Model training method, communication device, and storage medium

Abstract

The present disclosure relates to the technical field of communications, and in particular to a model training method, a communication device, and a storage medium. The model training method comprises: receiving first information from a second node, wherein the first information is used for indicating label information related to a first terminal and used for model training; and on the basis of the label information, performing model training on a model to be trained. In the present application, related information which can be used for model training can be quickly and accurately identified from received information in real time, and a corresponding training sample is generated, thereby facilitating the model training of models to be trained.

Description

Model training method, communication device and storage medium Technical Field

[0001] The present disclosure relates to the field of communication technology, and in particular to a model training method, a communication device, and a storage medium. Background Art

[0002] With the continuous advancement of artificial intelligence (AI) technology, AI can be used to assist wireless air interface transmission technology. This includes using AI-based models to determine some technical parameters of the wireless air interface, such as those related to positioning. However, obtaining the relevant data for model training has become a pressing technical challenge.

[0003] Summary of the Invention

[0004] The embodiments of the present disclosure propose a model training method, a communication device, and a storage medium to solve the technical problem of how to obtain relevant data for model training in related technologies.

[0005] According to a first aspect of an embodiment of the present disclosure, a model training method is proposed, which is executed by a first node. The method includes: receiving first information from a second node, where the first information is used to indicate label information related to the first terminal used for model training; and performing model training on a model to be trained based on the label information.

[0006] According to a second aspect of an embodiment of the present disclosure, a model training method is proposed, which is executed by a second node. The method includes: sending first information to a first node, where the first information is used to indicate label information related to the first terminal for model training.

[0007] According to the third aspect of an embodiment of the present disclosure, a model training device is proposed, which includes: a transceiver module for receiving first information from a second node, wherein the first information is used to indicate label information related to the first terminal used for model training; and a processing module for performing model training on a model to be trained based on the label information.

[0008] According to the fourth aspect of an embodiment of the present disclosure, a model training device is proposed, which includes: a processing module for determining first information, where the first information is used to indicate label information related to a first terminal used for model training; and a transceiver module for sending the first information to a first node.

[0009] According to the fifth aspect of the embodiments of the present disclosure, a terminal is proposed, comprising: one or more processors; a memory coupled to the processor, the memory storing executable instructions, wherein when the executable instructions are executed by the processor, the terminal executes the model training method described in the second aspect above.

[0010] According to the sixth aspect of an embodiment of the present disclosure, a network device is proposed, comprising: one or more processors; a memory coupled to the processor, the memory storing executable instructions, wherein when the executable instructions are executed by the processor, the network device executes the model training method described in the first or second aspect above.

[0011] According to the seventh aspect of the embodiments of the present disclosure, a communication device is proposed, comprising: one or more processors; a memory coupled to the processor, on which executable instructions are stored, wherein when the executable instructions are executed by the processor, the processor is used to call instructions so that the communication device executes the model training method described in the first aspect or the second aspect.

[0012] According to an eighth aspect of an embodiment of the present disclosure, a communication system is proposed, comprising a first node and a second node, wherein the first node is configured to implement the model training method described in the first aspect, and the second node is configured to implement the model training method described in the second aspect.

[0013] According to an eighth aspect of an embodiment of the present disclosure, a storage medium is proposed, which stores instructions. When the instructions are executed on a communication device, the communication device executes the model training method described in the first or second aspect above.

[0014] According to an embodiment of the present disclosure, the first node can determine at least one label and label information that can be used for model training based on the first information received from the second node, and then use the label information and the associated sample information as training samples to perform model training on the model to be trained. As can be seen from this, the present application can quickly and accurately identify relevant information that can be used for model training from the received information in real time and generate corresponding training samples, which helps to implement model training of the model to be trained, especially online model training. BRIEF DESCRIPTION OF THE DRAWINGS

[0015] In order to more clearly illustrate the technical solutions in the embodiments of the present disclosure, the following briefly introduces the drawings required for use in the description of the embodiments. Obviously, the drawings described below are only some embodiments of the present disclosure. For ordinary technicians in this field, other drawings can be obtained based on these drawings without any creative work.

[0016] FIG1 is a schematic diagram showing the architecture of a communication system according to an embodiment of the present disclosure.

[0017] FIG2 is an interactive schematic diagram illustrating a model training method according to an embodiment of the present disclosure.

[0018] FIG3A is a schematic flowchart of a model training method according to an embodiment of the present disclosure.

[0019] FIG3B is a schematic flowchart of a model training method according to an embodiment of the present disclosure.

[0020] FIG3C is a schematic flowchart of a model training method according to an embodiment of the present disclosure.

[0021] FIG3D is a schematic flowchart of a model training method according to an embodiment of the present disclosure.

[0022] FIG3E is a schematic flowchart of a model training method according to an embodiment of the present disclosure.

[0023] FIG3F is a schematic flowchart of a model training method according to an embodiment of the present disclosure.

[0024] FIG3G is a schematic flowchart of a model training method according to an embodiment of the present disclosure.

[0025] FIG4 is a schematic flowchart of a model training method according to an embodiment of the present disclosure.

[0026] FIG5 is a schematic block diagram showing the structure of a model training device according to an embodiment of the present disclosure.

[0027] FIG6 is a schematic block diagram showing the structure of a model training device according to an embodiment of the present disclosure.

[0028] FIG7 is a schematic structural diagram of a communication device proposed in an embodiment of the present disclosure.

[0029] FIG8 is a schematic diagram of the structure of a chip proposed in an embodiment of the present disclosure. DETAILED DESCRIPTION

[0030] The embodiments of the present disclosure provide a model training method, a communication device, and a storage medium.

[0031] In a first aspect, an embodiment of the present disclosure proposes a model training method, which is executed by a first node. The method includes: receiving first information from a second node, where the first information is used to indicate label information related to the first terminal used for model training; and performing model training on a model to be trained based on the label information.

[0032] In the above embodiment, the first node can determine at least one label and label information that can be used for model training based on the first information received from the second node, and then use the label information and the associated sample information as training samples to train the model to be trained. As can be seen, the present application can quickly and accurately identify relevant information that can be used for model training from the received information in real time and generate corresponding training samples, which helps to achieve model training of the model to be trained, especially online model training.

[0033] In conjunction with some embodiments of the first aspect, in some embodiments, the first information includes at least one of the following: a terminal identifier of the first terminal; a terminal type of the first terminal; tag information related to the first terminal; sample information related to the first terminal; a first identifier associated with the tag information and sample information; location information of the first terminal; speed information of the first terminal; a first timestamp, the first timestamp being used to indicate the time when the tag information was generated; and a validity period of the tag information.

[0034] In conjunction with some embodiments of the first aspect, in some embodiments, the model to be trained includes a model for positioning measurement; the label information includes label information related to positioning measurement; and the sample information includes measurement values ​​related to the positioning measurement.

[0035] In combination with some embodiments of the first aspect, in some embodiments, the tag information includes tag information associated with at least one transmitting and receiving point TRP.

[0036] In combination with some embodiments of the first aspect. In some embodiments, the label information includes at least one of the following: location information of the first terminal; identifier of the first node; identifier of the transmitting and receiving point TRP; receive-transmit time difference RxTxTimeDiff; reference signal received power of uplink sounding reference signal UL-SRS-RSRP; uplink angle of arrival UL-AoA; uplink time of arrival offset UL-RTOA; multiple uplink angles of arrival Multiple UL-AoA; reference signal received power preprocessing of uplink sounding reference signal UL SRS-RSRPP; direct propagation LoS information, used to indicate whether the uplink measurement is direct propagation LoS; non-direct propagation NLoS information, used to indicate whether the uplink measurement is non-direct propagation NLoS.

[0037] In combination with some embodiments of the first aspect, in some embodiments, before receiving the first information from the second node, the method further includes: sending a first request to the second node, where the first request is used to request the second node to obtain label information for model training.

[0038] In conjunction with some embodiments of the first aspect, in some embodiments, the first request includes at least one of the following: a terminal identifier of the first terminal; a terminal number of the first terminal; a purpose of the first information; location information of the first terminal; speed information of the first terminal; TRP information related to the tag information; type of information included in the tag information; time when the tag information was generated; and time when the first information was generated.

[0039] In combination with some embodiments of the first aspect, in some embodiments, sending the first request to the second node includes: sending the first request for the first terminal to the second node.

[0040] In combination with some embodiments of the first aspect, in some embodiments, before sending the first request for the first terminal to the second node, the method further includes: receiving second information related to the second terminal from the second node or the third node, the second information being used to indicate whether the second terminal is authorized and / or agrees to serve as the first terminal; and determining whether to use the second terminal as the first terminal based on the second information.

[0041] In combination with some embodiments of the first aspect. In some embodiments, the second information includes at least one of the following: indication information indicating whether the second terminal is authorized to be used for the model training; indication information indicating whether the second terminal is agreed to be used for the model training; and positioning information associated with the second terminal.

[0042] In combination with some embodiments of the first aspect, in some embodiments, the positioning information includes an identifier of a location management function LMF associated with the second terminal.

[0043] In combination with some embodiments of the first aspect, in some embodiments, performing model training on the to-be-trained model based on the label information includes: labeling sample information related to the first terminal based on the label information; and performing model training on the to-be-trained model based on the label information and the sample information.

[0044] In combination with some embodiments of the first aspect. In some embodiments, labeling the sample information related to the first terminal based on the label information includes: determining the sample information related to the first terminal labeled by the label information based on a matching condition; labeling the sample information based on the label information; wherein the matching condition includes at least one of the following: a first timestamp for generating the label information matches a second timestamp for generating the sample information; a time difference between a first moment when the first node receives the label information and a second moment when the sample information is received is less than a preset duration threshold; and the label information and the sample information are associated with the same first identifier.

[0045] In conjunction with some embodiments of the first aspect, in some embodiments, the first node is a base station; and the second node is a terminal, an access and mobility management function AMF, or a location management function LMF.

[0046] In a second aspect, an embodiment of the present disclosure proposes a model training method, which is executed by a second node. The method includes: sending first information to a first node, where the first information is used to indicate label information related to a first terminal for model training.

[0047] In combination with some embodiments of the second aspect, in some embodiments, the first information includes at least one of the following: a terminal identifier of the first terminal; a terminal type of the first terminal; tag information related to the first terminal; sample information related to the first terminal, the sample information being marked by the tag information; a first identifier associated with the tag information and the sample information; location information of the first terminal; speed information of the first terminal; a first timestamp, the first timestamp being used to indicate the time when the tag information was generated; and the validity period of the tag information.

[0048] In conjunction with some embodiments of the second aspect, in some embodiments, the model training includes model training for positioning measurements; the label information includes label information related to positioning measurements; and the sample information includes measurement values ​​related to the positioning measurements.

[0049] In combination with some embodiments of the second aspect, in some embodiments, the tag information includes tag information associated with at least one transmitting and receiving point TRP.

[0050] In combination with some embodiments of the second aspect. In some embodiments, the label information includes at least one of the following: location information of the first terminal; identifier of the first node; identifier of the transmitting and receiving point TRP; receive-transmit time difference RxTxTimeDiff; reference signal received power of uplink sounding reference signal UL-SRS-RSRP; uplink angle of arrival UL-AoA; uplink time of arrival offset UL-RTOA; multiple uplink angles of arrival Multiple UL-AoA; reference signal received power preprocessing of uplink sounding reference signal UL SRS-RSRPP; direct propagation LoS information, used to indicate whether the uplink measurement is direct propagation LoS; non-direct propagation NLoS information, used to indicate whether the uplink measurement is non-direct propagation NLoS.

[0051] In combination with some embodiments of the second aspect, in some embodiments, before sending the first information to the first node, the method further includes: receiving a first request from the first node, where the first request is used to request label information for model training.

[0052] In conjunction with some embodiments of the second aspect, in some embodiments, the first request includes at least one of the following: a terminal identifier of the first terminal; a terminal number of the first terminal; a purpose of the first information; location information of the first terminal; speed information of the first terminal; TRP information related to the tag information; type of information included in the tag information; generation time of the tag information; and generation time of the first information.

[0053] In combination with some embodiments of the second aspect, in some embodiments, receiving the first request from the first node includes: receiving the first request for the first terminal from the first node.

