CN117440312A

CN117440312A - Method performed by a first node and related device

Info

Publication number: CN117440312A
Application number: CN202210834168.7A
Authority: CN
Inventors: 熊琦; 赵龙海; 孙霏菲
Original assignee: Samsung Electronics Co Ltd
Current assignee: Samsung Electronics Co Ltd
Priority date: 2022-07-14
Filing date: 2022-07-14
Publication date: 2024-01-23

Abstract

The embodiment of the application provides a method executed by a first node and related equipment, and relates to the technical field of artificial intelligence. Wherein the method performed by the first node comprises: determining configuration information related to the machine learning model; based on the configuration information, positioning-related operations are performed using a machine learning model. The implementation of the method can realize accurate positioning in the actual channel condition. Meanwhile, the above-described method performed by the electronic device may be performed using an artificial intelligence model.

Description

Method performed by a first node and related device

Technical Field

The present application relates to the field of artificial intelligence, and in particular, to a method performed by a first node and related devices.

Background

In order to meet the increasing 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, a 5G or quasi 5G communication system is also referred to as a "super 4G network" or a "LTE-after-system".

The 5G communication system is implemented in a higher frequency (millimeter wave) band, for example, a 60GHz band, to achieve a higher data rate. In order to reduce propagation loss of radio waves and increase transmission distance, beamforming, massive Multiple Input Multiple Output (MIMO), full-dimensional MIMO (FD-MIMO), array antennas, analog beamforming, massive antenna techniques are discussed in 5G communication systems.

Further, in the 5G communication system, development of system network improvement is being performed based on advanced small cells, cloud Radio Access Networks (RANs), ultra dense networks, device-to-device (D2D) communication, wireless backhaul, mobile networks, cooperative communication, cooperative multipoint (CoMP), receiving-end interference cancellation, and the like.

In 5G systems, hybrid FSK and QAM modulation (FQAM) and Sliding Window Superposition Coding (SWSC) as Advanced Code Modulation (ACM), and Filter Bank Multicarrier (FBMC), non-orthogonal multiple access (NOMA) and Sparse Code Multiple Access (SCMA) as advanced access technologies have been developed.

Disclosure of Invention

The embodiment of the application provides a method for executing electronic equipment and related equipment, which can solve at least one technical problem in related technologies. The technical scheme is as follows:

according to an aspect of an embodiment of the present application, there is provided a method performed by a first node, including:

determining configuration information related to the machine learning model;

based on the configuration information, positioning-related operations are performed using the machine learning model.

In an embodiment, further comprising obtaining a request related to positioning;

the location-related request includes at least one of:

A first node receives a request related to positioning, which is triggered by a second node;

the first node itself triggers a positioning related request.

In an embodiment, determining to perform a positioning-related operation using the machine learning model when at least one of the following trigger conditions is met:

the measured reference signal received power value of the first signal is not greater than a first threshold value;

the measured path loss of the first signal is not less than a second threshold value;

the machine learning model is in an active state;

wherein the first signal includes at least one of a positioning reference signal, a sounding reference signal, a reference signal of a synchronization signal block, and a reference signal of channel state information.

In an embodiment, the determining uses a machine learning model to perform positioning related operations, comprising:

determining to perform a positioning-related operation using a machine learning model when at least one of the trigger conditions occurs no less than N times; the N is not less than 1.

In one embodiment, the positioning-related operations are performed by activating a machine learning model by at least one of:

the first node instructs to activate the machine learning model through the first trigger message, sends configuration information related to the machine learning model, and/or activates the machine learning model;

The first node receives an instruction for activating the machine learning model through the second trigger message, receives configuration information related to the machine learning model, and/or activates the machine learning model;

the first node requests the second node to trigger the machine learning model and/or configuration information related to the machine learning model through a third trigger message, and activates the machine learning model based on feedback of the second node;

the first node activates a machine learning model.

In an embodiment, the first trigger message includes at least one of: LET positioning protocol message, radio resource control configuration message, medium access control element, downlink control information;

the second trigger message includes at least one of: LTE positioning protocol messages, radio resource control configuration messages, medium access control elements, downlink control information;

the third trigger message includes at least one of: physical uplink control channel, medium access control element, physical random access channel, LTE positioning protocol message.

In one embodiment, determining configuration information associated with a machine learning model includes:

receiving configuration information related to a machine learning model;

Performing positioning-related operations based on the machine learning model determined by the configuration information.

In an embodiment, the configuration information includes information about one or more models contained by the machine learning model;

wherein the relevant information for each model includes at least one of:

model type information;

model parameter information;

the data set related parameters comprise at least one of data types of input and/or output data of the model, the number of corresponding data types and dimension information of the data.

In an embodiment, the number of data types is determined by at least one of:

a channel impulse response value not less than a third threshold value;

the top N and/or highest power top N channel impulse response values over the time of arrival in all channel impulse responses.

In an embodiment, the model parameters are determined by at least one of:

obtaining initial model parameters based on the determined probability distribution;

obtaining model parameters based on the received model parameter configuration;

based on a training optimization algorithm, a loss function, iteration times and/or learning rate, model parameters are obtained.

In one embodiment, the training step of the machine learning model comprises:

Determining the first node as training equipment;

acquiring resource configuration information for training;

training the machine learning model based on the training device and the resource configuration information for training;

a trained machine learning model and/or configuration information related to the trained machine learning model is determined.

In an embodiment, the training the machine learning model based on the training device and the resource configuration information for training includes at least one of:

the training equipment acquires input information related to a machine learning model based on the resource configuration information for training;

the training equipment feeds back the input information;

the training equipment feeds back the input information and output information corresponding to the input information;

training a machine learning model based on the input information and/or the output information.

In an embodiment, the machine learning model includes a first model and a second model; training of the machine learning model includes:

obtaining noisy input information using a first portion of a first model based on the input information;

based on the noisy input information, obtaining denoised output information using a second portion of the first model;

Training the first part and the second part of the first model based on the input information and the denoised output information to obtain configuration information related to the first model.

In an embodiment, the machine learning model based performing positioning related operations includes:

testing the validity of a machine learning model;

if so, performing positioning-related operations based on the machine learning model;

and if not, re-executing the step of determining to use the machine learning model to execute the operation related to the positioning.

In an embodiment, the testing the validity of the machine learning model includes:

obtaining test data;

if the test output information obtained by the machine learning model based on the input information in the test data meets any one of the following preset test conditions, the machine learning model is determined to be effective:

the difference value between the test output information and the output information in the test data is not larger than a first test threshold value;

the model performance represented by the test output information is better than the model performance represented by the output information in the test data.

In an embodiment, the machine learning model includes a first model and a second model; the performing positioning-related operations using the machine learning model includes:

Acquiring input information related to a machine learning model used;

and processing the input information through the first model and/or the second model to obtain output information related to positioning.

In an embodiment, said processing of said input information by said first model and/or said second model to obtain positioning related output information comprises at least one of:

determining whether the input information needs denoising processing or not based on a first noise value corresponding to the input information; if yes, processing the input information through the first model to obtain first denoising information, and processing the first denoising information through the second model to obtain output information related to positioning; if not, processing the input information through the second model to obtain output information related to positioning;

determining whether the input information needs to be repaired or not based on a channel impact response value corresponding to the input information; if yes, processing the input information through the first model to obtain first repair information, and processing the first repair information through the second model to obtain output information related to positioning; and if not, processing the input information through the second model to obtain output information related to positioning.

In an embodiment, determining whether the input information needs to be denoised based on a first noise value corresponding to the input information includes:

and comparing the first noise value corresponding to the input information with a first noise threshold value to determine whether the input information needs denoising processing or not.

In an embodiment, determining whether the input information needs to be repaired based on the channel impulse response value corresponding to the input information includes:

comparing a Channel Impulse Response (CIR) value corresponding to input information with a first CIR threshold value to obtain an effective CIR value;

and comparing the number of the effective CIR values with a first CIR number threshold value to determine whether the input information needs to be repaired or not.

In an embodiment, the first noise value comprises at least one of: RSRP, SNR, CIR amplitude value, time of arrival value of CIR.

In an embodiment, at least one of the following is further included:

triggering updating the machine learning model and/or configuration information related to the machine learning model based on preset events, count information and/or timing information;

triggering a recovery of the machine learning model and/or configuration information related to the machine learning model based on preset events, count information and/or timing information;

Terminating use of the machine learning model and/or configuration information associated with the machine learning model based on preset events, count information, and/or timing information;

wherein the preset event includes at least one of: the output information of the machine learning model does not meet the required threshold value; the number and/or type of input information obtained for input to the machine learning model does not satisfy the required threshold value;

the timing information includes: determining a start time when the machine learning model is used, and a stop time when the preset event occurs;

the count information includes: initial values corresponding to nodes that use the machine learning model are determined, and accumulated values corresponding to nodes at which a preset event occurs.

In an embodiment, the first node comprises one of: the system comprises User Equipment (UE) for initiating a positioning request, a positioning management entity for UE positioning and positioning auxiliary data transmission, a base station gNB or transmitting and receiving point for broadcasting the positioning auxiliary data and performing uplink positioning measurement, and the UE for downlink positioning measurement;

the second node comprises one of the following: the system comprises User Equipment (UE) initiating a positioning request, a positioning management entity for UE positioning and positioning auxiliary data issuing, a base station gNB or transmitting and receiving point for broadcasting the positioning auxiliary data and performing uplink positioning measurement, and the UE for downlink positioning measurement.

According to another aspect of an embodiment of the present application, there is provided an apparatus performed by a first node, the apparatus comprising:

a determining module for determining configuration information related to the machine learning model;

and the execution module is used for executing the operation related to positioning by using the machine learning model based on the configuration information.

According to another aspect of the embodiments of the present application, there is provided an electronic device including:

a transceiver;

one or more processors;

a memory;

one or more computer programs, wherein the one or more computer programs are stored in the memory and configured to be executed by the one or more processors, the one or more computer programs configured to: the method performed by the first node described above is performed.

According to yet another aspect of embodiments of the present application, there is provided a computer readable storage medium for storing computer instructions that, when run on a computer, cause the computer to perform the method performed by the first node as described above.

According to an aspect of embodiments of the present application, there is provided a computer program product comprising a computer program or instructions which, when executed by a processor, implement the steps of the method performed by the first node as described above.

