI / ML models, where, for example, the UE uses the measurements as input to its (multiple) AI / ML models and compares its output with the real location information associated with the measurements; training or retraining (multiple) UE-side AI / ML models; and data collection for AI / ML purposes, such as data that will later be transmitted to the UE itself or a server (e.g., a UE vendor-side OTT server outside the 3GPP network) for training or monitoring.
[0035] Go to Figure 2 Signaling flow 200 between UE 202 and NW 204 is shown. At 206, NW 204 may request capability information from the UE regarding support for AI / ML positioning, including support for AI- or machine learning-based positioning using relative spatial domain information. The associated spatial domain information is implicitly indicated through the use of relative spatial domain information. Figure 2 In the example, the auxiliary data is info#7, and the relative spatial domain information is the relative location information, i.e., implicit info#7. The UE's capability can indicate whether the UE can use the relative location information to check the consistency between training and inference (e.g., implicit information relative to the TRP location). However, this is only an illustrative example, and it should be understood that the auxiliary data can be different spatial domain information, such as any spatial domain information shown in Table 1, e.g., info#16. NW 204 can be, for example, the LMF described herein.
[0036] At 208, when NW 204 requests in 206 (if present) or requests proactively, UE 202 provides its capability information, which includes an indication that UE 202 supports the use of relative location information associated with info#7, for example, for consistency check purposes for AI / ML positioning.
[0037] At 210, UE 202 can request auxiliary data (AD) for AI / ML positioning, which contains implicit relative location information associated with info#7, such as geographic coordinates.
[0038] In some embodiments, this request may be part of UE 202 sending an on-demand PRS request, wherein UE 202 may instruct DL PRS to configure the required parameter settings.
[0039] At 212, when UE 202 requests (if present) in 210 or actively requests it, NW 204 provides UE 202 with auxiliary data for AI / ML positioning, which includes at least relative position information of the TRP, or an ID associated with that relative position information. The relative position information may be represented in Cartesian, polar, cylindrical, or spherical coordinates, for example, indicating the difference in distance on the x / y / x-axis, latitude / longitude, or in terms of range, such as distance and / or angle. In some embodiments, existing IEs in LPP (TS 37.355) may be utilized, for example, RelativeLocation-r16. The relative position information may also indicate the quality of the position information (e.g., the uncertainty or confidence level of the position coordinates, for example, as in LocationUncertainty-r16).
[0040] In the first example, NW 204 provides relative position information of the TRP with respect to a specific reference location unknown to UE 202. To do this, NW 204 determines the reference location based on its own implementation (e.g., it can choose one of the following as a reference: the TRP location, the centroid of the TRP location, an arbitrary / random geographical location within the network coverage area, etc.).
[0041] In this example, NW 204 indicates [Association ID for TRP#1: delta-latitude=+100, delta-longitude=-200 (in milliarcseconds); Association ID for TRP#2=delta-latitude=+200, delta-latitude=+150]. Furthermore, NW 204 can indicate whether the reference position is always fixed via, for example, a binary flag. Even if the reference position is fixed, the TRP position may change, which is visible to UE 202 via the change in association ID. In some cases, if the reference position is not always fixed, NW 204 may use another ID or use it as part of the association ID to signal the reference position (e.g., NW indicates [Association ID for reference position=ID#142954]).
[0042] In the second example, NW 204 provides relative position information of TRPs about each other, such as the distance D and / or angle A between each pair of TRPs in the TRP list from DLPRS transmission.
[0043] In this example, for the three TRPs configured for DL PRS transmission, the NW 204 provides an element-wise (triangular) matrix indicating the distance D between each TRP, together with the angle A of the vector between the TRPs (e.g., from the TRP in the first column to the TRP in the first row) relative to a reference vector, as follows:
[0044] In some embodiments, angle A may represent the angular difference between vectors originating from a reference point and pointing towards the TRP location. Where a reference point and / or vector is utilized (e.g., for angle information), NW 204 may also indicate the actual position information of the reference point and / or vector (if NW preferentially discloses this information). Alternatively, NW 204 may indicate whether the reference position and / or axis is always fixed via, for example, a binary flag. In some cases, if the reference point and / or axis is not always fixed, NW 204 may utilize another ID to indicate the reference point and / or axis (e.g., NW indicates [Associated ID for reference position = ID#142954]).
[0045] While NW204 can provide actual values of relative location information (e.g., the values of D and A between TRPs), NW204 can also provide an associated ID for each value. For example:
[0046] In some embodiments, the associated ID for each value may represent the size of the corresponding value (e.g., the distance difference between ID#215 and ID#125 is greater than the distance between ID#135 and ID#125).