[0054] In conjunction with some embodiments of the second aspect, in some embodiments, before receiving the first request for the first terminal from the first node, the method further includes: sending second information related to the second terminal to the first node, where the second information is used to indicate whether the second terminal is authorized and / or agrees to serve as the first terminal.

[0055] In combination with some embodiments of the second aspect. In some embodiments, the second information includes at least one of the following: indication information indicating whether the second terminal is authorized to be used for the model training; indication information indicating whether the second terminal is agreed to be used for the model training; and positioning information associated with the second terminal.

[0056] In conjunction with some embodiments of the second aspect, in some embodiments, the positioning information includes an identifier of a location management function LMF associated with the second terminal.

[0057] In combination with some embodiments of the second aspect, in some embodiments, after receiving the first request from the first node, the method further includes: sending a second request to a location management function LMF, where the second request is used to request label information related to the first terminal from the location management function LMF.

[0058] In conjunction with some embodiments of the second aspect, in some embodiments, the first node is a base station; and the second node is a terminal, an access and mobility management function AMF, or a location management function LMF.

[0059] In a third aspect, a model training device is proposed, which includes: a transceiver module for receiving first information from a second node, where the first information is used to indicate label information related to the first terminal used for model training; and a processing module for performing model training on a model to be trained based on the label information.

[0060] In a fourth aspect, a model training device is proposed, which includes: a processing module for determining first information, where the first information is used to indicate label information related to the first terminal used for model training; and a transceiver module for sending the first information to the first node.

[0061] In the fifth aspect, a model training device is proposed, including: a transceiver module for receiving first information from a second node, wherein the first information is used to indicate label information related to the first terminal used for model training; and a processing module for performing model training on a model to be trained based on the label information.

[0062] In the sixth aspect, a model training device is proposed, including: a processing module for determining first information, where the first information is used to indicate label information related to the first terminal used for model training; and a transceiver module for sending the first information to the first node.

[0063] In the seventh aspect, a terminal is proposed, comprising: one or more processors; a memory coupled to the processor, wherein the memory stores executable instructions, wherein when the executable instructions are executed by the processor, the terminal executes the model training method described in the optional embodiment of the second aspect above.

[0064] In the eighth aspect, a network device is proposed, comprising: one or more processors; a memory coupled to the processor, wherein the memory stores executable instructions, wherein when the executable instructions are executed by the processor, the network device executes the model training method described in the optional embodiment of the first or second aspect above.

[0065] In the ninth aspect, an embodiment of the present disclosure proposes a communication device, which includes: one or more processors; a memory coupled to the processor, on which executable instructions are stored, wherein when the executable instructions are executed by the processor, the processor calls the executable instructions so that the communication device executes the model training method described in the optional embodiment of the first aspect or the second aspect.

[0066] In the tenth aspect, an embodiment of the present disclosure proposes a communication system, which includes: a first node and a second node; wherein the first node is configured to execute the method described in the optional embodiment of the first aspect, and the second node is configured to execute the method described in the optional embodiment of the second aspect.

[0067] In the eleventh aspect, an embodiment of the present disclosure proposes a storage medium, which stores instructions. When the instructions are executed on a communication device, the communication device executes the method described in the optional embodiment of the first aspect or the second aspect.

[0068] In a twelfth aspect, an embodiment of the present disclosure proposes a program product. When the program product is executed by a communication device, the communication device executes the method described in the optional embodiment of the first aspect or the second aspect.

[0069] In a thirteenth aspect, an embodiment of the present disclosure proposes a computer program, which, when executed on a computer, enables the computer to execute the method as described in the first aspect or the optional embodiment of the second aspect.

[0070] It is understandable that the above-mentioned terminals, network devices, communication devices, communication systems, storage media, program products, and computer programs are all used to execute the methods proposed in the embodiments of the present disclosure. Therefore, the beneficial effects that can be achieved can refer to the beneficial effects of the corresponding methods and will not be repeated here.

[0071] The present disclosure provides a model training method, communication device, and storage medium. In some embodiments, the terms "information sending method," "information receiving method," "information processing method," and "communication method" are interchangeable; the terms "terminal," "network device," "information processing device," and "communication device" are interchangeable; and the terms "information processing system" and "communication system" are interchangeable.

[0072] The embodiments of the present disclosure are not exhaustive and are merely illustrative of some embodiments, and are not intended to be a specific limitation on the scope of protection of the present disclosure. In the absence of contradiction, each step in a certain embodiment can be implemented as an independent embodiment, and the steps can be arbitrarily combined. For example, a solution after removing some steps in a certain embodiment can also be implemented as an independent embodiment, and the order of the steps in a certain embodiment can be arbitrarily exchanged. In addition, the optional embodiments in a certain embodiment can be arbitrarily combined; in addition, the embodiments can be arbitrarily combined. For example, some or all steps of different embodiments can be arbitrarily combined, and a certain embodiment can be arbitrarily combined with the optional embodiments of other embodiments.

[0073] In each embodiment of the present disclosure, unless otherwise specified or provided for by logic, the terms and / or descriptions between the embodiments are consistent and can be referenced by each other. The technical features in different embodiments can be combined to form a new embodiment based on their inherent logical relationships.

[0074] The terms used in the embodiments of the present disclosure are only for the purpose of describing specific embodiments and are not intended to limit the present disclosure.

[0075] In the embodiments of the present disclosure, unless otherwise specified, elements expressed in the singular form, such as "a", "an", "the", "above", "said", "aforementioned", "this", etc., may mean "one and only one", or "one or more", "at least one", etc.

[0076] For example, when using articles such as “a”, “an”, and “the” in English in translation, the noun following the article can be understood as a singular expression or a plural expression.

[0077] In the embodiments of the present disclosure, “plurality” refers to two or more.

[0078] In some embodiments, the terms "at least one," "one or more," "a plurality of," "multiple," etc. may be used interchangeably.

[0079] In some embodiments, descriptions such as "at least one of A and B," "A and / or B," "A in one case, B in another case," or "in response to one case A, in response to another case B" may include the following technical solutions depending on the situation: in some embodiments, A (A is executed independently of B); in some embodiments, B (B is executed independently of A); in some embodiments, execution is selected from A and B (A and B are selectively executed); and in some embodiments, A and B (both A and B are executed). The above is also applicable when there are more branches such as A, B, and C.

[0080] In some embodiments, "A or B" and other descriptions may include the following technical solutions depending on the situation: in some embodiments, A (A is executed independently of B); in some embodiments, B (B is executed independently of A); in some embodiments, execution is selected from A and B (A and B are selectively executed). The above is also applicable when there are more branches such as A, B, C, etc.

[0081] The prefixes such as "first" and "second" in the embodiments of the present disclosure are only used to distinguish different description objects and do not constitute any restrictions on the position, order, priority, quantity or content of the description objects. For the statement of the description objects, please refer to the description in the context of the claims or embodiments, and no unnecessary restrictions should be constituted due to the use of prefixes.

[0082] For example, if the description object is "field," the ordinal number preceding "field" in "first field" and "second field" does not restrict the position or order of the "fields." "First" and "second" do not restrict whether the modified "fields" are in the same message, nor do they restrict the order of the "first field" and "second field." For another example, if the description object is "level," the ordinal number preceding "level" in "first level" and "second level" does not restrict the priority of the "levels." For another example, the number of description objects is not restricted by the ordinal number and can be one or more. For example, in the case of "first device," the number of "devices" can be one or more. Furthermore, the objects modified by different prefixes can be the same or different. For example, if the description object is "device," "first device" and "second device" can be the same or different devices, and their types can be the same or different. For another example, if the description object is "information," "first information" and "second information" can be the same or different information, and their content can be the same or different.

[0083] In some embodiments, “including A,” “comprising A,” “used to indicate A,” and “carrying A” can be interpreted as directly carrying A or indirectly indicating A.

[0084] In some embodiments, terms such as "in response to...", "in response to determining...", "in the case of...", "at the time of...", "when...", "if...", "if...", etc. can be used interchangeably.

[0085] In some embodiments, terms such as "greater than", "greater than or equal to", "not less than", "more than", "more than or equal to", "not less than", "higher than", "higher than or equal to", "not less than", and "above" can be replaced with each other, and terms such as "less than", "less than or equal to", "not greater than", "less than", "less than or equal to", "not more than", "lower than", "lower than or equal to", "not higher than", and "below" can be replaced with each other.

[0086] In some embodiments, devices and the like can be interpreted as physical or virtual, and their names are not limited to those in the embodiments.

[0087] The recorded names, "device", "equipment", "device", "circuit", "network element", "node", "function", "unit", "section", "system", "network", "chip", "chip system", "entity", "subject" and other terms can be used interchangeably.

[0088] In some embodiments, "network" can be interpreted as devices included in the network (eg, access network equipment, core network equipment, etc.).

[0089] In some embodiments, the terms "access network device (AN device)", "radio access network device (RAN device)", "base station (BS)", "radio base station" "fixed station", "node", "access point", "transmission point (TP)", "reception point (RP)", "transmission / reception point (TRP)", "panel", "antenna panel", "antenna array", "cell", "macro cell", "small cell", "femto cell", "pico cell", "sector", "cell group", "serving cell", "carrier", "component carrier", "bandwidth part (BWP)" and the like may be used interchangeably.

[0090] In some embodiments, the terms "terminal", "terminal device", "user equipment (UE)", "user terminal", "mobile station (MS)", "mobile terminal (MT)", subscriber station, mobile unit, subscriber unit, wireless unit, remote unit, mobile device, wireless device, wireless communication device, remote device, mobile subscriber station, access terminal, mobile terminal, wireless terminal, remote terminal, handset, user agent, mobile client, client, etc. can be used interchangeably.

[0091] In some embodiments, the access network device, the core network device, or the network device can be replaced by a terminal. For example, the various embodiments of the present disclosure can also be applied to a structure in which the communication between the access network device, the core network device, or the network device and the terminal is replaced by communication between multiple terminals (for example, device-to-device (D2D), vehicle-to-everything (V2X), etc.). In this case, it is also possible to set the structure in which the terminal has all or part of the functions of the access network device. In addition, terms such as "uplink" and "downlink" can also be replaced by terms corresponding to communication between terminals (for example, "side"). For example, uplink channels, downlink channels, etc. can be replaced by side channels, and uplinks, downlinks, etc. can be replaced by side links.

[0092] In some embodiments, the terminal may be replaced by an access network device, a core network device, or a network device. In this case, the access network device, the core network device, or the network device may have a structure that has all or part of the functions of the terminal.

[0093] In some embodiments, obtaining data, information, etc. may comply with the laws and regulations of the country where the data is obtained.

[0094] In some embodiments, data, information, etc. may be obtained with the user's consent.

[0095] In addition, each element, each row, or each column in the table of the embodiment of the present disclosure can be implemented as an independent embodiment, and the combination of any elements, any rows, and any columns can also be implemented as an independent embodiment.

[0096] FIG1 is a schematic diagram showing the architecture of a communication system according to an embodiment of the present disclosure.

[0097] As shown in Figure 1, the communication system 100 includes a first node 101 and a second node 102; wherein, the first node 101 can be a terminal or a network device, and the second node 102 can be a network device, wherein the network device includes at least one of the following: an access network device, a core network device.

[0098] In some embodiments, the terminal includes, for example, a mobile phone, a wearable device, an Internet of Things device, a car with communication function, a smart car, a tablet computer, a computer with wireless transceiver function, a virtual reality (VR) terminal device, an augmented reality (AR) terminal device, a wireless terminal device in industrial control, a wireless terminal device in self-driving, a wireless terminal device in remote medical surgery, a wireless terminal device in a smart grid, a wireless terminal device in transportation safety, a wireless terminal device in a smart city, and at least one of a wireless terminal device in a smart home, but is not limited thereto.

[0099] In some embodiments, the access network device is, for example, a node or device that accesses a terminal to a wireless network. The access network device may include an evolved NodeB (eNB), a next generation evolved NodeB (ng-eNB), a next generation NodeB (gNB), a node B (NB), a home node B (HNB), a home evolved nodeB (HeNB), a wireless backhaul device, a radio network controller (RNC), a base station controller (BSC), a base transceiver station (BTS), a base band unit (BBU), a mobile switching center, a base station in a 6G communication system, an open base station (Open RAN), a cloud base station (Cloud RAN), a base station in other communication systems, and at least one of an access node in a Wi-Fi system, but is not limited thereto.

