Model selection method, node, and system

Abstract

The present disclosure relates to a model selection method. The method executed by a first node comprises: determining first data which is used for model selection; and on the basis of the first data, determining a first AI model, which is used for positioning a terminal, among a plurality of AI models. Therefore, the first node can determine the first AI model, which is used for positioning the terminal, among the plurality of AI models, and then uses the first AI model to position the terminal, such that the terminal positioning accuracy can be improved, thereby ensuring high terminal positioning accuracy.

Description

Model selection methods, nodes and systems Technical Field

[0001] The present disclosure relates to the field of communication technology, and in particular to a model selection method, node, and system. Background Art

[0002] With the continuous development of artificial intelligence (AI) technology in recent years, AI-based solutions have been widely used in the field of wireless communication technology.

[0003] Summary of the Invention

[0004] The embodiments of the present disclosure provide a model selection method, node, and system for solving the problem of how to accurately select a first AI model for positioning a terminal from multiple AI models, thereby improving the accuracy of terminal positioning.

[0005] The embodiments of the present disclosure provide a model selection method, node, and system.

[0006] According to a first aspect of an embodiment of the present disclosure, a model selection method is proposed. The method is executed by a first node, including: determining first data for model selection; and determining, based on the first data, a first AI model among multiple AI models for positioning a terminal.

[0007] In the above embodiment, the first node may determine a first AI model from a plurality of AI models for locating the terminal, and then use the first AI model to locate the terminal, thereby improving the accuracy of terminal positioning.

[0008] According to a second aspect of an embodiment of the present disclosure, a model selection method is proposed, which is executed by a second node and includes: sending a first message to a first node, wherein the first message is used to indicate first data for model selection, and the first data is used by the first node to determine a first AI model among multiple AI models for positioning a terminal.

[0009] In the above embodiment, the second node can provide the first data to the first node, so that the first node can determine the first AI model used for positioning the terminal among multiple AI models based on the first data, thereby improving the accuracy of terminal positioning.

[0010] According to a third aspect of an embodiment of the present disclosure, a model selection method is proposed, wherein a second node sends a first message to a first node, wherein the first message is used to indicate first data for model selection; the first node determines the first data for model selection; and the first node determines, based on the first data, a first AI model among multiple AI models for positioning the terminal.

[0011] According to a fourth aspect of an embodiment of the present disclosure, a first node is provided, including: a processing module for determining first data for model selection; and a transceiver module for determining, based on the first data, a first AI model among multiple AI models for positioning a terminal.

[0012] According to a fifth aspect of an embodiment of the present disclosure, a second node is provided, including: a transceiver module, used to send a first message to a first node, wherein the first message is used to indicate first data for model selection, and the first data is used by the first node to determine a first AI model among multiple AI models for positioning a terminal.

[0013] According to a sixth aspect of an embodiment of the present disclosure, a first node is provided, comprising: one or more processors; wherein the first node is used to execute the method described in the first aspect above.

[0014] According to a seventh aspect of an embodiment of the present disclosure, a second node is provided, comprising: one or more processors; wherein the second node is used to execute the method described in the second aspect above.

[0015] According to an eighth aspect of an embodiment of the present disclosure, a communication system is provided, characterized in that it includes a first node and a second node, wherein the first node is configured to implement the method described in the first aspect above, and the second node is configured to implement the method described in the second aspect above.

[0016] According to a ninth aspect of an embodiment of the present disclosure, a storage medium is provided, which stores instructions, and is characterized in that when the instructions are executed on a communication device, the communication device executes the method described in the first and second aspects above. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] In order to more clearly illustrate the technical solutions in the embodiments of the present disclosure, the following drawings required for describing the embodiments are introduced. The following drawings are merely some embodiments of the present disclosure and do not impose specific limitations on the protection scope of the present disclosure.

[0018] FIG1 is an architecture diagram of a communication system provided by an embodiment of the present disclosure;

[0019] FIG2 is a schematic diagram of an implementation of an AI-based terminal positioning technology provided by an embodiment of the present disclosure;

[0020] FIG3 is a schematic diagram of an application mode of the AI-based terminal positioning technology provided by an embodiment of the present disclosure;

[0021] FIG4 is a schematic diagram of a method for performing model selection using a model selection module provided by an embodiment of the present disclosure;

[0022] FIG5A is a flow chart of a model selection method provided by an embodiment of the present disclosure;

[0023] FIG5B is a flowchart of another model selection method provided by an embodiment of the present disclosure;

[0024] FIG5C is a flowchart of another model selection method provided by an embodiment of the present disclosure;

[0025] FIG6A is a flowchart of another model selection method provided by an embodiment of the present disclosure;