The beneficial effects that technical scheme that this application embodiment provided brought are:

the embodiment of the application provides a method executed by a first node, in particular to determine configuration information related to a machine learning model; based on the configuration information, positioning-related operations are performed using a machine learning model. The implementation of the method and the device uses the AL/ML technology to execute the operation related to the positioning, during which the configuration information related to the machine learning model can be determined according to the positioning requirement of wireless communication, so that the operation related to the positioning can be executed by using the corresponding machine learning model according to the configuration information, and besides the operation related to the positioning can be executed under the condition of poor channel conditions (such as inaccuracy of channel information and the like) in the condition of relatively poor (such as non-line-of-sight environment), the operation related to the positioning can be executed based on the positioning information, and the like.

Drawings

In order to more clearly illustrate the technical solutions in the embodiments of the present application, the drawings that are required to be used in the description of the embodiments of the present application will be briefly described below.

Fig. 1 illustrates an example wireless network in accordance with various embodiments of the present application;

FIG. 2a illustrates an example wireless transmit path according to this application

Fig. 2b shows an example wireless receive path according to the present application;

FIG. 3a illustrates an example user device according to this application;

fig. 3b shows an example base station according to the present application;

fig. 4 shows a block diagram of a user equipment for performing a reception measurement method for positioning signals according to an embodiment of the present application;

FIG. 5 illustrates a flow chart of a method performed by a first node provided herein;

FIG. 6 illustrates a process flow diagram provided herein using a machine learning model;

FIG. 7 is a schematic diagram of a model training process provided herein;

FIG. 8 illustrates an effect of the present application providing for scheduling noise in different ways;

fig. 9 is a schematic structural diagram of an apparatus executed by a first node provided in the present application;

fig. 10 shows a schematic structural diagram of an electronic device provided in the present application.

Detailed Description

The following description with reference to the accompanying drawings is provided to facilitate a thorough understanding of the various embodiments of the present application as defined by the claims and their equivalents. The description includes various specific details to facilitate understanding but should be considered exemplary only. Accordingly, one of ordinary skill in the art will recognize that various changes and modifications of the various embodiments described herein can be made without departing from the scope and spirit of the present application. In addition, descriptions of well-known functions and constructions may be omitted for clarity and conciseness.

The terms and phrases used in the following specification and claims are not limited to their dictionary meanings, but are used only by the inventors to enable a clear and consistent understanding of the application. It should be apparent, therefore, to one skilled in the art that the following descriptions of the various embodiments of the present application are provided for illustration only and not for the purpose of limiting the application as defined by the appended claims and their equivalents.

It should 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 such surfaces.

The terms "comprises" or "comprising" may refer to the presence of a corresponding disclosed function, operation or component that may be used in various embodiments of the present application, rather than to the presence of one or more additional functions, operations or features. Furthermore, the terms "comprises" or "comprising" may be interpreted as referring to certain features, numbers, steps, operations, constituent elements, components, or combinations thereof, but should not be interpreted as excluding the existence of one or more other features, numbers, steps, operations, constituent elements, components, or combinations thereof.

The term "or" as used in the various embodiments of the present application 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.

Unless defined differently, all terms (including technical or scientific terms) used herein have the same meaning as understood by one of ordinary skill in the art described herein. The usual terms as defined in the dictionary are to be construed to have meanings consistent with the context in the relevant art and should not be interpreted in an idealized or overly formal manner unless expressly so defined herein.

The technical solution of the embodiment of the application can be applied to various communication systems, for example: global system for mobile communications (global system for mobile communications, GSM), code division multiple access (code division multiple access, CDMA) system, wideband code division multiple access (wideband code division multiple access, WCDMA) system, general packet radio service (general packet radio service, GPRS), long term evolution (long term evolution, LTE) system, LTE frequency division duplex (frequency division duplex, FDD) system, LTE time division duplex (time division duplex, TDD), universal mobile telecommunications system (universal mobile telecommunication system, UMTS), worldwide interoperability for microwave access (worldwide interoperability for microwave access, wiMAX) communication system, fifth generation (5th generation,5G) system, or New Radio (NR), and the like. In addition, the technical scheme of the embodiment of the application can be applied to future-oriented communication technologies.

Fig. 1 illustrates an example wireless network 100 in accordance with various embodiments of the present application. The embodiment of the wireless network 100 shown in fig. 1 is for illustration only. Other embodiments of the wireless network 100 can be used without departing from the scope of this application.

The wireless network 100 includes a gndeb (gNB) 101, a gNB 102, and a gNB 103.gNB 101 communicates with gNB 102 and gNB 103. The gNB 101 is also in communication with at least one Internet Protocol (IP) network 130, such as the Internet, a private IP network, or other data network.

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

The gNB 102 provides wireless broadband access to the network 130 for a first plurality of User Equipment (UEs) within the coverage area 120 of the gNB 102. The first plurality of UEs includes: UE 111, which may be located in a Small Business (SB); UE 112, which may be located in enterprise (E); UE 113, may be located in a WiFi Hotspot (HS); UE 114, which may be located in a first home (R); UE 115, which may be located in a second home (R); UE 116 may be a mobile device (M) such as a cellular telephone, wireless laptop, wireless PDA, etc. The gNB 103 provides wireless broadband access to the network 130 for a second plurality of UEs within the coverage area 125 of the gNB 103. The second plurality of UEs includes UE 115 and UE 116. In some embodiments, one or more of the gNBs 101-103 are 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 technology.

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

As described in more detail below, one or more of gNB 101, gNB 102, and gNB 103 includes a 2D antenna array as described in embodiments of the present application. In some embodiments, one or more of gNB 101, gNB 102, and gNB 103 support codebook designs and structures for systems with 2D antenna arrays.

Although fig. 1 shows one example of a wireless network 100, various changes can be made to fig. 1. For example, the wireless network 100 can include any number of gnbs and any number of UEs in any suitable arrangement. Also, the gNB 101 is capable of communicating directly with any number of UEs and providing those UEs with wireless broadband access to the network 130. Similarly, each gNB 102-103 is capable of communicating directly with the network 130 and providing direct wireless broadband access to the network 130 to the UE. Furthermore, the gnbs 101, 102, and/or 103 can provide access to other or additional external networks (such as external telephone networks or other types of data networks).

Fig. 2a and 2b illustrate example wireless transmit and receive paths according to the present application. In the following description, transmit path 200 can be described as implemented in a gNB (such as gNB 102), while receive path 250 can be described as implemented in a UE (such as UE 116). However, it should be understood that the receive path 250 can be implemented in the gNB and the transmit path 200 can be implemented in the UE. In some embodiments, receive path 250 is configured to support codebook designs and structures for systems with 2D antenna arrays as described in embodiments of the present application.

The transmit path 200 includes a channel coding and modulation block 205, a serial-to-parallel (S-to-P) block 210, an inverse N-point fast fourier transform (IFFT) block 215, a parallel-to-serial (P-to-S) block 220, an add cyclic prefix block 225, and an up-converter (UC) 230. The receive path 250 includes a down-converter (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.

In transmit path 200, a channel coding and modulation block 205 receives a set of information bits, applies coding, such as Low Density Parity Check (LDPC) coding, and modulates input bits, such as with Quadrature Phase Shift Keying (QPSK) or Quadrature Amplitude Modulation (QAM), to generate a sequence of frequency domain modulation symbols. A serial-to-parallel (S-to-P) block 210 converts (such as 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. Parallel-to-serial block 220 converts (such as multiplexes) the parallel time-domain output symbols from 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. Up-converter 230 modulates (such as up-converts) the output of 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 RF frequency.

The RF signal transmitted from the gNB 102 reaches the UE 116 after passing through the wireless channel, and an operation inverse to that at the gNB 102 is performed at the UE 116. Down-converter 255 down-converts the received signal to baseband frequency and remove cyclic prefix 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 to a parallel time-domain signal. The 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. The channel decoding and demodulation block 280 demodulates and decodes the modulation symbols to recover the original input data stream.

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

Each of the components in fig. 2a and 2b can be implemented using hardware alone, or using a combination of hardware and software/firmware. As a specific example, at least some of the components in fig. 2a and 2b may be implemented in software, while other components may be implemented by configurable hardware or a mixture of software and configurable hardware. For example, the FFT block 270 and IFFT block 215 may be implemented as configurable software algorithms, wherein the value of the point number N may be modified depending on the implementation.

Furthermore, although described as using an FFT and an IFFT, this is illustrative only and should not be construed as limiting the scope of the application. Other types of transforms can be used, such as Discrete Fourier Transform (DFT) and Inverse Discrete Fourier Transform (IDFT) functions. It should be appreciated that for DFT and IDFT functions, the value of the variable N may be any integer (such as 1, 2, 3, 4, etc.), while for FFT and IFFT functions, the value of the variable N may be any integer that is a power of 2 (such as 1, 2, 4, 8, 16, etc.).

Although fig. 2a and 2b show examples of wireless transmission and reception paths, various changes may be made to fig. 2a and 2 b. For example, the various components in fig. 2a and 2b can be combined, further subdivided, or omitted, and additional components can be added according to particular needs. Also, fig. 2a and 2b are 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.

Fig. 3a shows an example UE 116 according to the present application. The embodiment of UE 116 shown in fig. 3a is for illustration only, and UEs 111-115 of fig. 1 can have the same or similar configuration. However, the UE has a variety of configurations, and fig. 3a does not limit the scope of the present application to any particular implementation of the UE.

UE 116 includes an antenna 305, a Radio Frequency (RF) transceiver 310, transmit (TX) processing circuitry 315, a microphone 320, and Receive (RX) processing circuitry 325.UE 116 also includes speaker 330, processor/controller 340, input/output (I/O) interface 345, input device(s) 350, display 355, and memory 360. Memory 360 includes an Operating System (OS) 361 and one or more applications 362.

RF transceiver 310 receives an incoming RF signal from antenna 305 that is transmitted by the gNB of wireless network 100. The RF transceiver 310 down-converts the incoming RF signal to generate an Intermediate Frequency (IF) or baseband signal. The IF or baseband signal is sent to RX processing circuit 325, where RX processing circuit 325 generates a processed baseband signal by filtering, decoding, and/or digitizing the baseband or IF signal. The RX processing circuit 325 sends the processed baseband signals to a speaker 330 (such as for voice data) or to a processor/controller 340 (such as for web-browsing data) for further processing.