[0100] In some embodiments, a core network device may be a device including one or more network elements, or may be multiple devices or device groups, each including all or part of the one or more network elements. The network element may be virtual or physical. The core network may include, for example, at least one of an Evolved Packet Core (EPC), a 5G Core Network (5GCN), and a Next Generation Core (NGC).

[0101] In some embodiments, the technical solution of the present disclosure can be applied to the Open RAN architecture. In this case, the interfaces between or within the access network devices involved in the embodiments of the present disclosure can be transformed into internal interfaces of the Open RAN, and the processes and information interactions between these internal interfaces can be implemented through software or programs.

[0102] In some embodiments, the access network device can be composed of a centralized unit (CU) and a distributed unit (DU), where the CU can also be called a control unit. The CU-DU structure can be used to split the protocol layer of the access network device, with the functions of some protocol layers centrally controlled by the CU, and the functions of the remaining part or all of the protocol layers distributed in the DU, which is centrally controlled by the CU, but is not limited to this.

[0103] It can be understood that the communication system described in the embodiment of the present disclosure is for the purpose of more clearly illustrating the technical solution of the embodiment of the present disclosure, and does not constitute a limitation on the technical solution proposed in the embodiment of the present disclosure. Ordinary technicians in this field can know that with the evolution of the system architecture and the emergence of new business scenarios, the technical solution proposed in the embodiment of the present disclosure is also applicable to similar technical problems.

[0104] The following embodiments of the present disclosure may be applied to the communication system 100 shown in FIG1 , or a portion thereof, but are not limited thereto. The entities shown in FIG1 are illustrative only. The communication system may include all or part of the entities shown in FIG1 , or may include other entities outside of FIG1 . The number and form of the entities are arbitrary, and the entities may be physical or virtual. The connection relationships between the entities are illustrative only. The entities may be connected or disconnected, and the connection may be in any manner, including direct or indirect, wired or wireless.

[0105] The embodiments of the present disclosure can be applied to Long Term Evolution (LTE), LTE-Advanced (LTE-A), LTE-Beyond (LTE-B), SUPER 3G, IMT-Advanced, 4th generation mobile communication system (4G), 5th generation mobile communication system (5G), 5G new radio (NR), future radio access (FRA), new radio access technology (RAT), new radio (NR), new radio access (NX), future generation radio access (FX), Global System for Mobile communications (GSM (registered trademark)), CDMA2000, Ultra Mobile Broadband (UMB), IEEE 802.11 (Wi-Fi (registered trademark)), IEEE 802.16 (WiMAX (registered trademark)), IEEE 802.20, Ultra-WideBand (UWB), Bluetooth (registered trademark), Public Land Mobile Network (PLMN) networks, Device-to-Device (D2D) systems, Machine-to-Machine (M2M) systems, Internet of Things (IoT) systems, Vehicle-to-Everything (V2X), systems utilizing other communication methods, and next-generation systems based on and extending these methods. Furthermore, multiple systems may be combined (for example, a combination of LTE or LTE-A with 5G).

[0106] FIG2 is an interactive schematic diagram illustrating a model training method according to an embodiment of the present disclosure.

[0107] As shown in Figure 2, the model training method includes:

[0108] In step S201 , the second node 102 sends first information to the first node 101 , where the first information is used to indicate label information related to the first terminal for model training.

[0109] In some embodiments, the first information includes at least one of the following: a terminal identifier of the first terminal; a terminal type of the first terminal; tag information related to the first terminal; sample information related to the first terminal; a first identifier associated with the tag information and sample information; location information of the first terminal; speed information of the first terminal; a first timestamp, the first timestamp being used to indicate the moment when the tag information is generated; and the validity period of the tag information.

[0110] In some embodiments, the model to be trained includes a model for positioning measurement; the label information includes label information related to the positioning measurement; and the sample information includes measurement values ​​related to the positioning measurement.

[0111] In some embodiments, the tag information includes tag information associated with at least one transmitting and receiving point TRP.

[0112] In some embodiments, the label information includes at least one of the following: location information of the first terminal; identification of the first node; identification of the transmitting and receiving point TRP; receive-transmit time difference RxTxTimeDiff; reference signal received power of uplink sounding reference signal UL-SRS-RSRP; uplink angle of arrival UL-AoA; uplink arrival time offset UL-RTOA; multiple uplink angles of arrival Multiple UL-AoA; reference signal received power preprocessing of uplink sounding reference signal UL SRS-RSRPP; direct propagation LoS information, used to indicate whether the uplink measurement is direct propagation LoS; non-direct propagation NLoS information, used to indicate whether the uplink measurement is non-direct propagation NLoS.

[0113] In some embodiments, before step S201, the first node 101 may send a first request to the second node 102, where the first request is used to request the second node to obtain label information for model training.

[0114] In some embodiments, the first request includes at least one of the following: the terminal identification of the first terminal; the terminal number of the first terminal; the purpose of the first information; the location information of the first terminal; the speed information of the first terminal; the TRP information related to the tag information; the type of information contained in the tag information; the generation time of the tag information; the generation time of the first information.

[0115] In some embodiments, before step S201 , the first node 101 may send a first request for the first terminal to the second node.

[0116] In some embodiments, before sending a first request for the first terminal to the second node, the second node may send second information related to the second terminal to the first node, where the second information is used to indicate whether the second terminal is authorized and / or agreed to serve as the first terminal; and determine whether to use the second terminal as the first terminal based on the second information.

[0117] In some embodiments, the second information includes at least one of the following: indication information indicating whether the second terminal is authorized to be used for the model training; indication information indicating whether the second terminal is agreed to be used for the model training; and positioning information associated with the second terminal.

[0118] In some embodiments, the location information includes an identifier of a location management function LMF associated with the second terminal.

[0119] In some embodiments, after the first node 101 sends the first request to the second node 102, the second node may send a second request to the location management function LMF, where the second request is used to request label information related to the first terminal from the location management function LMF.

[0120] In some embodiments, the first node is a base station; the second node is a terminal, an access and mobility management function AMF or a location management function LMF.

[0121] In some embodiments, the terminal may send first information to the base station, where the first information is used to indicate label information related to the first terminal for model training.

[0122] In some embodiments, the AMF may send first information to the base station, and the terminal may send first information to the base station, where the first information is used to indicate label information related to the first terminal for model training.

[0123] In some embodiments, the LMF may send first information to the base station, and the terminal may send first information to the base station, where the first information is used to indicate label information related to the first terminal for model training.

[0124] Step S202: The first node 101 performs model training on the model to be trained based on the label information.

[0125] In some embodiments, step S202 includes: labeling sample information related to the first terminal based on the label information; and performing model training on a to-be-trained model based on the label information and the sample information.

[0126] In some embodiments, the tagging of the sample information related to the first terminal based on the tag information includes: determining, based on a matching condition, the sample information related to the first terminal tagged by the tag information; and tagging the sample information based on the tag information;

[0127] In some embodiments, the matching condition includes at least one of the following: a first timestamp for generating the tag information matches a second timestamp for generating the sample information; a time difference between a first moment when the first node receives the tag information and a second moment when the first node receives the sample information is less than a preset duration threshold; and the tag information and the sample information are associated with the same first identifier.

[0128] The communication method involved in the embodiments of the present disclosure may include at least one of steps S201 to 202. For example, step S201 may be implemented as an independent embodiment, step S202 may be implemented as an independent embodiment, and steps S201+S202 may be implemented as independent embodiments, but are not limited thereto.

[0129] In some embodiments, steps S201 and S202 may be performed in an interchangeable order or simultaneously.

[0130] In some embodiments, step S201 is optional, and one or more of these steps may be omitted or replaced in different embodiments.

[0131] In some embodiments, step S202 is optional, and one or more of these steps may be omitted or replaced in different embodiments.

[0132] In some embodiments, reference may be made to other optional embodiments described before or after the description corresponding to FIG. 2 .

[0133] In recent years, artificial intelligence (AI) technology has achieved continuous breakthroughs in various fields. AI is also rapidly interpenetrating into other disciplines, integrating knowledge from different disciplines while also providing new directions and methods for their development.

[0134] In the field of wireless communications, during 3GPP Release 18, RAN1 established a research project on artificial intelligence technology in wireless air interfaces. This project aims to study how to introduce artificial intelligence technology into wireless air interfaces and explore how artificial intelligence technology can assist in improving wireless air interface transmission technology. In the research of wireless air interface AI technology, one important research direction is to use AI-based models to determine some technical parameters of the wireless air interface, such as using AI-based positioning models to assist in determining the positioning information of the terminal. Such AI-based models can also be referred to as machine learning (ML)-based models.

[0135] AI-based models require pre-training. During the model training process, it is typically necessary to first determine the sample information used for model training and the label information corresponding to the sample information. The AI-based model to be trained is then trained based on the sample information and label information. The sample information includes the input data of the model to be trained during training, and the label information includes the actual output data used to guide the learning of the model to be trained. Through model training, the model to be trained can learn the relationship between the input data and the actual output data.

[0136] For example, in an AI-based positioning model, the Positioning Reference Unit (PRU) is a communication device with a known location, such as a terminal that supports the PRU function. The location information of the PRU can be used as label information for model training.

[0137] In some embodiments, the AI-based positioning model can be deployed in specific communication equipment for online model training according to actual needs. How to obtain relevant data for online model training becomes a technical problem that needs to be solved urgently.

[0138] Embodiments of the present disclosure provide a model training method. Figure 3A is a schematic flow chart of a model training method according to an embodiment of the present disclosure. The model training method shown in this embodiment can be performed by a first node. The first node can be a communication device deployed with a model to be trained and / or a communication device that performs model training on the model to be trained.

[0139] In some embodiments, the first node that can be used to perform model training may include a terminal, a base station (gNB), a location management function (LMF), etc.

[0140] In some embodiments, positioning based on an AI-based positioning model can be performed in a variety of deployment modes according to actual needs, including the following five:

[0141] For Direct AI / ML Positioning solutions:

[0142] Solution 1: Use the UE-side model to implement terminal-based positioning.

[0143] Solution 2: Use the LMF-side model to implement terminal-assisted LMF-based positioning;

[0144] Solution 3: Use a model deployed on the LMF side to implement positioning assisted by radio access network nodes (such as base stations (gNBs) and new radio-radio access networks (NR-RAN)).

[0145] For AI / ML-based assisted positioning solutions:

[0146] Solution 4: Use the model deployed on the terminal side to implement terminal-assisted LMF-based positioning;

[0147] Solution 5: Use the gNB-side model to implement positioning assisted by radio access network nodes.

[0148] For the sake of simplicity, this specification uses the example that the first node is a base station, that is, the base station performs model training. For example, the solution 5 shown above can be used.

[0149] As shown in FIG3A , the model training method may include the following steps:

[0150] In step S301, the first node receives first information from the second node, where the first information is used to indicate label information related to the first terminal for model training.

[0151] In some embodiments, a first node may receive first information from a second node, and tag information related to tags used for model training may be determined from the first information, wherein the first node is a node that performs model training.

[0152] In some embodiments, the tag may include a first terminal that can be used for model training, as well as other communication devices.

[0153] In some embodiments, the first node may receive first information from the second node, and determine at least one first terminal that can be used as a label for model training based on the first information, as well as label information related to each first terminal.

[0154] In some embodiments, the second node may be a terminal, an Access and Mobility Management Function (AMF), a Location Management Function (LMF), or the like.

[0155] The label information can be set according to the output data of the model training. In some embodiments, for the model training for positioning measurement, the label information may include relevant label information for positioning measurement, for example, it may include the location information of the first terminal, and label information obtained based on the location of the first terminal, the location of the first node and the configuration of the sounding reference signal (SRS).

[0156] In step S302, the first node performs model training on the model to be trained based on the label information.

[0157] In some embodiments, after determining the label and label information based on the first information, the first node may perform model training on the to-be-trained model based on the label information.

[0158] In some embodiments, the first node may determine the sample information corresponding to the label information from other received information, and establish an association relationship between the label information and the sample information.

[0159] In some embodiments, after determining at least one first terminal and label information related to each first terminal based on the first information, the first node can further determine, from other received information, sample information related to each first terminal that can correspond to the label information related to each first terminal, and establish an association relationship between the label information related to each first terminal and the sample information.

