Network node and method performed by same

Abstract

The invention relates to a network node in a communication system and a method performed by the same. In one aspect, a method executed by a first network node in a communication system is provided, comprising: obtaining a first AI model, the first AI model being determined from at least one AI model according to an application condition corresponding to the AI model; obtaining input data of the first AI model; and based on the input data, using a first AI model to obtain output data related to positioning, the first AI model being an AI model randomly determined from a plurality of AI models satisfying an application condition, or being determined from the plurality of AI models based on a fourth condition.

Description

Technical Field

[0001] The present invention relates to wireless communications, and more particularly, to a network node of a wireless communication system and a method executed therein. Background Art

[0002] To meet the increased demand for wireless data communication services since the deployment of 4G communication systems, efforts have been made to develop improved 5G or quasi-5G communication systems. Therefore, 5G or quasi-5G communication systems are also referred to as "beyond 4G networks" or "post-LTE systems."

[0003] 5G communication systems are implemented in higher-frequency (millimeter wave, mmWave) bands, such as the 60 GHz band, to achieve higher data rates. To reduce radio wave propagation losses and increase transmission distances, 5G communication systems utilize technologies such as beamforming, massive multiple-input multiple-output (MIMO), full-dimensional MIMO (FD-MIMO), array antennas, analog beamforming, and massive antennas.

[0004] In addition, in the 5G communication system, system network improvements are being developed based on advanced small cells, cloud radio access networks (RAN), ultra-dense networks, device-to-device (D2D) communications, wireless backhaul, mobile networks, collaborative communications, coordinated multi-point (CoMP), and receiving-end interference cancellation.

[0005] In 5G systems, hybrid FSK and QAM modulation (FQAM) and sliding window superposition coding (SWSC) have been developed as advanced coding modulation (ACM), as well as filter bank multi-carrier (FBMC), non-orthogonal multiple access (NOMA) and sparse code multiple access (SCMA) as advanced access technologies. Summary of the Invention

[0006] At least one embodiment of the present disclosure provides a method performed by a first network node in a communication system, including:

[0007] Obtaining a first AI model, where the first AI model is determined from at least one AI model according to an applicable condition corresponding to the AI model;

[0008] Obtaining input data for a first AI model;

[0009] Based on the input data, using the first AI model, obtaining output data related to positioning,

[0010] The first AI model is an AI model randomly determined from a plurality of AI models that meet the applicable conditions, or is determined from the plurality of AI models based on the fourth condition.

[0011] In one implementation, obtaining the first AI model includes:

[0012] The first network node determines a first AI model from the at least one AI model based on an applicable condition corresponding to the AI model, or

[0013] The first AI model is determined based on indication information received from the second network node, where the indication information is used to indicate an index of the first AI model determined by the second network node or a feature associated with the first AI model determined by the second network node.

[0014] In one implementation, the method further includes:

[0015] If the first AI model is determined by the first network node, the first network node sends information related to the determined first AI model to the UE or the second network node.

[0016] In one implementation, the fourth condition includes at least one of the following:

[0017] Minimal storage required;

[0018] Requires minimal computational complexity;

[0019] Requires minimum input data type and / or quantity;

[0020] The output data has the highest accuracy;

[0021] The most associated features;

[0022] The maximum number of applicable conditions is met;

[0023] This is a different AI model from the one selected last time.

[0024] In one implementation, the at least one AI model includes an AI model supported by two or all of the first network node, the UE, and the second network node.

[0025] In one implementation, the applicable condition includes at least one of the following:

[0026] The cell index corresponding to the AI model;

[0027] the conditions associated with the measurement results;

[0028] Storage-related conditions;

[0029] Complexity-related conditions;

[0030] Conditions related to output data accuracy;

[0031] Handle time-related conditions.

[0032] In one implementation, the conditions related to the measurement result include:

[0033] The first measurement value of the measurement result is not lower than the first threshold,

[0034] The first measurement value of the measurement result is within the first measurement threshold interval,

[0035] The number of paths whose power is not lower than the first power threshold in the measurement result is greater than the first number threshold,

[0036] The number of paths not lower than the first power threshold is greater than the number of measurement results of the first quantity threshold is greater than the second quantity threshold,

[0037] The probability that the number of paths not lower than the first power threshold in the measurement result is greater than the first number threshold is greater than the first probability threshold.

[0038] In one implementation, the method further includes:

[0039] Sending at least one of the following to the UE: configuration information related to reference signal resources and configuration information related to reference signal transmission windows;

[0040] Obtaining a first measurement result by measuring a first reference signal sent by the UE;

[0041] The first measurement result is used to determine the first AI model and / or to obtain input data of the first AI model.

[0042] In one implementation, the first measurement result is a measurement result obtained based on measurement, or is obtained by processing the measurement result obtained based on measurement, where the processing includes at least one of the following:

[0043] selecting a first measurement result from measurement results obtained based on the measurement based on a first condition;

[0044] transforming a measurement result obtained based on the measurement to obtain a first measurement result,

[0045] The first condition includes at least one of the following: the power corresponding to the measurement result is not lower than the second power threshold, the time corresponding to the measurement result is earlier than the first time threshold, and the phase corresponding to the measurement result is less than or equal to the first phase threshold.

[0046] In one implementation, the method further includes: sending the first measurement result to the second network node.

[0047] In one implementation, the input data includes at least one of the following:

[0048] First measurement result;

[0049] Data obtained based on the first measurement result and input format information of the first AI model.

[0050] In one implementation, the method further includes:

[0051] sending information related to the output data to the second network node,

[0052] The information related to the output data includes at least one of the following:

[0053] The output data, data obtained by processing the output data, information related to the timestamp of the output data, and quality indication information of the output data.

[0054] In one implementation, the method further includes:

[0055] measuring a second reference signal sent by the UE to obtain a second measurement result;

[0056] Obtaining a monitoring result of the first AI model based on the second measurement result;

[0057] The operation to be performed is determined based on the monitoring result, or the monitoring result is sent to the second network node, and / or information indicating the operation to be performed is received from the second network node.

[0058] In one implementation, the monitoring result is obtained based on a monitoring indicator, and the monitoring indicator is obtained based on a second measurement result.

[0059] The monitoring indicator includes at least one of the following: the second measurement result, a third measurement result obtained by processing the second measurement result, and characteristic data obtained based on the second measurement result.

[0060] The processing includes: selecting a third measurement result from the second measurement result based on the second condition, or transforming the second measurement result to obtain the third measurement result,

[0061] The characteristic data includes statistical characteristic data of the second measurement result, or a fourth measurement result selected from the second measurement result according to the second condition,

[0062] The second condition includes at least one of the following: the power corresponding to the measurement result is not lower than the third power threshold, the time corresponding to the measurement result is earlier than the second time threshold, and the phase corresponding to the measurement result is less than the second phase threshold.

[0063] In one implementation, if the monitoring indicator is greater than the threshold value N times in a row, the monitoring result is determined to be passed, where N is a positive integer; otherwise, the monitoring result is determined to be failed.

[0064] In one implementation, if the third condition is met, the operation includes at least one of the following:

[0065] Stop using AI-based targeting methods,

[0066] Falling back to non-AI based methods for positioning,

[0067] Re-determine the AI model to be used,

[0068] performing an update, optimization, or retraining of the first AI model,

[0069] Selecting a second AI model different from the first AI model and notifying the second network node,

[0070] receiving a second AI model indicated by a second network node,

[0071] receiving an instruction from a second network node to fall back to a non-AI based method for positioning and performing the fallback based on the instruction,

[0072] Report errors in AI model-based methods;

[0073] Among them, the third condition includes at least one of the following: the first AI model is the same as the AI model determined to be used last time, and the monitoring result is failed for M consecutive times, where M is an integer greater than or equal to 1.

[0074] In one implementation, the method further includes:

[0075] Sending first information related to the AI model supported by the first network node to the second network node or the UE,

[0076] The first information includes at least one of the following:

[0077] Index information of the AI model supported by the first network node;

[0078] Feature information associated with the AI model supported by the first network node;

[0079] A correspondence between an index of an AI model supported by the first network node and the associated features;

[0080] Information related to the input format of the AI model supported by the first network node;

[0081] Information related to the output format of the AI model supported by the first network node.

[0082] In one implementation, the information related to the input format includes at least one of the following: information related to the type of input data and / or information related to the amount of input data.

[0083] In one implementation, the type of the input data includes at least one of the following:

[0084] Channel impulse response CIR,

[0085] Power Delay Profile PDP,

[0086] Delay distribution DP,

[0087] Channel information characteristics obtained based on CIR, PDP, or DP,

[0088] Time value,

[0089] Power value,

[0090] Phase value,

[0091] Input data timestamp,

[0092] The path index corresponding to the input data,

[0093] The quantity of the input data includes at least one of the following: information related to the total quantity of all types of input data, information related to the individual quantities of each type of input data, and information related to a third quantity applied to all types.

[0094] In one implementation, the information related to the output format includes at least one of information related to the type of output data, information related to the amount of output data, and information related to the AI model processing time.

[0095] In one implementation, the type of the output data includes at least one of the following:

[0096] UE coordinate estimation;

[0097] an estimate of a second measurement value, the second measurement value comprising at least one of a time measurement value, a power measurement value, and a phase measurement value;

[0098] an estimate of the probability that the measurement result satisfies a third condition, the third condition including that the measurement result corresponds to a line-of-sight path, or that the number of multipaths in the measurement result exceeds a third number threshold;

[0099] The quantity of output data includes the total quantity of output data, the quantity corresponding to each type of output data, and the quantity corresponding to all types of output data.

[0100] In one implementation, the correspondence between the index and the feature of the supported AI model includes at least one of the following:

[0101] One AI model index corresponds to one feature.

[0102] An AI model index corresponds to multiple features.

[0103] Multiple AI model indexes correspond to one feature.

[0104] The ratio between indices and features of an AI model.

[0105] In one implementation, the method further includes: sending, to the second network node, at least one candidate AI model determined by the first network node based on the applicable conditions of the AI model.

[0106] In one implementation, the method further includes:

[0107] receiving a first measurement result from a second network node or a UE,

[0108] The first measurement result is obtained by the second network node by measuring the third reference signal sent by the UE, or is obtained by the UE by measuring the fourth reference signal sent by the second network node.

[0109] The first measurement result is used to determine the first AI model and / or to obtain input data of the first AI model.

[0110] At least one embodiment of the present disclosure provides a method performed by a second network node in a communication system, including:

[0111] Determine a first AI model that meets corresponding applicability conditions from at least one AI model;

[0112] Sending instruction information of the first AI model to the first network node,

[0113] The first AI model is an AI model randomly determined from a plurality of AI models that meet the applicable conditions, or is determined from the plurality of AI models based on the fourth condition.

[0114] In one implementation, the indication information is used to indicate an index of the first AI model and / or features associated with the first AI model.

[0115] In one implementation, the fourth condition includes at least one of the following:

[0116] Minimal storage required;

[0117] Requires minimal computational complexity;

[0118] Requires minimum input data type and / or quantity;

[0119] The output data has the highest accuracy;

[0120] The most associated features;

[0121] The maximum number of applicable conditions is met;

[0122] This is a different AI model from the one selected last time.

[0123] In one implementation, the at least one AI model includes an AI model supported by two or all of the first network node, the UE, and the second network node.

[0124] In one implementation, the applicable condition includes at least one of the following:

[0125] The cell index corresponding to the AI model;

[0126] the conditions associated with the measurement results;

[0127] Storage-related conditions;

[0128] Complexity-related conditions;

[0129] Conditions related to output data accuracy;

[0130] Handle time-related conditions.

[0131] In one implementation, the conditions related to the measurement result include:

[0132] The first measurement value of the measurement result is not lower than the first threshold,

[0133] The first measurement value of the measurement result is within the first measurement threshold interval,

[0134] The number of paths whose power is not lower than the first power threshold in the measurement result is greater than the first number threshold,

[0135] The number of paths not lower than the first power threshold is greater than the number of measurement results of the first quantity threshold is greater than the second quantity threshold,

[0136] The probability that the number of paths not lower than the first power threshold in the measurement result is greater than the first number threshold is greater than the first probability threshold.

[0137] In one implementation, the method further includes:

[0138] Sending at least one of the following to the UE: configuration information related to reference signal resources and configuration information related to reference signal transmission windows;

[0139] Obtaining a first measurement result by measuring a first reference signal sent by the UE;

[0140] The first measurement result is used to determine the first AI model and / or to obtain input data of the first AI model.

[0141] In one implementation, the first measurement result is a measurement result obtained based on measurement, or is obtained by processing the measurement result obtained based on measurement, where the processing includes at least one of the following:

[0142] selecting a first measurement result from measurement results obtained based on the measurement based on a first condition;

[0143] transforming a measurement result obtained based on the measurement to obtain a first measurement result,

[0144] The first condition includes at least one of the following: the power corresponding to the measurement result is not lower than the second power threshold, the time corresponding to the measurement result is earlier than the first time threshold, and the phase corresponding to the measurement result is less than or equal to the first phase threshold.

[0145] In one implementation, the method further includes: receiving a first measurement result from a first network node.

[0146] In one implementation, the input data includes at least one of the following:

[0147] First measurement result;

[0148] Data obtained based on the first measurement result and input format information of the first AI model.

[0149] In one implementation, the method further includes:

[0150] receiving information related to the output data from the first network node,

[0151] The information related to the output data includes at least one of the following:

[0152] The output data, data obtained by processing the output data, information related to the timestamp of the output data, and quality indication information of the output data.

[0153] In one implementation, the method further includes:

[0154] Receive a monitoring result of the first AI model from the first network node, and / or send information indicating an operation to be performed to the first network node.

[0155] In one implementation, if the third condition is met, the operation includes at least one of the following:

[0156] Stop using AI-based targeting methods,

[0157] Falling back to non-AI based methods for positioning,

[0158] Re-determine the AI model to be used,

[0159] performing an update, optimization, or retraining of the first AI model,

[0160] Select a second AI model different from the first AI model and notify the second network node,

[0161] receiving a second AI model indicated by a second network node,

[0162] receiving an instruction from a second network node to fall back to a non-AI based method for positioning and performing the fallback based on the instruction,

[0163] Report errors in AI model-based methods;

[0164] Among them, the third condition includes at least one of the following: the first AI model is the same as the AI model determined to be used last time, and the monitoring result is failed for M consecutive times, where M is an integer greater than or equal to 1.

[0165] In one implementation, the method further includes:

[0166] receiving, from the first network node, first information related to an AI model supported by the first network node;

[0167] The first information includes at least one of the following:

[0168] Index information of the AI model supported by the first network node;

[0169] Feature information associated with the AI model supported by the first network node;

[0170] A correspondence between an index of an AI model supported by the first network node and the associated features;

[0171] Information related to the input format of the AI model supported by the first network node;

[0172] Information related to the output format of the AI model supported by the first network node.

[0173] In one implementation, the information related to the input format includes at least one of the following: information related to the type of input data and / or information related to the amount of input data.

[0174] In one implementation, the type of the input data includes at least one of the following:

[0175] Channel impulse response CIR,

[0176] Power Delay Profile PDP,

[0177] Delay distribution DP,

[0178] Channel information characteristics obtained based on CIR, PDP, or DP,

[0179] Time value,

[0180] Power value,

[0181] Phase value,

[0182] Input data timestamp,

[0183] The path index corresponding to the input data,

[0184] The quantity of the input data includes at least one of the following: information related to the total quantity of all types of input data, information related to the individual quantities of each type of input data, and information related to a third quantity applied to all types.

[0185] In one implementation, the information related to the output format includes at least one of information related to the type of output data, information related to the amount of output data, and information related to the AI model processing time.

[0186] In one implementation, the type of the output data includes at least one of the following:

[0187] UE coordinate estimation;

[0188] an estimate of a second measurement value, the second measurement value comprising at least one of a time measurement value, a power measurement value, and a phase measurement value;

[0189] an estimate of the probability that the measurement result satisfies a third condition, the third condition including that the measurement result corresponds to a line-of-sight path, or that the number of multipaths in the measurement result exceeds a third number threshold;

[0190] The quantity of output data includes the total quantity of output data, the quantity corresponding to each type of output data, and the quantity corresponding to all types of output data.

[0191] In one implementation, the correspondence between the index and the feature of the supported AI model includes at least one of the following:

[0192] One AI model index corresponds to one feature.

[0193] An AI model index corresponds to multiple features.

[0194] Multiple AI model indexes correspond to one feature.

[0195] The ratio between indices and features of an AI model.

[0196] In one implementation, the method further includes: receiving, from the first network node, at least one candidate AI model determined by the first network node based on an applicable condition of the AI model.

[0197] In one implementation, the first network node is a Transmit Receiving Point TRP, and the second network node is a Location Management Function LMF.

[0198] In one implementation, the first network node is a LMF, and the second network node is a TRP.

[0199] At least one embodiment of the present disclosure provides a method executed by a user equipment (UE) in a communication system, including:

[0200] Receiving first configuration information related to AI model-based positioning measurement from the first network node, where the first configuration information includes at least one of the following: configuration information related to reference signal resources, configuration information related to measurement windows, and configuration information related to measurement result reporting resources;

[0201] A first measurement result obtained by performing measurement based on the first configuration information is sent to the first network node, or a reference signal is sent to the first network node based on the first configuration information.

[0202] In one implementation, the method further includes: receiving indication information of a first AI model from the first network node, where the first AI model is determined by the first network node from at least one AI model based on an applicable condition corresponding to the AI model.