[0026] FIG6B is a flowchart of another model selection method provided by an embodiment of the present disclosure;

[0027] FIG6C is a flowchart of another model selection method provided by an embodiment of the present disclosure;

[0028] FIG7A is a flowchart of another model selection method provided by an embodiment of the present disclosure;

[0029] FIG7B is a flowchart of another model selection method provided by an embodiment of the present disclosure;

[0030] FIG7C is a flowchart of another model selection method provided by an embodiment of the present disclosure;

[0031] FIG8A is a flowchart of another model selection method provided by an embodiment of the present disclosure;

[0032] FIG8B is a flowchart of another model selection method provided by an embodiment of the present disclosure;

[0033] FIG9A is a structural diagram of a first node provided by an embodiment of the present disclosure;

[0034] FIG9B is a structural diagram of a second node provided by an embodiment of the present disclosure;

[0035] FIG10A is a structural diagram of a communication device provided by an embodiment of the present disclosure;

[0036] FIG10B is a schematic structural diagram of a chip provided in an embodiment of the present disclosure. DETAILED DESCRIPTION

[0037] The embodiments of the present disclosure provide a model selection method, node, and system.

[0038] In a first aspect, an embodiment of the present disclosure proposes a model selection method, which is executed by a first node and includes: determining first data for model selection; and determining, based on the first data, a first AI model among multiple AI models for positioning the terminal.

[0039] In the above embodiment, the first node can determine the first AI model used for positioning the terminal among multiple AI models based on the first data, which can improve the accuracy of terminal positioning.

[0040] In conjunction with some embodiments of the first aspect, in some embodiments, the first node determines first data for model selection, including: receiving a first message sent by the second node, wherein the first message is used to indicate the first data for model selection;

[0041] In the above embodiment, the first node can obtain the first data for model selection from the second node. When the first data is data known to the second node, it can be obtained directly from the second node, avoiding forwarding through other nodes and reducing overhead.

[0042] In combination with some embodiments of the first aspect, in some embodiments, the above method further includes: the first node sends a first request message to the second node, wherein the first request message is used to request to obtain the first data.

[0043] In the above embodiment, the first node can send a first request message to the second node, requesting the second node to provide the first data. The first node can directly request the second node to obtain the first data known to the second node, so as to obtain the first data from the second node, thereby improving data transmission efficiency.

[0044] In combination with some embodiments of the first aspect, in some embodiments, the above method also includes: the first node determines the second data; the first node determines the positioning result of the terminal based on the second data and the first AI model.

[0045] In the above embodiment, the first node can determine the second data and determine the positioning result of the terminal based on the second data and the determined first AI model. Since the first AI model is selected from multiple AI models based on the first data, the first AI model used to locate the terminal can match the channel scenario or channel condition reflected by the first data, and can obtain a more accurate terminal positioning result, which can improve the accuracy of terminal positioning.

[0046] In combination with some embodiments of the first aspect, in some embodiments, the first node determines the positioning result of the terminal based on the second data and the first AI model, including: determining the first parameter based on the second data and the first AI model; and determining the positioning result of the terminal based on the first parameter.

[0047] In the above embodiment, the first node can determine the first parameter based on the second data and the first AI model, and then determine the positioning result of the terminal based on the first parameter, thereby realizing the positioning of the terminal and improving the accuracy of the terminal positioning.

[0048] In combination with some embodiments of the first aspect, in some embodiments, the first node determines the second data, including: receiving a second message sent by the second node, wherein the second message is used to indicate the second data; and determining the second data according to the second message.

[0049] In the above embodiment, the first node can receive the second message sent by the second node and determine the second data. If the second data is data known to the second node, it can be obtained directly from the second node, avoiding forwarding through other nodes and reducing overhead.

[0050] In combination with some embodiments of the first aspect, in some embodiments, the above method further includes: the first node sends a second request message to the second node, wherein the second request message is used to request to obtain the second data.

[0051] In the above embodiment, the first node can send a second request message to the second node, requesting to obtain the second data. The second node can provide the second data to the first node based on the request of the first node. The first node can directly request the second node to obtain the second data known to the second node, so as to obtain the second data from the second node, which can improve data transmission efficiency.

[0052] In combination with some embodiments of the first aspect, in some embodiments, the above method also includes: the first node sends indication information to the second node, wherein the indication information is used to indicate the determined first AI model, and the first AI model is used by the second node to locate the terminal based on the second data; or the first node sends indication information to the third node, wherein the indication information is used to indicate the determined first AI model, and the first AI model is used by the third node to locate the terminal based on the second data.