[0047] In some embodiments, in addition to the TRP ID, NW 204 may also indicate the Physical Cell ID (PCI), Global Cell ID (GCI), ARFCN, or PRS ID of the candidate NR TRP used for measurement.
[0048] At 214, UE 202 utilizes the received implicit information Info#7 relative to the TRP location (as well as any other information in the AD) in one or more of the following ways.
[0049] If AD is provided for inference, UE 202 performs a consistency check by identifying whether the implicit information #7 currently used for inference differs from the information #7 used by UE 202 in the past for training one or more AI / ML models. That is, UE 202 checks for discrepancies in the TRP location between the measurements used for training and those used for inference. UE 202 can then assess and determine whether the degree of difference between training and inference is tolerable, sufficient, or acceptable, for example, in terms of AI / ML model performance and / or location QoS requirements.
[0050] UE 202 then determines whether to use the provided AD for inference, or for (re)training and / or monitoring, thereby determining whether to use the AD to perform data collection.
[0051] UE 202 also utilizes relative TRP location information to select from the configured TRPs that can provide the best geometrical accuracy attenuation (GDOP) (or any other DOP metric, such as horizontal or vertical DOP) by combining the provided information with coarse UE 202 location information (including angle / time / power-based measurements from the TRPs).
[0052] If UE 202 will use AD for training data collection, UE 202 stores implicit info#7 or its associated ID to utilize the consistency check as described above when performing any inference later. In one embodiment, UE 202 may categorize the measurements it collects based on its associated ID / info#7 when creating different datasets for training and / or monitoring.
[0053] At 216, UE 202 notifies NW 204 about its use of AD. For example, UE 202 may indicate whether implicit information Info#7 is consistent between training and inference, thereby indicating whether it can use implicit information Info#7 to perform inference. In some embodiments, UE 202 may indicate the degree of difference in the AD used between training and inference.
[0054] In one embodiment, UE 202 informs NW 204 which of the configured TRPs(s) it has selected for collecting DL measurements and can report the calculated GDOP based on this (e.g., if configured).
[0055] At 218, based on the foregoing steps, UE 202 and / or NW 204 determine and perform the necessary LCM actions, such as inference, monitoring, training, or data collection on a specific AI / ML model(s), or switching from one model to another for use in inference, or switching / rolling back between AI / ML and / or non-AI / ML methods (e.g., traditional methods) for localization. For example, UE 202 may indicate that performance monitoring or further retraining of its AI / ML model is needed because the TRP location differs significantly between training and inference; or UE 202 may indicate that it wishes to use AD to collect measurements in order to train a new AI / ML model from scratch.
[0056] To reduce signaling and processing overhead, one embodiment considers the scenario where UE 202 may only want to receive updates that are critical to changes in the associated ID, i.e., only when the amount of change is critical to the AI / ML model it is used for positioning. As an example, UE 202 could determine that a change has a significant impact on the performance of its AI / ML model only if the amount of change in the TRP location exceeds a certain threshold.
[0057] Therefore, UE 202 can request an updated association ID from the network only if the data between the previous association ID and the current association ID exceeds a certain threshold, based on the sensitivity of its (multiple) AI / ML models. For example, when UE 202 requests auxiliary data for AI / ML positioning, this request can be sent at 210.
[0058] Using this method, the LMF determines when to broadcast the association ID (e.g., at 212). If the relative distance changes little (e.g., does not exceed a predetermined threshold set by UE 202), the LMF does not send the association ID. By avoiding such redundant updates, the network thus reduces signaling overhead and processing costs at UE 202. In some embodiments, the threshold may be configured by the network, or determined by the UE and indicated to the network.
[0059] According to the first aspect, the subject matter is provided for: (i) receiving relative spatial domain information about a reference spatial domain from at least one network node, wherein the reference spatial domain information is unknown to the device; and (ii) using the relative spatial domain information in conjunction with positioning based on artificial intelligence or machine learning to determine the location of the device. The first aspect may be implemented in algorithms, encoded in a distribution medium or in a computer program product, and implemented as methods executed by the devices. The devices may include components for causing the devices to perform at least the methods. The components may include at least one processor; and at least one memory storing the algorithms as instructions that, when executed by the at least one processor, cause the devices to perform at least the methods.