[0203] At least one embodiment of the present disclosure provides a network node in a communication system, comprising: a transceiver configured to send and / or receive signals, and a controller configured to control the network node to execute the method according to the embodiment of the present disclosure.

[0204] At least one embodiment of the present disclosure provides a UE in a communication system, including: a transceiver configured to send and / or receive signals, and a controller configured to control the UE to execute the method according to the embodiment of the present disclosure. BRIEF DESCRIPTION OF THE DRAWINGS

[0205] Figure 1 An example wireless network according to various embodiments of the present disclosure is shown;

[0206] Figure 2a and Figure 2b Example wireless transmit and receive paths according to the present disclosure are shown;

[0207] Figure 3a An example user device according to the present disclosure is shown, and Figure 3b An example base station according to the present disclosure is shown; and

[0208] Figure 4 2 is a block diagram illustrating a network node device for executing a positioning method according to an embodiment of the present invention. DETAILED DESCRIPTION

[0209] The following description, with reference to the accompanying drawings, is provided to facilitate a comprehensive understanding of the various embodiments of the present disclosure as defined by the claims and their equivalents. This description includes various specific details to facilitate understanding but should be considered as illustrative only. Therefore, one of ordinary skill in the art will recognize that various changes and modifications can be made to the various embodiments described herein without departing from the scope and spirit of the present disclosure. Furthermore, descriptions of well-known functions and structures may be omitted for the sake of clarity and conciseness.

[0210] The terms and expressions used in the following description and claims are not limited to their dictionary meanings, but are merely used by the inventor to enable a clear and consistent understanding of the present disclosure. Therefore, it should be apparent to those skilled in the art that the following description of various embodiments of the present disclosure is provided for illustration purposes only and not for the purpose of limiting the present disclosure as defined by the appended claims and their equivalents.

[0211] It will be understood that the singular forms "a," "an," and "the" include plural referents unless the context clearly dictates otherwise. Thus, for example, reference to "a component surface" includes reference to one or more of such surfaces.

[0212] The terms "include" or "may include" refer to the presence of the corresponding disclosed functions, operations, or components that can be used in various embodiments of the present disclosure, rather than limiting the presence of one or more additional functions, operations, or features. In addition, the terms "include" or "have" can be interpreted as indicating certain characteristics, numbers, steps, operations, constituent elements, components, or combinations thereof, but should not be interpreted as excluding the possibility of the presence of one or more other characteristics, numbers, steps, operations, constituent elements, components, or combinations thereof.

[0213] The term "or" used in various embodiments of the present disclosure includes any of the listed terms and all combinations thereof. For example, "A or B" may include A, may include B, or may include both A and B.

[0214] Unless otherwise defined, all terms (including technical or scientific terms) used in this disclosure have the same meaning as understood by those skilled in the art described in this disclosure. Common terms as defined in dictionaries are interpreted as having a meaning consistent with the context in the relevant technical field and should not be interpreted in an idealized or overly formal manner unless explicitly defined in this disclosure.

[0215] The technical solutions of the embodiments of the present application can be applied to various communication systems, such as: global system for mobile communications (GSM) system, code division multiple access (CDMA) system, wideband code division multiple access (WCDMA) system, general packet radio service (GPRS), long term evolution (LTE) system, LTE frequency division duplex (FDD) system, LTE time division duplex (TDD) system, universal mobile telecommunication system (UMTS), world-wide interoperability for microwave access (WiMAX) communication system, fifth generation (5G) system or new radio (NR), etc. In addition, the technical solutions of the embodiments of the present application can be applied to future-oriented communication technologies.

[0216] Figure 1 An example wireless network 100 is shown in accordance with various embodiments of the present disclosure. Figure 1 The embodiment of the wireless network 100 shown in FIGURE 1 is for illustration only. Other embodiments of the wireless network 100 can be used without departing from the scope of this disclosure.

[0217] Wireless network 100 includes gNodeB (gNB) 101, gNB 102, and gNB 103. gNB 101 communicates with gNB 102 and gNB 103. gNB 101 also communicates with at least one Internet Protocol (IP) network 130, such as the Internet, a private IP network, or other data network.

[0218] Depending on the network type, other well-known terms such as "base station" or "access point" can be used instead of "gNodeB" or "gNB." For convenience, the terms "gNodeB" and "gNB" are used in this patent document to refer to network infrastructure components that provide wireless access to remote terminals. Also, depending on the network type, other well-known terms such as "mobile station," "subscriber station," "remote terminal," "wireless terminal," or "user device" can be used instead of "user equipment" or "UE." For convenience, the terms "user equipment" and "UE" are used in this patent document to refer to a remote wireless device that wirelessly accesses a gNB, whether the UE is a mobile device (such as a mobile phone or smartphone) or what is typically considered a stationary device (such as a desktop computer or vending machine).

[0219] gNB 102 provides wireless broadband access to network 130 for a first plurality of user equipment (UEs) within gNB 102's coverage area 120. The first plurality of UEs includes: UE 111, which may be located in a small business (SB); UE 112, which may be located in an enterprise (E); UE 113, which may be located in a WiFi hotspot (HS); UE 114, which may be located in a first residence (R); UE 115, which may be located in a second residence (R); and UE 116, which may be a mobile device (M) such as a cellular phone, wireless laptop, or wireless PDA. gNB 103 provides wireless broadband access to network 130 for a second plurality of UEs within gNB 103's coverage area 125. The second plurality of UEs includes UE 115 and UE 116. In some embodiments, one or more of gNBs 101-103 may be capable of communicating with each other and with UEs 111-116 using 5G, Long Term Evolution (LTE), LTE-A, WiMAX, or other advanced wireless communication technologies.

[0220] The dashed lines illustrate the approximate extents of coverage areas 120 and 125, which are shown as approximately circular for purposes of illustration and explanation only. It should be clearly understood that coverage areas associated with gNBs, such as coverage areas 120 and 125, can have other shapes, including irregular shapes, depending on the configuration of the gNB and variations in the radio environment associated with natural and man-made obstacles.

[0221] As described in more detail below, one or more of gNB 101, gNB 102, and gNB 103 include a 2D antenna array as described in embodiments of the present disclosure. In some embodiments, one or more of gNB 101, gNB 102, and gNB 103 supports codebook design and structure for systems with 2D antenna arrays.

[0222] although Figure 1 One example of a wireless network 100 is shown, but Figure 1 Various changes may be made. For example, wireless network 100 can include any number of gNBs and any number of UEs in any suitable arrangement. Furthermore, gNB 101 can communicate directly with any number of UEs and provide those UEs with wireless broadband access to network 130. Similarly, each gNB 102-103 can communicate directly with network 130 and provide UEs with direct wireless broadband access to network 130. Furthermore, gNBs 101, 102, and / or 103 can provide access to other or additional external networks, such as an external telephone network or other type of data network.

[0223] Figure 2a and Figure 2b Example wireless transmit and receive paths according to the present disclosure are shown. In the following description, transmit path 200 can be described as being implemented in a gNB (such as gNB 102), while receive path 250 can be described as being implemented in a UE (such as UE 116). However, it should be understood that receive path 250 can be implemented in a gNB and transmit path 200 can be implemented in a UE. In some embodiments, receive path 250 is configured to support codebook design and structure for systems with 2D antenna arrays as described in embodiments of the present disclosure.

[0224] The transmit path 200 includes a channel coding and modulation block 205, a serial-to-parallel (S-to-P) block 210, an N-point inverse fast Fourier transform (IFFT) block 215, a parallel-to-serial (P-to-S) block 220, an add cyclic prefix block 225, and an upconverter (UC) 230. The receive path 250 includes a downconverter (DC) 255, a remove cyclic prefix block 260, a serial-to-parallel (S-to-P) block 265, an N-point fast Fourier transform (FFT) block 270, a parallel-to-serial (P-to-S) block 275, and a channel decoding and demodulation block 280.

[0225] In the transmit path 200, the channel coding and modulation block 205 receives a set of information bits, applies coding (such as low-density parity check (LDPC) coding), and modulates the input bits (such as using quadrature phase shift keying (QPSK) or quadrature amplitude modulation (QAM)) to generate a sequence of frequency-domain modulation symbols. The serial-to-parallel (S-to-P) block 210 converts (e.g., demultiplexes) the serial modulation symbols into parallel data to generate N parallel symbol streams, where N is the number of IFFT / FFT points used in the gNB 102 and UE 116. The N-point IFFT block 215 performs an IFFT operation on the N parallel symbol streams to generate a time-domain output signal. The parallel-to-serial block 220 converts (e.g., multiplexes) the parallel time-domain output symbols from the N-point IFFT block 215 to generate a serial time-domain signal. The add cyclic prefix block 225 inserts a cyclic prefix into the time-domain signal. The upconverter 230 modulates (such as upconverts) the output of the add cyclic prefix block 225 to an RF frequency for transmission via a wireless channel. The signal can also be filtered at baseband before being converted to an RF frequency.

[0226] The RF signal transmitted from gNB 102 arrives at UE 116 after traversing the wireless channel. UE 116 performs operations that are the inverse of those performed at gNB 102. Downconverter 255 downconverts the received signal to baseband frequency, and cyclic prefix removal block 260 removes the cyclic prefix to generate a serial time-domain baseband signal. Serial-to-parallel block 265 converts the time-domain baseband signal into parallel time-domain signals. N-point FFT block 270 performs an FFT algorithm to generate N parallel frequency-domain signals. Parallel-to-serial block 275 converts the parallel frequency-domain signals into a sequence of modulated data symbols. Channel decoding and demodulation block 280 demodulates and decodes the modulated symbols to recover the original input data stream.

[0227] Each of gNBs 101-103 may implement a transmit path similar to 200 for transmitting in the downlink to UEs 111-116 and may implement a receive path similar to 250 for receiving in the uplink from UEs 111-116. Similarly, each of UEs 111-116 may implement a transmit path 200 for transmitting in the uplink to gNB 101-103 and may implement a receive path 250 for receiving in the downlink from gNB 101-103.

[0228] Figure 2a and Figure 2b Each of the components in can be implemented using hardware alone, or a combination of hardware and software / firmware. As a specific example, Figure 2a and Figure 2bAt least some of the components in the embodiment may be implemented in software, while other components may be implemented in configurable hardware or a mixture of software and configurable hardware. For example, FFT block 270 and IFFT block 215 may be implemented as configurable software algorithms, wherein the value of the number of points N may be modified according to the implementation.

[0229] Furthermore, although described as using FFT and IFFT, this is illustrative only and should not be construed as limiting the scope of the present disclosure. Other types of transforms can be used, such as discrete Fourier transform (DFT) and inverse discrete Fourier transform (IDFT) functions. It should be understood that for DFT and IDFT functions, the value of the variable N can be any integer (such as 1, 2, 3, 4, etc.), while for FFT and IFFT functions, the value of the variable N can be any integer that is a power of 2 (such as 1, 2, 4, 8, 16, etc.).

[0230] although Figure 2a and Figure 2b Examples of wireless transmit and receive paths are shown, but Figure 2a and Figure 2b Make various changes. For example, Figure 2a and Figure 2b The various components in can be combined, further subdivided, or omitted, and additional components can be added according to specific needs. Figure 2a and Figure 2b It is intended to illustrate examples of the types of transmit and receive paths that can be used in a wireless network. Any other suitable architecture can be used to support wireless communications in a wireless network.

[0231] Figure 3a An example UE 116 is shown in accordance with the present disclosure. Figure 3a The embodiment of UE 116 shown in FIGURE 1 is for illustration only, and Figure 1 UEs 111-115 can have the same or similar configurations. However, UEs have a variety of configurations, and Figure 3a The scope of this disclosure is not limited to any particular implementation of the UE.

[0232] UE 116 includes an antenna 301, a radio frequency (RF) transceiver 302, transmit (TX) processing circuitry 303, a microphone 304, and receive (RX) processing circuitry 305. UE 116 also includes a speaker 306, a controller / processor 307, an input / output (I / O) interface 308, input device(s) 309, a display 310, and a memory 311. Memory 311 includes an operating system (OS) 312 and one or more applications 313.

[0233] RF transceiver 302 receives incoming RF signals from antenna 301, transmitted by a gNB of wireless network 100. RF transceiver 302 downconverts the incoming RF signals to generate an intermediate frequency (IF) or baseband signal. The IF or baseband signal is sent to RX processing circuitry 305, which generates a processed baseband signal by filtering, decoding, and / or digitizing the baseband or IF signal. RX processing circuitry 305 sends the processed baseband signal to speaker 306 (such as for voice data) or to controller / processor 307 (such as for web browsing data) for further processing.

[0234] The TX processing circuit 303 receives analog or digital voice data from the microphone 304, or other outgoing baseband data (such as network data, email, or interactive video game data) from the controller / processor 307. The TX processing circuit 303 encodes, multiplexes, and / or digitizes the outgoing baseband data to generate a processed baseband or IF signal. The RF transceiver 302 receives the outgoing processed baseband or IF signal from the TX processing circuit 303 and up-converts the baseband or IF signal into an RF signal that is transmitted via the antenna 301.

[0235] The controller / processor 307 can include one or more processors or other processing devices and execute an OS 312 stored in a memory 311 to control the overall operation of the UE 116. For example, the controller / processor 307 can control the reception of forward channel signals and the transmission of reverse channel signals through the RF transceiver 302, the RX processing circuitry 305, and the TX processing circuitry 303 in accordance with well-known principles. In some embodiments, the controller / processor 307 includes at least one microprocessor or microcontroller.

[0236] The controller / processor 307 is also capable of executing other processes and programs resident in the memory 311, such as operations for channel quality measurement and reporting for a system with a 2D antenna array as described in embodiments of the present disclosure. The controller / processor 307 is capable of moving data into or out of the memory 311 as required by the executed processes. In some embodiments, the controller / processor 307 is configured to execute applications 313 based on the OS 312 or in response to signals received from the gNB or operator. The controller / processor 307 is also coupled to the I / O interface 308, which provides the UE 116 with the ability to connect to other devices such as laptops and handheld computers. The I / O interface 308 serves as the communication path between these accessories and the controller / processor 307.

[0237] Controller / processor 307 is also coupled to input device(s) 309 and display 310. An operator of UE 116 can input data into UE 116 using input device(s) 309. Display 310 can be a liquid crystal display or other display capable of presenting text and / or at least limited graphics (such as from a website). Memory 311 is coupled to controller / processor 307. A portion of memory 311 can include random access memory (RAM), while another portion of memory 311 can include flash memory or other read-only memory (ROM).

[0238] although Figure 3a An example of a UE 116 is shown, but it is possible to Figure 3a Make various changes. For example, Figure 3a The various components in can be combined, further subdivided, or omitted, and additional components can be added according to specific needs. As a specific example, the controller / processor 307 can be divided into multiple processors, such as one or more central processing units (CPUs) and one or more graphics processing units (GPUs). Moreover, although Figure 3a The UE 116 is shown configured as a mobile phone or smartphone, but the UE can be configured to operate as other types of mobile or stationary devices.

[0239] Figure 3b An example gNB 102 according to the present disclosure is shown. Figure 3b The embodiment of the gNB 102 shown in FIGURE 1 is for illustration only, and Figure 1 Other gNBs can have the same or similar configurations. However, gNBs have a variety of configurations, and Figure 3b The scope of this disclosure is not limited to any particular implementation of a gNB. It should be noted that gNB 101 and gNB 103 can include the same or similar structure as gNB 102.

[0240] like Figure 3b As shown in FIG, gNB 102 includes multiple antennas 370a-370n, multiple RF transceivers 372a-372n, transmit (TX) processing circuitry 374, and receive (RX) processing circuitry 376. In some embodiments, one or more of the multiple antennas 370a-370n comprise a 2D antenna array. gNB 102 also includes a controller / processor 378, memory 380, and a backhaul or network interface 382.

[0241] RF transceivers 372a-372n receive incoming RF signals from antennas 370a-370n, such as signals transmitted by a UE or other gNB. RF transceivers 372a-372n downconvert the incoming RF signals to generate IF or baseband signals. The IF or baseband signals are sent to RX processing circuitry 376, which filters, decodes, and / or digitizes the baseband or IF signals to generate processed baseband signals. RX processing circuitry 376 sends the processed baseband signals to controller / processor 378 for further processing.

[0242] The TX processing circuitry 374 receives analog or digital data (such as voice data, network data, email, or interactive video game data) from the controller / processor 378. The TX processing circuitry 374 encodes, multiplexes, and / or digitizes the outgoing baseband data to generate processed baseband or IF signals. The RF transceivers 372a-372n receive the outgoing processed baseband or IF signals from the TX processing circuitry 374 and up-convert the baseband or IF signals into RF signals that are transmitted via the antennas 370a-370n.

[0243] The controller / processor 378 can include one or more processors or other processing devices that control the overall operation of the gNB 102. For example, the controller / processor 378 can control the reception of forward channel signals and the transmission of reverse channel signals via the RF transceivers 372a-372n, the RX processing circuitry 376, and the TX processing circuitry 374 in accordance with well-known principles. The controller / processor 378 can also support additional functionality, such as more advanced wireless communication functions. For example, the controller / processor 378 can perform blind interference sensing (BIS) procedures, such as those performed by a Blind Interference Sensing (BIS) algorithm, and decode received signals with interference signals subtracted. The controller / processor 378 can support any of a variety of other functions within the gNB 102. In some embodiments, the controller / processor 378 includes at least one microprocessor or microcontroller.