[0160] For example, the first node receives the first information from the second node, and determines the first terminals T1 and T2 that can serve as labels, as well as label information B1 related to T1 and label information B2 related to T2 from the first information; the first node further determines sample information A1 related to T1 and sample information A2 related to T2 from other received information, and establishes an association relationship between the label information B1, B2 and the sample information T1, T2.

[0161] In some embodiments, for a model used for positioning measurement, the sample information of the first terminal may include sample information used for positioning measurement, such as a series of measurement values ​​obtained when performing positioning measurement.

[0162] In some embodiments, the first node can provide the label information together with the associated sample information as training samples to the model to be trained, and the model can learn how to map the input to the correct output, wherein the sample information is the input data we use to train the machine learning model, the label is the actual output value or category associated with each sample information, and the label information represents the expected target predicted by the model.

[0163] It should be noted that the embodiment shown in FIG. 3A can be implemented independently or in combination with at least one other embodiment in the present disclosure. The specific selection can be made as needed and the present disclosure does not limit it.

[0164] In some embodiments, the first node is a base station, the second node is a terminal, and the terminal is a first terminal that can be used for model training; the base station can receive first information from the terminal, and the first information can be used to indicate label information related to the terminal; the base station can perform model training on the model to be trained based on the label information of the terminal; wherein the first information can be included in a radio resource control (RRC) message sent by the terminal to the base station.

[0165] In some embodiments, the first node is a base station and the second node is an AMF; the base station can receive first information from the AMF, and the first information can be used to indicate label information related to at least one first terminal, and the first information can be used to indicate label information related to at least one first terminal; the base station can perform model training on the to-be-trained model based on the label information related to at least one first terminal; wherein the first information can be included in a Next Generation Application Protocol (NGAP) message sent by the AMF to the base station.

[0166] In some embodiments, the first node is a base station and the second node is an LMF; based on the fact that first information can be received from the LMF, the first information is used to indicate label information related to at least one first terminal, and the first information can be used to indicate label information related to at least one first terminal; the base station can perform model training on the to-be-trained model based on the label information related to the at least one first terminal; wherein the first information can be included in a New Radio Positioning Protocol A (NRPPa) message sent by the LMF to the base station.

[0167] Based on the above embodiment, the first node can determine at least one label and label information that can be used for model training based on the first information received from the second node, and then use the label information and the associated sample information as training samples to perform model training on the model to be trained. It can be seen that the present application can quickly and accurately identify relevant information that can be used for model training from the received information in real time and generate corresponding training samples, which helps to achieve model training of the model to be trained, especially online model training.

[0168] In some embodiments, in step S302, the first node may label sample information related to the first terminal based on the label information; and perform model training on a to-be-trained model based on the label information and the sample information.

[0169] In some embodiments, after determining at least one first terminal and label information associated with each first terminal based on the first information, the first node may further determine sample information associated with each first terminal that corresponds to the label information associated with each first terminal from other received information; the associated sample information is then annotated with the label information associated with each first terminal to generate training samples, and a model to be trained may be trained based on the training samples. For example, the sample information may be input as input data into the model to be trained, and the obtained output data may be compared with the label information to calculate the loss to appropriately adjust the parameters of the model to be trained.

[0170] In some embodiments, labeling the sample information related to the first terminal based on the label information includes: the first node determines the sample information related to the first terminal labeled by the label information based on a matching condition; and labeling the sample information based on the label information.

[0171] In some embodiments, the matching condition can be set according to actual needs and may include at least one of the following: the first timestamp for generating the tag information matches the second timestamp for generating the sample information; the time difference between the first moment when the first node receives the tag information and the second moment when the sample information is received is less than a preset duration threshold; the tag information and the sample information are associated with the same first identifier.

[0172] In some embodiments, the first information may include at least one of the following: a terminal identifier (UE ID) of the first terminal; a terminal type of the first terminal; tag information related to the first terminal; sample information related to the first terminal; a first identifier associated with the tag information and the sample information; location information of the first terminal; speed information of the first terminal; a first timestamp, the first timestamp being used to indicate the moment when the tag information is generated; and the validity period of the tag information.

[0173] The terminal type of the first terminal may include at least one of a positioning reference unit PRU, a non-PRU, a fixed terminal (fixed UE) and a mobile terminal (mobile UE), but is not limited thereto.

[0174] The first identifier associated with the tag information and sample information may also be referred to as a measurement ID, and is used to indicate that the tag information and sample information originate from a measurement process corresponding to the measurement ID, such as an SRS-based positioning measurement process. The first identifier may be used to determine the association between the tag information and the sample information.

[0175] The location information of the first terminal may be used to indicate the geographic location coordinates of the first terminal, etc.

[0176] The speed information of the first terminal may include information such as the moving speed and moving direction of the first terminal.

[0177] The validity period of the tag information can be used to indicate that the tag information remains unchanged during the validity period. Accordingly, the validity period can also be used to indicate the validity period of the sample information.

[0178] Based on the first information as described above, the first node can determine the label information related to each first terminal in at least one first terminal that can be used as a label for model training, and determine the association between the label information and the sample information to generate training samples, so that model training of the model to be trained can be implemented based on the training samples.

[0179] The label information and sample information can be determined based on the role of the model to be trained. For example, the model to be trained can be a model for adding channel state information (CSI), a model for beam management, or a model for positioning measurement. For simplicity, the model used for positioning measurement is used as an example in this specification.

[0180] In some embodiments, the model to be trained is a model for positioning measurement, and the model training includes model training for positioning measurement; accordingly, the label information is label information related to the positioning measurement, and the sample information is sample information related to the positioning measurement. For example, the positioning measurement may include an SRS-based positioning measurement, and the sample information may include a measurement value obtained during the SRS-based positioning measurement process, and the label information may include measurement result information calculated by the second node based on the SRS configuration, the location information of the first terminal, and the location information of the first node.

[0181] In some embodiments, the label information may include at least one of the following: location information of the first terminal; an identifier of the first node; a receive-transmit time difference (RxTxTimeDiff); an uplink sounding reference signal reference signal received power (UL-SRS-RSRP); an uplink angle of arrival (UL-AoA); an uplink time offset of arrival (UL-RTOA); multiple uplink angles of arrival (Multiple UL-AoA); an uplink sounding reference signal reference signal received power preprocessing (UL SRS-RSRPP); direct line of sight (LoS) information, used to indicate whether the uplink measurement is direct line of sight LoS; and non-line of sight (NLoS) information, used to indicate whether the uplink measurement is non-line of sight NLoS.

[0182] It can be seen that the first node can obtain the label and label information related to the positioning measurement from the second node, and mark the sample information used for the positioning measurement based on the label information used for the positioning measurement to generate a training sample for the positioning measurement, thereby facilitating the model training of the model to be trained based on the training sample, so as to use the trained model to assist in obtaining the positioning measurement result.

[0183] In some embodiments, the first node may include at least one transmission and reception point (TRP). Accordingly, the tag information may include tag information related to at least one transmission and reception point (TRP), for example, an information list composed of tag information related to multiple TRPs. The tag information related to the TRP may be calculated by the second node based on the configuration of the SRS, the location information of the first terminal, and the location information of the TRP.

[0184] In some embodiments, the label information related to TRP may include at least one of the following: location information of the first terminal; identification of the first node; identification of the transmitting and receiving point TRP; receive-transmit time difference RxTxTimeDiff; reference signal received power of the uplink sounding reference signal UL-SRS-RSRP; uplink angle of arrival UL-AoA; uplink arrival time offset UL-RTOA; multiple uplink angles of arrival Multiple UL-AoA; reference signal received power preprocessing of the uplink sounding reference signal UL SRS-RSRPP; direct propagation LoS information, used to indicate whether the uplink measurement is direct propagation LoS; non-direct propagation NLoS information, used to indicate whether the uplink measurement is non-direct propagation NLoS.

[0185] It can be seen that by obtaining label information related to multiple TRPs, sample information related to each TRP can be annotated to generate training samples for model training, so that model training of the model to be trained can be achieved based on the training samples.

[0186] In some embodiments, as shown in a schematic flowchart of a model training method in FIG3B , the model training method includes the following steps.

[0187] In step S311, the first node sends a first request to the second node, where the first request is used to request the second node to obtain label information for model training.

[0188] In some embodiments, the first request may include at least one of the following: the terminal identification of the first terminal; the terminal number of the first terminal; the purpose of the first information; the location information of the first terminal; the speed information of the first terminal; the TRP information related to the tag information; the type of information contained in the tag information; the generation time of the tag information; the generation time of the first information.

[0189] The purpose of the first information may also be considered as instructing the first node to send the first request to the second node, and may include, for example, model training for positioning measurement.

[0190] The TRP information related to the tag information is one or more TRP information, and each TRP information may include at least one of the following: TRP identification; TRP type; TRP location information, etc.

[0191] The information type included in the tag information may include at least one type of the above tag information, for example: RxTxTimeDiff, UL-SRS-RSRP, UL-AoA, UL-RTOA, Multiple UL-AoA, SRS-RSRPP, etc.

[0192] In some embodiments, after receiving the first request, the second node may determine the first information to be sent to the first node based on the first request.

[0193] In step S312, the first node receives first information from the second node, where the first information is used to indicate label information related to the first terminal for model training.

[0194] In step S313, the first node performs model training on the model to be trained based on the label information.

[0195] Among them, steps S312-S313 can implement the method embodiment shown above in steps S301-S302 in Figure 3A, and the repeated parts are not repeated here.

[0196] In some embodiments, the first node is a base station and the second node is a terminal; the base station can send a first request to the terminal to request first information; the base station can receive first information from the terminal, and the first information can be used to indicate label information related to the terminal; the base station can perform model training on the to-be-trained model based on the label information of the terminal; wherein the first request can be included in an RRC message sent by the base station to the terminal, and the first information can be included in an RRC message sent by the terminal to the base station.

[0197] In some embodiments, the first node is a base station and the second node is an AMF; the base station can send a first request to the AMF to request first information; the base station can receive first information from the AMF, and the first information can be used to indicate label information related to at least one first terminal; the base station can perform model training on the to-be-trained model based on the label information related to at least one first terminal; wherein the first request can be included in an NGAP message sent by the base station to the AMF; the first information can be included in an NGAP message sent by the AMF to the base station.

[0198] In some embodiments, the first node is a base station and the second node is an LMF; the base station can send a first request to the LMF to request first information; the base station can receive first information from the LMF, the first information is used to indicate label information related to at least one first terminal, and the first information can be used to indicate label information related to at least one first terminal; the base station can perform model training on the to-be-trained model based on the label information related to at least one first terminal; wherein the first request can be included in the NRPPa message sent by the base station to the LMF, and the first information can be included in the NRPPa message sent by the LMF to the base station.

[0199] Based on the above embodiment, the first node can request the required first information from the second node by sending a first request to the second node, so that the second node can send the first information based on the needs of the first node, so that the first node can determine the label information that can be used for model training based on the first information to realize model training of the model to be trained.

[0200] In some embodiments, the first terminal that can be used as a label for model training can be determined by the first node, or the first terminal that can be used as a label for model training can be determined by the second node.

[0201] In some embodiments, before sending a first request to a second node, a first node may first determine at least one first terminal that can serve as a label for model training, and then send the first request to the second node for the at least one first terminal. For example, the first request may include a terminal identifier for the at least one first terminal.

[0202] In some embodiments, FIG3C shows a schematic flow chart of a model training method, wherein the model training method includes the following steps.

[0203] In step S321, the first node receives second information related to the second terminal from the second node or the third node, where the second information is used to indicate whether the second terminal is authorized and / or consents to serve as the first terminal.

[0204] Among them, the second terminal can be any terminal connected to the current communication network. For example, when the second node or the third node detects that a new terminal has connected to the current communication network, it can send second information corresponding to the new terminal to the first node. The second information is used to indicate whether the new terminal is authorized and / or agreed to be used as a label for model training, that is, the first terminal.

[0205] In some embodiments, the third node may be a communication device in a terminal, AMF or LMF that is different from the second node.

[0206] In some embodiments, if the second node is a terminal or LMF, the third node is an AMF.