TX processing circuitry 315 receives analog or digital voice data from microphone 320 or other outgoing baseband data (such as network data, email, or interactive video game data) from processor/controller 340. TX processing circuitry 315 encodes, multiplexes, and/or digitizes the outgoing baseband data to generate a processed baseband or IF signal. RF transceiver 310 receives outgoing processed baseband or IF signals from TX processing circuitry 315 and up-converts the baseband or IF signals to RF signals for transmission via antenna 305.

Processor/controller 340 can include one or more processors or other processing devices and execute OS 361 stored in memory 360 to control the overall operation of UE 116. For example, processor/controller 340 may be capable of controlling the reception of forward channel signals and the transmission of reverse channel signals by RF transceiver 310, RX processing circuit 325, and TX processing circuit 315 in accordance with well-known principles. In some embodiments, processor/controller 340 includes at least one microprocessor or microcontroller.

Processor/controller 340 is also capable of executing other processes and programs resident in memory 360, such as operations for channel quality measurement and reporting for systems having 2D antenna arrays as described in embodiments of the present application. Processor/controller 340 is capable of moving data into and out of memory 360 as needed to perform the process. In some embodiments, the processor/controller 340 is configured to execute the application 362 based on the OS 361 or in response to a signal received from the gNB or operator. The processor/controller 340 is also coupled to an I/O interface 345, where the I/O interface 345 provides the UE 116 with the ability to connect to other devices, such as laptop computers and handheld computers. I/O interface 345 is the communication path between these accessories and processor/controller 340.

The processor/controller 340 is also coupled to an input device(s) 350 and a display 355. An operator of UE 116 can input data into UE 116 using input device(s) 350. Display 355 may be a liquid crystal display or other display capable of presenting text and/or at least limited graphics (such as from a website). Memory 360 is coupled to processor/controller 340. A portion of memory 360 can include Random Access Memory (RAM) and another portion of memory 360 can include flash memory or other Read Only Memory (ROM).

Although fig. 3a shows one example of UE 116, various changes can be made to fig. 3 a. For example, the various components in FIG. 3a can be combined, further subdivided, or omitted, and additional components can be added according to particular needs. As a particular example, the processor/controller 340 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 fig. 3a shows the UE 116 configured as a mobile phone or smart phone, the UE can be configured to operate as other types of mobile or stationary devices.

Fig. 3b shows an example gNB 102 according to the present application. The embodiment of the gNB 102 shown in fig. 3b is for illustration only, and other gnbs of fig. 1 can have the same or similar configuration. However, the gNB has a variety of configurations, and fig. 3b does not limit the scope of the present application to any particular embodiment of the gNB. Note that gNB 101 and gNB 103 can include the same or similar structures as gNB 102.

As shown in fig. 3b, the gNB 102 includes a plurality of antennas 370a-370n, a plurality of RF transceivers 372a-372n, transmit (TX) processing circuitry 374, and Receive (RX) processing circuitry 376. In certain embodiments, one or more of the plurality of antennas 370a-370n comprises a 2D antenna array. The gNB 102 also includes a controller/processor 378, a memory 380, and a backhaul or network interface 382.

The RF transceivers 372a-372n receive incoming RF signals, such as signals transmitted by UEs or other gnbs, from antennas 370a-370 n. The RF transceivers 372a-372n down-convert the incoming RF signals to generate IF or baseband signals. The IF or baseband signal is sent to RX processing circuit 376, where RX processing circuit 376 generates a processed baseband signal by filtering, decoding, and/or digitizing the baseband or IF signal. The RX processing circuit 376 sends the processed baseband signals to a controller/processor 378 for further processing.

TX processing circuitry 374 receives analog or digital data (such as voice data, network data, email, or interactive video game data) from controller/processor 378. TX processing circuitry 374 encodes, multiplexes, and/or digitizes the outgoing baseband data to generate a processed baseband or IF signal. 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 to RF signals for transmission via the antennas 370a-370 n.

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, controller/processor 378 may be capable of controlling the reception of forward channel signals and the transmission of backward channel signals via RF transceivers 372a-372n, RX processing circuit 376, and TX processing circuit 374 in accordance with well-known principles. The controller/processor 378 is also capable of supporting additional functions, such as higher-level wireless communication functions. For example, the controller/processor 378 can perform a Blind Interference Sensing (BIS) process such as that performed by a BIS algorithm and decode the received signal from which the interference signal is subtracted. Controller/processor 378 may support any of a variety of other functions in gNB 102. In some embodiments, controller/processor 378 includes at least one microprocessor or microcontroller.

Controller/processor 378 is also capable of executing programs and other processes residing in memory 380, such as a basic OS. Controller/processor 378 is also capable of supporting channel quality measurements and reporting for systems having 2D antenna arrays as described in embodiments of the present application. In some embodiments, the controller/processor 378 supports communication between entities such as web RTCs. Controller/processor 378 is capable of moving data into and out of memory 380 as needed to perform the process.

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 through a backhaul connection or through a network. The backhaul or network interface 382 can support communication through 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 technologies or NR, LTE, or LTE-a), the backhaul or network interface 382 can allow the gNB 102 to communicate with other gnbs over wired or wireless backhaul connections. When the gNB 102 is implemented as an access point, the backhaul or network interface 382 can allow the gNB 102 to communicate with a larger network (such as the internet) through a wired or wireless local area network or through a wired or wireless connection. The backhaul or network interface 382 includes any suitable structure, such as an ethernet or RF transceiver, that supports communication over a wired or wireless connection.

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

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

Although fig. 3b shows one example of the gNB 102, various changes may be made to fig. 3 b. For example, the gNB 102 can include any number of each of the components shown in FIG. 3 a. As a particular example, the 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 particular 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).

The time domain unit (also referred to as a time unit) in the present application may be one OFDM symbol, one OFDM symbol group (composed of a plurality of OFDM symbols), one slot group (composed of a plurality of slots), one subframe group (composed of a plurality of subframes), one system frame group (composed of a plurality of system frames); or absolute time units such as 1 millisecond, 1 second, etc.; the time unit may also be a combination of granularity, e.g., N1 slots plus N2 OFDM symbols.

The frequency domain unit (also referred to as frequency unit) in the present application may be: one subcarrier, one subcarrier group (composed of a plurality of subcarriers), one Resource Block (RB), which may also be referred to as a physical resource block (physical resource block, PRB), one resource block group (composed of a plurality of RBs), one band part (BWP), one band part group (composed of a plurality of BWP), one band/carrier, one band group/carrier group; or absolute frequency domain units such as 1 hz, 1 khz, etc.; the frequency domain unit may also be a combination of granularity, e.g. M1 PRBs plus M2 subcarriers.

Exemplary embodiments of the present application are further described below with reference to the accompanying drawings.

The text and drawings are provided as examples only to assist the reader in understanding the present application. They are not intended nor should they be construed as limiting the scope of the present application in any way. While certain embodiments and examples have been provided, it will be apparent to those of ordinary skill in the art from this disclosure that variations may be made to the embodiments and examples shown without departing from the scope of the application.

As used herein, the singular forms "a", "an", "the" and "the" are intended to include the plural forms as well, unless expressly stated otherwise, as understood by those skilled in the art. It will be further understood that the terms "comprises" and/or "comprising," when used in this specification, specify the presence of stated features, integers, steps, operations, elements, and/or components, but do not preclude the presence or addition of one or more other features, integers, steps, operations, elements, components, and/or groups thereof. It will be understood that when an element is referred to as being "connected" or "coupled" to another element, it can be directly connected or coupled to the other element or intervening elements may also be present. Further, "connected" or "coupled" as used herein may include wirelessly connected or wirelessly coupled. The term "and/or" as used herein includes all or any element and all combination of one or more of the associated listed items.

It will be understood by those skilled in the art that all terms (including technical and scientific terms) used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this application belongs unless defined otherwise. It will be further understood that terms, such as those defined in commonly used dictionaries, should be interpreted as having a meaning that is consistent with their meaning in the context of the prior art and will not be interpreted in an idealized or overly formal sense unless expressly so defined herein.

As used herein, a "terminal" or "terminal device" includes both a device of a wireless signal receiver having no transmitting capability and a device of receiving and transmitting hardware having receiving and transmitting hardware capable of bi-directional communication over a bi-directional communication link, as will be appreciated by those skilled in the art. Such a device may include: a cellular or other communication device having a single-line display or a multi-line display or a cellular or other communication device without a multi-line display; a PCS (Personal Communications Service, personal communication system) that may combine voice, data processing, facsimile and/or data communication capabilities; a PDA (Personal Digital Assistant ) that can include a radio frequency receiver, pager, internet/intranet access, web browser, notepad, calendar and/or GPS (Global Positioning System ) receiver; a conventional laptop and/or palmtop computer or other appliance that has and/or includes a radio frequency receiver. As used herein, "terminal," "terminal device" may be portable, transportable, installed in a vehicle (aeronautical, maritime, and/or land-based), or adapted and/or configured to operate locally and/or in a distributed fashion, to operate at any other location(s) on earth and/or in space. The "terminal" and "terminal device" used herein may also be a communication terminal, a network access terminal, and a music/video playing terminal, for example, may be a PDA, a MID (Mobile Internet Device ), and/or a mobile phone with a music/video playing function, and may also be a smart tv, a set top box, and other devices.

The term "send" in this application may be used interchangeably with "transmit," "report," "notification," etc., without departing from the scope of this application.

The transmission link of the wireless communication system mainly includes: downlink communication link from 5G nb to User Equipment (UE), uplink communication link from UE to network.

A node for positioning measurements in a wireless communication system, such as the current wireless communication system, comprises: the UE initiating the positioning request message is used for a positioning management entity (Location Management Function, LMF) for UE positioning and positioning assistance data delivery, broadcasting the positioning assistance data and a gNB or a Transmission-Reception Point (TRP) for uplink positioning measurement, and is used for downlink positioning measurement. Furthermore, the method of the present application may also be extended to be applied to other communication systems, such as automotive communication (V2X), i.e. bypass link communication (sidelink communication), where the transmitting receiving point or UE may be any device of V2X.