[0244] The controller / processor 378 is also capable of executing programs and other processes resident in the memory 380, such as a basic OS. The controller / processor 378 is also capable of supporting channel quality measurement and reporting for systems having 2D antenna arrays as described in embodiments of the present disclosure. In some embodiments, the controller / processor 378 supports communication between entities such as web RTC. The controller / processor 378 is capable of moving data into or out of the memory 380 as needed by the executing processes.

[0245] The controller / processor 378 is also coupled to a backhaul or network interface 382. The backhaul or network interface 382 allows the gNB 102 to communicate with other devices or systems via a backhaul connection or over a network. The backhaul or network interface 382 can support communication over any suitable wired or wireless connection(s). For example, when the gNB 102 is implemented as part of a cellular communication system (such as one supporting 5G or new radio access technology, or NR, LTE, or LTE-A), the backhaul or network interface 382 can allow the gNB 102 to communicate with other gNBs via a wired or wireless backhaul connection. When the gNB 102 is implemented as an access point, the backhaul or network interface 382 can allow the gNB 102 to communicate over a wired or wireless local area network or with a larger network, such as the Internet, via a wired or wireless connection. The backhaul or network interface 382 includes any suitable structure that supports communication over a wired or wireless connection, such as an Ethernet or RF transceiver.

[0246] Memory 380 is coupled to controller / processor 378. A portion of memory 380 can include RAM, while another portion of memory 380 can include flash memory or other ROM. In some embodiments, a plurality of instructions, such as a BIS algorithm, are stored in the memory. The plurality of instructions are configured to cause controller / processor 378 to perform the BIS process and decode the received signal after subtracting at least one interfering signal determined by the BIS algorithm.

[0247] As described in more detail below, the transmit and receive paths of gNB 102 (implemented using RF transceivers 372a-372n, TX processing circuitry 374, and / or RX processing circuitry 376) support aggregated communications with FDD cells and TDD cells.

[0248] although Figure 3b An example of a gNB 102 is shown, but the Figure 3b For example, gNB 102 can include any number of Figure 3a . As a specific example, an access point can include a number of backhaul or network interfaces 382, and the controller / processor 378 can support routing functions to route data between different network addresses. As another specific example, while shown as including a single instance of TX processing circuitry 374 and a single instance of RX processing circuitry 376, the gNB 102 can include multiple instances of each (such as one for each RF transceiver).

[0249] The time domain unit (also called time unit) in this application can be: an OFDM symbol, an OFDM symbol group (consisting of multiple OFDM symbols), a time slot, a time slot group (consisting of multiple time slots), a subframe, a subframe group (consisting of multiple subframes), a system frame, a system frame group (consisting of multiple system frames); it can also be an absolute time unit, such as 1 millisecond, 1 second, etc.; the time unit can also be a combination of multiple granularities, such as N1 time slots plus N2 OFDM symbols.

[0250] The frequency domain unit (also called frequency unit) in this application can be: a subcarrier, a subcarrier group (consisting of multiple subcarriers), a resource block (RB), which can also be called a physical resource block (PRB), a resource block group (consisting of multiple RBs), a bandwidth part (BWP), a band part group (consisting of multiple BWPs), a band / carrier, a band group / carrier group; it can also be an absolute frequency domain unit, such as 1 Hz, 1 kHz, etc.; the frequency domain unit can also be a combination of multiple granularities, such as M1 PRBs plus M2 subcarriers.

[0251] Exemplary embodiments of the present disclosure are further described below with reference to the accompanying drawings.

[0252] The text and drawings are provided as examples only to help readers understand the present disclosure. They are not intended to, and should not be interpreted as, limiting the scope of the present disclosure in any way. Although certain embodiments and examples have been provided, it will be apparent to those skilled in the art based on what is disclosed herein that the embodiments and examples shown may be modified without departing from the scope of the present disclosure.

[0253] It will be understood by those skilled in the art that, unless expressly stated otherwise, the singular forms "a", "an", "said" and "the" used herein may also include the plural forms. It should be further understood that the term "comprising" used in the specification of the present application refers to the presence of the features, integers, steps, operations, elements and / or components, but does not exclude the presence or addition of one or more other features, integers, steps, operations, elements, components and / or groups thereof. It should be understood that when we refer to an element as being "connected" or "coupled" to another element, it may be directly connected or coupled to the other element, or there may be intermediate elements. In addition, "connected" or "coupled" as used herein may include wireless connections or wireless couplings. The term "and / or" used herein includes all or any units and all combinations of one or more associated listed items.

[0254] It will be understood by those skilled in the art that, unless otherwise defined, all terms (including technical and scientific terms) used herein have the same meaning as commonly understood by those skilled in the art to which this application belongs. It should also be understood that terms such as those defined in common dictionaries should be understood to have meanings consistent with their meanings in the context of the prior art and will not be interpreted in an idealized or overly formal sense unless specifically defined as herein.

[0255] As will be understood by those skilled in the art, the terms "terminal" and "terminal device" as used herein include both devices having a wireless signal receiver, i.e., devices having only a wireless signal receiver without transmitting capability, and devices having receiving and transmitting hardware capable of two-way communication over a two-way communication link. Such devices may include: cellular or other communication devices having a single-line display, a multi-line display, or a cellular or other communication device without a multi-line display; a PCS (Personal Communications Service) which may combine voice, data processing, fax, and / or data communication capabilities; a PDA (Personal Digital Assistant) which may include a radio frequency receiver, a pager, Internet / Intranet access, a web browser, a notepad, a calendar, and / or a GPS (Global Positioning System) receiver; and conventional laptop and / or palmtop computers or other devices having and / or including a radio frequency receiver. As used herein, the terms "terminal" or "terminal device" may be portable, transportable, installed in a vehicle (air, sea, and / or land), or adapted and / or configured to operate locally, and / or in a distributed manner, at any other location on Earth and / or in space. The terms "terminal" or "terminal device" as used herein may also refer to a communication terminal, an Internet terminal, or a music / video playback terminal, such as a PDA, an MID (Mobile Internet Device), and / or a mobile phone with music / video playback capabilities, or a smart TV, a set-top box, or other device.

[0256] Without departing from the scope of the present invention, the term "send" in the present invention may be used interchangeably with "transmit," "report," "notify," etc.

[0257] The text and drawings are provided as examples only to help readers understand the present disclosure. They are not intended to, and should not be interpreted as, limiting the scope of the present disclosure in any way. Although certain embodiments and examples have been provided, it will be apparent to those skilled in the art based on what is disclosed herein that the embodiments and examples shown may be modified without departing from the scope of the present disclosure.

[0258] The transmission links of the wireless communication system mainly include: the downlink communication link from the 5G gNB to the user equipment (UE) and the uplink communication link from the UE to the network.

[0259] In wireless communication systems, such as current wireless communication systems, the nodes used for positioning measurements include: a UE that initiates a positioning request message, a Location Management Function (LMF) for UE positioning and delivering positioning assistance data, a gNB or Transmission-Reception Point (TRP) that broadcasts positioning assistance data and performs uplink positioning measurements, and a UE that performs downlink positioning measurements. Furthermore, the method of the present invention can also be extended to other communication systems, such as vehicle-to-everything (V2X) communications, such as sidelink communications, where the TRP or UE can be any device in V2X.

[0260] In recent years, artificial intelligence (AI) technology, exemplified by deep learning algorithms, has seen a resurgence, resolving long-standing challenges across various industries and achieving significant technical and commercial success. With the continuous evolution of wireless communication systems, these air interface issues have been subject to ongoing research and attempts to introduce new approaches. Machine learning (ML) methods can be employed to address some communication issues. Machine learning (ML) methods generally refer to both the design of ML algorithms and the design of the ML models upon which they are based. Solutions based on AI deep learning (DL) technologies typically refer to ML algorithms that use artificial neural networks as their model. Deep learning network models typically consist of multiple layers of stacked artificial neural networks. The weights within the neural networks are adjusted by training with existing data, and then used during the inference phase to achieve the desired task in unprecedented scenarios. Furthermore, DL-based solutions generally require higher computing power than conventional, rule-based solutions or algorithms. This often requires dedicated computing chips within the devices running DL algorithms to support their efficient operation.

[0261] Using machine learning-based AI algorithms to solve communication problems typically requires that the conditions required for machine learning problems be met. Device location acquisition is a typical example of air interface-related communication problems that, to some extent, meet these conditions. Therefore, machine learning algorithms can be used to solve these problems and achieve better results than traditional solutions during communication transmission, such as in non-line-of-sight environments.

[0262] While traditional positioning algorithms can provide normal service in some scenarios for currently used wireless communication systems, machine learning algorithms, due to their fundamentally different architecture and characteristics, require a completely different approach to their use. Current wireless communication systems (fourth, fifth, and potentially sixth generation) have strict, unified standards that govern the configuration and behavior of the air interface during communication. Therefore, considering the new machine learning technologies used in next-generation wireless communication systems, the air interface design must be tailored to the characteristics of both the new communication system and the machine learning algorithms. Key considerations include the specific implementation process for implementing machine learning algorithms within the air interface of wireless communication systems, including signal transmission and interaction between user equipment and base stations, activation and deactivation of machine learning algorithms and models, and updates to these algorithms and models during use.

[0263] Therefore, based on the above problems, in order to use machine learning-based solutions in wireless communication systems, it is necessary to propose effective technical methods to specify the specific methods for implementing these solutions in the system, the processes that need to exist, etc., and establish a suitable framework for machine learning-based methods to solve air interface-related problems in wireless communications.

[0264] In this document, the term "AI method" is used to include "machine learning algorithms and models," "AI (artificial intelligence) / ML (machine learning)-based technologies," "AI / ML for NR air interface," "AI / ML technologies," "AI / ML architectures," "AI / ML models," "AI / ML for air interface," "AI / ML methods," "AI / ML-related algorithms," "AI / ML-based algorithms," and "AI / ML solutions." The model used in the AI method is referred to as the AI model, including other descriptions such as AI / ML models.

[0265] The present invention provides a method for applying and configuring a machine learning-based algorithm and model in a wireless communication system to complete or realize the positioning operation and acquisition of positioning information of the wireless communication system, especially when the AI model is deployed on the network side (including the base station side or the high-level entity side). The purpose of the present invention is to solve how to use a machine learning-based solution in a wireless communication system to solve the problems that need to be solved in the air interface of wireless communication, propose how to use the architecture, process, method, etc. of the machine learning solution in the wireless communication system, and realize the application of the machine learning algorithm in the wireless communication system by designing these architectures, processes, methods, etc., so as to achieve the effect that compared with the traditional existing methods, a better machine learning method can be used and implemented smoothly in the communication system, thereby further improving the positioning performance of the wireless communication system.

[0266] The following will introduce the positioning-related operations proposed in the present invention using AI methods in combination with exemplary descriptions, such as when the AI model is deployed on the network side (including the base station side, such as the transmit-receive point (TRP); or the high-level entity side, such as the location management function (LMF)).

[0267] Example 1 (AI model deployed on the first network node (e.g., TRP))

[0268] One embodiment of the present invention describes example operations involved when the model is deployed on a network-side transceiver node (Transmit-receive point, TRP, which may also be replaced by gNB, base station node, etc.), including one or more of the following:

[0269] Optionally, the TRP reports supported AI models, for example, the TRP notifies the LMF or the UE of the AI models supported by the TRP, for example, including one or more of the following:

[0270] The TRP determines the signaling method used for the notification, including one or more of the following:

[0271] ■ Downlink control channel PDCCH (if sent to UE)

[0272] ■MAC CE (if sent to UE)

[0273] ■RRC high-level signaling (such as sent to UE or LMF)

[0274] ■NRPPa message (such as sent to LMF)

[0275] ○ The TRP determines the content to be reported, including one or more of the following:

[0276] The index (or index set, or index list) of supported AI models, such as a list of model IDs;

[0277] ■The features (or feature sets, or feature lists) associated with the supported AI models. Optionally, the corresponding features can be replaced by the corresponding feature index; similarly, the feature set can be replaced by the feature set index, or the feature list can be replaced by the feature index list;

[0278] ■The correspondence between the index of the supported AI model and the features associated with the AI model; for example, including one or more of the following:

[0279] The index of an AI model and the features associated with an AI model can correspond one-to-one; for example, a feature associated with an AI model can correspond to the index of a unique AI model;

[0280] The index of an AI model can correspond to features associated with multiple AI models. For example, an AI model index can correspond to features associated with multiple AI models (such as a feature set or feature list). This can be replaced by an AI model index configuration that includes features associated with multiple AI models (such as a feature set or feature list). This is suitable for situations where an AI model may be applicable to multiple features.

[0281] The indexes of multiple AI models can correspond to the features associated with one AI model. For example, the indexes of multiple AI models (such as an index set or index list) can correspond to the same feature associated with one AI model. This can be replaced by including the indexes of multiple AI models (such as an index set or index list) in the configuration of the feature associated with one AI model. This is applicable when there may be multiple available AI models for a feature associated with one AI model.

[0282] The network node (e.g., LMF) configures the TRP configuration regarding the corresponding ratio of AI model indexes and AI model-associated features, and determines the number of features corresponding to an AI model index, or the number of model indexes corresponding to an AI model-associated feature, based on the configuration;

[0283] ■ The applicable conditions for supported AI models, including one or more of the following:

[0284] One or more cell indexes (or index sets or lists), for example, an AI model can be used in the cells corresponding to the one or more cell indexes; the cell index can be a logical index or a physical cell index; the cell index can be replaced by a TRP index, a sector index, or a zone index, etc.;

[0285] RSRP threshold-related conditions include:

[0286] √ Single RSRP threshold: when the RSRP value measured downlink is higher (or not lower) than the RSRP threshold, the supported AI model can be used; for example, when the RSRP value measured downlink is not higher (or lower) than the RSRP threshold, the supported AI model cannot be used; conversely, when the RSRP value measured downlink is not higher (or lower) than the RSRP threshold, the supported AI model can be used; for example, when the RSRP value measured downlink is higher (or not lower) than the RSRP threshold, the supported AI model cannot be used; and / or

[0287] An RSRP threshold interval (e.g., an interval consisting of an RSRP upper limit and an RSRP lower limit). If the RSRP value measured downlink is within the interval (e.g., not greater than the upper limit and not less than the lower limit), the supported AI model can be used. If the RSRP value measured downlink is not within the interval (e.g., greater than the upper limit or less than the lower limit), the supported AI model cannot be used.

[0288] √ The RSRP value measured in the downlink may be replaced by the RSRP value measured in the uplink, for example, when TRP is used for uplink measurement;

[0289] √The measured RSRP value may be replaced by a measured SNR or SINR value;

[0290] Multipath threshold-related conditions include one or more of the following:

[0291] √ The number of paths in the measurement results that are higher than (or not lower than) a power threshold value P1 is limited to a threshold value T1 (e.g., T1 is a positive integer). For example, in the downlink measurement results, there are X (e.g., X is a positive integer) paths that are higher than (or not lower than) a power threshold value. When X is greater than (or not less than) T1, the supported AI model can be used. For example, when X is not greater than (or less than) T1, the supported AI model cannot be used; and / or

[0292] √ The number of paths above (or not below) a power threshold value P1 in the results of a number threshold T2 (T2 is a positive integer) measurements is greater than or equal to the threshold T1 (T1 is a positive integer). For example, in the measurement results of Y (Y is a positive integer) downlink measurements, there are X (for example, X is a positive integer) paths above (or not below) a power threshold value in each measurement result, and X is greater than (or not less than) T1. When Y is greater than (or not less than) T2, the supported AI model can be used. For example, when Y is not greater than (or less than) T2, the supported AI model cannot be used; and / or

[0293] √ The number of paths in the measurement results that are higher than (or not lower than) a power threshold value P1 is greater than the probability threshold G1 of threshold T1 (T1 is a positive integer). For example, in the downlink measurement results, there are X (if X is a positive integer) paths that are higher than (or not lower than) a power threshold value P1, and the probability value of X is greater than (or not less than) T1 is GX, where G1 and GX are decimals between 0 and 1 with a certain step size, such as 0.1; or percentage values. When GX is greater than (or not less than) G1, the supported AI model can be used. For example, when GX is not greater than (or less than) G1, the supported AI model cannot be used.

[0294] √ The RSRP value measured in the downlink may be replaced by the RSRP value measured in the uplink, for example, when TRP is used for uplink measurement;

[0295] Storage threshold-related conditions, such as conditions related to the storage threshold required for using an AI model. When the storage space provided by a node using an AI model meets (e.g., is greater than or not less than) the storage threshold required for using an AI model, the node can use the AI model; otherwise, if it does not meet the threshold, the AI model cannot be used. The storage space or storage capacity may include input data, output data, intermediate computational data, and one or more hyperparameters used by an AI model, and may be expressed as related numerical values in units such as bits or bytes.

[0296] Complexity threshold-related conditions, such as conditions related to the complexity threshold required for using an AI model. When the computing space provided by a node using an AI model meets (e.g., is greater than or not less than) the complexity threshold required for using an AI model, the node can use the AI model; otherwise, if it does not meet the requirements, the AI model cannot be used. The computing space may include input data, output data, intermediate computational data, and the number of computations required for one or more hyperparameters used by the AI model, expressed, for example, in FLOPS.

[0297] Output data accuracy (e.g., error) requires relevant conditions. For example, if the error of the output data supported by an AI model can meet (e.g., not greater than or less than) the required data error threshold, then the node can use the AI model; otherwise, if it does not meet the requirements, the AI model cannot be used. For example, if the output data is position coordinates and the accuracy (error) requirement is within 1 meter, if the accuracy of the AI model's position coordinate estimation can only be guaranteed within 5 meters, the AI model cannot be used. If the accuracy of the AI model's position coordinate estimation can be guaranteed within 0.8 meters, for example, if it meets the error requirement range, then the AI model is applicable. The same principle can be extended to other output data types such as measurement estimates.