[0207] In some embodiments, the second information may include at least one of the following: indication information indicating whether the second terminal is authorized to be used for the model training, such as label authorized information; indication information indicating whether the second terminal is agreed to be used for the model training, such as label consent information; and positioning information associated with the second terminal.

[0208] In some embodiments, the location information includes an identifier of a location management function LMF associated with the second terminal.

[0209] In some embodiments, the second information can be carried by a protocol message used for signaling transmission in the 5G core network, such as an NGAP message, and the NGAP message includes but is not limited to: an initial UE context request message, a UE context modification request message, a path switching confirmation message, a switching request message, etc.

[0210] In step S322, the first node determines whether to use the second terminal as the first terminal based on the second information.

[0211] In some embodiments, the first node may determine, based on the second information, the second terminal authorized or agreed to be used for model training as the first terminal that can serve as a label for the model to be trained.

[0212] In step S323, the first node sends a first request for the at least one first terminal to the second node, where the first request is used to request the second node to obtain label information for model training, so that the second node can determine the first information to be sent to the first node based on the first request.

[0213] In some embodiments, after receiving the first request for the at least one first terminal, the second node may send first information related to the first terminal to the first node.

[0214] In some embodiments, the first request may be carried by an NRPPa message, and the NRPPa message may include but is not limited to a data collection request message.

[0215] In step S324, the first node receives first information from the second node, where the first information is used to indicate label information related to the first terminal for model training.

[0216] In step S325 , the first node performs model training on the model to be trained based on the label information.

[0217] Among them, steps S323-S325 can implement the method embodiment shown above in steps S311-S313 in Figure 3B, and the repeated parts are not repeated here.

[0218] For example, the second node sends the second information of the second terminals T11, T12, T13, and T14 to the first node, wherein the second information of T11 and T13 includes an indication of authorization for model training; the first node can determine T11 and T13 as the first terminal based on the second information; the first node sends a first request to the second node, and the first request includes the terminal identification of T11 and T13; after receiving the first request, if the second node obtains the label information of T11, it can send the first information related to T11 to the first node; the first node determines the label information related to T11 based on the first information related to T11, and uses the label information related to T11 to mark the sample information related to T11, and generates training samples related to T11; the first node uses the training samples related to T11 to train the model to be trained.

[0219] In some embodiments, the first node is a base station, the second node is a terminal, and the third node is an AMF; the base station can receive second information from the AMF, and the second information is used to indicate whether the terminal is authorized and / or agrees to serve as the first terminal; the base station determines that the terminal can serve as the first terminal based on the second information; the base station can send a first request to the terminal to request tag information related to the terminal; the base station can receive first information from the terminal, and the first information can be used to indicate tag information related to the terminal; the base station can perform model training on the to-be-trained model based on the tag information of the terminal; wherein the second information can be included in the NGAP message sent by the AMF to the base station, the first request can be included in the RRC message sent by the base station to the terminal, and the first information can be included in the RRC message sent by the terminal to the base station.

[0220] In some embodiments, the first node is a base station and the second node is an AMF; the base station can receive second information from the AMF, and the second information is used to indicate whether at least one second terminal is authorized and / or agreed to be a first terminal; the base station selects at least one first terminal from at least one second terminal based on the second information; the base station can send a first request to the AMF to request tag information related to the selected at least one first terminal; the base station can receive first information from the AMF, and the first information can be used to indicate tag information related to at least one first terminal; the base station can perform model training on the to-be-trained model based on the tag information related to at least one first terminal; wherein the second information can be included in an NGAP message sent by the AMF to the base station, the first request can be included in an NGAP message related to the UE sent by the base station to the AMF; the first information can be included in an NGAP message sent by the AMF to the base station.

[0221] In some embodiments, the first node is a base station, the second node is an LMF, and the third node is an AMF; the base station can receive second information from the AMF, and the second information is used to indicate whether at least one second terminal is authorized and / or agreed to be a first terminal; the base station selects at least one first terminal from at least one second terminal based on the second information; the base station can send a first request to the LMF to request tag information related to the selected at least one first terminal; the base station can receive first information from the LMF, and the first information is used to indicate tag information related to at least one first terminal, and the first information can be used to indicate tag information related to at least one first terminal; the base station can perform model training on the to-be-trained model based on the tag information related to at least one first terminal; wherein the second information can be included in the NGAP message sent by the AMF to the base station, the first request can be included in the NRPPa message related to the UE sent by the base station to the LMF, and the first information can be included in the NRPPa message sent by the LMF to the base station.

[0222] Based on the above embodiment, the first node can first determine at least one first terminal according to actual needs, and then send a first request for at least one first terminal to the second node, thereby helping the second node to send first information related to the first terminal that better meets the needs of the first node to the first node, and facilitating the first node to perform model training on the model to be trained based on the obtained first information.

[0223] In some embodiments, the first request sent by the first node to the second node may be a first request not directed to a specific first terminal, that is, the first request is included in a non-UE-related message. In this case, the first request may include relevant screening conditions for determining the first terminal, such as requirements for the terminal type and number of terminals; requirements for the location and speed information of the terminal; and requirements for the type of information of the tag information to be sent. After receiving the first request, the second node may determine at least one first terminal that can be used as a tag for model training based on the screening conditions in the first request, and send first information related to the at least one first terminal to the first node.

[0224] In some embodiments, the first node is a base station and the second node is a terminal; the base station can send a first request to the terminal to request first information; the base station can receive first information from the terminal, and the first information can be used to indicate label information related to the terminal; the base station can perform model training on the to-be-trained model based on the label information of the terminal; wherein the first request can be included in an RRC message sent by the base station to the terminal, and the first information can be included in an RRC message sent by the terminal to the base station.

[0225] In some embodiments, the first node is a base station and the second node is an AMF; the base station can send a first request to the AMF to request first information; the base station can receive first information from the AMF, and the first information can be used to indicate label information related to at least one first terminal; the base station can perform model training on the to-be-trained model based on the label information related to at least one first terminal; wherein the first request can be included in a non-UE-related NGAP message sent by the base station to the AMF; the first information can be included in an NGAP message sent by the AMF to the base station.

[0226] In some embodiments, the first node is a base station and the second node is an LMF; the base station can send a first request to the LMF to request first information; the base station can receive first information from the LMF, the first information is used to indicate label information related to at least one first terminal, and the first information can be used to indicate label information related to at least one first terminal; the base station can perform model training on the to-be-trained model based on at least one first terminal-related label information; wherein the first request can be included in a non-UE-related NRPPa message sent by the base station to the LMF, and the first information can be included in an NRPPa message sent by the LMF to the base station.

[0227] Based on the above embodiment, when the first node is unable to determine the first terminal, it can also send the screening conditions for the first terminal to the second node through the first request, and the second node determines at least one first terminal according to the needs of the first node and sends the relevant first information, so that the first node obtains the label information related to the first terminal that meets the screening conditions, which helps the first node to perform model training on the model to be trained based on the obtained first information.

[0228] Figure 3D shows a process interaction diagram of a model training method. The model training method uses the base station gNB as the first node, the LMF as the second node, and the AMF as the third node, as shown in Figure 3D, and includes the following steps.

[0229] S331 and terminal T31 access the communication network through the base station gNB, such as the 5G core network 5gc.

[0230] S332: The AMF sends a first message carrying second information to the gNB. The second information may be represented as label context info. The second information may be used to indicate information related to the terminal T31 and the label, that is, to indicate whether the terminal T31 authorizes and / or agrees to use the label as a label for model training.

[0231] In some embodiments, the label context information label context info may be included in the terminal context UE context.

[0232] In some embodiments, the first message may adopt a protocol message used for signaling transmission in the 5G core network, such as an NGAP message. The NGAP message may include but is not limited to: an initial UE context request message, a UE context modification request message, a path switching confirmation message, a switching request message, etc.

[0233] In some embodiments, the second information may include at least one of the following information: label authorized information, used to indicate whether the terminal is authorized as a label for positioning AI model training; label consent information, used to indicate whether the terminal agrees to be used as a label for positioning AI model training; LMF information associated with the terminal label, used to indicate the LMF identifier associated with the terminal.

[0234] S333. When the base station gNB needs to perform model training on the model to be trained, the base station may select the terminal T31 as a label for positioning AI model training according to the second information, that is, determine the terminal T31 as the first terminal.

[0235] S334. The base station gNB sends a second message carrying a first request to the LMF. The first request can be expressed as a label information request label info request, which is used to request the first information.

[0236] In some embodiments, the first request may be a first request for a specific terminal T31. In this case, the second message may be a terminal-related NRPPa message, which may include but is not limited to a data collection request message.

[0237] S335. LMF sends a third message carrying first information to the base station gNB based on the received first request, where the first information can be expressed as label info.

[0238] The base station gNB can perform positioning AI model training based on the received first information, that is, perform model training on the model to be trained.

[0239] In some embodiments, the third message may be an NRPPa message, which may include but is not limited to a data collection request feedback data collection response message and a measurement request measurement request message.

[0240] FIG3E shows a schematic diagram of a process interaction of a model training method. The difference between FIG3E and FIG3D is that the model training method uses terminal T31 as the second node, as shown in FIG3E , and includes the following steps.

[0241] In step S344, the base station gNB may send a second message carrying the first request to the terminal T31. The second message may be a radio resource control (RRC) message, including but not limited to: an RRC reconfiguration message and a UE information request message.

[0242] In step S345, terminal T31 may send a third message carrying the first information to the base station gNB based on the received first request. The third message may be an RRC message, including but not limited to a UE assistance information message and a UE information feedback message. The first information may be used to indicate tag information related to terminal T31.

[0243] The other steps in FIG. 3E are the same as those in FIG. 3D , and the same parts are not repeated here.

[0244] FIG3F shows a schematic diagram of the process interaction of a model training method. The difference between FIG3F and FIG3D in the model training method is that AMF is used as the second node and there is no third node.

[0245] In step S354, the base station gNB may send a second message carrying the first request to the AMF. The second message may be an NGAP message, including but not limited to a data collection request message.

[0246] In some embodiments, after receiving the first request, the AMF may initiate location services (LCS) for the terminal T31 to the LMF according to the first request to obtain tag information related to the T31.

[0247] In step S355, the AMF may send a third message carrying the first information to the base station gNB, where the third message may be an NGAP message, including but not limited to a data collection feedback data collection response message.

[0248] The other steps in FIG. 3F are the same as those in FIG. 3D , and the same parts are not repeated here.

[0249] Figure 3G shows a process interaction diagram of a model training method. The model training method uses the base station gNB as the first node and the LMF as the second node. The difference between Figure 3G and Figure 3D is that in the technical solution of Figure 3D, the first node determines the first terminal that can be used as a label for model training, and in the technical solution of Figure 3G, the second node determines the first terminal that can be used as a label for model training. As shown in Figure 3G, the following steps are included.

[0250] S361. The base station gNB sends a fourth message carrying a first request (such as a label info request) to the LMF; the first request is used to request first information (such as label info).

[0251] In some embodiments, the label may be a PRU with known location information.

[0252] S362. LMF selects at least one suitable first terminal as a label for model training based on the first request, and determines the location information of each first terminal.

[0253] In some embodiments, the first terminal may be a PRU with known location information.

[0254] In some embodiments, the fourth message may be a non-UE related NRPPa message, including but not limited to: a data collection request message.

[0255] S363. Optionally, the LMF may perform a positioning related procedure on the first terminal selected as the tag to obtain tag information related to the first terminal.

[0256] S364. The LMF sends a fifth message carrying first information to the base station gNB, where the first information is used to indicate label information, so that the base station gNB performs AI training based on the label information, that is, model training for the model to be trained.

[0257] In some embodiments, the fifth message may adopt UE-related signaling, such as a UE-related NRPPa message, and the specific content is the same as that of the above step S335.

[0258] In some embodiments, the fifth message may adopt non-UE related signaling, such as a non-UE related NRPPa message, and the NRPPa message may include but is not limited to a data collection request feedback data collection response message and a measurement request measurement request message.

[0259] In some embodiments, the fifth message carrying the first information may include one or more positioning measurement results and label information corresponding to each positioning measurement result, so that the base station gNB performs model training for the model to be trained based on the one or more positioning measurement results and the label information corresponding to each positioning measurement result.

[0260] Among them, step S364 can occur during the execution of step S363 or be executed separately.