In recent years, an Artificial Intelligence (AI) technology represented by a deep learning algorithm is raised again, so that the problems existing in various industries for many years are solved, and great technical and commercial success is achieved. As wireless communication systems continue to evolve, these problems in the air interface have also been investigated and attempts have been made to introduce new approaches to address. To address some of the problems encountered during communication, a machine learning approach may be enabled. Among them, a method of Machine Learning (ML) generally refers to an algorithm design including machine learning and a machine learning model design on which the algorithm is based. Solutions based on AI Deep Learning (DL) technology generally refer to algorithms in machine learning technology that model artificial neural networks. Deep learning network models are typically composed of multiple layers of stacked artificial neural networks, with weight parameters in the neural network being adjusted by training existing data, and then used in the reasoning stage to achieve the task goals in the non-encountered situation. Meanwhile, generally speaking, DL-based solutions require better computational power than the related classical algorithms compared to general fixed rule-based solutions or algorithms, which typically require special purpose computational chips in the devices running the DL algorithms to support more efficient operation of the DL algorithms.

Problems encountered in communications that are solved using the AI algorithm based on machine learning generally need to satisfy the conditions that the problem of machine learning possesses. Among the existing problems associated with the air interface in communications, acquiring device position is a typical class of conditions that are met to some extent and can therefore be addressed using machine learning algorithms and achieve better results than associated solutions in communications transmission, for example in non-line-of-sight environments.

Although for currently used wireless communication systems, the associated positioning algorithms may provide normal service in some scenarios; however, for machine learning algorithms, the method of use is quite different from traditional algorithms due to its quite different architecture and features. Since present day wireless communication systems (fourth generation, fifth generation, and possibly sixth generation wireless communication systems in the future) have strict unified standards restricting the configuration method and behavior of the air interface in the communication process. As such, the design of the air interface must be designed in combination with the characteristics of the new communication system and the machine learning algorithm in view of the new technology of machine learning used in the new generation wireless communication system. Where for machine learning based algorithms to be implemented in the air interface of a wireless communication system, specific implementation procedures, such as how signals are transmitted and interacted between a user equipment and a base station, procedures for activating and deactivating machine learning algorithms and models, updates in the use of machine learning algorithms and models, etc., need to be specified, which is an important point to consider.

Therefore, in order to use a solution based on machine learning in a wireless communication system based on the above-mentioned problems, it is necessary to propose an effective technical method to define a specific implementation of these solutions in the system, a process that needs to exist, and the like, and to establish a suitable framework for solving the problem related to the interface in the wireless communication hollow by the solution based on machine learning.

In the present application, a first type of method used includes: based on "machine learning algorithms and models", "AI (artificial intelligence)/ML (machine learning) -based techniques", "AI/ML for NR air interfaces", "AI/ML techniques", "AI/ML architecture", "AI/ML model", "AI/ML for air interfaces", "AI/ML method" and "AI/ML correlation algorithms", "AI/ML-based algorithms" and "AI/ML schemes".

The present application provides for the application and configuration of machine learning based algorithms and models in a wireless communication system to accomplish or effect location operations and acquisition of location information for the wireless communication system. The present application aims to solve the problem that needs to be solved in an air interface of wireless communication by using a solution based on machine learning in a wireless communication system, proposes an architecture, a flow, a method, etc. of using the solution based on machine learning in the wireless communication system, and designs the architecture, the flow, the method, etc. to implement application of a machine learning algorithm in the wireless communication system, so as to achieve the effect that a machine learning method with better effect can be smoothly used and implemented in the communication system compared with the related existing method, thereby enabling a positioning method based on machine learning to be better applicable to the actual wireless communication system.

The method performed by the first node provided in the embodiment of the present application is described below with reference to fig. 5.

Specifically, the method performed by the first node includes steps S101-S102:

step S101: determining configuration information related to the machine learning model;

step S102: based on the configuration information, positioning-related operations are performed using the machine learning model.

Specifically, configuration information related to a machine learning model is first determined, and then positioning-related operations are performed using the corresponding machine learning model based on the configuration information; if the corresponding configuration information can be given for different scene requirements; as in the context of positioning measurements, positioning-related operations may be performed by configuring a model with denoising functionality for loud problems. Wherein the positioning related operation may be estimating positioning information, performing a subsequent positioning related operation based on the estimated positioning information, etc.

In one embodiment of the present application, a machine learning model (also referred to as a first type of method) is used to perform positioning-related operations, such as obtaining positioning information, performing subsequent positioning-related operations based on the positioning information, and so on. The first type of method proposed in this application uses ML/AI technology, and in addition to being able to perform positioning-related operations in cases of relatively "bad" (e.g., non-line-of-sight environments), positioning-related operations may also be performed in cases of poor channel conditions (e.g., inaccuracy of channel information, etc.).

The present application describes a device (denoted device a in the present application) that uses a first type of method, comprising one or more of the following parts (also referred to as phases, modes or operations) when using the first type of method:

a first part: a triggering portion; the trigger portion is optional. In the triggering portion, it is determined whether to trigger a positioning-related operation and/or a positioning information acquisition, and/or whether to trigger a first type of method and a flow of the first type of method; optionally, in the triggering portion, one or more of the following three operations are included:

operation 1: it is determined whether a positioning related operation is triggered.

If the device a is a network-side device (e.g., a base station device, an LMF, etc.), the acquisition of the positioning information may be triggered by obtaining a requirement of a higher layer (e.g., an application layer); and/or, if the device a is a user device (e.g. a mobile phone, or an automobile in V2X, etc.), the acquisition of the positioning information may be triggered based on the requirements of the higher layer.

Alternatively, the positioning related request may relate to an interaction between the system nodes, or may be triggered based on the needs of the nodes themselves only, wherein when step S101 is performed by the first node, the positioning related request may comprise a positioning related request received by the first node and triggered by the second node; the first node itself triggers a positioning related request.

Wherein the first node comprises one of: the system comprises User Equipment (UE) initiating a positioning request, a positioning management entity for UE positioning and positioning auxiliary data issuing, a base station gNB or transmitting and receiving point for broadcasting the positioning auxiliary data and performing uplink positioning measurement, and the UE for downlink positioning measurement.

Operation 2: and determining whether a preset trigger condition is met.

If the preset triggering condition is met, determining to use a first type of method; if the preset triggering condition is not met, determining that the first type of method is not used; this has the advantage of better targeting of the first type of method, which can be used when the relevant method may not give good results; optionally, the preset trigger condition includes one or more of the following conditions:

condition 1: the measured Reference Signal Received Power (RSRP) value of the first signal is less than (or not greater than) a first threshold value; optionally, the reference signal received power of the first signal includes the reference signal received power of the first path and/or the reference signal received power of the X paths; the X stripes may be X stripes with the largest path impulse response (and or reference signal received power) and/or X stripes with the smallest path delay (delay); the first threshold value is obtained by receiving an instruction and/or is preset; the trigger condition set by the condition 1 can realize that the first type of method is triggered to be used only when the channel condition is poor.

Condition 2: the measured path loss (pathloss) of the first signal is greater than (or not less than) the second threshold value; optionally, the path loss of the first signal includes the path loss of the first path and/or the path loss of the X paths; the X stripes may be X stripes with the greatest path impulse response and/or X stripes with the least path delay (delay); wherein the second threshold value is obtained by receiving an instruction and/or is preset; the trigger condition set by condition 2 may implement that the first type of method is triggered to be used only when the channel condition is relatively poor.

Condition 3: the first type of method is a valid first type of method, namely, a first type of method passing the test, and the test referred to in the embodiment of the present application includes all or part of operations in the following test section.

Condition 4: 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, where N is a sum obtained by receiving an instruction or is preset, for example, when the trigger condition counter reaches n+1 times.

Wherein the first signal comprises reference signals for positioning (e.g. downlink PRS (positioning reference signal) and uplink SRS (sounding reference signal) in a cellular wireless communication system, etc.), and/or other reference signals in the wireless system, e.g. SSB (synchronization signal block) and/or CSI-RS (channel state information-reference signal), etc.; wherein the measurement of the first signal may be used to obtain input training information and/or input information in the run section.

Alternatively, when the first type of method includes N (N >1 positive integer) AI/ML models, the preset trigger condition can be used to determine whether to use the AI/ML models in which M (M is a positive integer not greater than N); alternatively, N and M may be values preconfigured by the network device or dynamically configured (via DCI and or higher layer signaling).

Operation 3: executing a triggering process; activating the machine learning model to perform positioning related operations by at least one of:

the first node activates a machine learning model.

Optionally, executing the trigger flow includes one or more of the following three sub-operations:

Sub-operation 1: when the network side device (e.g., LMF (location management function) and/or base station device) triggers the use of the first type of method according to the above trigger condition, the network side device indicates and/or activates the use of the first type of method through LPP (LTE Positioning Protocol ) message, RRC (radio resource control) configuration message, MAC CE (medium access control element) and/or DCI (downlink control information).

Sub-operation 2: when the UE triggers to use the first type of method according to the above trigger condition, the UE receives an instruction to use or activate the first type of method through an LPP (LTE positioning protocol) message, an RRC (radio resource control) configuration message, a MAC CE (media access control element) and/or DCI (downlink control information), or the UE requests to the network side device to use the first type of method through a PUCCH (physical uplink control channel), a MAC CE, a PRACH (physical random access channel) channel and/or an LPP message; the UE receives feedback of the request from the network side equipment to determine whether a first type of method is used or not; the feedback includes the method that the network side device instructs and/or activates to use the first type of method in sub-operation 1 described above.

Sub-operation 3: when the UE triggers to use the first type of method according to the triggering condition, the UE starts to use the first type of method; this approach may be applied in the case where the first type of method is deployed on the UE side.

A second part: a transmitting and/or receiving part of the configuration information, which part is optional; in this section, device a performs the transmission and/or reception of configuration information associated with the first type of method, which may help devices using and/or training the first type of method to better use (e.g., reason) and train; specifically, the first node may receive configuration information related to the machine learning model, then determine a machine learning model to be used based on the configuration information, and perform positioning-related operations with the determined machine learning model.

Alternatively, the configuration information may include information about one or more models included in the machine learning model, that is, model composition information of a first type of method, specifically, the first type of method includes N AI/ML model parts; for example, when n=1, the first class of methods has only one AI/ML model; when n=2, the first class of methods can be obtained by combining 2 AI/ML models; similarly, N can be other positive integers and is obtained by combining a plurality of AI/ML models; wherein the plurality of AI/ML models in the first class of methods may use the same input training data and or different output training labels.