[0298] Conditions related to processing time requirements, such as conditions related to the processing time required to use an AI model. When the processing time required to run an AI model meets (e.g., is not greater than or less than) a processing time threshold, the node can use the AI model; otherwise, if it does not meet the threshold, the AI model cannot be used. The processing time may include the processing time required for one or more of the input data, output data, intermediate computational data, and hyperparameters used by the AI model, and can be expressed using the number and value of time units, such as X symbols, X time slots, or X milliseconds, X seconds, etc.

[0299] ■The type and / or quantity of input data required by the supported AI models, such as input format information, where

[0300] The input data type may include a channel impulse response (CIR), a power delay profile (PDP), a delay profile (DP), a channel information feature (e.g., a channel information feature value extracted by calculation from the CIR, PDP, or DP); and / or

[0301] The input data type may also include one or more of the following:

[0302] √ time value,

[0303] √Power value

[0304] √Phase value

[0305] √Channel information characteristic value

[0306] √The timestamp of the input data, such as the time unit index corresponding to the input data;

[0307] One or more or all of the above three values can be per-path values, and thus can also include a path index.

[0308] The quantity of the input data may correspond to, for example, the quantity value of any of the above data types; for example, the number of required path indices, and / or the number of required time values, and / or the number of required power values, and / or the number of required phase values; wherein one data type may have one quantity value, and / or multiple or all data types may share the same quantity value; or the quantity of the input data may be the total quantity of all types of input data;

[0309] ■The supported AI model output data types and / or quantities, such as output format information, where

[0310] The output data types include one or more of the following:

[0311] √ The coordinate estimate of the UE, which can be a coordinate estimate in a local coordinate system or a coordinate estimate in a global coordinate system;

[0312] √ estimation of a specific measurement value, the specific measurement value including at least one or more of a time measurement value (e.g., arrival time or arrival time difference), a power measurement value, a phase measurement value (phase value or phase difference value), etc.;

[0313] √ an estimate of a specific probability value, where the specific probability value includes one or more of the probability of at least a line-of-sight path (e.g., the probability of a line-of-sight path), the probability that the number of multipaths exceeds a threshold, etc.;

[0314] The quantity of the output data may, for example, correspond to the quantity value of any of the above-mentioned output data types; for example, the number of coordinate estimates outputted, and / or the number of estimates of specific measurement values outputted, and / or the number of estimates of specific probability values outputted; wherein one output data type may have one quantity value, and / or multiple or all output data types may share the same quantity value; or the quantity of the output data may be the total quantity of all types of data outputted;

[0315] The time unit value required to run the AI model from the input data to obtain the output data (e.g., the processing time of the AI model), for example, how much time is required to obtain the output data from the input data through the AI model;

[0316] ○ Optionally, LMF feeds back the AI models that LMF also supports from the supported AI models notified by TRP; for example, TRP receives the AI models supported by LMF indicated by LMF (such as AI model index, index set or index list; or feature index, index set or index list associated with AI model); for example, the AI models supported by LMF indicated by the LMF may be a subset of the supported AI models notified by TRP; for example, TRP notifies that AI model indexes 0, 1, 2, 3, and 4 are supported; TRP receives LMF feedback that LMF supports AI model indexes 0, 1, and 4; for example, TRP may determine that the AI model indexes supported by both TRP and LMF are 0, 1, and 4;

[0317] The TRP or LMF determines the AI model currently in use. For example, the TRP or LMF uses a method to determine the AI model currently in use, including one or more of the following:

[0318] ○ Optionally, before the TRP or LMF determines the currently available AI model, the TRP or LMF triggers the use of the AI method for positioning operations, for example, the TRP or LMF determines not to use other non-AI methods (such as traditional RAT dependent methods, DL-TDOA, etc.) for positioning operations, and the trigger includes one or more of the following:

[0319] ■ Determine whether certain trigger conditions are met; if the certain trigger conditions are met, determine to use the AI method; if the certain trigger conditions are not met, do not use the AI method; the advantage of this is that the AI method is more targeted and can be used when traditional methods may not produce good results; optionally, the certain trigger conditions include one or more of the following:

[0320] The measured first signal is a multipath signal, specifically, the measured first signal has more than one path; wherein different paths have different arrival times and / or received power values;

[0321] The measured first signal is a non-line-of-sight signal, specifically including: when a line-of-sight / non-line-of-sight indication (LoS / NLoS indicator) is false, for example, the measured first signal is a non-line-of-sight signal (for example, when the indication is a hard indication, the indication is NLoS); and / or when a value of the line-of-sight / non-line-of-sight indication (for example, when the indication is a soft indication) is less than (or not greater than) a probability threshold value, for example, when the measured first signal is highly likely to be non-line-of-sight; wherein the threshold value is obtained by receiving an instruction and / or is preset;

[0322] The measured reference signal received power (RSRP) value of the first signal is greater than (or not less than) a threshold value; wherein the threshold value is obtained by receiving an instruction and / or is preset;

[0323] When the Tx Timing Error (Tx TE) or the TEG (Television Group) of the first signal is greater than or (or not less than) a threshold value; wherein the threshold value is obtained by receiving an instruction and / or is preset; and / or

[0324] A receive time error (Rx Timing Error, Rx TE) or receive TEG of the first signal is greater than or (or not less than) a threshold value; wherein the threshold value is obtained by receiving an instruction and / or is preset;

[0325] The sending or receiving TE or TEG of the first signal is greater than or (or not less than) a threshold value; wherein the threshold value is obtained by receiving an instruction and / or is preset;

[0326] The sending and receiving TE or TEG of the first signal belongs to a specific range, wherein the specific range is obtained by receiving an instruction and / or is preset;

[0327] The uncertainty range in the positioning assistance information is greater than (or not less than) a threshold value; wherein the threshold value is obtained by receiving an instruction and / or is preset;

[0328] Optionally, when an instruction to use the AI method is received; for example, the instruction of the AI method may be sent by a network device such as a base station device or a LMF to the UE;

[0329] Optionally, when the at least one trigger condition occurs not less than (or greater than) N times, N is a positive integer not less than 1, and N is obtained by receiving an instruction and / or is preset, for example, when the trigger condition counter reaches N+1 times;

[0330] When the AI method is a valid AI method, such as an AI method that passes a test, the test includes all or part of the operations in the test section below;

[0331] The first signal includes a reference signal used for positioning (such as a downlink PRS (Positioning Reference Signal) and an uplink SRS (Sounding Reference Signal) used for positioning in a cellular wireless communication system), and / or other reference signals in a wireless system, such as an SSB (Synchronization Signal Block) and / or a CSI-RS (Channel State Information-Reference Signal);

[0332] ■Execute the trigger process; optionally, executing the trigger process includes one or more of the following operations:

[0333] When the network side device (e.g., LMF (location management function) and / or base station device) triggers the use of the AI method according to the above trigger conditions; the use of the AI method is indicated and / or activated through an LPP (LTE Positioning Protocol) message and / or an RRC (radio resource control) configuration message and / or a MAC CE (media access control element) and / or a DCI (downlink control information);

[0334] When the UE triggers the use of the AI method according to the above trigger conditions; the UE receives an instruction to use or activate the AI method through an LPP (LTE Positioning Protocol) message and / or an RRC (Radio Resource Control) configuration message and / or a MAC CE (Media Access Control Element) and / or a DCI (Downlink Control Information), or the UE requests the network side device to use the AI method through a PUCCH (Physical Uplink Control Channel) and / or a MAC CE and / or a PRACH (Physical Random Access Channel) channel and / or an LPP message; the UE receives feedback from the network side device on the request to determine whether to use the AI method; the feedback includes the method of the above network side device indicating and / or activating the use of the AI method;

[0335] When the UE triggers the use of the AI method according to the above trigger conditions, the UE directly starts using the AI method. This method is more suitable when the AI method is deployed on the UE side.

[0336] ○ When TRP is determined, for example, TRP is used to finalize the AI model to be used; specifically, including one or more of the following

[0337] ■TRP identifies one or more AI models that meet the applicable conditions for supported AI models, where

[0338] The supported AI model may be an AI model supported by the UE or an AI model supported by both the TRP and the LMF;

[0339] The applicable conditions of the supported AI models refer to the description of the applicable conditions of the supported AI models in the aforementioned TRP notification of supported AI models; they will not be repeated here;

[0340] The applicable conditions of the supported AI model include satisfying all applicable conditions before the conditions are satisfied; or satisfying one or X conditions before the conditions are satisfied. The TRP receives an instruction from the LMF to determine whether to operate according to whether one, X, or all (all) conditions are satisfied before the conditions are satisfied.

[0341] The one or more AI models may include indexes of one or more AI models (such as an index set or index list) or feature indexes associated with one or more AI models (such as an index set or index list);

[0342] ■When the TRP determines that the applicability conditions of a supported AI model are met, the AI model is determined to be the AI model to be used;

[0343] When the TRP determines that X (where X is a positive integer) supported AI models meet the applicable conditions, the TRP determines the AI model to use based on certain rules, including one or more of the following:

[0344] TRP selects an AI model with the best characteristics among X AI models as the AI model to be used. The best characteristics include at least one of the following:

[0345] √ AI models that require minimal storage

[0346] √ Requires AI models with minimal computational complexity

[0347] AI models that require minimal input data type and / or number

[0348] √Can produce AI models with the highest output data accuracy

[0349] √ AI models that correspond to the most AI model-related features

[0350] √ AI model with the largest number of applicable conditions met;

[0351] √ It is not the AI model selected in the previous positioning operation using AI methods

[0352] The TRP randomly selects one AI model to be used from the X AI models (e.g., with equal probability). Specifically, when there are Y AI models that meet the above-mentioned optimal characteristics, the TRP randomly selects one AI model to be used from the Y (e.g., with equal probability) AI models (e.g., with equal probability).

[0353] ■Optionally, the TRP notifies the LMF and / or UE of the determined AI model to be used; for example, the TRP notifies the LMF and / or UE of the determined AI model index to be used and / or the feature index associated with the AI model;

[0354] When the LMF determines, for example, the LMF determines the AI model to be used and notifies the TRP of the determined AI model to be used (e.g., including the determined AI model index and / or the feature index associated with the AI model), the specific operations determined by the LMF include one or more of the following:

[0355] LMF determines one or more AI models that meet the applicable conditions of the supported AI models, where

[0356] The supported AI model may be an AI model supported by the TRP or an AI model supported by both the TRP and the LMF;

[0357] The applicable conditions of the supported AI models refer to the description of the applicable conditions of the supported AI models in the aforementioned TRP reporting of supported AI models; no further details are given here;

[0358] The applicable conditions of the supported AI model include satisfying all applicable conditions before the conditions are satisfied; or satisfying one or X conditions before the conditions are satisfied. The TRP receives an instruction from the LMF to determine whether to operate according to whether one, X, or all (all) conditions are satisfied before the conditions are satisfied.

[0359] The one or more AI models may include indexes of one or more AI models (such as an index set or index list) or feature indexes associated with one or more AI models (such as an index set or index list);

[0360] ■When LMF determines that the applicability conditions of a supported AI model are met, the AI model is determined to be the AI model to be used;

[0361] When the LMF determines that X (where X is a positive integer) supported AI models meet the applicable conditions, the TRP determines the AI model to use based on certain rules, including one or more of the following:

[0362] LMF selects an AI model with the best characteristics among X AI models as the AI model to be used. The best characteristics include at least one of the following:

[0363] √ AI models that require minimal storage

[0364] √ Requires AI models with minimal computational complexity

[0365] AI models that require minimal input data type and / or number

[0366] √Can produce AI models with the highest output data accuracy

[0367] √ AI models that correspond to the most AI model-related features

[0368] √ AI model with the largest number of applicable conditions met;

[0369] √ It is not the AI model selected in the previous positioning operation using AI methods;

[0370] LMF randomly selects an AI model to be used from the X AI models (e.g., with equal probability). Specifically, when there are Y AI models that meet the above-mentioned optimal characteristics, TRP randomly selects an AI model to be used from the Y (e.g., with equal probability) AI models.

[0371] ○ Optionally, when the AI model determined by TRP or LMF is different from the AI model determined previously, TRP or LMF determines to use the AI model; otherwise, for example, when the AI model determined by TRP or LMF is the same as the AI model determined previously, the subsequent operations may include at least one of the following (for example, the following operations may also be performed on the TRP or LMF).

[0372] (Executed when the model's monitoring result is Failure):

[0373] ■TRP terminates the use of AI methods;

[0374] ■TRP selects another AI model and notifies LMF;

[0375] LMF selects another AI model and notifies TRP; TRP receives the notification indicating the AI model to be used;

[0376] ■TRP determines fallback to other non-AI methods for positioning

[0377] ■LMF decides to fall back to other non-AI methods for positioning and notifies the TRP; the TRP receives the notification and decides to fall back to other non-AI methods for positioning;

[0378] ■ TRP reporting AI method error;

[0379] ■LMF reported AI method errors;

[0380] The TRP obtains measurement results, for example, by measuring relevant uplink signals. The measurement results are used in AI-based positioning, such as determining AI models, generating input data, and training. Specifically, operations related to the TRP obtaining measurement results include one or more of the following:

[0381] The UE obtains a reference signal resource configuration for measurement, which is provided by a network node (TRP and / or LMF). The reference signal resource configuration includes: the number and position of reference signals within a certain time unit (such as the symbol index of the reference signal in a time slot), the frequency domain unit position of the reference signal (such as the frequency domain unit interval value from a frequency domain reference point to determine the frequency domain starting position of the reference signal), the number of time units and / or frequency domain units occupied by a reference signal (such as the number of symbols and PRBs of a reference signal); the number of repetitions of a reference signal within a certain time unit, etc.

[0382] Optionally, the UE obtains a configuration for sending, and based on the sent configuration, the UE may determine a time window in which it may send, such as an SRS transmission time window configuration for an AI method;

[0383] ■ Preferably, the UE obtains the priority of the reference signal in the time window, for example, the UE receives the priority indication or performs a priority determination, and obtains, based on the priority indication or priority determination, that when the reference signal collides with other signals (such as downlink signal reception and / or uplink signal transmission) (for example, their time domain units overlap or the time domain unit interval is less than or not greater than a certain threshold), the UE gives priority to sending the reference signal (for example, the reference signal has a higher priority than or not lower than the other signals) or the UE gives priority to receiving or sending the other signals (for example, the reference signal has a lower priority than or not higher than the other signals). When the two signals have the same priority, the UE autonomously determines to send the reference signal and / or receive or send the other signals;

[0384] ○ Based on the reference signal resource configuration obtained for transmission and / or the configuration used for transmission, the UE transmits the reference signal

[0385] The TRP determines a measurement result. For example, the TRP measures a reference signal to obtain a measurement result. This may include processing the measurement result, which may include one or more of the following:

[0386] Obtaining a final measurement result based on the initial measurement result according to certain rules, wherein the initial or final measurement result may include one or more of the aforementioned AI input data types; the type and quantity of the initial measurement result may be the same as or different from the type and quantity of the final measurement result; the certain rules may include one or more of the following:

[0387] A measurement result that satisfies a certain threshold value is selected from the initial measurement results as the final measurement result; the measurement result that satisfies the certain threshold value includes at least one of the following:

[0388] The initial measurement result contains a power value that is higher than (or not lower than) a power threshold value;

[0389] The time value included in the initial measurement result is earlier than (or no later than) or less than (or no greater than) a time threshold. Specifically, the time threshold can be a threshold value of a time unit index, or a set or list of time unit indices used for the final measurement result. For example, the measurement results of the first X (where X is a positive integer) path time unit indices are counted as the final measurement result.

[0390] The initial measurement result contains a phase value that is less than (or not greater than) a phase threshold value;

[0391] A final measurement result is calculated from the initial measurement result according to a certain calculation method; for example, the initial measurement result is CIR, PDP, or DP, and the final measurement result is calculated using an existing calculation formula as a channel information characteristic value (or a set or list of channel information characteristic values);

[0392] Optionally, the TRP reports or feeds back the measurement results. For example, the TRP reports the feedback content related to the obtained measurement results (which may be the initial measurement results or the final measurement results) to the LMF. Specifically, the TRP reports or feeds back the measurement results.