[0060] The first aspect may include any single feature or any combination of features from the following: wherein, when executed using at least one processor, the instruction further causes the device to: provide capability information of the device indicating the ability to perform artificial intelligence or machine learning-based positioning using the relative spatial domain information, wherein, when executed using the at least one processor, the instruction further causes the device to: request the relative spatial domain information, wherein the request indicates a threshold, and the relative spatial domain information is received when the difference between the relative spatial domain information and previous relative spatial domain information exceeds the threshold, wherein the relative spatial domain information is represented by at least one associated identifier, wherein the spatial domain information is associated with at least one of the following: location, distance, angle, power value, latitude coordinates, or longitude coordinates, wherein the spatial domain information includes at least one of the following: spatial orientation information of one or more reference signal resources of at least one network node; geographic coordinates of at least one network node; effective area of the spatial domain information; location of one or more positioning reference units. The instruction includes: positioning information; beam or antenna information of at least one network node; or expected angle information of at least one network node, wherein at least one network node includes at least one transmit / receive point, wherein relative spatial domain information indicates whether reference spatial domain information is fixed, or an identifier associated with reference spatial domain information, wherein using relative spatial domain information includes performing a consistency / validity check of the spatial domain information, wherein when the instruction is executed using at least one processor, the device further causes the device to perform: reporting the results of the consistency / validity check to the network, wherein when the instruction is executed using at least one processor, the device further causes the device to perform at least one of: localization inference using an artificial intelligence or machine learning model; artificial intelligence or machine learning model monitoring; training data collection; retraining of an artificial intelligence or machine learning model; or training of a new artificial intelligence or machine learning model, wherein when the instruction is executed using the at least one processor, the device further causes the device to perform: selecting network nodes to be used for artificial intelligence or machine learning-based localization based on the relative spatial domain information.
[0061] Figure 3 Example method 300 is shown. Method 300 can be implemented by an instance of the user equipment described herein. Figure 3The steps shown in the boxes are not considered mandatory. Method 300 can be implemented by a processor. At 302, method 300 may include the processor providing capability information of the device, indicating the ability to perform AI- or machine learning-based localization using relative spatial domain information. At 304, method 300 may include the processor, in response to a request, receiving relative spatial domain information about reference spatial domain information, wherein the reference spatial domain information is unknown to the device. At 306, method 300 may include the processor using the relative spatial domain information in conjunction with AI / ML learning-based localization to determine the location of the device, including a check of the spatial domain information. At 306, method 300 may include the processor reporting the results of a consistency / validity check to the network. At 306, method 300 may include the processor determining and performing (multiple) actions based on the results.
[0062] According to the second aspect, the following are provided: (i) determining relative spatial domain information of at least one network node with respect to reference spatial domain information, wherein the relative spatial domain information is used in conjunction with a positioning technique based on artificial intelligence or machine learning to determine the location of a user equipment, wherein the reference spatial domain information is unknown to the user equipment; and (ii) transmitting the relative spatial domain information to the user equipment. The second aspect may be implemented in algorithms, encoded in a distribution medium or in a computer program product, and implemented as methods executed by means of means of means. The means may include components for causing the means to perform at least the methods. The components may include at least one processor; and at least one memory storing the algorithms as instructions, which, when executed by the at least one processor, cause the means to perform at least the methods.
[0063] The second aspect may include any single feature or any combination of features from the following: wherein, when executed using at least one processor, the instruction further causes the device to perform: receiving at least one result of a consistency / validity check of spatial domain information from the user equipment; wherein, when executed using the at least one processor, the instruction further causes the device to perform: receiving capability information from the user equipment indicating the user equipment's ability to perform AI- or machine learning-based positioning using relative spatial domain information; wherein, when executed using at least one processor, the instruction further causes the device to perform: receiving a request for relative spatial domain information from the user equipment, and wherein sending the relative spatial domain information is in response to the request, wherein the request indicates a threshold, and the relative spatial domain information is sent when the difference between the relative spatial domain information and previous relative spatial domain information exceeds the threshold, wherein the relative spatial domain information is represented by at least one associated identifier, wherein the at least one associated identifier is associated with a plurality of network nodes, wherein the spatial domain information Associated with at least one of the following: location, distance, angle, power value, latitude coordinates, or longitude coordinates, wherein the spatial domain information includes at least one of the following: spatial orientation information of one or more reference signal resources of at least one network node; geographic coordinates of at least one network node; effective area of the spatial domain information; location information of one or more positioning reference units; beam or antenna information of at least one network node; or expected angle information of at least one network node, wherein at least one network node includes at least one transmit / receive point, wherein the relative spatial domain information indicates whether the reference spatial domain information is fixed, or an identifier associated with the reference spatial domain information, or wherein the instructions, when executed using at least one processor, also cause the device to perform or trigger the user equipment to perform at least one of the following: performing positioning inference using an artificial intelligence or machine learning model; monitoring an artificial intelligence or machine learning model; collecting training data; retraining an artificial intelligence or machine learning model; or training a new artificial intelligence or machine learning model.