[0261] The embodiments of the present disclosure provide a model training method. Figure 4 is a schematic flow chart of a model training method according to an embodiment of the present disclosure. The model training method shown in this embodiment can be executed by a network device.

[0262] As shown in FIG4 , the model training method may include the following steps:

[0263] In step S401, the second node sends first information to the first node, where the first information is used to indicate label information related to the first terminal for model training.

[0264] In some embodiments, the second node can send first information to the first node so that the first node can determine label information related to labels used for model training from the first information, and perform model training on the model to be trained deployed on the first node based on the label information.

[0265] In some embodiments, the tag may include a first terminal that can be used to perform model training on the model to be trained, as well as other communication devices.

[0266] In some embodiments, the second node can send the first information to the second node so that the first node can determine at least one first terminal that can be used as a label for model training based on the first information, as well as label information related to each first terminal, and perform model training on the model to be trained based on the label information.

[0267] In some embodiments, the first node may be a communication device deployed with a model to be trained and / or a communication device that performs model training on the model to be trained. The first node may be a base station gNB, etc.

[0268] The label information can be set according to the output data of the model to be trained. In some embodiments, for a model used for positioning measurement, the label information may include relevant label information for positioning measurement, for example, it may include the location information of the first terminal, or label information obtained based on measurements such as the location of the first terminal, the location of the first node, and the configuration of the sounding reference signal SRS.

[0269] In some embodiments, after determining the label and label information based on the first information, the first node may perform model training on the to-be-trained model based on the label information.

[0270] In some embodiments, the first node may determine the sample information corresponding to the label information from other received information, and establish an association relationship between the label information and the sample information.

[0271] In some embodiments, after determining at least one first terminal and label information related to each first terminal based on the first information, the first node can further determine, from other received information, sample information related to each first terminal that can correspond to the label information related to each first terminal, and establish an association relationship between the label information related to each first terminal and the sample information.

[0272] In some embodiments, for a model used for positioning measurement, the sample information of the first terminal may include sample information used for positioning measurement, such as a series of measurement values ​​obtained when performing positioning measurement.

[0273] In some embodiments, the first node can provide the label information together with the associated sample information as training samples to the model to be trained, and the model can learn how to map the input to the correct output, wherein the sample information is the input data we use to train the machine learning model, the label is the actual output value or category associated with each sample information, and the label information represents the expected target predicted by the model.

[0274] It should be noted that the embodiment shown in FIG. 4 can be implemented independently or in combination with at least one other embodiment in the present disclosure. The specific selection can be made as needed and the present disclosure does not limit it.

[0275] Based on the above embodiment, the second node can send the first information to the first node to indicate at least one label and label information that can be used for model training, and then use the label information and the associated sample information as training samples to train the model to be trained. It can be seen that the present application can quickly and accurately identify relevant information that can be used for model training from the received information in real time and generate corresponding training samples, which helps to achieve model training of the model to be trained, especially online model training.

[0276] In some embodiments, the first node may label the sample information related to the first terminal based on the label information; and perform model training on the to-be-trained model based on the label information and the sample information.

[0277] In some embodiments, after determining at least one first terminal and label information associated with each first terminal based on the first information, the first node may further determine sample information associated with each first terminal that corresponds to the label information associated with each first terminal from other received information; the associated sample information is then annotated with the label information associated with each first terminal to generate training samples, and a model to be trained may be trained based on the training samples. For example, the sample information may be input as input data into the model to be trained, and the obtained output data may be compared with the label information to calculate the loss to appropriately adjust the parameters of the model to be trained.

[0278] In some embodiments, labeling the sample information related to the first terminal based on the label information includes: the first node determines the sample information related to the first terminal labeled by the label information based on a matching condition; and labeling the sample information based on the label information.

[0279] In some embodiments, the matching condition can be set according to actual needs and may include at least one of the following: the first timestamp for generating the tag information matches the second timestamp for generating the sample information; the time difference between the first moment when the first node receives the tag information and the second moment when the sample information is received is less than a preset duration threshold; the tag information and the sample information are associated with the same first identifier.

[0280] In some embodiments, the first information may include at least one of the following: a terminal identifier (UE ID) of the first terminal; a terminal type of the first terminal; tag information related to the first terminal; sample information related to the first terminal; a first identifier associated with the tag information and the sample information; location information of the first terminal; speed information of the first terminal; a first timestamp, the first timestamp being used to indicate the moment when the tag information is generated; and the validity period of the tag information.

[0281] The terminal type of the first terminal may include at least one of a positioning reference unit PRU, a non-PRU, a fixed terminal (fixed UE) and a mobile terminal (mobile UE), but is not limited thereto.

[0282] The first identifier associated with the tag information and sample information may also be called a measurement ID, which is used to indicate that the tag information and sample information originate from a measurement process corresponding to the measurement ID. The first identifier may be used to determine the association relationship between the tag information and the sample information.

[0283] The location information of the first terminal may be used to indicate the geographic location coordinates of the first terminal, etc.

[0284] The speed information of the first terminal may include information such as the moving speed and moving direction of the first terminal.

[0285] The validity period of the tag information can be used to indicate that the tag information remains unchanged during the validity period. Accordingly, the validity period can also be used to indicate the validity period of the sample information.

[0286] Based on the first information as described above, the first node can determine the label information related to each first terminal in at least one first terminal that can be used as a label for model training, and determine the association between the label information and the sample information to generate training samples, so that model training of the model to be trained can be implemented based on the training samples.

[0287] In some embodiments, the model to be trained includes a model for positioning measurement, and the model training includes model training for positioning measurement; accordingly, the label information includes label information related to the positioning measurement; and the sample information includes measurement values ​​related to the positioning measurement. For example, the positioning measurement may include an SRS-based positioning measurement, and the sample information may include measurement values ​​obtained during the SRS-based positioning measurement process, and the label information may include measurement result information calculated by the second node based on the SRS configuration, the location information of the first terminal, and the location information of the first node.

[0288] In some embodiments, the label information may include at least one of the following: location information of the first terminal; identification of the first node; RxTxTimeDiff; UL-SRS-RSRP; UL-AoA; UL-RTOA); Multiple UL-AoA; UL SRS-RSRPP; LoS information, used to indicate whether the uplink measurement is direct propagation LoS; NLoS information, used to indicate whether the uplink measurement is non-direct propagation NLoS.

[0289] It can be seen that the second node sends the first information indicating the label and label information related to the positioning measurement to the first node, and labels the sample information used for the positioning measurement based on the label information used for the positioning measurement to generate a training sample for the positioning measurement, thereby facilitating the model training of the model to be trained based on the training sample, so as to use the trained model to assist in obtaining the positioning measurement result.

[0290] In some embodiments, the tag information includes tag information associated with at least one transmitting and receiving point TRP. Accordingly, the tag information may include tag information associated with at least one transmitting and receiving point TRP, for example, an information list composed of a plurality of TRP-related tag information. The tag information associated with the TRP may be calculated by the second node based on the configuration of the SRS, the location information of the first terminal, and the location information of the TRP.

[0291] In some embodiments, the label information related to TRP may include at least one of the following: location information of the first terminal; identification of the first node; identification of the transmitting and receiving point TRP; receive-transmit time difference RxTxTimeDiff; reference signal received power of the uplink sounding reference signal UL-SRS-RSRP; uplink angle of arrival UL-AoA; uplink arrival time offset UL-RTOA; multiple uplink angles of arrival Multiple UL-AoA; reference signal received power preprocessing of the uplink sounding reference signal UL SRS-RSRPP; direct propagation LoS information, used to indicate whether the uplink measurement is direct propagation LoS; non-direct propagation NLoS information, used to indicate whether the uplink measurement is non-direct propagation NLoS.

[0292] It can be seen that by obtaining label information related to multiple TRPs, sample information related to each TRP can be annotated to generate training samples for model training, so that model training of the model to be trained can be achieved based on the training samples.

[0293] In some embodiments, before sending the first information to the first node, the method further includes: the second node receiving a first request from the first node, where the first request is used to request label information for model training.

[0294] In some embodiments, the first request may include at least one of the following: the terminal identification of the first terminal; the terminal number of the first terminal; the purpose of the first information; the location information of the first terminal; the speed information of the first terminal; the TRP information related to the tag information; the type of information contained in the tag information; the generation time of the tag information; the generation time of the first information.

[0295] The purpose of the first information may also be considered as instructing the first node to send the first request to the second node, and may include, for example, model training for positioning measurement.

[0296] The TRP information related to the tag information is one or more TRP information, and each TRP information may include at least one of the following: TRP identification; TRP type; TRP location information, etc.

[0297] The information type included in the tag information may include at least one type of the above tag information, for example: RxTxTimeDiff, UL-SRS-RSRP, UL-AoA, UL-RTOA, Multiple UL-AoA, SRS-RSRPP, etc.

[0298] Based on the above embodiment, the second node can determine the needs of the first node based on the first request sent by the first node, and send first information based on the needs of the first node, so that the first node can determine the label information that can be used for model training based on the first information to realize model training of the model to be trained.

[0299] In some embodiments, the first terminal that can be used as a label for model training can be determined by the first node, or the first terminal that can be used as a label for model training can be determined by the second node.

[0300] In some embodiments, the second node may receive a first request for the first terminal from the first node. For example, the first request may include a terminal identifier of the at least one first terminal.

[0301] In some embodiments, before receiving the first request for the first terminal from the first node, the method also includes: the second node sending second information related to the second terminal to the first node, the second information being used to indicate whether the second terminal is authorized and / or agreed to serve as the first terminal.

[0302] The second terminal can be any terminal connected to the current communication network. For example, when the second node detects that a new terminal has connected to the current communication network, it can send second information corresponding to the new terminal to the first node. The second information is used to indicate whether the new terminal is authorized and / or agreed to be the first terminal.

[0303] In some embodiments, the second information includes at least one of the following: indication information indicating whether the second terminal is authorized to be used for the model training; indication information indicating whether the second terminal is agreed to be used for the model training; and positioning information associated with the second terminal.

[0304] In some embodiments, the location information includes an identifier of a location management function LMF associated with the second terminal.

[0305] In some embodiments, the second information can be carried by a protocol message used for signaling transmission in the 5G core network, such as an NGAP message, and the NGAP message includes but is not limited to: an initial UE context request message, a UE context modification request message, a path switching confirmation message, a switching request message, etc.

[0306] In some embodiments, the first node may determine, based on the second information, the second terminal authorized or agreed to be used for model training as at least one first terminal that can serve as a label for the model to be trained.

[0307] In some embodiments, the first request may be carried by an NRPPa message, and the NRPPa message may include but is not limited to a data collection request message.

[0308] In some embodiments, the second node may receive a first request for the at least one first terminal from the first node, where the first request is used to request the second node to obtain label information for model training; the first node may send first information related to the first terminal to the first node.

[0309] Based on the above embodiment, the first node can first determine at least one first terminal according to actual needs, and then send a first request for at least one first terminal to the second node, thereby helping the second node to send first information related to the first terminal that better meets the needs of the first node to the first node, and facilitating the first node to perform model training on the model to be trained based on the obtained first information.

[0310] In some embodiments, after receiving the first request from the first node, the method further comprises:

[0311] The second node may send a second request to the location management function LMF, where the second request is used to request label information related to the first terminal.

[0312] In some embodiments, the names of information, etc. are not limited to the names described in the embodiments, and terms such as "information", "message", "signal", "signaling", "report", "configuration", "indication", "instruction", "command", "channel", "parameter", "domain", "field", "symbol", "symbol", "codeword", "codebook", "codeword", "codepoint", "bit", "data", "program", and "chip" can be used interchangeably.

[0313] In some embodiments, terms such as "moment", "time point", "time", and "time position" can be replaced with each other, and terms such as "duration", "period", "time window", "window", and "time" can be replaced with each other.

[0314] In some embodiments, the terms "component carrier (CC)", "cell", "frequency carrier", "carrier frequency" and the like can be used interchangeably.

[0315] In some embodiments, "obtain", "get", "get", "receive", "transmit", "bidirectional transmission", "send and / or receive" can be interchangeable, and can be interpreted as receiving from other entities, obtaining from protocols, obtaining from higher layers, obtaining by self-processing, autonomous implementation, etc.