[0393] ■TRP determines the feedback content, which includes the initial measurement results and / or the final measurement results;

[0394] ■ The TRP determines the feedback method, for example, the TRP notifies the LMF and other core network entities through NRPPa (new radio (NR) Positioning Protocol A) or other dedicated signaling;

[0395] The TRP obtains AI model input data. For example, the TRP obtains the input data of the AI model to be used based on the above measurement results, specifically including at least one of the following:

[0396] ○TRP determines the measurement results as input data for the AI model;

[0397] ○ When the measurement result is final, the TRP determines the measurement result as the AI model input data;

[0398] ○ When the measurement result is an initial measurement result, TRP processes the measurement result in the same way as described above to obtain the final measurement result from the initial measurement result according to certain rules to obtain the model input data;

[0399] ○ TRP obtains the input data used based on the measurement results and the required input data type and size of the AI model used;

[0400] ○ In addition, in one implementation, the TRP may obtain characteristic data of the input data, which may include, for example, statistical characteristic data of the input data (such as mean, variance, X-order norm, etc., where X is a positive integer) and / or input data selected from the input data according to certain rules. For example, the characteristic data may be used by the UE or network node to monitor the performance of the AI model. In one implementation, preferably, the TRP stores or feeds back the characteristic data to the LMF; the certain rule may be at least one of the following:

[0401] The input data contains a power value that is higher than (or not lower than) a power threshold value;

[0402] The time value included in the input data is earlier than (or no later than) or less than (or no greater than) a time threshold value; in particular, the time threshold value can be a threshold value of a time unit index, or a set or list of time unit indexes used to obtain the selected input data; for example, the input data of the first X (X is a positive integer) path time unit indexes are counted as the selected input data;

[0403] The input data contains a phase value that is less than (or not greater than) a phase threshold value;

[0404] The TRP obtains AI model output data, for example, the TRP obtains AI model output data based on the determined AI model and the obtained input data; wherein

[0405] The type and / or quantity of the AI model output data is confirmed according to the output data type and / or quantity reported by the AI model to be used;

[0406] Optionally, the TRP reports information related to the obtained output data to the LMF, including one or more of the following:

[0407] ■The information related to the obtained output data may include at least one of the following:

[0408] Directly the output data of the AI model;

[0409] Data obtained by processing the output data of the AI model, the processing method may be a calculated data value obtained by calculating according to an existing technical formula;

[0410] A timestamp of the AI model output data obtained. Optionally, the timestamp of the output data may be a separate timestamp or obtained based on the timestamp of the input data used by the AI model, for example, the timestamp of the output data is the same as the timestamp of the input data used by the AI model, or the timestamp of the output data is equal to the timestamp of the input data used by the AI model plus a time unit interval value. Optionally, the time unit interval value may be a preset value or obtained based on the time unit value required to execute the AI model from the input data to obtain the output data.

[0411] A quality indication of the obtained AI model output data, wherein the quality indication may be:

[0412] √Hard indication, such as a 1-bit indication, where "0" indicates that the output data quality is poor or does not meet the requirements; "1" indicates that the output data quality is good or meets the requirements; and / or

[0413] √Soft indicators, such as using a certain interval between 0 and 1 (such as 0.1) to indicate the quality level of the output data and the probability of good quality. For example, 0 represents the worst output data and 1 represents the best output data. Starting from 0 and increasing the step size by 0.1, the data quality gradually increases from the worst to the best.

[0414] The TRP and / or LMF monitors the currently used AI model. For example, the TRP and / or LMF can detect whether the AI model is functioning properly and meets current service requirements in a specific manner. Specifically, the specific manner includes one or more of the following:

[0415] When the LMF performs monitoring, for example, the LMF determines the monitoring results; specific operations include one or more of the following:

[0416] ■The UE obtains the reference signal resource configuration required for monitoring. The reference signal resource configuration is provided by a network node (such as a TRP and / or LMF). The reference signal resource configuration includes: the number and position of reference signals within a certain time unit (such as the symbol index of the reference signal in a time slot), the frequency domain unit position of the reference signal (such as the frequency domain unit interval value from a frequency domain reference point to determine the frequency domain starting point of the reference signal), the number of time units and / or frequency domain units occupied by a reference signal (such as the number of symbols and PRBs of a reference signal); the number of repetitions of a reference signal within a certain time unit, etc.

[0417] ■ Optionally, the UE obtains a configuration for sending a reference signal required for monitoring. Based on the configuration sent, the UE can determine a time window in which it can send, such as an SRS sending window for monitoring;

[0418] Preferably, the UE obtains the priority of the reference signal in the time window, for example, the UE receives the priority indication or performs a priority judgment, and obtains, according to the priority indication or priority judgment, that when the reference signal collides with other signals (such as downlink signal reception and / or uplink signal transmission) (for example, the time domain units of the two overlap or the time domain unit interval is less than or not greater than a certain threshold value), the UE gives priority to sending the reference signal (for example, the reference signal priority is higher than or not lower than other signals) or the UE gives priority to receiving or sending other signals (for example, the reference signal priority is lower than or not higher than other signals). When the two have the same priority, the UE autonomously determines to send the reference signal and / or receive or send other signals;

[0419] ■ Based on the obtained reference signal resource configuration required for monitoring and / or the configuration for sending the reference signal required for monitoring, the UE transmits the reference signal. Based on the measurement of the reference signal received from the UE, the TRP obtains a measurement result, and the TRP feeds the obtained measurement result back to the LMF. The measurement result may be similar to the aforementioned initial measurement result or final measurement result. The details are not repeated here.

[0420] Based on the obtained measurement results, the LMF performs certain operations to obtain monitoring indicators, which may include at least one of the following:

[0421] LMF determines the measurement results as monitoring indicators;

[0422] When the measurement result is the final measurement result, LMF determines the measurement result as a monitoring indicator;

[0423] When the measurement result is an initial measurement result, LMF processes the measurement result in the same way as described above for obtaining the final measurement result from the initial measurement result according to certain rules to obtain the monitoring index;

[0424] LMF obtains characteristic data of the measurement results, which include statistical characteristic data of the measurement results (such as mean, variance, X-order norm, etc.) and / or measurement results selected from the measurement results according to certain rules as characteristic data. LMF uses this characteristic data as the monitoring indicator. The certain rule can be at least one of the following:

[0425] The power value included in the measurement result is higher than (or not lower than) a power threshold value;

[0426] The time value included in the measurement result is earlier than (or no later than) or less than (or no greater than) a time threshold. Specifically, the time threshold can be a threshold value of a time unit index, or a set or list of time unit indices used to obtain characteristic data. For example, the measurement results of the first X (X is a positive integer) path time unit indices are counted as characteristic data.

[0427] The phase value contained in the measurement result is less than (or not greater than) a phase threshold value;

[0428] ■ Based on the obtained monitoring indicators, the LMF obtains a monitoring result (including pass or fail) according to certain operations. Exemplary operations may include: when the obtained monitoring indicator is better than a certain threshold (or when the situation occurs once, or the situation occurs more than (or not less than) N times (or equal to N+1 times), or the situation occurs more than (or not less than) N times (or equal to N+1 times) continuously), the LMF determines that the monitoring result is passed; otherwise, for example, when the obtained monitoring indicator is worse than a certain threshold (or when the situation occurs once, or the situation occurs more than (or not less than) N times (or equal to N+1 times), or the situation occurs more than (or not less than) N times (or equal to N+1 times) continuously), the LMF determines that the monitoring result is not passed;

[0429] ■Based on the monitoring indicators and / or monitoring results obtained, the LMF determines the subsequent operation and instructs the TRP to perform the subsequent operation; the TRP receives the instruction of the subsequent operation from the LMF and performs the subsequent operation according to the instruction;

[0430] When the obtained monitoring indicator is better than a certain threshold (or the situation occurs once, or the situation occurs more than (or not less than) N times (or equal to N+1 times), or the situation occurs more than (or not less than) N times (or equal to N+1 times) continuously), the subsequent operation is to continue to use the currently determined AI model and / or AI method for positioning; otherwise, for example, when the obtained monitoring indicator is worse than a certain threshold (or the situation occurs once, or the situation occurs more than (or not less than) N times (or equal to N+1 times), or the situation occurs more than (or not less than) N times (or equal to N+1 times) continuously), the subsequent operation is to stop using the AI method for positioning and / or fall back to a non-AI method (RAT-dependent positioning method and other RAT-independent positioning methods) and / or trigger an update of the current AI model (update or optimization finetuning or retraining) and / or enter the aforementioned operation of executing TRP or LMF to determine the currently used AI model; or

[0431] When the monitoring result is passed (or the situation occurs once, or the situation occurs more than (or not less than) N times (or equal to N+1 times), or the situation occurs continuously more than (or not less than) N times (or equal to N+1 times)), the subsequent operation is to continue to use the currently determined AI model and / or AI method for positioning; otherwise, for example, when the monitoring result is failed (or the situation occurs once, or the situation occurs more than (or not less than) N times (or equal to N+1 times), or the situation occurs continuously more than (or not less than) N times (or equal to N+1 times)), the subsequent operation is to stop using the AI method for positioning and / or fall back to a non-AI method (RAT-dependent positioning method and other RAT-independent positioning methods) and / or trigger an update of the current AI model (update or optimization finetuning or retraining) and / or enter the aforementioned operation of executing TRP or LMF to determine the currently used AI model;

[0432] o When the TRP performs monitoring, for example, the TRP determines the monitoring results; exemplary operations may include one or more of the following:

[0433] ■The UE obtains the reference signal resource configuration required for monitoring, which is provided by a network node (e.g., a TRP and / or LMF). The reference signal resource configuration includes at least one of the following: the number and position of reference signals within a certain time unit (e.g., the symbol index of the reference signal in a time slot), the frequency domain unit position of the reference signal (e.g., the frequency domain unit interval value from a frequency domain reference point to determine the frequency domain starting position of the reference signal), the number of time units and / or frequency domain units occupied by a reference signal (e.g., the number of symbols and PRBs of a reference signal), and the number of repetitions of a reference signal within a certain time unit.

[0434] ■ Optionally, the UE obtains a configuration for sending a reference signal required for monitoring. Based on the configuration sent, the UE can determine a time window in which it can send, such as an SRS sending window for monitoring;

[0435] Preferably, the UE obtains the priority of the reference signal in the time window, for example, the UE receives the priority indication or performs a priority judgment, and obtains, according to the priority indication or priority judgment, that when the reference signal collides with other signals (such as downlink signal reception and / or uplink signal transmission) (for example, the time domain units of the two overlap or the time domain unit interval is less than or not greater than a certain threshold value), the UE gives priority to sending the reference signal (for example, the reference signal priority is higher than or not lower than other signals) or the UE gives priority to receiving or sending other signals (for example, the reference signal priority is lower than or not higher than other signals). When the two have the same priority, the UE autonomously determines to send the reference signal and / or receive or send other signals;

[0436] ■ Based on the obtained reference signal resource configuration required for monitoring and / or the configuration for sending the reference signal required for monitoring, the UE transmits the reference signal, and the TRP obtains a measurement result based on the measurement of the reference signal. The measurement result may be similar to the aforementioned initial measurement result or final measurement result. The details are not repeated here.

[0437] ■ Based on the measurement results obtained, TRP obtains monitoring indicators according to certain operations; specifically, they include:

[0438] TRP determines the measurement results as monitoring indicators;

[0439] When the measurement result is final, the TRP determines the measurement result as a monitoring indicator;

[0440] When the measurement result is an initial measurement result, the TRP processes the measurement result in the same way as described above for obtaining the final measurement result from the initial measurement result according to certain rules to obtain the monitoring indicator;

[0441] The TRP obtains characteristic data of the measurement results. The characteristic data may include statistical characteristic data of the measurement results (such as mean, variance, X-order norm, etc.) and / or measurement results selected from the measurement results according to certain rules as characteristic data. The TRP uses the characteristic data as the monitoring indicator. The certain rules may be at least one of the following:

[0442] The power value included in the measurement result is higher than (or not lower than) a power threshold value;

[0443] The time value included in the measurement result is earlier than (or no later than) or less than (or no greater than) a time threshold. Specifically, the time threshold can be a threshold value of a time unit index, or a set or list of time unit indices used to obtain characteristic data. For example, the measurement results of the first X (X is a positive integer) path time unit indices are counted as characteristic data.

[0444] The phase value contained in the measurement result is less than (or not greater than) a phase threshold value;

[0445] Based on the obtained monitoring indicators, the TRP performs certain operations to obtain a monitoring result (including a pass or fail). Exemplary operations include: when the obtained monitoring indicator is better than a certain threshold (or when the condition occurs once, or when the condition occurs more than (or not less than) N times (or equal to N+1 times), or when the condition occurs more than (or not less than) N times (or equal to N+1 times) consecutively), the TRP determines the monitoring result as a pass; otherwise, for example, when the obtained monitoring indicator is worse than a certain threshold (or when the condition occurs once, or when the condition occurs more than (or not less than) N times (or equal to N+1 times), or when the condition occurs more than (or not less than) N times (or equal to N+1 times) consecutively), the TRP determines the monitoring result as a fail;

[0446] ■TRP reports the above monitoring indicators and / or the above monitoring results; LMF determines the subsequent operation based on the obtained monitoring indicators and / or monitoring results, and instructs TRP to perform the subsequent operation; TRP receives the instruction of the subsequent operation from LMF and performs the subsequent operation according to the instruction; wherein,

[0447] When the obtained monitoring indicator is better than a certain threshold (or the situation occurs once, or the situation occurs more than (or not less than) N times (or equal to N+1 times), or the situation occurs more than (or not less than) N times (or equal to N+1 times) continuously), the subsequent operation is to continue to use the currently determined AI model and / or AI method for positioning; otherwise, for example, when the obtained monitoring indicator is worse than a certain threshold (or the situation occurs once, or the situation occurs more than (or not less than) N times (or equal to N+1 times), or the situation occurs more than (or not less than) N times (or equal to N+1 times) continuously), the subsequent operation is to stop using the AI method for positioning and / or fall back to a non-AI method (for example, a RAT-dependent positioning method and / or other RAT-independent positioning method) and / or trigger an update of the current AI model (update or optimization finetuning or retraining) and / or enter the aforementioned operation of executing TRP or LMF to determine the currently used AI model; or

[0448] When the monitoring result is passed (or the situation occurs once, or the situation occurs more than (or not less than) N times (or equal to N+1 times), or the situation occurs continuously more than (or not less than) N times (or equal to N+1 times)), the subsequent operation is to continue to use the currently determined AI model and / or AI method for positioning; otherwise, for example, when the monitoring result is failed (or the situation occurs once, or the situation occurs more than (or not less than) N times (or equal to N+1 times), or the situation occurs continuously more than (or not less than) N times (or equal to N+1 times)), the subsequent operation is to stop using the AI method for positioning and / or fall back to a non-AI method (for example, a RAT-dependent positioning method and / or other RAT-independent positioning method) and / or trigger an update of the current AI model (update or optimization finetuning or retraining) and / or enter the aforementioned operation of executing TRP or LMF to determine the currently used AI model;

[0449] ■ Based on the monitoring indicators and / or monitoring results obtained, TRP determines the subsequent actions and provides feedback to LMF on the subsequent actions determined;

[0450] When the obtained monitoring indicator is better than a certain threshold (or the situation occurs once, or the situation occurs more than (or not less than) N times (or equal to N+1 times), or the situation occurs more than (or not less than) N times (or equal to N+1 times) continuously), the subsequent operation is to continue to use the currently determined AI model and / or AI method for positioning; otherwise, for example, when the obtained monitoring indicator is worse than a certain threshold (or the situation occurs once, or the situation occurs more than (or not less than) N times (or equal to N+1 times), or the situation occurs more than (or not less than) N times (or equal to N+1 times) continuously), the subsequent operation is to stop using the AI method for positioning and / or fall back to a non-AI method (for example, a RAT-dependent positioning method and another RAT-independent positioning method) and / or trigger an update of the current AI model (update or optimization finetuning or retraining) and / or enter the aforementioned operation of executing TRP or LMF to determine the currently used AI model; or

[0451] When the monitoring result is passed (or the situation occurs once, or the situation occurs more than (or not less than) N times (or equal to N+1 times), or the situation occurs more than (or not less than) N times (or equal to N+1 times) continuously), the subsequent operation is to continue to use the currently determined AI model and / or AI method for positioning; otherwise, for example, when the monitoring result is not passed (or the situation occurs once, or the situation occurs more than (or not less than) N times (or equal to N+1 times), or the situation occurs more than (or not less than) N times (or equal to N+1 times) continuously), the subsequent operation is to stop using the AI method for positioning and / or fall back to a non-AI method (for example, a RAT-dependent positioning method and / or other RAT-independent positioning method) and / or trigger an update of the current AI model (update or optimization finetuning or retraining) and / or enter the aforementioned operation of executing TRP or LMF to determine the currently used AI model.