[0064] Figure 4 Example method 400 is shown. Method 400 can be implemented by the user equipment instance described herein. Figure 4The steps shown in the box are not considered mandatory. Method 400 can be implemented by a processor. At 402, method 400 may include the processor receiving capability information of the user equipment, which indicates the capability to perform AI- or machine learning-based positioning using relative spatial domain information. At 404, method 400 may include the processor determining relative spatial domain information with respect to reference spatial domain information, wherein the reference spatial domain information is unknown to the user equipment. At 406, method 400 may include the processor sending the relative spatial domain information in response to a request for it. At 408, method 400 may include the processor receiving the result of a consistency / validity check of the spatial domain information from the user equipment based on time information. At 410, method 400 may include the processor determining and performing (multiple) actions based on the result.
[0065] According to the third aspect, the subject matter includes: (i) receiving relative spatial domain information about each other from multiple network nodes; and (ii) using the relative spatial domain information in conjunction with positioning based on artificial intelligence or machine learning to determine the location of a device. The third aspect may be implemented in algorithms, encoded in a distribution medium or computer program product, and implemented as methods executed by the devices. The devices may include components for causing the devices to perform at least the methods. The components may include at least one processor; and at least one memory storing the algorithms as instructions that, when executed by the at least one processor, cause the devices to perform at least the methods.
[0066] The third aspect may include any single feature or any combination of features from the following: wherein the instruction, when executed using at least one processor, also causes the device to: provide capability information of the device indicating the ability to perform artificial intelligence or machine learning-based positioning using the relative spatial domain information, wherein the instruction, when executed using the at least one processor, also causes the device to: request the relative spatial domain information, wherein the request indicates a threshold, and the relative spatial domain information is received when the difference between the relative spatial domain information and previous relative spatial domain information exceeds the threshold, wherein the relative spatial domain information is represented by at least one associated identifier, wherein the spatial domain information is associated with at least one of the following: location, distance, angle, power value, latitude coordinates, or longitude coordinates, wherein the spatial domain information includes at least one of the following: spatial orientation information of one or more reference signal resources of at least one network node; geographic coordinates of at least one network node; spatial The instructions include: the effective area of the relative spatial domain information; the location information of one or more positioning reference units; the beam or antenna information of at least one network node; or the expected angle information of at least one network node, wherein at least one network node includes at least one transmit / receive point, wherein using relative spatial domain information includes performing a consistency / validity check of the spatial domain information, wherein when the instructions are executed using at least one processor, the device further causes the device to: report the results of the consistency / validity check to the network, wherein when the instructions are executed using at least one processor, the device further causes the device to: perform positioning inference using an artificial intelligence or machine learning model; monitor an artificial intelligence or machine learning model; collect training data; retrain an artificial intelligence or machine learning model; or train a new artificial intelligence or machine learning model, wherein when the instructions are executed using the at least one processor, the device further causes the device to: select network nodes to be used for AI / ML-based positioning based on the relative spatial domain information.
[0067] Figure 5 Example method 500 is shown. Method 500 can be implemented by an instance of the user equipment described herein. Figure 5The steps shown in the boxes are not considered mandatory. Method 500 can be implemented by a processor. At 502, method 500 may include the processor providing capability information of the device, indicating the ability to perform AI- or machine learning-based localization using relative spatial domain information. At 504, method 500 may include the processor receiving relative spatial domain information about each other from multiple network nodes in response to a request. At 506, method 500 may include the processor using the relative spatial domain information in conjunction with AI / ML learning-based localization to determine the location of the device, including a check of the spatial domain information. At 506, method 500 may include the processor reporting the results of the consistency / validity check to the network. At 510, method 500 may include the processor determining and performing (multiple) actions based on the results.
[0068] According to the fourth aspect, the subject matter includes: (i) determining relative spatial domain information of multiple network nodes about each other, wherein the relative spatial domain information is used in conjunction with positioning techniques based on artificial intelligence or machine learning to determine the location of a user equipment; and (ii) sending the relative location information to the user equipment. The fourth aspect may be implemented in algorithms, encoded in a distribution medium or in a computer program product, and implemented as methods executed by means of means of means. The means may include components for causing the means to perform at least the methods. The components may include at least one processor; and at least one memory storing the algorithms as instructions, which, when executed by the at least one processor, cause the means to perform at least the methods.