[0316] In some embodiments, terms such as "send", "transmit", "report", "download", "transmit", "bidirectional transmission", "send and / or receive" can be used interchangeably.

[0317] Corresponding to the aforementioned embodiments of the model training method, the present disclosure also provides embodiments of a terminal and a network device.

[0318] FIG5 is a schematic block diagram of a model training device according to an embodiment of the present disclosure. As shown in FIG5 , the terminal may be a model training device, and the device includes a processing module 501 and a transceiver module 502 .

[0319] In some embodiments, the transceiver module 502 is used to receive first information from the second node, where the first information is used to indicate label information related to the first terminal used for model training; the processing module 501 is used to perform model training on the model to be trained based on the label information.

[0320] It should be noted that the modules included in the terminal are not limited to the modules described in the above embodiments, and may also include other modules, such as a storage module, a display module, etc.

[0321] In some embodiments, the first information includes at least one of the following: a terminal identifier of the first terminal; a terminal type of the first terminal; tag information related to the first terminal; sample information related to the first terminal; a first identifier associated with the tag information and sample information; location information of the first terminal; speed information of the first terminal; a first timestamp, the first timestamp being used to indicate the moment when the tag information is generated; and the validity period of the tag information.

[0322] In some embodiments, the model to be trained includes a model for positioning measurement, and the model training includes model training for positioning measurement; the label information includes label information related to positioning measurement; and the sample information includes measurement values ​​related to the positioning measurement.

[0323] In some embodiments, the tag information includes tag information associated with at least one transmitting and receiving point TRP.

[0324] In some embodiments, the label information includes at least one of the following: location information of the first terminal; identification of the first node; identification of the transmitting and receiving point TRP; receive-transmit time difference RxTxTimeDiff; reference signal received power of uplink sounding reference signal UL-SRS-RSRP; uplink angle of arrival UL-AoA; uplink arrival time offset UL-RTOA; multiple uplink angles of arrival Multiple UL-AoA; reference signal received power preprocessing of uplink sounding reference signal UL SRS-RSRPP; direct propagation LoS information, used to indicate whether the uplink measurement is direct propagation LoS; non-direct propagation NLoS information, used to indicate whether the uplink measurement is non-direct propagation NLoS.

[0325] In some embodiments, the transceiver module 502 is further used to send a first request to the second node, where the first request is used to request the second node to obtain label information for model training.

[0326] In some embodiments, the first request includes at least one of the following: the terminal identification of the first terminal; the terminal number of the first terminal; the purpose of the first information; the location information of the first terminal; the speed information of the first terminal; the TRP information related to the tag information; the type of information contained in the tag information; the generation time of the tag information; the generation time of the first information.

[0327] In some embodiments, the transceiver module 502 is configured to send a first request for the first terminal to the second node.

[0328] In some embodiments, the transceiver module 502 is used to receive second information related to the second terminal from the second node or the third node, and the second information is used to indicate whether the second terminal is authorized and / or agreed to serve as the first terminal; the processing module 501 is also used to determine whether to use the second terminal as the first terminal based on the second information.

[0329] In some embodiments, the second information includes at least one of the following: indication information indicating whether the second terminal is authorized to be used for the model training; indication information indicating whether the second terminal is agreed to be used for the model training; and positioning information associated with the second terminal.

[0330] In some embodiments, the location information includes an identifier of a location management function LMF associated with the second terminal.

[0331] In some embodiments, the processing module 501 is configured to label sample information related to the first terminal based on the label information; and perform model training on a to-be-trained model based on the label information and the sample information.

[0332] In some embodiments, the processing module 501 is used to determine sample information related to the first terminal marked by the label information based on a matching condition; mark the sample information based on the label information; wherein the matching condition includes at least one of the following: a first timestamp for generating the label information matches a second timestamp for generating the sample information; a time difference between a first moment when the first node receives the label information and a second moment when the sample information is received is less than a preset duration threshold; the label information and the sample information are associated with the same first identifier.

[0333] In some embodiments, the first node is a base station; the second node is a terminal, an access and mobility management function AMF or a location management function LMF.

[0334] FIG6 is a schematic block diagram of a model training device according to an embodiment of the present disclosure. As shown in FIG6 , the network device may be a model training device, and the device includes a processing module 601 and a transceiver module 602 .

[0335] In some embodiments, the transceiver module 602 is used to receive first information from the second node, where the first information is used to indicate label information related to the first terminal used for model training; the processing module 601 is used to perform model training on the model to be trained based on the label information.

[0336] In some embodiments, the first information includes at least one of the following: a terminal identifier of the first terminal; a terminal type of the first terminal; tag information related to the first terminal; sample information related to the first terminal, the sample information being marked by the tag information; a first identifier associated with the tag information and the sample information; location information of the first terminal; speed information of the first terminal; a first timestamp, the first timestamp being used to indicate the moment when the tag information is generated; and the validity period of the tag information.

[0337] In some embodiments, the model to be trained includes a model for positioning measurement, and the model training includes model training for positioning measurement; the label information includes label information related to positioning measurement; and the sample information includes measurement values ​​related to the positioning measurement.

[0338] In some embodiments, the tag information includes tag information associated with at least one transmitting and receiving point TRP.

[0339] In some embodiments, the label information includes at least one of the following: location information of the first terminal; identification of the first node; identification of the transmitting and receiving point TRP; receive-transmit time difference RxTxTimeDiff; reference signal received power of uplink sounding reference signal UL-SRS-RSRP; uplink angle of arrival UL-AoA; uplink arrival time offset UL-RTOA; multiple uplink angles of arrival Multiple UL-AoA; reference signal received power preprocessing of uplink sounding reference signal UL SRS-RSRPP; direct propagation LoS information, used to indicate whether the uplink measurement is direct propagation LoS; non-direct propagation NLoS information, used to indicate whether the uplink measurement is non-direct propagation NLoS.

[0340] In some embodiments, the transceiver module 602 is further used to receive a first request from the first node, where the first request is used to request label information for model training.

[0341] In some embodiments, the first request includes at least one of the following: the terminal identification of the first terminal; the terminal number of the first terminal; the purpose of the first information; the location information of the first terminal; the speed information of the first terminal; the TRP information related to the tag information; the type of information contained in the tag information; the generation time of the tag information; the generation time of the first information.

[0342] In some embodiments, the transceiver module 602 is configured to receive a first request for the first terminal from the first node.

[0343] In some embodiments, the transceiver module 602 is further configured to send second information related to the second terminal to the first node, where the second information is configured to indicate whether the second terminal is authorized and / or agrees to serve as the first terminal.

[0344] In some embodiments, the second information includes at least one of the following: indication information indicating whether the second terminal is authorized to be used for the model training; indication information indicating whether the second terminal is agreed to be used for the model training; and positioning information associated with the second terminal.

[0345] In some embodiments, the location information includes an identifier of a location management function LMF associated with the second terminal.

[0346] In some embodiments, the transceiver module 602 is further configured to send a second request to the location management function LMF, where the second request is configured to request tag information related to the first terminal.

[0347] In some embodiments, the first node is a base station; the second node is a terminal, an access and mobility management function AMF or a location management function LMF.

[0348] It should be noted that the modules included in the model training device are not limited to the modules described in the above embodiments, and may also include other modules, such as a storage module, a display module, etc.

[0349] For the device embodiment, since it basically corresponds to the method embodiment, the relevant parts can be referred to the partial description of the method embodiment. The device embodiment described above is merely illustrative, wherein the modules described as separate components may or may not be physically separated, and the components displayed as modules may or may not be physical modules, that is, they may be located in one place, or they may be distributed on multiple network modules. Some or all of the modules can be selected according to actual needs to achieve the purpose of the scheme of this embodiment. Those of ordinary skill in the art can understand and implement it without paying any creative work.

[0350] An embodiment of the present disclosure also proposes a terminal, comprising: one or more processors; a memory coupled to the processor, the memory storing executable instructions, wherein when the executable instructions are executed by the processor, the terminal executes the model training method described in the above embodiment.

[0351] An embodiment of the present disclosure also proposes a network device, comprising: one or more processors; a memory coupled to the processor, wherein the memory stores executable instructions, wherein when the executable instructions are executed by the processor, the network device executes the model training method described in the above embodiment.

[0352] An embodiment of the present disclosure also proposes a communication device, comprising: one or more processors; a memory coupled to the processor, wherein the memory stores executable instructions, wherein when the executable instructions are executed by the processor, the processor calls the executable instructions so that the communication device executes the model training method described in the above optional embodiment.

[0353] An embodiment of the present disclosure also proposes a communication system, including a first node and a second node, wherein the first node is configured to implement the model training method described in the above optional embodiment, and the second node is configured to implement the model training method described in the above optional embodiment.

[0354] An embodiment of the present disclosure further proposes a storage medium storing instructions, which, when executed on a communication device, enables the communication device to execute the model training method described in the above optional embodiment.

[0355] The embodiments of the present disclosure further provide an apparatus for implementing any of the above methods. For example, an apparatus is provided, comprising units or modules for implementing each step performed by a terminal in any of the above methods. For another example, another apparatus is provided, comprising units or modules for implementing each step performed by a network device (e.g., an access network device, a core network function node, a core network device, etc.) in any of the above methods.

[0356] It should be understood that the division of the various units or modules in the above device is merely a division of logical functions. In actual implementation, they may be fully or partially integrated into a physical entity, or they may be physically separated. In addition, the units or modules in the device may be implemented in the form of a processor calling software: for example, the device includes a processor, the processor is connected to a memory, and the memory stores instructions. The processor calls the instructions stored in the memory to implement any of the above methods or implement the functions of the various units or modules of the above device, wherein the processor is, for example, a general-purpose processor, such as a central processing unit (CPU) or a microprocessor, and the memory is a memory within the device or a memory outside the device. Alternatively, the units or modules in the device can be implemented in the form of hardware circuits, and the functions of some or all of the units or modules can be realized by designing the hardware circuits. The above-mentioned hardware circuits can be understood as one or more processors; for example, in one implementation, the above-mentioned hardware circuit is an application-specific integrated circuit (ASIC), which realizes the functions of some or all of the above units or modules by designing the logical relationship of the components in the circuit; for example, in another implementation, the above-mentioned hardware circuit can be realized by a programmable logic device (PLD). Taking a field programmable gate array (FPGA) as an example, it can include a large number of logic gate circuits, and the connection relationship between the logic gate circuits is configured by configuring the configuration file, thereby realizing the functions of some or all of the above units or modules. All units or modules of the above devices can be realized in the form of software called by the processor, or in the form of hardware circuits, or in part by the form of software called by the processor, and the rest by hardware circuits.

[0357] In the embodiments of the present disclosure, the processor is a circuit with signal processing capabilities. In one implementation, the processor can be a circuit with instruction reading and execution capabilities, such as a central processing unit (CPU), a microprocessor, a graphics processing unit (GPU) (which can be understood as a microprocessor), or a digital signal processor (DSP). In another implementation, the processor can implement certain functions through the logical relationship of the hardware circuit. The logical relationship of the above-mentioned hardware circuit is fixed or reconfigurable. For example, the processor is a hardware circuit implemented by an application-specific integrated circuit (ASIC) or a programmable logic device (PLD), such as an FPGA. In a reconfigurable hardware circuit, the process of the processor loading a configuration document and implementing the hardware circuit configuration can be understood as the process of the processor loading instructions to implement the functions of some or all of the above units or modules. In addition, it can also be a hardware circuit designed for artificial intelligence, which can be understood as an ASIC, such as a neural network processing unit (NPU), a tensor processing unit (TPU), a deep learning processing unit (DPU), etc.

[0358] Figure 7 is a schematic diagram of the structure of a communication device 7100 proposed in an embodiment of the present disclosure. Communication device 7100 can be a network device (e.g., an access network device, a core network device, etc.), a terminal (e.g., a user equipment, etc.), a chip, a chip system, or a processor that supports a network device to implement any of the above methods, or a chip, a chip system, or a processor that supports a terminal to implement any of the above methods. Communication device 7100 can be used to implement the methods described in the above method embodiments. For details, please refer to the description of the above method embodiments.