[0452] Example 2 (AI model deployed on the second network node (e.g., LMF))

[0453] Another embodiment of the present invention describes the specific operations involved when the model is deployed in a high-level functional entity on the network side, such as LMF (which may also be replaced by other specific functional entities), including one or more of the following:

[0454] ● Optionally, the UE or TRP reports the supported AI models, for example, the TRP notifies the LMF or the UE of the AI models supported by the TRP, and / or the UE notifies the LMF of the AI models supported by the UE,

[0455] For example, one or more of the following:

[0456] The TRP determines the signaling method used for the notification, including one or more of the following:

[0457] ■ Downlink control channel PDCCH (if sent to UE)

[0458] ■MAC CE (if sent to UE)

[0459] ■RRC high-level signaling (such as sent to UE or LMF)

[0460] ■NRPPa message (such as sent to LMF)

[0461] The UE determines the signaling method used for the notification, including one or more of the following:

[0462] ■Uplink control channel PUCCH (such as sent to TRP)

[0463] ■MAC CE (if sent to TRP)

[0464] ■RRC high-level signaling (such as sent to TRP or LMF)

[0465] ■LPPa message (such as sent to LMF)

[0466] ○ The UE or TRP determines the content to be reported, including one or more of the following:

[0467] The index (or index set, or index list) of supported AI models, such as a list of model IDs;

[0468] ■The features (or feature sets, or feature lists) associated with the supported AI models. Optionally, the corresponding features can be replaced by the corresponding feature index; similarly, the feature set can be replaced by the feature set index, or the feature list can be replaced by the feature index list;

[0469] ■The correspondence between the index of supported AI models and the features associated with the AI models; specifically, including one or more of the following:

[0470] The index of an AI model and the features associated with an AI model can correspond one to one; for example, a feature associated with an AI model can correspond to the index of a unique AI model; in particular,

[0471] The index of an AI model can correspond to features associated with multiple AI models; for example, an AI model index can correspond to features associated with multiple AI models (such as a feature set or feature list), which can be replaced by an AI model index configuration that includes features associated with multiple AI models (such as a feature set or feature list); this is suitable for situations where an AI model may be applicable to multiple features; and / or

[0472] The indexes of multiple AI models can correspond to features associated with one AI model; for example, the indexes of multiple AI models (such as an index set or index list) can correspond to the same feature associated with one AI model, and the configuration of a feature associated with one AI model can be replaced by including indexes of multiple AI models (such as an index set or index list); this is applicable when there may be multiple available AI models for a feature associated with one AI model; and / or

[0473] A configuration of the corresponding ratio of AI model indexes to AI model-associated features, whereby the number of features corresponding to an AI model index, or the number of model indexes corresponding to an AI model-associated feature, is determined based on the configuration;

[0474] ■ Conditions under which the supported AI models are applicable, including one or more of the following:

[0475] One or more cell indexes (or index sets or lists), for example, an AI model can be used in the cells corresponding to the one or more cell indexes; the cell index can be a logical index or a physical cell index; the cell index can be replaced by a TRP index, a sector index, or a zone index, etc.;

[0476] RSRP threshold-related conditions include:

[0477] √ Single RSRP threshold: when the RSRP value measured downlink is higher (or not lower) than the RSRP threshold, the supported AI model can be used; for example, when the RSRP value measured downlink is not higher (or lower) than the RSRP threshold, the supported AI model cannot be used; conversely, when the RSRP value measured downlink is not higher (or lower) than the RSRP threshold, the supported AI model can be used; for example, when the RSRP value measured downlink is higher (or not lower) than the RSRP threshold, the supported AI model cannot be used; and / or

[0478] An RSRP threshold interval (e.g., an interval consisting of an RSRP upper limit and an RSRP lower limit). If the RSRP value measured downlink is within the interval (e.g., not greater than the upper limit and not less than the lower limit), the supported AI model can be used. If the RSRP value measured downlink is not within the interval (e.g., greater than the upper limit or less than the lower limit), the supported AI model cannot be used.

[0479] √ The RSRP value measured in the downlink may be replaced by the RSRP value measured in the uplink, for example, when TRP is used for uplink measurement;

[0480] √The measured RSRP value may be replaced by a measured SNR or SINR value;

[0481] Multipath threshold related conditions include:

[0482] √ The number of paths in the measurement results that are higher than (or not lower than) a power threshold value P1 is limited to a threshold value T1 (T1 is a positive integer). For example, in the downlink measurement results, there are X (X is a positive integer) paths that are higher than (or not lower than) a power threshold value. When X is greater than (or not less than) T1, the supported AI model can be used. For example, when X is not greater than (or less than) T1, the supported AI model cannot be used; and / or

[0483] √ The number of paths that are higher than (or not lower than) a power threshold value P1 in the results of a number threshold T2 (T2 is a positive integer) measurements is greater than or equal to the threshold T1 (T1 is a positive integer). For example, in the measurement results of Y (Y is a positive integer) downlink measurements, there are X (X is a positive integer) paths that are higher than (or not lower than) a power threshold value in each measurement result, and X is greater than (or not less than) T1. When Y is greater than (or not less than) T2, the supported AI model can be used. For example, when Y is not greater than (or less than) T2, the supported AI model cannot be used; and / or

[0484] √ The number of paths in the measurement results that are higher than (or not lower than) a power threshold value P1 is greater than the probability threshold G1 of threshold T1 (T1 is a positive integer). For example, in the downlink measurement results, there are X (X is a positive integer) paths that are higher than (or not lower than) a power threshold value P1, and the probability value of X is greater than (or not less than) T1 is GX, where G1 and GX are decimals between 0 and 1 with a certain step size, such as 0.1; or percentage values. When GX is greater than (or not less than) G1, the supported AI model can be used. For example, when GX is not greater than (or less than) G1, the supported AI model cannot be used.

[0485] √ The RSRP value measured in the downlink may be replaced by the RSRP value measured in the uplink, for example, when TRP is used for uplink measurement;

[0486] Storage threshold-related conditions, such as conditions related to the storage threshold required for using an AI model. When the storage space provided by a node using an AI model meets (e.g., is greater than or not less than) the storage threshold required for using an AI model, the node can use the AI model; otherwise, if it does not meet the requirements, the AI model cannot be used. The storage space or storage capacity may include input data, output data, intermediate computational data, and one or more hyperparameters used by the AI model, represented by bit or byte values.

[0487] Complexity threshold-related conditions, such as conditions related to the complexity threshold required for using an AI model. When the computing space provided by a node using an AI model meets (e.g., is greater than or not less than) the complexity threshold required for using an AI model, the node can use the AI model; otherwise, if it does not meet the requirements, the AI model cannot be used. The computing space may include input data, output data, intermediate computational data, and the number of computations required for one or more hyperparameters used by the AI model, for example, expressed in FLOPS.

[0488] Output data accuracy (e.g., error) requires relevant conditions. For example, if the error of the output data supported by an AI model can meet (e.g., not greater than or less than) the required data error threshold, then the node can use the AI model; otherwise, if it does not meet the requirements, the AI model cannot be used. For example, if the output data is position coordinates and the accuracy (error) requirement is within 1 meter, if the accuracy of the AI model's position coordinate estimation can only be guaranteed within 5 meters, the AI model cannot be used. If the accuracy of the AI model's position coordinate estimation can be guaranteed within 0.8 meters, for example, if it meets the error requirement range, then the AI model is applicable. Similarly, it can be extended to other output data types such as measurement estimates.

[0489] Conditions related to processing time requirements, such as conditions related to the processing time required to use an AI model. When the processing time required to run an AI model meets (e.g., is not greater than or less than) a processing time threshold, the node can use the AI model; otherwise, if it does not meet the threshold, the AI model cannot be used. The processing time may include the processing time required for one or more of the input data, output data, intermediate computational data, and hyperparameters used by the AI model, and can be expressed using the number and value of time units, such as X symbols, X time slots, or X milliseconds, X seconds, etc.

[0490] ■The type and / or quantity of input data required by the supported AI models, such as input format information, where

[0491] The input data type may include channel impulse response CIR, power delay profile PDP, delay profile DP, channel information features (e.g., channel information feature values extracted by calculation from CIR or PDP or DP); and / or

[0492] The input data type may also include one or more of the following:

[0493] √ time value,

[0494] √Power value

[0495] √Phase value

[0496] √Channel information characteristic value

[0497] √The timestamp of the input data, such as the time unit index corresponding to the input data;

[0498] One or more or all of the above three values can be per-path values, and thus can also include a path index.

[0499] The quantity of the input data, for example, corresponds to the quantity value of any of the above data types; for example, the number of required path indices, and / or the number of required time values, and / or the number of required power values, and / or the number of required phase values; wherein one data type may have one quantity value, and / or multiple or all data types may share the same quantity value; or the total quantity of all input data types;

[0500] ■The type and / or quantity of AI model output supported, e.g., output format information,

[0501] in

[0502] The output data types include one or more of the following:

[0503] √ The coordinate estimate of the UE, which can be a coordinate estimate in a local coordinate system or a coordinate estimate in a global coordinate system;

[0504] √ estimation of specific measurement values, the specific measurement values including at least one or more of time measurement values (arrival time or arrival time difference), power measurement values, phase measurement values (phase value or phase difference value), etc.;

[0505] √ an estimate of a specific probability value, the specific probability value including one or more of the probability of at least a line-of-sight path (also, for example, the probability of a line-of-sight path), the probability that the number of multipaths exceeds a threshold, etc.;

[0506] The quantity of the output data, for example, corresponds to the quantity value of any of the above-mentioned output data types; for example, the number of coordinate estimates output, and / or the number of estimates of specific measurement values output, and / or the number of estimates of specific probability values output; wherein one output data type may have one quantity value, and / or multiple or all output data types may share the same quantity value; or the total quantity of all output data types;

[0507] The time unit value required to run the AI model from the input data to obtain the output data (e.g., AI model processing time), for example, how much time is required to obtain the output data from the input data through the AI model;

[0508] ○ Optionally, the LMF feeds back the AI model also supported by the LMF from the supported AI models notified by the UE and / or TRP; for example, the UE and / or TRP receive the AI model supported by the LMF indicated by the LMF (such as an AI model index, an index set or an index list; or a feature index, an index set or an index list associated with the AI model); for example, the AI model supported by the LMF indicated by the LMF may be a subset of the supported AI models notified by the UE and / or TRP; for example, the TRP notifies that AI model indexes 0, 1, 2, 3, and 4 are supported; the TRP receives feedback from the LMF that the LMF supports AI model indexes 0, 1, and 4; for example, the TRP may determine that the AI model indexes supported by both the TRP and the LMF are 0, 1, and 4; for another example, the TRP notifies that AI model indexes 0, 1, 2, 3, and 4 are supported; the UE notifies that AI models 1, 2, 3, and 4 are supported; the UE and / or TRP receive feedback from the LMF that the LMF supports AI model indexes 0, 1, and 4; for example, the TRP may determine that the AI model indexes supported by both the UE, the TRP, and the LMF are 1 and 4;

[0509] LMF determines the currently used AI model. For example, LMF determines the currently used AI model based on a certain method, such as one or more of the following:

[0510] ○ Optionally, before the LMF determines the currently available AI model, the TRP or LMF triggers the use of the AI method for positioning operations, for example, the TRP or LMF determines not to use other non-AI methods (such as traditional RAT dependent methods, DL-TDOA, etc.) for positioning operations, and the trigger includes one or more of the following:

[0511] ■ Determine whether certain trigger conditions are met; if the certain trigger conditions are met, determine to use the AI method; if the certain trigger conditions are not met, do not use the AI method; the advantage of this is that the AI method is more targeted and can be used when traditional methods may not produce good results; optionally, the certain trigger conditions include one or more of the following:

[0512] The measured first signal is a multipath signal, specifically, the measured first signal has more than one path; wherein different paths have different arrival times and / or received power values;

[0513] The measured first signal is a non-line-of-sight signal, specifically including: when a line-of-sight / non-line-of-sight indication (LoS / NLoS indicator) is false, for example, the measured first signal is a non-line-of-sight signal (for example, when the indication is a hard indication, the indication is NLoS); and / or when a value of the line-of-sight / non-line-of-sight indication (for example, when the indication is a soft indication) is less than (or not greater than) a probability threshold value, for example, when the measured first signal is highly likely to be non-line-of-sight; wherein the threshold value is obtained by receiving an instruction and / or is preset;

[0514] The measured reference signal received power (RSRP) value of the first signal is greater than (or not less than) a threshold value; wherein the threshold value is obtained by receiving an instruction and / or is preset;

[0515] When the Tx Timing Error (Tx TE) or the TEG (Television Group) of the first signal is greater than or (or not less than) a threshold value; wherein the threshold value is obtained by receiving an instruction and / or is preset; and / or

[0516] A receive time error (Rx Timing Error, Rx TE) or receive TEG of the first signal is greater than or (or not less than) a threshold value; wherein the threshold value is obtained by receiving an instruction and / or is preset;

[0517] The sending or receiving TE or TEG of the first signal is greater than or (or not less than) a threshold value; wherein the threshold value is obtained by receiving an instruction and / or is preset;

[0518] The sending and receiving TE or TEG of the first signal belongs to a specific range, wherein the specific range is obtained by receiving an instruction and / or is preset;

[0519] The uncertainty range in the positioning assistance information is greater than (or not less than) a threshold value; wherein the threshold value is obtained by receiving an instruction and / or is preset;

[0520] Optionally, when an instruction to use the AI method is received; for example, the instruction of the AI method may be sent by a network device such as a base station device or a LMF to the UE;

[0521] Optionally, when the at least one trigger condition occurs not less than (or greater than) N times, N is a positive integer not less than 1, and N is obtained by receiving an instruction and / or is preset, for example, when the trigger condition counter reaches N+1 times;

[0522] When the AI method is a valid AI method, such as an AI method that passes a test, the test includes all or part of the operations in the test section below;

[0523] The first signal includes a reference signal used for positioning (such as a downlink PRS (Positioning Reference Signal) and an uplink SRS (Sounding Reference Signal) used for positioning in a cellular wireless communication system), and / or other reference signals in a wireless system, such as an SSB (Synchronization Signal Block) and / or a CSI-RS (Channel State Information-Reference Signal);

[0524] ■Execute the trigger process; optionally, executing the trigger process includes one or more of the following operations:

[0525] When the network side device (e.g., LMF (location management function) and / or base station device) triggers the use of the AI method according to the above trigger conditions; the use of the AI method is indicated and / or activated through an LPP (LTE Positioning Protocol) message and / or an RRC (radio resource control) configuration message and / or a MAC CE (media access control element) and / or a DCI (downlink control information);

[0526] When the UE triggers the use of the AI method according to the above trigger conditions; the UE receives an instruction to use or activate the AI method through an LPP (LTE Positioning Protocol) message and / or an RRC (Radio Resource Control) configuration message and / or a MAC CE (Media Access Control Element) and / or a DCI (Downlink Control Information), or the UE requests the network side device to use the AI method through a PUCCH (Physical Uplink Control Channel) and / or a MAC CE and / or a PRACH (Physical Random Access Channel) channel and / or an LPP message; the UE receives feedback from the network side device on the request to determine whether to use the AI method; the feedback includes the method of the above network side device indicating and / or activating the use of the AI method;

[0527] When the UE triggers the use of the AI method according to the above trigger conditions, the UE directly starts using the AI method. This method is more suitable when the AI method is deployed on the UE side.

[0528] ○ When TRP assists in the determination, for example, TRP determines the AI model to be used and feeds back the determined model or models to LMF for final determination; for example, including one or more of the following:

[0529] ■TRP identifies one or more AI models that meet the applicable conditions for supported AI models, where

[0530] The supported AI model may be the supported AI model reported by the UE, or the supported AI model reported by the TRP, or an AI model supported by the UE and / or TRP and / or LMF;

[0531] The applicable conditions of the supported AI models refer to the description of the applicable conditions of the supported AI models in the aforementioned TRP notification of supported AI models; they will not be repeated here;

[0532] The applicable conditions of the supported AI model include satisfying all applicable conditions before the conditions are satisfied; or satisfying one or X conditions before the conditions are satisfied. The TRP receives an instruction from the LMF to determine whether to operate according to whether one, X, or all (all) conditions are satisfied before the conditions are satisfied.

[0533] The one or more AI models may include indexes of one or more AI models (such as an index set or index list) or feature indexes associated with one or more AI models (such as an index set or index list);

[0534] ■When the TRP determines that the applicable conditions of a supported AI model are met, the AI model is determined to be the AI model to be used; the TRP notifies the LMF and / or UE of the determined AI model to be used; for example, the TRP notifies the LMF and / or UE of the determined AI model index and / or the feature index associated with the AI model;

[0535] When the TRP determines that X (where X is a positive integer) supported AI models meet the applicable conditions, for example, there are X applicable AI model candidates, the TRP determines the AI model to use based on certain rules, including one or more of the following:

[0536] TRP selects an AI model with the best characteristics among X AI models as the AI model to be used. The best characteristics include at least one of the following:

[0537] √ AI models that require minimal storage

[0538] √ AI models that require minimal computational complexity

[0539] AI models that require minimal input data type and / or number

[0540] √Can produce AI models with the highest output data accuracy

[0541] √ AI models that correspond to the most AI model-related features

[0542] √ AI model with the largest number of applicable conditions met;

[0543] √ It is not the AI model selected in the previous positioning operation using AI methods

[0544] The TRP randomly selects one AI model to be used from the X AI models (e.g., with equal probability). Specifically, when there are Y AI models that meet the above-mentioned optimal characteristics, the TRP randomly selects one AI model to be used from the Y (Y is a positive integer) AI models (e.g., with equal probability).

[0545] The TRP notifies the LMF and / or UE of the determined AI model to be used; for example, the TRP notifies the LMF and / or UE of the determined AI model index and / or the feature index associated with the AI model;

[0546] ■Optionally, when the TRP determines that X (where X is a positive integer) supported AI models satisfy applicable conditions, for example, there are X applicable AI model candidates; the TRP notifies the LMF and / or UE of the X AI model candidates; for example, the TRP notifies the LMF and / or UE of the determined AI model index and / or the feature index associated with the AI model; when notifying the LMF, the LMF determines the AI model to be used according to certain rules, and the certain rules are as described above and will not be repeated here;

[0547] ○ When the LMF determines, for example, the LMF determines the AI model to be used; and notifies the TRP or UE of the determined AI model to be used (including the determined AI model index and / or the feature index associated with the AI model), the specific operations determined by the LMF include one or more of the following:

[0548] LMF determines one or more AI models that meet the applicable conditions of the supported AI models, where

[0549] The supported AI model may be an AI model supported by the TRP or an AI model supported by both the TRP and the LMF;

[0550] The applicable conditions of the supported AI models refer to the description of the applicable conditions of the supported AI models in the aforementioned TRP reporting of supported AI models; they will not be repeated here;

[0551] The applicable conditions of the supported AI model include satisfying all applicable conditions before the conditions are satisfied; or satisfying one or X conditions before the conditions are satisfied. The TRP receives an instruction from the LMF to determine whether to operate according to whether one, X, or all (all) conditions are satisfied before the conditions are satisfied.