[0069] The fourth aspect may include any single feature or any combination of features from the following: the apparatus of claim 27, wherein when the instruction is executed using at least one processor, it further causes the apparatus to perform: receiving at least one result of a consistency / validity check of spatial domain information from the user equipment, wherein when the instruction is executed using the at least one processor, it further causes the apparatus to perform: receiving capability information from the user equipment, the capability information indicating the user equipment's ability to perform artificial intelligence or machine learning-based positioning using relative spatial domain information, wherein when the instruction is executed using at least one processor, it further causes the apparatus to perform: receiving a request for relative spatial domain information from the user equipment, and wherein sending the relative spatial domain information is in response to the request, wherein the request indicates a threshold, and the relative spatial domain information is sent when the difference between the relative spatial domain information and previous relative spatial domain information exceeds the threshold, wherein the relative spatial domain information is represented by at least one associated identifier, wherein At least one associated identifier is associated with a plurality of network nodes, wherein spatial domain information is associated with at least one of the following: location, distance, angle, power value, latitude coordinates, or longitude coordinates, wherein the spatial domain information includes at least one of the following: spatial orientation information of one or more reference signal resources of at least one network node; geographic coordinates of at least one network node; effective area of spatial domain information; location information of one or more positioning reference units; beam or antenna information of at least one network node; or expected angle information of at least one network node, wherein at least one network node includes at least one transmit / receive point, wherein when the instruction is executed using at least one processor, it also causes the device to perform or trigger the user equipment to perform at least one of the following: performing positioning inference using an artificial intelligence or machine learning model; monitoring an artificial intelligence or machine learning model; collecting training data; retraining an artificial intelligence or machine learning model; or training a new artificial intelligence or machine learning model.
[0070] Figure 6 Example method 600 is shown. Method 600 can be implemented by an instance of the user equipment described herein. Figure 6The steps shown in the boxes are not considered mandatory. Method 600 can be implemented by a processor. At 602, method 600 may include a processor receiving capability information of a user equipment indicating the ability to perform AI- or machine learning-based localization using relative spatial domain information. At 510, method 600 may include a processor determining relative spatial domain information of multiple network nodes about each other, wherein the relative spatial domain information is used to determine the location of the user equipment. At 606, method 600 may include a processor sending the relative spatial domain information in response to a request for such information. At 608, method 600 may include a processor receiving the result of a spatial domain information consistency / validity check from the user equipment based on time information. At 610, method 600 may include a processor determining and performing (multiple) actions based on the result.
[0071] As used in this article, the term “non-transient” refers to a limitation on the medium itself (i.e., tangible, not signaling), rather than a limitation on the persistence of data storage (e.g., RAM and ROM).
[0072] As used in this application, the term "circuit system" may refer to one or more or all of the following: (a) a hardware circuit implementation only (such as an implementation only in analog and / or digital circuit systems); and (b) a combination of hardware circuits and software, such as (if applicable): (i) a combination of (multiple) analog and / or digital hardware circuits having software / firmware, and (ii) any part of (multiple) hardware processors having software (including (multiple) digital signal processors, software, and (multiple) memories, which work together to enable a device (such as a mobile phone or a server) to perform various functions); and (c) (multiple) hardware circuits and / or (multiple) processors, such as (multiple) microprocessors or a portion thereof, which require software (e.g., firmware) to operate, but may be absent when operation is not required.
[0073] This definition of circuit system applies to all uses of the term in this application (including in any claim). As another example, as used in this application, the term circuit system also covers only hardware circuitry or a processor (or multiple processors) or portions of hardware circuitry or a processor and its accompanying software and / or firmware implementation. For example, and if applicable to a particular claim element, the term circuit system also covers baseband integrated circuits or processor integrated circuits for mobile devices, or similar integrated circuits in servers, cellular network devices or other computing or network devices.
[0074] It should be understood that the foregoing description is illustrative only. Various alternatives and modifications can be devised by those skilled in the art. For example, the features described in each dependent claim can be combined with each other in any suitable combination. In addition, features from the different embodiments described above can be selectively combined into a new embodiment. Therefore, this description is intended to cover all alternatives, modifications, and variations that fall within the scope of the appended claims.