[0359] As shown in Figure 7, the communication device 7100 includes one or more processors 7101. The processor 7101 can be a general-purpose processor or a dedicated processor, for example, a baseband processor or a central processing unit. The baseband processor can be used to process communication protocols and communication data, and the central processing unit can be used to control the communication device (such as a base station, a baseband chip, a terminal device, a terminal device chip, a DU or a CU, etc.), execute programs, and process program data. The processor 7101 is used to call instructions to enable the communication device 7100 to perform any of the above methods.

[0360] In some embodiments, the communication device 7100 further includes one or more memories 7102 for storing instructions. Optionally, all or part of the memories 7102 may be located outside the communication device 7100.

[0361] In some embodiments, the communication device 7100 further includes one or more transceivers 7103. When the communication device 7100 includes one or more transceivers 7103, the communication steps such as sending and receiving in the above method are performed by the transceiver 7103, and the other steps are performed by the processor 7101.

[0362] In some embodiments, a transceiver may include a receiver and a transmitter, which may be separate or integrated. Optionally, the terms transceiver, transceiver unit, transceiver, and transceiver circuit may be used interchangeably; the terms transmitter, transmitting unit, transmitter, and transmitting circuit may be used interchangeably; and the terms receiver, receiving unit, receiver, and receiving circuit may be used interchangeably.

[0363] Optionally, the communication device 7100 further includes one or more interface circuits 7104, which are connected to the memory 7102. The interface circuits 7104 may be configured to receive signals from the memory 7102 or other devices, and may be configured to send signals to the memory 7102 or other devices. For example, the interface circuits 7104 may read instructions stored in the memory 7102 and send the instructions to the processor 7101.

[0364] The communication device 7100 described in the above embodiment may be a network device or a terminal, but the scope of the communication device 7100 described in the present disclosure is not limited thereto, and the structure of the communication device 7100 may not be limited by FIG. 7 . The communication device may be an independent device or may be part of a larger device. For example, the communication device may be: 1) an independent integrated circuit IC, or a chip, or a chip system or subsystem; (2) a collection of one or more ICs, optionally, the above IC collection may also include a storage component for storing data or programs; (3) an ASIC, such as a modem; (4) a module that can be embedded in other devices; (5) a receiver, a terminal device, an intelligent terminal device, a cellular phone, a wireless device, a handheld device, a mobile unit, an in-vehicle device, a network device, a cloud device, an artificial intelligence device, etc.; (6) others, etc.

[0365] FIG8 is a schematic diagram of the structure of a chip 8200 according to an embodiment of the present disclosure. If the communication device 7100 can be a chip or a chip system, reference can be made to the schematic diagram of the structure of the chip 8200 shown in FIG8 , but the present disclosure is not limited thereto.

[0366] The chip 8200 includes one or more processors 8201, and the processor 8201 is used to call instructions so that the chip 8200 executes any of the above methods.

[0367] In some embodiments, the chip 8200 further includes one or more interface circuits 8202, which are connected to the memory 8203. The interface circuit 8202 can be used to receive signals from the memory 8203 or other devices, and can be used to send signals to the memory.

[0368] 8203 or other devices to send signals. For example, the interface circuit 8202 can read the instructions stored in the memory 8203 and send the instructions to the processor 8201. Optionally, the terms interface circuit, interface, transceiver pin, transceiver, etc. can be used interchangeably.

[0369] In some embodiments, the chip 8200 further includes one or more memories 8203 for storing instructions. Alternatively, all or part of the memories 8203 may be outside the chip 8200.

[0370] The present disclosure also proposes a storage medium having instructions stored thereon. When the instructions are executed on the communication device 7100, the communication device 7100 executes any of the above methods. Optionally, the storage medium is an electronic storage medium. Optionally, the storage medium is a computer-readable storage medium, but is not limited thereto and may also be a storage medium readable by other devices. Optionally, the storage medium may be a non-transitory storage medium, but is not limited thereto and may also be a temporary storage medium.

[0371] The present disclosure also provides a program product, which, when executed by the communication device 7100, enables the communication device 7100 to perform any of the above methods. Optionally, the program product is a computer program product.

[0372] The present disclosure also proposes a computer program, which, when executed on a computer, causes the computer to perform any one of the above methods.

Claims

1. A model training method, characterized in that: Executed by the first node, the method includes: receiving first information from the second node, where the first information is used to indicate label information related to the first terminal for model training; Model training is performed on the model to be trained based on the label information.

2. The method according to claim 1, characterized in that The first information includes at least one of the following: a terminal identifier of the first terminal; a terminal type of the first terminal; tag information related to the first terminal; Sample information related to the first terminal; a first identifier associated with the label information and the sample information; location information of the first terminal; speed information of the first terminal; a first timestamp, where the first timestamp is used to indicate a time when the tag information is generated; The validity period of the tag information.

3. The method according to claim 2, characterized in that The model to be trained includes a model for positioning measurement; the label information includes label information related to positioning measurement; and the sample information includes measurement values ​​related to the positioning measurement.

4. The method according to any one of claims 1 to 3, characterized in that The tag information includes tag information associated with at least one transmitting and receiving point TRP.

5. The method according to any one of claims 1 to 4, characterized in that: The tag information includes at least one of the following: location information of the first terminal; an identifier of the first node; Identification of the transmitting and receiving points TRP; Receive-send time difference RxTxTimeDiff; Uplink sounding reference signal received power UL-SRS-RSRP; Uplink angle of arrival UL-AoA; Uplink arrival time offset UL-RTOA; Multiple UL-AoA; Uplink sounding reference signal received power preprocessing UL SRS-RSRPP; Direct propagation LoS information, used to indicate whether the uplink measurement is direct propagation LoS; Non-direct propagation NLoS information is used to indicate whether the uplink measurement is non-direct propagation NLoS.

6. The method according to any one of claims 1 to 5, characterized in that: Before receiving the first information from the second node, the method further includes: A first request is sent to the second node, where the first request is used to request the second node to obtain label information for model training.

7. The method according to claim 6, characterized in that The first request includes at least one of the following: a terminal identifier of the first terminal; the terminal quantity of the first terminal; purpose of the first information; location information of the first terminal; speed information of the first terminal; TRP information related to the tag information; The type of information contained in the tag information; The generation time of the tag information; The time when the first information is generated.

8. The method according to claim 6 or 7, characterized in that The sending the first request to the second node includes: A first request for the first terminal is sent to the second node.

9. The method according to claim 8, characterized in that Before sending the first request for the first terminal to the second node, the method further includes: receiving second information related to the second terminal from the second node or the third node, where the second information is used to indicate whether the second terminal is authorized and / or agreed to serve as the first terminal; Based on the second information, it is determined whether to use the second terminal as the first terminal.

10. The method according to claim 9, characterized in that The second information includes at least one of the following: Indication information indicating whether the second terminal is authorized to be used for the model training; Indication information indicating whether to approve the use of the second terminal for the model training; Positioning information associated with the second terminal.

11. The method according to claim 10, characterized in that The positioning information includes an identifier of a positioning management function LMF associated with the second terminal.

12. The method according to any one of claims 1 to 11, characterized in that: The performing model training on the to-be-trained model based on the label information includes: marking sample information related to the first terminal based on the tag information; Model training is performed on the model to be trained based on the label information and sample information.

13. The method according to claim 12, characterized in that The marking of the sample information related to the first terminal based on the tag information includes: Determining, based on a matching condition, sample information related to the first terminal that is marked by the tag information; marking the sample information based on the label information; The matching condition includes at least one of the following: A first timestamp for generating the tag information matches a second timestamp for generating the sample information; A time difference between a first moment when the first node receives the label information and a second moment when the first node receives the sample information is less than a preset time threshold; The label information and the sample information are associated with the same first identifier.

14. The method according to any one of claims 1 to 13, characterized in that: The first node is a base station; the second node is a terminal, an access and mobility management function AMF or a location management function LMF.

15. A model training method, characterized in that: Executed by the second node, the method includes: Sending first information to the first node, wherein the first information is used to indicate the first terminal related to the model training tag information.

16. The method according to claim 15, characterized in that The first information includes at least one of the following: a terminal identifier of the first terminal; a terminal type of the first terminal; tag information related to the first terminal; Sample information related to the first terminal, the sample information being marked by the label information; a first identifier associated with the label information and the sample information; location information of the first terminal; speed information of the first terminal; a first timestamp, where the first timestamp is used to indicate a time when the tag information is generated; The validity period of the tag information.

17. The method according to claim 16, characterized in that The model training includes model training for positioning measurement; the label information includes label information related to the positioning measurement; and the sample information includes measurement values ​​related to the positioning measurement.

18. The method according to claim 15 or 16, characterized in that The tag information includes tag information associated with at least one transmitting and receiving point TRP.

19. The method according to any one of claims 15 to 18, characterized in that: The tag information includes at least one of the following: location information of the first terminal; an identifier of the first node; Identification of the transmitting and receiving points TRP; Receive-send time difference RxTxTimeDiff; Uplink sounding reference signal received power UL-SRS-RSRP; Uplink angle of arrival UL-AoA; Uplink arrival time offset UL-RTOA; Multiple UL-AoA; Uplink sounding reference signal received power preprocessing UL SRS-RSRPP; Direct propagation LoS information, used to indicate whether the uplink measurement is direct propagation LoS; Non-direct propagation NLoS information is used to indicate whether the uplink measurement is non-direct propagation NLoS.

20. The method according to any one of claims 15 to 19, characterized in that: Before sending the first information to the first node, the method further includes: A first request is received from the first node, where the first request is used to request label information for model training.

21. The method according to claim 20, characterized in that The first request includes at least one of the following: a terminal identifier of the first terminal; the terminal quantity of the first terminal; purpose of the first information; location information of the first terminal; speed information of the first terminal; TRP information related to the tag information; The type of information contained in the tag information; The generation time of the tag information; The time when the first information is generated.

22. The method according to claim 20 or 21, characterized in that The receiving a first request from the first node includes: A first request for the first terminal is received from the first node.

23. The method according to claim 22, characterized in that Before receiving the first request for the first terminal from the first node, the method further includes: Second information related to the second terminal is sent to the first node, where the second information is used to indicate whether the second terminal is authorized and / or agreed to serve as the first terminal.

24. The method according to claim 23, wherein The second information includes at least one of the following: Indication information indicating whether the second terminal is authorized to be used for the model training; Indication information indicating whether to approve the use of the second terminal for the model training; Positioning information associated with the second terminal.

25. The method according to claim 24, characterized in that The positioning information includes an identifier of a positioning management function LMF associated with the second terminal.

26. The method according to any one of claims 20 to 24, characterized in that: After receiving the first request from the first node, the method further includes: A second request is sent to the location management function LMF, where the second request is used to request tag information related to the first terminal.

27. The method according to any one of claims 15 to 26, characterized in that: The first node is a base station; the second node is a terminal, an access and mobility management function AMF or a location management function LMF.

28. A model training device, characterized in that: The device comprises: a transceiver module, configured to receive first information from the second node, where the first information is used to indicate label information related to the first terminal for model training; A processing module is used to perform model training on the to-be-trained model based on the label information.

29. A model training device, characterized in that: The device comprises: a processing module, configured to determine first information indicating label information associated with the first terminal for model training; The transceiver module is configured to send the first information to the first node.

30. A terminal, characterized in that: include: one or more processors; A memory coupled to the processor, wherein the memory stores executable instructions, wherein when the executable instructions are executed by the processor, the terminal executes the model training method according to any one of claims 15 to 27.

31. A network device, characterized in that: include: one or more processors; A memory coupled to the processor, wherein the memory stores executable instructions, wherein when the executable instructions are executed by the processor, the network device executes the model training method described in any one of claims 1 to 14, or the model training method described in any one of claims 15 to 27.

32. A communication device, characterized in that: include: one or more processors; A memory coupled to the processor, wherein the memory stores executable instructions, wherein when the executable instructions are executed by the processor, the processor is used to call instructions so that the communication device executes the model training method described in any one of claims 1 to 14, or the model training method described in any one of claims 15 to 27.

33. A communication system, characterized in that: It includes a first node and a second node, wherein the first node is configured to implement the model training method according to any one of claims 1 to 14, and the second node is configured to implement the model training method according to any one of claims 15 to 27.

34. A storage medium storing instructions, characterized in that: When the instruction is executed on a communication device, the communication device executes the model training method described in any one of claims 1-14 and / or the model training method described in any one of claims 15-27.

Images