[0552] The one or more AI models may include indexes of one or more AI models (such as an index set or index list) or feature indexes associated with one or more AI models (such as an index set or index list);

[0553] ■When LMF determines that the applicability conditions of a supported AI model are met, the AI model is determined to be the AI model to be used;

[0554] When the LMF determines that X (where X is a positive integer) supported AI models meet the applicable conditions, the TRP determines the AI model to use based on certain rules, including one or more of the following:

[0555] LMF selects an AI model with the best characteristics among X AI models as the AI model to be used. The best characteristics include at least one of the following:

[0556] √ AI models that require minimal storage

[0557] √ Requires AI models with minimal computational complexity

[0558] AI models that require minimal input data type and / or number

[0559] √Can produce AI models with the highest output data accuracy

[0560] √ AI models that correspond to the most AI model-related features

[0561] √ AI model with the largest number of applicable conditions met;

[0562] √ It is not the AI model selected in the previous positioning operation using AI methods;

[0563] LMF randomly selects one AI model to be used from the X AI models (with equal probability). Specifically, when there are Y AI models that meet the above optimal characteristics, TRP randomly selects one AI model to be used from the Y (Y is a positive integer) AI models (with equal probability).

[0564] Optionally, when the AI model determined by the TRP or LMF is different from the AI model determined previously, the TRP or LMF determines to use the AI model; otherwise, for example, when the AI model determined by the TRP or LMF is the same as the AI model determined previously, subsequent operations may include at least one of the following:

[0565] ■TRP terminates the use of AI methods;

[0566] ■TRP selects another AI model and notifies LMF;

[0567] LMF selects another AI model and notifies TRP; TRP receives the notification indicating the AI model to be used;

[0568] ■TRP determines fallback to other non-AI methods for positioning

[0569] ■LMF decides to fall back to other non-AI methods for positioning and notifies the TRP; the TRP receives the notification and decides to fall back to other non-AI methods for positioning;

[0570] ■ TRP reporting AI method error;

[0571] ■LMF reported AI method errors;

[0572] The TRP obtains measurement results, for example, by measuring relevant uplink signals. The measurement results are used in positioning based on AI methods, such as determining AI models, generating input data, and training. For example, operations related to the TRP obtaining measurement results include one or more of the following:

[0573] The UE obtains a reference signal resource configuration for measurement, which is provided by a network node (TRP and / or LMF). The reference signal resource configuration includes: the number and position of reference signals within a certain time unit (such as the symbol index of the reference signal in a time slot), the frequency domain unit position of the reference signal (such as the frequency domain unit interval value from a frequency domain reference point to determine the frequency domain starting position of the reference signal), the number of time units and / or frequency domain units occupied by a reference signal (such as the number of symbols and PRBs of a reference signal); the number of repetitions of a reference signal within a certain time unit, etc.

[0574] Optionally, the UE obtains a configuration for sending, and based on the sending configuration, the UE may determine a time window in which it may send, such as an SRS transmission time window configuration for an AI method;

[0575] ■ Preferably, the UE obtains the priority of the reference signal in the time window, for example, the UE receives the priority indication or performs a priority determination, and obtains, based on the priority indication or priority determination, that when the reference signal collides with other signals (such as downlink signal reception and / or uplink signal transmission) (for example, their time domain units overlap or the time domain unit interval is less than or not greater than a certain threshold), the UE gives priority to sending the reference signal (for example, the reference signal has a higher priority than or not lower than the other signals) or the UE gives priority to receiving or sending the other signals (for example, the reference signal has a lower priority than or not higher than the other signals). When the two signals have the same priority, the UE autonomously determines to send the reference signal and / or receive or send the other signals;

[0576] ○ Based on the reference signal resource configuration obtained for transmission and / or the configuration used for transmission, the UE transmits the reference signal

[0577] The TRP determines a measurement result. For example, the TRP measures a reference signal to obtain a measurement result. This may include processing the measurement result, which may include one or more of the following:

[0578] Obtaining final measurement results according to certain rules based on the initial measurement results, wherein the measurement results may include one or more of the aforementioned AI input data types; the type and quantity of the initial measurement results may be the same as or different from the type and quantity of the final measurement results; the certain rules may include one or more of the following:

[0579] A measurement result that satisfies a certain threshold value is selected from the initial measurement results as the final measurement result; the measurement result that satisfies the certain threshold value includes at least one of the following:

[0580] The initial measurement result contains a power value that is higher than (or not lower than) a power threshold value;

[0581] The time value included in the initial measurement result is earlier than (or no later than) or less than (or no greater than) a time threshold. Specifically, the time threshold can be a threshold value of a time unit index, or a set or list of time unit indices used for the final measurement result. For example, the measurement results of the first X (where X is a positive integer) path time unit indices are counted as the final measurement result.

[0582] The initial measurement result contains a phase value that is less than (or not greater than) a phase threshold value;

[0583] A final measurement result is calculated from the initial measurement result according to a certain calculation method; for example, the initial measurement result is CIR, PDP, or DP, and the final measurement result is calculated using an existing calculation formula as a channel information characteristic value (or a set or list of channel information characteristic values);

[0584] Optionally, the TRP reports or feeds back the measurement results. For example, the TRP reports the feedback content related to the obtained measurement results (which may be the initial measurement results or the final measurement results) to the LMF. Specifically, the TRP reports or feeds back the measurement results.

[0585] ■TRP determines the feedback content, which includes the initial measurement results and / or the final measurement results;

[0586] ■TRP determines the feedback method, for example, TRP notifies LMF and other core network entities via NRPPa or other dedicated signaling;

[0587] Optionally, the UE obtains a measurement result, for example, by measuring a relevant downlink signal. The measurement result is used in positioning based on an AI method, such as determining an AI model, generating input data, and training. Specifically, operations related to the UE obtaining the measurement result include one or more of the following:

[0588] The UE obtains a reference signal resource configuration for measurement, which is provided by a network node. The reference signal resource configuration includes: the number and position of reference signals within a certain time unit (e.g., the symbol index of the reference signal in a time slot), the frequency domain unit position of the reference signal (e.g., the frequency domain unit interval value from a frequency domain reference point to determine the frequency domain starting position of the reference signal), the number of time units and / or frequency domain units occupied by a reference signal (e.g., the number of symbols and PRBs of a reference signal); the number of repetitions of a reference signal within a certain time unit, etc.

[0589] The UE obtains a configuration for measurement. Based on the measurement configuration, the UE may determine a time window in which measurements may be performed, such as a measurement gap (MG) configuration and / or a positioning reference signal processing window (PPW) configuration for the AI method; or a measurement period obtained based on a reference signal period and an MG (or PPW) configuration period. For example, the time window may be an MG, a PPW, or the measurement period.

[0590] ■ Preferably, the UE obtains the priority of the reference signal in the time window, for example, the UE receives the priority indication or performs a priority determination, and obtains, based on the priority indication or priority determination, that when the reference signal collides with other signals (such as downlink signal reception and / or uplink signal transmission) (for example, time domain units of the two overlap or the time domain unit interval is less than or not greater than a certain threshold), the UE prioritizes measuring the measurement signal (for example, the measurement signal has a higher priority than or not lower than the other signal) or the UE prioritizes receiving or sending the other signal (for example, the measurement signal has a lower priority than or not higher than the other signal). When the two signals have the same priority, the UE autonomously determines to measure the measurement signal and / or receive or send the other signal;

[0591] The UE obtains the resource configuration for reporting the measurement results. Based on the resource configuration, the UE can determine the resource configuration that can be used to report the measurement result related information. For example, the resource configuration of the PUSCH includes the number and position (symbol index) of the PUSCH symbols in a time unit.

[0592] ○ Based on the obtained reference signal resource configuration for measurement and / or the configuration used for measurement and / or the resource configuration used for measurement result reporting, the UE performs reference signal measurement

[0593] The UE determines a measurement result, for example, by measuring a reference signal to obtain the measurement result, which also includes processing the measurement result, specifically including one or more of the following:

[0594] Obtaining final measurement results according to certain rules based on the initial measurement results, wherein the measurement results may include one or more of the aforementioned AI input data types; the type and quantity of the initial measurement results may be the same as or different from the type and quantity of the final measurement results; the certain rules may include one or more of the following:

[0595] A measurement result that satisfies a certain threshold value is selected from the initial measurement results as the final measurement result; the measurement result that satisfies the certain threshold value includes at least one of the following:

[0596] The initial measurement result contains a power value that is higher than (or not lower than) a power threshold value;

[0597] The time value included in the initial measurement result is earlier than (or no later than) or less than (or no greater than) a time threshold. Specifically, the time threshold can be a threshold value of a time unit index, or a set or list of time unit indices used for the final measurement result. For example, the measurement results of the first X (X is a positive integer) path time unit indices are counted as the final measurement result.

[0598] The initial measurement result contains a phase value that is less than (or not greater than) a phase threshold value;

[0599] A final measurement result is calculated from the initial measurement result according to a certain calculation method; for example, the initial measurement result is CIR, PDP, or DP, and the final measurement result is calculated using an existing calculation formula as a channel information characteristic value (or a set or list of channel information characteristic values);

[0600] ○ Optionally, the UE reports or feeds back the measurement result, for example, the UE reports the feedback content related to the obtained measurement result (which may be the above-mentioned initial measurement result or the final measurement result) to the network node (e.g., TRP and / or LMF); specifically including:

[0601] ■ The UE determines feedback content, where the feedback content includes an initial measurement result and / or a final measurement result;

[0602] The UE determines the feedback method, for example, via the uplink control channel (PUCCH) (e.g., in the form of UCI), MAC CE, or RRC high-level signaling. If reporting to a core network entity such as the LMF, it is via LPPa signaling or other dedicated signaling.

[0603] The LMF obtains AI model input data. For example, the LMF obtains the input data of the AI model to be used based on the above measurement results, which specifically includes at least one of the following:

[0604] ○LMF determines the measurement results as input data for the AI model;

[0605] ○ When the measurement result is the final measurement result, LMF determines the measurement result as the AI model input data;

[0606] ○ When the measurement result is an initial measurement result, LMF processes the measurement result in the same way as described above to obtain the final measurement result from the initial measurement result according to certain rules to obtain the model input data;

[0607] ○LMF obtains the input data used based on the measurement results and the required input data type and size of the AI model used;

[0608] The LMF obtains characteristic data of the input data, which includes statistical characteristic data of the input data (such as mean, variance, X-order norm, etc.) and / or input data selected from the input data according to certain rules. Preferably, the TRP stores or feeds back the characteristic data to the LMF;

[0609] The certain rule may be at least one of the following:

[0610] The input data contains a power value that is higher than (or not lower than) a power threshold value;

[0611] The time value included in the input data is earlier than (or no later than) or less than (or no greater than) a time threshold value; in particular, the time threshold value can be a threshold value of a time unit index, or a set or list of time unit indexes used to obtain the selected input data; for example, the input data of the first X (X is a positive integer) path time unit indexes are counted as the selected input data;

[0612] The input data contains a phase value that is less than (or not greater than) a phase threshold value;

[0613] LMF obtains AI model output data, for example, LMF obtains AI model output data based on the determined AI model and the obtained input data; wherein

[0614] The type and / or quantity of the AI model output data is confirmed according to the output data type and / or quantity reported by the AI model to be used;

[0615] Optionally, the LMF obtains information related to the output data, specifically including one or more of the following:

[0616] ■The information related to the obtained output data may include at least one of the following:

[0617] Directly the output data of the AI model;

[0618] Data obtained by processing the output data of the AI model, the processing method may be a calculated data value obtained by calculating according to an existing technical formula;

[0619] A timestamp of the AI model output data obtained. Optionally, the timestamp of the output data may be a separate timestamp or obtained based on the timestamp of the input data used by the AI model, for example, the timestamp of the output data is the same as the timestamp of the input data used by the AI model, or the timestamp of the output data is equal to the timestamp of the input data used by the AI model plus a time unit interval value. Optionally, the time unit interval value may be a preset value or obtained based on the time unit value required to execute the AI model from the input data to obtain the output data.

[0620] A quality indication of the obtained AI model output data, wherein the quality indication may be:

[0621] √Hard indication, such as a 1-bit indication, where "0" indicates that the output data quality is poor or does not meet the requirements; "1" indicates that the output data quality is good or meets the requirements; and / or

[0622] √Soft indicators, such as using a certain interval between 0 and 1 (such as 0.1) to indicate the quality level of the output data and the probability of good quality. For example, 0 represents the worst output data and 1 represents the best output data. Starting from 0 and increasing the step size by 0.1, the data quality gradually increases from the worst to the best.

[0623] The TRP and / or LMF monitor the currently used AI model. For example, the TRP and / or LMF needs to use a certain method to detect whether the AI model is working properly and meets the current service requirements. Specifically, the certain method includes one or more of the following:

[0624] When the LMF performs monitoring, for example, the LMF determines the monitoring results; specific operations include one or more of the following:

[0625] ■The UE obtains the reference signal resource configuration required for monitoring. The reference signal resource configuration is provided by the network node (TRP and / or LMF). The reference signal resource configuration includes: the number and position of reference signals within a certain time unit (such as the symbol index of the reference signal in a time slot), the frequency domain unit position of the reference signal (such as the frequency domain unit interval value from a frequency domain reference point to determine the frequency domain starting point of the reference signal), the number of time units and / or frequency domain units occupied by a reference signal (such as the number of symbols and PRBs of a reference signal); the number of repetitions of a reference signal within a certain time unit, etc.

[0626] ■ Optionally, the UE obtains a configuration for sending a reference signal required for monitoring. Based on the configuration sent, the UE can determine a time window in which it can send, such as an SRS sending window for monitoring;

[0627] Preferably, the UE obtains the priority of the reference signal in the time window, for example, the UE receives the priority indication or performs a priority judgment, and obtains, according to the priority indication or priority judgment, that when the reference signal collides with other signals (such as downlink signal reception and / or uplink signal transmission) (for example, the time domain units of the two overlap or the time domain unit interval is less than or not greater than a certain threshold value), the UE gives priority to sending the reference signal (for example, the reference signal priority is higher than or not lower than other signals) or the UE gives priority to receiving or sending other signals (for example, the reference signal priority is lower than or not higher than other signals). When the two have the same priority, the UE autonomously determines to send the reference signal and / or receive or send other signals;

[0628] ■ Based on the obtained reference signal resource configuration required for monitoring and / or the configuration for sending the reference signal required for monitoring, the UE transmits the reference signal. The TRP receives the reference signal sent by the UE based on measurements and obtains a measurement result. The TRP then reports the obtained measurement result to the LMF. This measurement result may be similar to the aforementioned initial measurement result or final measurement result. The details are not repeated here.

[0629] ■Based on the measurement results, LMF obtains monitoring indicators according to certain operations; specifically including:

[0630] LMF determines the measurement results as monitoring indicators;

[0631] When the measurement result is the final measurement result, LMF determines the measurement result as a monitoring indicator;

[0632] When the measurement result is an initial measurement result, LMF processes the measurement result in the same way as described above for obtaining the final measurement result from the initial measurement result according to certain rules to obtain the monitoring index;

[0633] LMF obtains characteristic data of the measurement results, which include statistical characteristic data of the measurement results (such as mean, variance, X-order norm, etc.) and / or measurement results selected from the measurement results according to certain rules as characteristic data. LMF uses this characteristic data as the monitoring indicator. The certain rule can be at least one of the following:

[0634] The power value included in the measurement result is higher than (or not lower than) a power threshold value;

[0635] The time value included in the measurement result is earlier than (or no later than) or less than (or no greater than) a time threshold. Specifically, the time threshold can be a threshold value of a time unit index, or a set or list of time unit indices used to obtain characteristic data. For example, the measurement results of the first X (X is a positive integer) path time unit indices are counted as characteristic data.

[0636] The phase value contained in the measurement result is less than (or not greater than) a phase threshold value;

[0637] ■Based on the obtained monitoring indicators, the LMF obtains the monitoring results (including pass or fail) according to certain operations. Specifically, the operations include: when the obtained monitoring indicators are better than a certain threshold (or the situation occurs once, or the situation occurs more than (or not less than) N times (or equal to N+1 times), or the situation occurs more than (or not less than) N times (or equal to N+1 times) continuously), the LMF determines that the monitoring result is passed; otherwise, for example, when the obtained monitoring indicators are worse than a certain threshold (or the situation occurs once, or the situation occurs more than (or not less than) N times (or equal to N+1 times), or the situation occurs more than (or not less than) N times (or equal to N+1 times) continuously), the LMF determines that the monitoring result is not passed;

[0638] ■Based on the obtained monitoring indicators and / or monitoring results, the LMF determines a subsequent operation and, optionally, instructs the UE or TRP to perform the subsequent operation; the UE or TRP receives the instruction of the subsequent operation from the LMF and performs the subsequent operation according to the instruction; wherein,

[0639] When the obtained monitoring indicator is better than a certain threshold, (or the situation occurs once, or the situation occurs more than (or not less than) N times (or equal to N+1 times), or the situation occurs more than (or not less than) N times (or equal to N+1 times) continuously), the subsequent operation is to continue to use the currently determined AI model and / or AI method for positioning; otherwise, for example, when the obtained monitoring indicator is worse than a certain threshold, (or the situation occurs once, or the situation occurs more than (or not less than) N times (or equal to N+1 times), or the situation occurs more than (or not less than) N times (or equal to N+1 times) continuously), the subsequent operation is to stop using the AI method for positioning and / or fall back to a non-AI method (RAT-dependent positioning method and other RAT-independent positioning methods) and / or trigger an update of the current AI model (update or optimization finetuning or retraining) and / or enter the aforementioned operation of executing LMF to determine the currently used AI model; or

[0640] When the monitoring result is passed (or the situation occurs once, or the situation occurs more than (or not less than) N times (or equal to N+1 times), or the situation occurs more than (or not less than) N times (or equal to N+1 times) continuously), the subsequent operation is to continue to use the currently determined AI model and / or AI method for positioning; otherwise, for example, when the monitoring result is failed (or the situation occurs once, or the situation occurs more than (or not less than) N times (or equal to N+1 times), or the situation occurs more than (or not less than) N times (or equal to N+1 times) continuously), the subsequent operation is to stop using the AI method for positioning and / or fall back to a non-AI method (for example, a RAT-dependent positioning method and another RAT-independent positioning method) and / or trigger an update of the current AI model (update or finetuning or retraining) and / or enter the aforementioned operation of executing LMF to determine the currently used AI model;

[0641] o When the TRP performs monitoring, for example, the TRP determines the monitoring results; exemplary operations include one or more of the following:

[0642] ■The UE obtains the reference signal resource configuration required for monitoring. The reference signal resource configuration is provided by the network node (TRP and / or LMF). The reference signal resource configuration includes: the number and position of reference signals within a certain time unit (such as the symbol index of the reference signal in a time slot), the frequency domain unit position of the reference signal (such as the frequency domain unit interval value from a frequency domain reference point to determine the frequency domain starting point of the reference signal), the number of time units and / or frequency domain units occupied by a reference signal (such as the number of symbols and PRBs of a reference signal); the number of repetitions of a reference signal within a certain time unit, etc.