Claims
1. A device for communication, comprising: At least one processor; as well as At least one memory, the at least one memory storing instructions, which, when executed using the at least one processor, cause the device to perform: Receive relative spatial domain information about each other from multiple network nodes; as well as The relative spatial domain information is used in conjunction with positioning based on artificial intelligence or machine learning to determine the location of the device.
2. The apparatus of claim 1, wherein the instructions, when executed using the at least one processor, further cause the apparatus to perform: Provide capability information for the device, the capability information indicating the ability to perform positioning based on artificial intelligence or machine learning using the relative spatial domain information; or Request the relative spatial domain information.
3. The apparatus of claim 2, wherein the request indicates a threshold, and the relative spatial domain information is received when the difference between the relative spatial domain information and previous relative spatial domain information exceeds the threshold.
4. The apparatus according to any of the preceding claims, wherein the relative spatial domain information is represented by at least one associated identifier; The spatial domain information is associated with at least one of the following: location, distance, angle, power value, latitude coordinates, or longitude coordinates; The spatial domain information includes at least one of the following: spatial orientation information of one or more reference signal resources of the at least one network node; geographic coordinates of the at least one network node; effective area of the spatial domain information; position information of one or more positioning reference units; beam or antenna information of the at least one network node; or expected angle information of the at least one network node. The at least one network node includes at least one transmission receiving point; The use of the relative spatial domain information includes: performing a consistency / validity check on the spatial domain information; and the instruction, when executed using the at least one processor, further causes the device to: report the result of the consistency / validity check to the network; When the instructions are executed using the at least one processor, the device further causes the device to perform at least one of the following: localization inference using an artificial intelligence or machine learning model; monitoring of an artificial intelligence or machine learning model; collection of training data; retraining of an artificial intelligence or machine learning model; or training of a new artificial intelligence or machine learning model; or When the instructions are executed using the at least one processor, the device also performs the following: selecting network nodes to be used for positioning based on artificial intelligence or machine learning, based on the relative spatial domain information.
5. A method for communication, comprising: Receive relative spatial domain information about each other from multiple network nodes; as well as The relative spatial domain information is used in conjunction with positioning based on artificial intelligence or machine learning to determine the location of the user device.
6. A device for communication, comprising: At least one processor; as well as At least one memory, the at least one memory storing instructions, which, when executed using the at least one processor, cause the device to perform: Determine the relative spatial domain information of multiple network nodes with respect to each other, wherein the relative spatial domain information is used in conjunction with positioning based on artificial intelligence or machine learning to determine the location of a user device; and The relative location information is sent to the user equipment.
7. The apparatus of claim 6, wherein the instructions, when executed using the at least one processor, further cause the apparatus to: receive at least one result of the consistency / validity check of the spatial domain information from the user equipment; The instructions, when executed using the at least one processor, further cause the device to: receive capability information from the user equipment, the capability information indicating the user equipment's ability to perform positioning based on artificial intelligence or machine learning using the relative spatial domain information; or The instructions, when executed using the at least one processor, also cause the apparatus to: receive a request from the user equipment for the relative spatial domain information, and wherein sending the relative spatial domain information is in response to the request.
8. The apparatus of claim 7, wherein the request indicates a threshold, and the relative spatial domain information is sent when the difference between the relative spatial domain information and previous relative spatial domain information exceeds the threshold.
9. The apparatus according to any one of claims 6 to 8, wherein the relative spatial domain information is represented by at least one associated identifier; and wherein the at least one associated identifier is associated with a plurality of network nodes; The spatial domain information is associated with at least one of the following: location, distance, angle, power value, latitude coordinates, or longitude coordinates; The spatial domain information includes at least one of the following: spatial orientation information of one or more reference signal resources of the at least one network node; geographic coordinates of the at least one network node; effective area of the spatial domain information; position information of one or more positioning reference units; beam or antenna information of the at least one network node; or expected angle information of the at least one network node. The at least one network node includes at least one transmission receiving point; or When the instructions are executed using the at least one processor, the device also causes the user equipment to perform or trigger at least one of the following: location inference using an artificial intelligence or machine learning model; monitoring of an artificial intelligence or machine learning model; collection of training data; retraining of an artificial intelligence or machine learning model; or training of a new artificial intelligence or machine learning model.
10. A method for communication, comprising: Determine the relative spatial domain information of multiple network nodes with respect to each other, wherein the relative spatial domain information is used in conjunction with positioning based on artificial intelligence or machine learning to determine the location of a user device; and The relative location information is sent to the user equipment.