Wherein the configuration information associated with the first type of method includes one or more of:

configuration information 1: type information of the first type of method (and/or the single AI/ML model) includes at least one of: types determined by AI methods, types determined by the number of FLOPs (floating point operands) of the neural network model, types determined by the latency requirements, types determined by the required/supported data size (size of data set and/or size of data dimension), and types determined by the computational operations used (e.g., convolution and/or matrix operations).

Configuration information 2: model parameter information; super parameter configuration information and/or weight parameters and/or bias parameter configuration information may be included.

Wherein the hyper-parameter configuration information comprises at least one of the following: learning rate (learning), number of layers (numberoflayers), batch size (batch size), number of data set iterations (epochtimes), and cut-off value (clipvalue). Optionally, other super parameters may be included, not specifically recited herein.

The weight parameter and/or bias parameter configuration may include initial values (e.g., initial weight parameters, initial bias parameter settings, and/or initial weight parameters and/or initial bias parameter settings derived from received signaling) and/or updated values (e.g., updated weight parameters and/or bias parameter updated values derived from training, updating, and/or recovering), among others. Specifically, the determination of the weight parameter and/or bias parameter configuration may be implemented by at least one of the following processing methods:

The treatment method 1 comprises the following steps: the initial weight parameters and/or initial bias parameters are set, including initial weight parameters and/or bias parameters obtained according to the determined probability distribution.

The treatment method 2 comprises the following steps: setting according to the received weight parameter configuration and/or bias parameter configuration, for example weight parameters and/or bias parameters obtained by training or pre-training; such an arrangement may be more suitable for performing on-line training or for performing on-line training again according to a first type of method resulting from pre-training.

The treatment method 3 comprises the following steps: the weight parameters and/or bias parameters are obtained and/or updated according to a training optimizer model (also called training optimization algorithm, such as random gradient descent, driving amount gradient descent and the like), a loss function, iteration number optimization strength and/or learning rate; for example, an updated value is obtained.

Alternatively, the above method for determining the configuration of the weight parameter and/or the bias parameter may be implemented on the configuration of the hyper-parameters, that is, the model parameters referred to in the embodiment of the present application may be determined by one of the above processing methods 1, 2 and 3.

Configuration information 3: data set related parameters comprising at least one of: a number of data type parameters of a set of data (e.g., a set of data for positioning includes N channel impulse response values, where N is the number of data type parameters), and dimension information of the data; wherein a set of data may refer to data comprised of input and/or output data of a model; the N is obtained by receiving an instruction and or is preset.

Optionally, the size of the data set may be specific to the training portion, and/or specific to the test portion, and/or common to the test portion and the training portion.

Optionally, the number of data type parameters in the data set is determined according to a preset numerical condition; this condition may help screen more suitable and efficient input information and/or reduce signaling overhead; the preset numerical conditions include at least one of the following:

numerical condition 1: channel impulse response values greater than (or not less than) a third threshold value; the third threshold value is obtained by receiving an instruction and/or is preset; for example, a total of 4096 channel impulse response values, only N channel impulse responses greater than the third threshold value, are communicated (transmitted and/or received); n does not exceed a maximum value Nmax, wherein said N, nmax is obtained by receiving instructions and/or is preset.

Numerical condition 2: the first N channel impulse response values with the maximum power and/or the first N channel impulse response values with the maximum power on the arrival time in all channel impulse responses, wherein N is obtained by receiving instructions and or is preset.

The channel impulse response value comprises a power value and/or an arrival time of an arrival path.

Alternatively, the configuration information associated with the first type of method may be provided for transmission by device B, and/or other devices (e.g., device a using the first type of method) may be provided for transmission, which device B receives.

Alternatively, the configuration information may be for a first type of method model or a single or multiple AI/ML models in a first type of method.

Third section: a training section; the training part is optional. In this section, the first type of method used requires training by training data to obtain a trained first type of method; the device that can provide training data is denoted device B in this application; optionally, in this section, one or more of the following operations are included:

operation 1: confirmation of the training device (device B), wherein a device meeting the following condition or conditions may confirm as a training device or may confirm as a candidate training device (e.g., a condition to be met when the first node is determined as a training device): with known (or determined) location information; reporting the ability to act as a training device; the status indication that may be a training device is active (e.g., on, available, etc.); satisfying certain state conditions.

Wherein the certain state condition includes one or more of the following state conditions:

state condition 1: the measured first signal is a single-path signal, specifically, the measured first signal comprises only one path; wherein, the arrival time and/or the receiving power value of only one path accords with a set threshold value; wherein the threshold value is obtained by receiving an instruction and/or is preset.

State condition 2: the measured first signal is a line-of-sight signal, specifically comprising: when the line of sight/non-line of sight indication (LoS/NLoS indicator) is true, i.e. the measured first signal is the line of sight signal (e.g. when the indication is a hard indication, the indication is LoS); and/or the value of the line-of-sight/non-line-of-sight indication (e.g., when the indication is a soft indication) is greater than (not less than) a probability threshold value, i.e., when the measured first signal is of high probability of being line-of-sight; wherein the threshold value is obtained by receiving an instruction and/or is preset.

State condition 3: the measured Reference Signal Received Power (RSRP) value of the first signal is greater than (not less than) the fourth threshold value; and or the measured path loss value of the first signal is less than (not greater than) a fifth threshold value; wherein the threshold value is obtained by receiving an instruction and/or is preset.

State condition 4: a transmission time Error (Tx TE) or a transmission Time Error Group (TEG) of the first signal is less than or (not greater than) a sixth threshold; wherein the threshold value is obtained by receiving an instruction and/or is preset.

State condition 5: a reception time Error (Rx TE) or reception TEG of the first signal is smaller than or (not larger than) a seventh threshold value; wherein the threshold value is obtained by receiving an instruction and/or is preset.

State condition 6: the transmission and/or reception TE or TEG of the first signal is smaller than or (not larger than) an eighth threshold value; wherein the threshold value is obtained by receiving an instruction and/or is preset.

State condition 7: the transmission and/or reception of the first signal TE or TEG belongs to a specific range (first range); wherein the specific range is obtained by receiving an instruction and/or is preset.

Operation 2: transmission and/or reception of resource configuration information for training; wherein the resource configuration information for training includes one or more of:

configuration information related to the first type of method in the training section;

Positioning reference signal related configuration information (including index of positioning reference signal configuration, time-frequency resource position, period, etc. of positioning reference signal) for training;

relevant configurations of measurement intervals (MG) and/or PRS processing windows (PRS processingwindow, PPW) for training measurements, including time length of MG and/or PPW, period size, time start position, etc.; configuring the measurement interval for training may better control the time at which training data is needed, since training data is obtained over a certain time range and is valid for a certain period of time, e.g. beyond a certain time the training device may be moved to other places (e.g. a change in geographical position), the previously given training data will no longer be suitable; valid training data can help to obtain a suitable and valid first class of methods.

Operation 3: training of the first type of method is performed according to the confirmed training equipment and the resources used for training; training operations comprising one or more of:

training operation 1: the training device obtains input information related to the first type of method based on the obtained resource configuration information for training.

Training operation 2: optionally, the training device feeds back the obtained input information related to the first type of method.

Training operation 3: optionally, the training device feeds back the obtained input information related to the first type of method and the output information corresponding to the input information, for example, the training device UE feeds back channel impulse response information (i.e. the input information related to the first type of method) obtained according to the received positioning reference signal and the position information (including global position information and/or local position information, i.e. the output information corresponding to the input information) of the training device to the network side device; wherein the output information corresponding to the input information may include the location information of the device a, and/or information related to the location information calculation (e.g., time of arrival, angle of arrival; angle of departure), etc.; this method is more suitable for the case where the first type of method is deployed on the network side.

Training operation 4: and training the first type of method according to the input information related to the first type of method and/or the output information corresponding to the input information provided by the obtained training equipment.

Optionally, the input information related to the first type of method has the same meaning as the input training data; or the output information corresponding to the input information has the same meaning as the output training label.

Training operation 5: optionally [ first training mode ]: the training data (low noise channel information or non-noise channel information) is input, the noisy channel information (such as Gaussian noise information) after the noise process is obtained through AI learning, and then the obtained noisy channel information is denoised through AI learning to obtain denoised channel information, so that the similarity between the denoised channel information and the input low noise channel information is maximum. Wherein the machine learning model may include at least one model, such as may include a first model and a second model; on this basis, the first model may comprise a first part and a second part, and thus when training the machine learning model, the following training steps may be included:

obtaining noisy input information using a first portion of the first model based on the input information;

Specifically, training data X will be input ₀ (taking the channel impulse response value as an example, e.g. in case of high signal to noise ratio) X will be ₀ Is identified as q (x) ₀ ) For example, X0 comprises 4096 CIR values using an iterative forward procedure, e.g., iterative T steps; in each iteration, the channel impulse response value (X _t-1 ) A first distribution (denoted q (x _t |x _t-1 ) Noise scheduling to obtain a new channel impulse response value (X) _t ) The purpose is to train the channel impulse response value under the condition of high signal-to-noise ratio to be consistent with the channel impulse response value X of the second distribution _T 。

Wherein the first distribution q (x _t |x _t-1 ) May be a gaussian distribution and or a binomial distribution and or an exponential distribution and or a bernoulli distribution, etc., alternatively, the gaussian distribution has a mean sqrt (1-beta _t )*X _t-1 The variance is βtI. The beta is _t A noise variance scheduling (noise variance scheduling) for the t-th step, wherein the selection of the noise variance scheduling affects the training time and/or training effect of the AI/ML model, and the noise variance scheduling mode can be linear scheduling (linear scheduling), cosine scheduling or exponential scheduling; specifically, the scheduling manner may be selected according to the training purpose of the AI/ML model, for example, in the present application, the training data is an impulse response value of the channel path, and the impulse response value is exponentially faded according to the delay size of the channel path; thus, the selection index schedule may be more consistent with the scenarios in this application, e.g., β _t =a x exp (b x T/T), where a, b are related configuration parameters such that β _t Less than (not greater than) a certain threshold and or from t=1 to t=t can step up.