[0643] ■ Optionally, the UE obtains a configuration for sending a reference signal required for monitoring. Based on the configuration sent, the UE can determine a time window in which it can send, such as an SRS sending window for monitoring;

[0644] Preferably, the UE obtains the priority of the reference signal in the time window, for example, the UE receives the priority indication or performs a priority judgment, and obtains, according to the priority indication or priority judgment, that when the reference signal collides with other signals (such as downlink signal reception and / or uplink signal transmission) (for example, the time domain units of the two overlap or the time domain unit interval is less than or not greater than a certain threshold value), the UE gives priority to sending the reference signal (for example, the reference signal priority is higher than or not lower than other signals) or the UE gives priority to receiving or sending other signals (for example, the reference signal priority is lower than or not higher than other signals). When the two have the same priority, the UE autonomously determines to send the reference signal and / or receive or send other signals;

[0645] ■ Based on the obtained reference signal resource configuration required for monitoring and / or the configuration for sending the reference signal required for monitoring, the UE transmits the reference signal, and the TRP obtains a measurement result based on the measurement. The TRP feeds back the obtained measurement result to the LMF; the measurement result may be similar to the aforementioned initial measurement result or final measurement result; the details are not repeated here;

[0646] ■ Based on the measurement results obtained, TRP obtains monitoring indicators according to certain operations; specifically, they include:

[0647] TRP determines the measurement results as monitoring indicators;

[0648] When the measurement result is final, the TRP determines the measurement result as a monitoring indicator;

[0649] When the measurement result is an initial measurement result, the TRP processes the measurement result in the same way as described above for obtaining the final measurement result from the initial measurement result according to certain rules to obtain the monitoring indicator;

[0650] The TRP obtains characteristic data of the measurement results, which include statistical characteristic data of the measurement results (such as mean, variance, X-order norm, etc.) and / or measurement results selected from the measurement results according to certain rules as characteristic data. The TRP uses this characteristic data as the monitoring indicator. The certain rules can be at least one of the following:

[0651] The power value included in the measurement result is higher than (or not lower than) a power threshold value;

[0652] The time value included in the measurement result is earlier than (or no later than) or less than (or no greater than) a time threshold. Specifically, the time threshold can be a threshold value of a time unit index, or a set or list of time unit indices used to obtain characteristic data. For example, the measurement results of the first X (X is a positive integer) path time unit indices are counted as characteristic data.

[0653] The phase value contained in the measurement result is less than (or not greater than) a phase threshold value;

[0654] Based on the obtained monitoring indicators, the TRP performs certain operations to obtain a monitoring result (including a pass or fail). Exemplary operations include: when the obtained monitoring indicator is better than a certain threshold (or when the condition occurs once, or when the condition occurs more than (or not less than) N times (or equal to N+1 times), or when the condition occurs more than (or not less than) N times (or equal to N+1 times) consecutively), the TRP determines the monitoring result as a pass; otherwise, for example, when the obtained monitoring indicator is worse than a certain threshold (or when the condition occurs once, or when the condition occurs more than (or not less than) N times (or equal to N+1 times), or when the condition occurs more than (or not less than) N times (or equal to N+1 times) consecutively), the TRP determines the monitoring result as a fail;

[0655] ■TRP reports the above monitoring indicators and / or the above monitoring results; LMF determines the subsequent operation based on the obtained monitoring indicators and / or monitoring results, and instructs TRP to perform the subsequent operation; TRP receives the instruction of the subsequent operation from LMF and performs the subsequent operation according to the instruction; wherein,

[0656] When the obtained monitoring indicator is better than a certain threshold (or the situation occurs once, or the situation occurs more than (or not less than) N times (or equal to N+1 times), or the situation occurs more than (or not less than) N times (or equal to N+1 times) continuously), the subsequent operation is to continue to use the currently determined AI model and / or AI method for positioning; otherwise, for example, when the obtained monitoring indicator is worse than a certain threshold (or the situation occurs once, or the situation occurs more than (or not less than) N times (or equal to N+1 times), or the situation occurs more than (or not less than) N times (or equal to N+1 times) continuously), the subsequent operation is to stop using the AI method for positioning and / or fall back to a non-AI method (for example, a RAT-dependent positioning method and another RAT-independent positioning method) and / or trigger an update of the current AI model (update or optimization finetuning or retraining) and / or enter the aforementioned operation of executing LMF to determine the currently used AI model; or

[0657] When the monitoring result is passed (or the situation occurs once, or the situation occurs more than (or not less than) N times (or equal to N+1 times), or the situation occurs more than (or not less than) N times (or equal to N+1 times) continuously), the subsequent operation is to continue to use the currently determined AI model and / or AI method for positioning; otherwise, for example, when the monitoring result is failed (or the situation occurs once, or the situation occurs more than (or not less than) N times (or equal to N+1 times), or the situation occurs more than (or not less than) N times (or equal to N+1 times) continuously), the subsequent operation is to stop using the AI method for positioning and / or fall back to a non-AI method (for example, a RAT-dependent positioning method and another RAT-independent positioning method) and / or trigger an update of the current AI model (update or finetuning or retraining) and / or enter the aforementioned operation of executing LMF to determine the currently used AI model;

[0658] ■ Based on the monitoring indicators and / or monitoring results obtained, TRP determines the subsequent actions and provides feedback to LMF on the subsequent actions determined;

[0659] When the obtained monitoring indicator is better than a certain threshold, (the situation occurs once, or the situation occurs more than (or not less than) N times (or equal to N+1 times), or the situation occurs more than (or not less than) N times (or equal to N+1 times) continuously), the subsequent operation is to continue to use the currently determined AI model and / or AI method for positioning; otherwise, for example, when the obtained monitoring indicator is worse than a certain threshold, (the situation occurs once, or the situation occurs more than (or not less than) N times (or equal to N+1 times), or the situation occurs more than (or not less than) N times (or equal to N+1 times) continuously), the subsequent operation is to stop using the AI method for positioning and / or fall back to a non-AI method (RAT-dependent positioning method and other RAT-independent positioning methods) and / or trigger an update of the current AI model (update or optimization finetuning or retraining) and / or enter the aforementioned operation of executing LMF to determine the currently used AI model; or

[0660] When the monitoring result is passed (this situation occurs once, or this situation occurs more than (or not less than) N times (or equal to N+1 times), or this situation occurs more than (or not less than) N times (or equal to N+1 times) continuously), the subsequent operation is to continue to use the currently determined AI model and / or AI method for positioning; otherwise, for example, when the monitoring result is not passed (this situation occurs once, or this situation occurs more than (or not less than) N times (or equal to N+1 times), or this situation occurs more than (or not less than) N times (or equal to N+1 times) continuously), the subsequent operation is to stop using the AI method for positioning and / or fall back to a non-AI method (RAT-dependent positioning method and other RAT-independent positioning methods) and / or trigger an update of the current AI model (update or optimization finetuning or retraining) and / or enter the aforementioned operation of executing LMF to determine the currently used AI model.

[0661] Figure 4 FIG2 shows a schematic diagram of the structure of a network node device (eg, TRP or LMF, etc.) 400 according to at least one embodiment of the present disclosure. Figure 4, the network node device 400 includes a transceiver 401 and a controller 402. The transceiver 401 is configured to send data or signals and receive data or signals. The controller 402 is coupled to the transceiver 401 and is configured to perform control so that the network node device 400 performs the method according to the embodiment of the present disclosure. In one implementation, the network node device 400 may further include a memory (not shown), on which computer-executable instructions are stored. When the instructions are executed by the controller 402, the network node device 400 can perform at least one method corresponding to the above-mentioned embodiments of the present disclosure.

[0662] The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present invention should be included in the scope of protection of the present invention.

[0663] Those skilled in the art will appreciate that the present invention includes devices for performing one or more of the operations described herein. These devices may be specially designed and manufactured for the desired purpose, or they may include known devices found in general-purpose computers. These devices have computer programs stored therein, which are selectively activated or reconfigured. Such computer programs may be stored on a device (e.g., a computer) readable medium or on any type of medium suitable for storing electronic instructions and coupled to a bus, including but not limited to any type of disk (including floppy disks, hard disks, optical disks, CD-ROMs, and magneto-optical disks), ROM (Read-Only Memory), RAM (Random Access Memory), EPROM (Erasable Programmable Read-Only Memory), EEPROM (Electrically Erasable Programmable Read-Only Memory), flash memory, magnetic cards, or optical cards. In other words, a readable medium includes any medium that can be used by a device (e.g., a computer) to store or transmit information in a form that can be read.

[0664] Those skilled in the art will appreciate that each block in these structural diagrams and / or block diagrams and / or flow charts, as well as combinations of blocks in these structural diagrams and / or block diagrams and / or flow charts, can be implemented using computer program instructions. Those skilled in the art will appreciate that these computer program instructions can be provided to a general-purpose computer, a specialized computer, or a processor of other programmable data processing methods for implementation, thereby executing the schemes specified in the blocks or multiple blocks of the structural diagrams and / or block diagrams and / or flow charts disclosed in the present invention through the processor of the computer or other programmable data processing method.

[0665] Those skilled in the art will appreciate that the steps, measures, and schemes in the various operations, methods, and processes discussed in the present invention may be interchanged, modified, combined, or deleted. Furthermore, other steps, measures, and schemes in the various operations, methods, and processes discussed in the present invention may also be interchanged, modified, rearranged, decomposed, combined, or deleted. Furthermore, steps, measures, and schemes in the prior art that are similar to those disclosed in the present invention may also be interchanged, modified, rearranged, decomposed, combined, or deleted.

[0666] The above descriptions are only partial embodiments of the present invention. It should be pointed out that ordinary technicians in this technical field can make several improvements and modifications without departing from the principles of the present invention. These improvements and modifications should also be regarded as within the scope of protection of the present invention.

Claims

1. A method performed by a first network node in a communication system, comprising: Obtaining a first AI model, where the first AI model is determined from at least one AI model according to an applicable condition corresponding to the AI model; Obtaining input data for a first AI model; Based on the input data, using the first AI model, obtaining output data related to positioning, The first AI model is an AI model randomly determined from a plurality of AI models that meet the applicable conditions, or is determined from the plurality of AI models based on the fourth condition.

2. The method according to claim 1, wherein Obtaining the first AI model includes: The first network node determines a first AI model from the at least one AI model based on an applicable condition corresponding to the AI model, or The first AI model is determined based on indication information received from the second network node, where the indication information is used to indicate an index of the first AI model determined by the second network node or a feature associated with the first AI model determined by the second network node.

3. The method according to claim 2, further comprising: If the first AI model is determined by the first network node, the first network node sends information related to the determined first AI model to the UE or the second network node.

4. The method according to any one of claims 1 to 3, wherein The fourth condition includes at least one of the following: Minimal storage required; Requires minimal computational complexity; Requires minimum input data type and / or quantity; The output data has the highest accuracy; The most associated features; The maximum number of applicable conditions is met; This is a different AI model from the one selected last time.

5. The method according to claim 1, wherein The at least one AI model includes an AI model supported by two or all of the first network node, the UE, and the second network node.

6. The method according to claim 1, wherein The applicable conditions include at least one of the following: The cell index corresponding to the AI model; the conditions associated with the measurement results; Storage-related conditions; Complexity-related conditions; Conditions related to output data accuracy; Handle time-related conditions.

7. The method according to claim 6, wherein: The conditions related to the measurement results include: The first measurement value of the measurement result is not lower than the first threshold, The first measurement value of the measurement result is within the first measurement threshold interval, The number of paths whose power is not lower than the first power threshold in the measurement result is greater than the first number threshold, The number of paths not lower than the first power threshold is greater than the number of measurement results of the first quantity threshold is greater than the second quantity threshold, The probability that the number of paths not lower than the first power threshold in the measurement result is greater than the first number threshold is greater than the first probability threshold.

8. The method according to claim 1, further comprising: Sending at least one of the following to the UE: configuration information related to reference signal resources and configuration information related to reference signal transmission windows; Obtaining a first measurement result by measuring a first reference signal sent by the UE; The first measurement result is used to determine the first AI model and / or to obtain input data of the first AI model.

9. The method according to claim 8, wherein The first measurement result is a measurement result obtained based on measurement, or is obtained by processing the measurement result obtained based on measurement, wherein the processing includes at least one of the following: selecting a first measurement result from measurement results obtained based on the measurement based on a first condition; transforming a measurement result obtained based on the measurement to obtain a first measurement result, The first condition includes at least one of the following: the power corresponding to the measurement result is not lower than the second power threshold, the time corresponding to the measurement result is earlier than the first time threshold, and the phase corresponding to the measurement result is less than or equal to the first phase threshold.

10. The method according to claim 9, wherein: The input data includes at least one of the following: First measurement result; Data obtained based on the first measurement result and input format information of the first AI model.

11. The method according to claim 1 , further comprising: sending information related to the output data to the second network node, The information related to the output data includes at least one of the following: The output data, data obtained by processing the output data, information related to the timestamp of the output data, and quality indication information of the output data.

12. The method according to claim 1, further comprising: measuring a second reference signal sent by the UE to obtain a second measurement result; Obtaining a monitoring result of the first AI model based on the second measurement result; The operation to be performed is determined based on the monitoring result, or the monitoring result is sent to the second network node, and / or information indicating the operation to be performed is received from the second network node.

13. The method according to claim 12, wherein: The monitoring result is obtained based on the monitoring indicator, and the monitoring indicator is obtained based on the second measurement result, The monitoring indicator includes at least one of the following: the second measurement result, a third measurement result obtained by processing the second measurement result, and characteristic data obtained based on the second measurement result. The processing includes: selecting a third measurement result from the second measurement result based on the second condition, or transforming the second measurement result to obtain the third measurement result, The characteristic data includes statistical characteristic data of the second measurement result, or a fourth measurement result selected from the second measurement result according to the second condition, The second condition includes at least one of the following: the power corresponding to the measurement result is not lower than the third power threshold, the time corresponding to the measurement result is earlier than the second time threshold, and the phase corresponding to the measurement result is less than the second phase threshold.

14. The method according to claim 13, wherein If the monitoring indicator is greater than the threshold value for N consecutive times, the monitoring result is determined to be passed, where N is a positive integer; otherwise, the monitoring result is determined to be failed.

15. The method according to any one of claims 12 to 14, wherein If the third condition is met, the operation includes at least one of the following: Stop using AI-based targeting methods, Falling back to non-AI based methods for positioning, Re-determine the AI model to be used, performing an update, optimization, or retraining of the first AI model, Select a second AI model different from the first AI model and notify the second network node, receiving a second AI model indicated by a second network node, receiving an instruction from a second network node to fall back to a non-AI based method for positioning and performing the fallback based on the instruction, Report errors in AI model-based methods; Among them, the third condition includes at least one of the following: the first AI model is the same as the AI model determined to be used last time, and the monitoring result is failed for M consecutive times, where M is an integer greater than or equal to 1.

16. The method according to claim 1, further comprising: Sending first information related to the AI model supported by the first network node to the second network node or the UE, The first information includes at least one of the following: Index information of the AI model supported by the first network node; Feature information associated with the AI model supported by the first network node; A correspondence between an index of an AI model supported by the first network node and the associated features; Information related to the input format of the AI model supported by the first network node; Information related to the output format of the AI model supported by the first network node.

17. The method according to claim 1, further comprising: At least one candidate AI model determined by the first network node based on the applicable condition of the AI model is sent to the second network node.

18. The method of claim 1, further comprising: receiving a first measurement result from a second network node or a UE, The first measurement result is obtained by the second network node by measuring the third reference signal sent by the UE, or is obtained by the UE by measuring the fourth reference signal sent by the second network node. The first measurement result is used to determine the first AI model and / or to obtain input data of the first AI model.

19. A method performed by a second network node in a communication system, comprising: Determine a first AI model that meets corresponding applicability conditions from at least one AI model; Sending instruction information of the first AI model to the first network node, The first AI model is an AI model randomly determined from a plurality of AI models that meet the applicable conditions, or is determined from the plurality of AI models based on the fourth condition.

20. A network node in a communication system, comprising: a transceiver configured to transmit and / or receive signals, A controller is configured to control the network node to execute the method according to any one of claims 1-19.

Images