The second distribution may be a gaussian distribution or a binomial distribution (Binomial distribution), and the corresponding second distribution may be selected according to the training purpose of the AI/ML model, for example, in this application, noise in a wireless communication scenario is considered, and according to the central limit theorem, the gaussian distribution is selected more appropriately under the action of multiple factors.

Optionally, continuing to obtain X _T Performing reverse denoising operation; x is to be _T Is identified as p (x) _T ) An iterative backward procedure is used, for example iterative T steps; in each iteration, the channel impulse response value (X _t ) A third distribution (denoted p (x _t-1 |x _t ) And obtains a new channel impulse response value (X) of step t-1 _t-1 ) Maximizing the similarity of the distribution of the resulting X0, denoted p (X0), to q (X0) in order to simulate noisy channel impulse response values X _T Training to conform to a fourth distribution of channel impulse response values X' ₀ So that X' ₀ Can approach X ₀ The method comprises the steps of carrying out a first treatment on the surface of the Wherein optionally learning by the neural network comprises optimizing a parameter configuration of the AI/ML model species by minimizing a loss function (lossfunction); wherein optionally, the resulting similarity of the distribution of X0 (denoted p (X0)) to q (X0) comprises maximizing a desired log likelihood equation (expected log-direction) for p (X0).

The type and/or expected and/or variance values of the first and/or second and/or third and/or fourth profiles may be dynamically configured by pre-configuration and/or by DCI (and/or higher layer signaling) of the base station apparatus.

Training operation 6: optionally [ second training mode ]: according to input training data (taking a channel impulse response value as an example, for example, the channel impulse response value under the condition of high signal-to-noise ratio) and output training labels, parameter configuration (such as configuration information related to the first type of method) of the AI/ML model of the first type of method is adjusted, so that the similarity between the output information obtained according to the training data and the output training labels is maximum; for example, the first type of method is a supervised learning model, such as DenseNet, etc.

In the training method of the machine learning model (the description of the model can refer to fig. 7) provided in the embodiment of the present application, the distribution q (x ₀ ) Defined as the start of the forward Markov chain process, the dataset distribution q (x ₀ ) By adding noise at each step (e.g., beta at step t _t ) Gradually transitioning from one distribution to another, such as gaussian or binomial, and then learning the inversion process by using a neural network to maximize the similarity between the endpoint distributions of the two processes, i.e., to maximize the dataset distribution q (x ₀ ) And learning distribution p (x ₀ ) Similarity between them. Wherein the data set distribution q (x ₀ ) Can be expressed as shown in the following formula (1):

wherein, the forward conditional probability thereof is shown in the following formula (2):

wherein beta is _t Is the noise variance of the schedule at step t. Endpoint distribution p (x) ₀ ) The following formula (3) can be expressed:

it will be appreciated that when beta _t As zero is approached and the number of time steps goes to infinity, the reversal process has the same functional form as the forward process. Thus, when beta _t When smaller and T is larger, the conditional probability p (x _t-1 |x _t ) Also gaussian. Training is by maximizing the expected log-likelihood E _q (log p(x ₀ ) A lower bound equivalent to minimizing the loss function shown in equation (4):

wherein, is oc _t ＝s＝1 _t1 -β _t 。

In the present application, noise scheduling in the forward process is consideredI.e. beta _t The choice of (c) will affect the training time and the performance of the training model. The noise scheduling includes linear scheduling and cosine scheduling. Thus, the model may be trained to learn CIR patterns using exponential scheduling in embodiments of the present application. This example considers that the CIR path power decays exponentially with increasing delay, so there are many paths of small power that can increase resolution to better train the model.

Wherein beta is _t Can be expressed as shown in the following formula (5):

in equation (5), a and b are two parameters of the noise schedule, the values of which can be chosen such that β _t Is a small value and gradually increases from t=1 to t=t. FIG. 8 shows beta under different schedules _t Values, where a=1e-4, b=5, the parameters of the other schedules are chosen accordingly so that they are for β ₁ And beta _t All having the same value. As can be seen from fig. 8, unlike the linear scheduling, the noise variance β of the exponential scheduling _t The initial step size grows slower than the linear scheduling, and has larger diversity compared with the cosine scheduling.

Alternatively, the training algorithm of the machine learning model (diffusion model-based denoising algorithm) described above may be referred to as follows:

first, set up

Then, the T iteration is assigned as t..1.;

on this basis, the processing is performed by the following formula (6) and formula (7):

and finally returns to

Wherein 1-alpha in the formula (6) and the formula (7) _t ＝β _t ；∝ _t ＝s＝1 _t1 -β _t 。

Operation 4: determining a first type of method after training and/or configuration information related to the first type of method after training; comprising one or more of the following adjustment operations:

adjustment operation 1: in the training process, adjusting configuration information related to the first type of method; obtaining configuration information related to the first type of method after training to obtain a new first type of method; alternatively, this approach is more suitable for the case where the training part is performed using the apparatus of the first type of method.

Adjustment operation 2: and adjusting the configuration information related to the first type of method according to the obtained configuration information related to the first type of method after training to obtain a new first type of method, wherein the method is more suitable for the condition that the using equipment of the first type of method does not (or does not directly) perform training part, and the configuration information of the updated first type of method after training is obtained from other equipment to obtain the new first type of method.

In the embodiment of the present application, after model training is completed, the prior distribution of the CIR may be approximated as p (x ₀ ). Given a noise CIR, the goal is to obtain a noise-free (or relatively low noise) CIR by using the prior distribution of the CIR and the noise CIR. It is assumed that the noise CIR can be expressed as the following formula (8):

y＝x ₀ + z...

Wherein,x ₀ the posterior probability of (2) may be expressed as the following formula (9):

wherein q (x ₀ ) Is x ₀ Can approximate p (x ₀ ) The conditional probability may beThe Maximum A Posteriori (MAP) estimate of x may be represented by the following equation (10):

wherein x is ₀ The MMSE estimate of (2) may be expressed as follows (11):

wherein x is ₀ The explicit probability p (x 0) is required for MMSE or MAP estimation, which can be found inAnd performing integration processing. However, each diffusion step p (x _t-1 I x) is gaussian distributed and can be computed explicitly. Thus, an auxiliary process can be defined for y, as shown in equation (12) below:

y _t ＝x _t +z _t t=0, 1,2, where, t. the formula (12)

Wherein candidates for the auxiliary process can be determined by the following formula (11):

in particular, it may be obtained by solving a recursive estimation problem based on MAP or MMSE criteriaIs represented by the following equation (14) and equation (15):

fourth part: a test section; the test portion is optional. In this section, the validity of the first type of method used is tested, and if the first type of method used is confirmed to be valid, a valid first type of method can be obtained; if the used first type method is confirmed to be invalid, the invalid first type method can be obtained, and then the trigger part is returned to determine the first type method to be used again; in this section, the event-based trigger test and/or the count-timing based trigger test may be described in detail below with reference to the updated section. The test has the advantages that whether the first kind of method obtained through training is really effective and good in use under the current situation can be judged; optionally, in this section, one or more of the following test operations are included:

Test operation 1: obtaining test data; the test data are used for testing the validity of the used first type of method, and comprise input information of the used first type of method and/or output information corresponding to the input information; alternatively, the input information of the method of the first type used and the output information corresponding to the input information may be from the device B and/or the device C that provides exclusively test data.

Test operation 2: determining the validity of a first type of method of testing; if the first type of method can successfully pass the test, for example, the test output information obtained according to the input information in the first type of method and the test data meets a preset test condition, the first type of method for testing is determined to be effective, and the preset test condition includes:

test condition 1: the difference value between the test output information and the output information in the test data is smaller than (or not larger than) a first test threshold value, wherein the first test threshold value is obtained by receiving an instruction and/or is preset; the method is suitable for comparison of positioning accuracy, for example, the output information of the test is positioning position information of the equipment C obtained by applying the first type of method and the input information of the test, the output information in the test data is real positioning position information of the equipment C, positioning errors are obtained by comparing the difference values of the output information and the real positioning position information of the equipment C, the smaller the positioning errors are, the more accurate the positioning results obtained by the first type of method are indicated, and when the obtained positioning errors are smaller (or not larger) than a set first threshold value, the first type of method of the test can be determined to pass the test successfully, otherwise, the first type of method of the test is determined to fail to pass the test successfully.

Test condition 2: the test output information is better (or not worse) than the output information in the test data; the model performance as characterized by the test output information is superior to the model performance as characterized by the output information in the test data.

Test operation 3: completing a test flow; when the first type of method of the test is determined to be valid and/or the first type of method of the test meets the certain condition, the test flow may be considered to be successfully completed; when the first type of method of the test is determined to be not effective and/or the first type of method of the test does not meet the certain condition, the test flow may be considered to be completed unsuccessfully;

optionally, the first type of method used may be a first type of method after training is completed and/or a first type of method obtained according to configuration information related to the first type of method after training is completed;

fifth part: a run (or inferencing) section; in this section, the output information is to be obtained using the obtained (or determined) first-type method and/or the configuration information related to the first-type method, based on the obtained input information; optionally, in this section, one or more of the following operations are included:

operation 1: determining a parameter configuration associated with a first type of method used, comprising:

The parameter configuration information related to the first type of method comprises the same parameter configuration information as the parameter configuration information related to the first type of method introduced in the training part; optionally, the parameter configuration information is obtained by the device a by receiving configuration signaling sent by other devices; for example, the device a is a UE, and determines parameter configuration information required by a first type of method currently used by receiving parameter configuration information of the first type of method trained by the network side device; and/or

Configuring a first class of methods using the determined parameter configuration information; optionally, a lower layer (e.g., physical layer) receives a parameter configuration indication from a higher layer, and performs configuration of the first type of method.

Operation 2: obtaining input information related to a first type of method used; comprising

Obtaining input information related to a first type of method by receiving and/or measuring a first signal;

obtaining input information related to a first type of method by receiving feedback from other devices;

the input information includes data set-related parameters in the configuration information related to the first type of method in the training section.

Operation 3: output information obtained according to the input information and using a first type of method; wherein optionally, when the input information meets a certain condition (for example, meets a condition in the triggering part), a first AI/ML model in the first type of method is used for reasoning, and the output information obtained by reasoning is used as a second AI/ML model in the first type of method for reasoning to obtain the output information. Wherein the machine learning model may comprise a first model and a second model, such that, for different input information, the input information may be processed by the first model and/or the second model to obtain positioning-related output information, which may comprise at least one of the following:

Specifically, in the following example, the input information is the channel impulse response, the first type of method includes two AI/ML models, model 1 is obtained according to the first training method; the model 2 is obtained according to a second training method, and the output information is detailed position information corresponding to the channel impact.

Optionally, comparing a first noise value corresponding to the input information with a first noise threshold value to determine whether the input information needs to be subjected to denoising processing. As shown in fig. 6, the input information w= (X ₀ +Z), Z is a noise term as X _T Comparing with a first noise threshold (for example, RSRP is smaller than the threshold and/or path is larger than the threshold), the device a determines that the input information needs to be denoised by using the model 1 in the first type method (denoising process shown in fig. 6), so as to obtain first denoising information X' ₀ The method comprises the steps of carrying out a first treatment on the surface of the In the case of estimating X'0 (e.g., maximum a posterior, MAP estimation or minimum mean square error, MMSE estimation), it is necessary to integrate the previous T-1 step value, e.g., integrate X1, X2 … XT to obtain X0, and for the sake of calculation, the embodiment of the present application defines the CIR of the T-th step as W _t ＝X _t +Z _t The method comprises the steps of carrying out a first treatment on the surface of the I.e. a true value X _t Plus a noise value Z _t The method comprises the steps of carrying out a first treatment on the surface of the The Wt selected has an important influence on the result of the operation, e.g. W _t Can be equal to W, so that the same noisy channel information is input in each step as the obtained input; or W _t Can be used forEqual to a linear variation value based on W, e.g. W _t ＝sqrt[(T-t)/T]*W＝Xt+sqrt[(T-t)/T]* Z, the benefit of this is that W is just entered _T The Gaussian white noise is similar to that in the first training method, so that the denoising effect of the model 1 is optimal; and then the obtained X' ₀ Model 2 entered into this first class of methods yields positioning-related output information corresponding to W.

Alternatively, as shown in fig. 6, the input information w= (X ₀ +Z), Z is a noise term as X _T And comparing with a second noise threshold value (for example, RSRP is not less than the threshold value and or pathloss is not greater than the threshold value), and inputting W into the model 2 in the first type of method to obtain output information corresponding to W and relevant to positioning.

Wherein the first noise value comprises at least one of: RSRP, SNR, CIR amplitude value, time of arrival value of CIR.

Optionally, the method can be further extended to a usage scenario (such as information repair) where the number of CIRs of the channel impulse response value is incomplete, for example, if the number of CIRs in the input information W is less than (not greater than) a threshold value, the device a determines that the input information needs to be repaired by using the model 1 in the first type of method; setting the dimension of the input training data to be N and representing a mask vector (mask) as M, wherein M is {0,1} ^N Wherein if the i-th element is missing, it means that the i-th element M (i) =0; if the i-th element exists, the i-th element M (i) =1 is represented. Other operation methods are the same as above, X only when M (i) =0 _T (i) Represented as 0; if M (i) =1 is X _T (i) Denoted W (i) (i.e. application test or run input information).

Alternatively, when the CIR number in the input information (such as the channel information shown in fig. 6) is greater than the corresponding threshold value, the output information (such as the location information shown in fig. 6) related to the positioning is obtained by processing the input information through the model 2 in the first class of methods.

Optionally, determining whether the input information needs to be repaired based on the channel impulse response corresponding to the input information includes:

Firstly screening effective CIR values in input information, and then comparing the effective numbers with corresponding first CIR number threshold values based on the effective numbers, wherein when the effective numbers are lower than the threshold, the effective numbers are subjected to repair processing by using a model 1, and the first repair information obtained after the repair processing can be input into a model 2 for processing, and position information is output; otherwise, the input information is directly input into the model 2, and the position information is output.

Optionally, the method of obtaining (or determining) the first type further comprises a method of the first type obtained by testing and/or a method of the first type that is valid.

Alternatively, the output information may include location information of the device a, and/or information related to location information calculation (e.g., signal arrival Time of arrival, angle of departure), etc.

Sixth section: an updating section; the update section is optional. When using the first type of method, the first type of method used and/or configuration information related to the first type of method used may change, for example, because of a change in environment (such as a change in channel condition, etc.), and the first type of method used and/or configuration information related to the first type of method used needs to be adjusted; the benefit of this update is that the first type of method can be modified with less effort and/or in a shorter time so that it can be re-worked; optionally, in this section, one or more of the following update operations are included:

update operation 1: trigger updates, including event-based trigger updates and/or count-timed trigger updates, specifically, trigger updates based on preset events and/or count-timed trigger updates.

Triggering update based on the event; i.e. when a preset event occurs, the updating of the first type of method is initiated, in particular the preset event comprises one or more of the following events:

Event 1: when the output information of the first type of method does not meet the required threshold value, wherein the threshold value is obtained by receiving an instruction and/or is preset; for example, if the first type of method is used for obtaining positioning information, the difference between the output positioning position obtained by using the first type of method and the actual positioning position (or the expected positioning position, or the positioning position obtained by other methods, etc.) is greater than a certain threshold; alternatively, the threshold may be an uncertainty (uncertity) range of location information.

Event 2: when the number and/or the type of the obtained input information do not meet the required threshold value, the threshold value is obtained by receiving an instruction and/or is preset; for example, in the first type of method used for obtaining positioning information, the device a does not obtain enough channel impulse response information, and cannot use the first type of method to obtain positioning position information; for example:

obtaining input information provided by less than or not more than N devices, wherein N is obtained by receiving instructions and or is preset;

obtaining measurement results of less than or not more than N positioning reference signal resources, wherein N is obtained by receiving an instruction and or is preset;

Less or no more than N CIR/RSRP/angle-related/phase-related information is obtained, wherein N is a sum or preset obtained by receiving an instruction.

Trigger updating based on count and/or timing; conditions and operational combinations comprising one or more of the following:

determining to use the first type of method or receiving an instruction of using the first type of method, wherein an operation counter of the first type of method is initially set to be 1 and/or the operation of the first type of method is started;

when the event described in the event-based trigger occurs, the running counter is incremented by 1 and/or the counter of the first class of methods stops counting (or is determined to expire);

when one run period (cycle) is completed, then the run counter is incremented by 1 and/or the counter of the first class of methods stops counting (or is determined to expire); the operation period comprises the steps of obtaining input information according to a first type of method, and applying the first type of method to obtain the input information; optionally, the output information is output information (e.g., the difference between the output positioning position and the actual positioning position (or the expected positioning position, or the positioning position obtained by other methods, etc.) is less than or not greater than a certain threshold);

optionally, when satisfactory output information is obtained, the running counter is incremented by 1 and/or the counter of the first class of methods stops counting (or is determined to expire);

When the value counter_value of the counter reaches or exceeds a set maximum value max (e.g., counter_value=max+1), a termination portion and/or an update portion and/or a recovery portion may be performed.

Update operation 2: updating the used first type of method and/or configuration information related to the used first type of method, including sending and/or obtaining the configuration information of the update to be performed; specifically, the method comprises one or more of the following combinations:

training, including all or part of operations in the training part, to obtain updated configuration information related to the first type of method;

requesting other devices to update configuration information related to the first type of method;

receiving the update of the configuration information related to the first type of method sent by other equipment;

optionally, performing a test; the test involves all or part of the operations in the test section described above.

Seventh section: a recovery section; the recovery section is optional. When the used first type of method does not meet the performance requirement or cannot work normally, the used first type of method and/or configuration information related to the used first type of method may need to be recovered; the recovery can correct the first type of method with larger force and/or longer time so that the method can work again; optionally, in this section, one or more of the following operations are included:

Triggering a recovery flow; when a certain triggering condition is met, triggering a recovery flow; the certain triggering conditions include:

the preset event in the update trigger based on the event trigger; optionally, the preset event occurs up to or not less than N times, where N is a sum obtained by receiving an instruction or is preset;

conditions and/or operations in the above-described count and/or timing based update triggers;

the recovery of triggers may be event-based and/or count-timing based, for details of which reference is made to the detailed description of the update section above.

Performing recovery including searching for new (or candidate) training devices and/or training resources and/or training data to train and/or update;

determining a recovery result, including obtaining a recovered first type of method or configuration information related to the first type of method; optionally, the recovered first-class method or the configuration information related to the first-class method further includes testing the recovered first-class method or the first-class method obtained according to the configuration information related to the first-class method, and obtaining the recovered first-class method and/or the configuration information related to the first-class method based on a result of the testing.

Eighth section: a terminating portion; the terminating portion is optional. When the used first type method is used for a certain time and/or does not meet the requirement and/or cannot work normally, the used first type method and/or configuration information related to the used first type method can be terminated; optionally, in this section, one or more of the following operations are included:

terminating according to the termination triggering condition; the termination triggering condition comprises all or part of the triggering condition for triggering the recovery flow; alternatively, the triggering may be terminated based on an event and/or based on a count timer, the details of which are described in the updating section above.

Optionally, operations in the respective parts of the above-described trigger part, the transmission and/or reception part of the configuration information, the training part, the test part, the operation reasoning part, the updating part, the restoring part, the terminating part, and the like may be exchanged, combined, and/or replaced with each other;

alternatively, the device a and/or the device B may be a network device, a user device, or a device supporting bypass communication.

Alternatively, the first type of method described in this application may be replaced with one or more AI/ML models in the first type of method.

As an exemplary embodiment of the present application, a method for performing a positioning operation may simply include a training portion and a running portion.

As yet another exemplary embodiment of the present application, a method for performing a positioning operation may basically include a training portion, a testing portion and a running portion.

As yet another exemplary embodiment of the present application, a method for performing a positioning operation may include a training portion, a testing portion, a running portion, and a terminating portion.

As yet another exemplary embodiment of the present application, a method for performing a positioning operation may include a training portion, a testing portion, a running portion, an updating portion, and a terminating portion;

as yet another exemplary embodiment of the present application, a method for performing a positioning operation may include a training portion, a testing portion, a running portion, an updating portion, a testing portion, and a terminating portion.

As yet another exemplary embodiment of the present application, a method for performing a positioning operation may include a training portion, a testing portion, a running portion, an updating portion, a testing portion (failure), and a terminating portion.

As yet another exemplary embodiment of the present application, a method for performing a positioning operation may include a training portion, a test portion, a running portion, an updating portion, a test portion (failure), a recovery portion, a test portion, a running portion, an updating portion, a test portion, and a termination portion.

The above exemplary embodiments are merely illustrative and many adaptations may be made by those of ordinary skill in the art within the scope of the present application.

The embodiment of the present application provides an apparatus executed by a first node, as shown in fig. 9, the apparatus 100 may include: a determination module 101, and an execution module 102.

Wherein the determining module 101 is configured to determine configuration information related to the machine learning model; an execution module 102 for executing positioning related operations using the machine learning model based on the configuration information.

The apparatus of the embodiments of the present application may perform the method provided by the embodiments of the present application, and implementation principles of the method are similar, and actions performed by each module in the apparatus of each embodiment of the present application correspond to steps in the method of each embodiment of the present application, and detailed functional descriptions of each module of the apparatus may be referred to in the corresponding method shown in the foregoing, which is not repeated herein.

Referring to fig. 4, the present embodiment also provides an electronic device (user equipment) 500 for a reception measurement method of a positioning signal. The user equipment comprises a memory 501 and a processor 502, on which computer executable instructions are stored which, when executed by the processor 502, perform at least one method according to the above embodiments of the present application. The foregoing description of the preferred embodiments of the present invention is not intended to limit the invention to the precise form disclosed, and any modifications, equivalents, improvements and alternatives falling within the spirit and principles of the present invention are intended to be included within the scope of the present invention.

Those skilled in the art will appreciate that the present application includes reference to apparatus for performing one or more of the operations described herein. These devices may be specially designed and constructed for the required purposes, or may comprise known devices in general purpose computers. These devices have computer programs stored therein that are selectively activated or reconfigured. Such a computer program may be stored in a device (e.g., a computer) readable medium or any type of medium suitable for storing electronic instructions and respectively 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), ROMs (Read-Only memories), RAMs (Random Access Memory, random access memories), EPROMs (Erasable Programmable Read-Only memories), EEPROMs (Electrically Erasable Programmable Read-Only memories), flash memories, magnetic cards, or optical cards. That is, a readable medium includes any medium that stores or transmits information in a form readable by a device (e.g., a computer).

An electronic device is provided in an embodiment of the present application, including a transceiver, a memory, a processor, and a computer program stored on the memory, where the processor executes the computer program to implement steps performed by a first node.

In an alternative embodiment, an electronic device is provided, as shown in fig. 10, the electronic device 1000 shown in fig. 10 includes: a processor 1001 and a memory 1003. The processor 1001 is coupled to the memory 1003, such as via a bus 1002. Optionally, the electronic device 1000 may further include a transceiver 1004, where the transceiver 1004 may be used for data interaction between the electronic device and other electronic devices, such as transmission of data and/or reception of data, etc. It should be noted that, in practical applications, the transceiver 1004 is not limited to one, and the structure of the electronic device 1000 is not limited to the embodiments of the present application.

The processor 1001 may be a CPU (Central Processing Unit ), general purpose processor, DSP (Digital Signal Processor, data signal processor), ASIC (Application Specific Integrated Circuit ), FPGA (Field Programmable Gate Array, field programmable gate array) or other programmable logic device, transistor logic device, hardware components, or any combination thereof. Which may implement or perform the various exemplary logic blocks, modules, and circuits described in connection with this disclosure. The processor 1001 may also be a combination that implements computing functionality, such as a combination comprising one or more microprocessors, a combination of a DSP and a microprocessor, or the like.

Bus 1002 may include a path to transfer information between the components. Bus 1002 may be a PCI (Peripheral Component Interconnect, peripheral component interconnect standard) bus, or EISA (Extended Industry Standard Architecture ) bus, among others. The bus 1002 may be divided into an address bus, a data bus, a control bus, and the like. For ease of illustration, only one thick line is shown in fig. 10, but not only one bus or one type of bus.

The Memory 1003 may be, but is not limited to, ROM (Read Only Memory) or other type of static storage device that can store static information and instructions, RAM (Random Access Memory ) or other type of dynamic storage device that can store information and instructions, EEPROM (Electrically Erasable Programmable Read Only Memory ), CD-ROM (Compact Disc Read Only Memory, compact disc Read Only Memory) or other optical disk storage, optical disk storage (including compact discs, laser discs, optical discs, digital versatile discs, blu-ray discs, etc.), magnetic disk storage media, other magnetic storage devices, or any other medium that can be used to carry or store a computer program and that can be Read by a computer.

The memory 1003 is used to store a computer program for executing the embodiments of the present application, and is controlled to be executed by the processor 1001. The processor 1001 is arranged to execute a computer program stored in the memory 1003 to implement the steps shown in the foregoing method embodiments.

Among them, electronic devices include, but are not limited to: smart phones, tablet computers, notebook computers, smart speakers, smart watches, vehicle-mounted devices, and the like.

Embodiments of the present application provide a computer readable storage medium having a computer program stored thereon, where the computer program, when executed by a processor, may implement the steps and corresponding content of the foregoing method embodiments.

The embodiments of the present application also provide a computer program product, which includes a computer program, where the computer program can implement the steps of the foregoing method embodiments and corresponding content when executed by a processor.

In the embodiments provided herein, the above-described method performed by the first node may be performed using an artificial intelligence model.

The apparatus provided by the present application may implement at least one module of the plurality of modules through an AI model. The functions associated with the AI may be performed by a non-volatile memory, a volatile memory, and a processor.

The processor may include one or more processors. At this time, the one or more processors may be general-purpose processors (e.g., central Processing Units (CPUs), application Processors (APs), etc.), or purely graphics processing units (e.g., graphics Processing Units (GPUs), vision Processing Units (VPUs), and/or AI-specific processors (e.g., neural Processing Units (NPUs)).

The one or more processors control the processing of the input data according to predefined operating rules or Artificial Intelligence (AI) models stored in the non-volatile memory and the volatile memory. Predefined operational rules or artificial intelligence models are provided through training or learning.

Here, providing by learning refers to deriving a predefined operation rule or an AI model having a desired characteristic by applying a learning algorithm to a plurality of learning data. The learning may be performed in the apparatus itself in which the AI according to the embodiment is performed, and/or may be implemented by a separate server/system.

The AI model may be comprised of layers comprising a plurality of neural networks. Each layer has a plurality of weight values, and the calculation of one layer is performed by the calculation result of the previous layer and the plurality of weights of the current layer. Examples of neural networks include, but are not limited to, convolutional Neural Networks (CNNs), deep Neural Networks (DNNs), recurrent Neural Networks (RNNs), boltzmann machines limited (RBMs), deep Belief Networks (DBNs), bi-directional recurrent deep neural networks (BRDNNs), generation countermeasure networks (GANs), and deep Q networks.

A learning algorithm is a method of training a predetermined target device (e.g., a robot) using a plurality of learning data so that, allowing, or controlling the target device to make a determination or prediction. Examples of such learning algorithms include, but are not limited to, supervised learning, unsupervised learning, semi-supervised learning, or reinforcement learning.

It will be understood by those within the art that each block of the block diagrams and/or flowchart illustrations, and combinations of blocks in the block diagrams and/or flowchart illustrations, can be implemented by computer program instructions. Those skilled in the art will appreciate that these computer program instructions can be implemented in a processor of a general purpose computer, special purpose computer, or other programmable data processing method, such that the blocks of the block diagrams and/or flowchart illustration are implemented by the processor of the computer or other programmable data processing method.

Those of skill in the art will appreciate that the various operations, methods, steps in the flow, actions, schemes, and alternatives discussed in the present application may be alternated, altered, combined, or eliminated. Further, other steps, means, or steps in a process having various operations, methods, or procedures discussed in this application may be alternated, altered, rearranged, split, combined, or eliminated. Further, steps, measures, schemes in the prior art with various operations, methods, flows disclosed in the present application may also be alternated, altered, rearranged, decomposed, combined, or deleted.

The foregoing is only a partial embodiment of the present application, and it should be noted that, for a person skilled in the art, several improvements and modifications can be made without departing from the principle of the present application, and these improvements and modifications should also be considered as the protection scope of the present application.

Claims

1. A method performed by a first node, comprising:

determining configuration information related to the machine learning model;

2. The method of claim 1, further comprising obtaining a request related to positioning;

the location-related request includes at least one of:

the first node itself triggers a positioning related request.

3. The method of claim 1, wherein determining configuration information related to a machine learning model comprises:

receiving configuration information related to a machine learning model;

4. A method according to claim 1 or 3, wherein the configuration information comprises information about one or more models comprised by the machine learning model;

Wherein the relevant information for each model includes at least one of:

model type information;

model parameter information;

5. The method of claim 4, wherein the number of data types is determined by at least one of:

a channel impulse response value not less than a third threshold value;

6. The method of claim 4, wherein the model parameters are determined by at least one of:

obtaining model parameters based on the received model parameter configuration;

7. The method of claim 1, wherein the machine learning model comprises a first model and a second model; training of the machine learning model includes:

8. The method of claim 1, wherein the machine learning model comprises a first model and a second model; the performing positioning-related operations using the machine learning model includes:

acquiring input information related to a machine learning model used;

9. The method of claim 8, wherein processing the input information by the first model and/or the second model yields positioning-related output information, comprising at least one of:

10. The method of claim 9, wherein determining whether the input information requires denoising based on the first noise value corresponding to the input information comprises:

11. The method according to claim 9 or 10, wherein determining whether the input information requires repair processing based on the channel impulse response value corresponding to the input information, comprises:

12. The method according to any of claims 9-11, wherein the first noise value comprises at least one of: RSRP, SNR, CIR amplitude value, time of arrival value of CIR.

13. The method according to any one of claims 1 to 12, wherein,

the first node comprises one of the following: the system comprises User Equipment (UE) for initiating a positioning request, a positioning management entity for UE positioning and positioning auxiliary data transmission, a base station gNB or transmitting and receiving point for broadcasting the positioning auxiliary data and performing uplink positioning measurement, and the UE for downlink positioning measurement;

14. An electronic device, comprising:

a transceiver;

one or more processors;

a memory;

one or more computer programs, wherein the one or more computer programs are stored in the memory and configured to be executed by the one or more processors, the one or more computer programs configured to: method according to any one of claims 1 to 13.