[0053] In the above embodiment, the first node can send indication information to the second node or the third node, indicating the determined first AI model, so as to instruct the second node or the third node to use the first AI model to locate the terminal based on the second data. The second node or the third node can determine the first AI model for locating the terminal from multiple AI models based on the indication information of the first node, and then use the first AI model to locate the terminal. There is no need for the second node or the third node to select a model, which can improve processing efficiency. In addition, positioning the terminal based on the selected first AI model can improve the accuracy of terminal positioning.

[0054] In combination with some embodiments of the first aspect, in some embodiments, the above method also includes: the first node sends a third message to the second node, wherein the third message is used to indicate the second data, and the second data is used by the second node to locate the terminal based on the first AI model; or the first node sends a third message to the third node, wherein the third message is used to indicate the second data, and the second data is used by the third node to locate the terminal based on the first AI model.

[0055] In the above embodiment, the first node can send a third message to the second node or the third node, provide the second node or the third node with second data, so as to use the second data to locate the terminal at the second node or the third node. The second node or the third node can directly obtain the second data known to the first node from the second node, avoiding forwarding through other nodes, thereby reducing overhead.

[0056] In combination with some embodiments of the first aspect, in some embodiments, the above method also includes: the first node receives a third request message sent by the second node, wherein the third request message is used to request to obtain the second data; or the first node receives a third request message sent by the third node, wherein the third request message is used to request to obtain the second data.

[0057] In the above embodiment, the first node can receive a third request message sent by the second node or the third node, and provide the second data to the second node or the third node based on the request of the second node or the third node. The second node or the third node can directly request the first node to obtain the second data known to the first node, so as to obtain the second data from the first node, which can improve data transmission efficiency.

[0058] In combination with some embodiments of the first aspect, in some embodiments, the first node is any one of the following: a terminal; an access network device; a location management function LMF.

[0059] In the above embodiment, the first node may be at least one of a terminal, an access network device, and an LMF. At least one of the terminal, the access network device, and the LMF may determine the first AI model among multiple AI models for positioning the terminal based on the first data, thereby improving the accuracy of terminal positioning.

[0060] In combination with some embodiments of the first aspect, in some embodiments, the first node is a terminal, and the second node is an access network device or LMF; or the first node is an access network device, and the second node is a terminal or LMF; or the first node is an LMF, and the second node is a terminal or an access network device.

[0061] In the above embodiments, the terminal can obtain the first data and / or the second data from the access network device or LMF to determine the first AI model and locate the terminal, or the access network device can obtain the first data and / or the second data from the terminal or LMF to determine the first AI model and locate the terminal, or the LMF can obtain the first data and / or the second data from the terminal or the access network device to determine the first AI model and locate the terminal, thereby improving the accuracy of terminal positioning.

[0062] In combination with some embodiments of the first aspect, in some embodiments, the first node is a terminal and the third node is an LMF; or the first node is a terminal, the second node is an access network device, and the third node is an LMF; or the first node is an access network device and the third node is an LMF; or the first node is an access network device, the second node is a terminal, and the third node is an LMF; or the first node is an LMF and the third node is a terminal or an access network device; or the first node is an LMF, the second node is a terminal, and the third node is an access network device; or the first node is an LMF, the second node is an access network device, and the third node is a terminal.

[0063] In combination with some embodiments of the first aspect, in some embodiments, the first data includes at least one of the following: a reference signal; a reference signal received power RSRP of the reference signal; a channel impulse response CIR determined based on the reference signal; a time domain sampling point number of the maximum power receiving path in the CIR determined based on the reference signal; and a power value of the maximum power receiving path in the CIR determined based on the reference signal.

[0064] In the above embodiment, the first node can determine the first AI model based on the first data, and can determine the first AI model for positioning the terminal based on the channel scenario or channel condition reflected by the first data, and can ensure that the determined first AI model can match the current channel scenario or channel condition. When using the first AI model to position the terminal, the accuracy of terminal positioning can be improved, and a higher terminal positioning accuracy can be ensured.

[0065] In combination with some embodiments of the first aspect, in some embodiments, the second data includes at least one of the following: a reference signal; an RSRP of the reference signal; a CIR determined based on the reference signal; a time domain sampling point number of the maximum power receiving path in the CIR determined based on the reference signal; and a power value of the maximum power receiving path in the CIR determined based on the reference signal.

[0066] In the above embodiment, the first node can use the first AI model to locate the terminal based on the second data, and can use the first AI model to locate the terminal based on the channel scenario or channel condition matched by the second data, thereby improving the accuracy of terminal positioning and ensuring higher terminal positioning accuracy.

[0067] In combination with some embodiments of the first aspect, in some embodiments, the first parameter includes at least one of the following: ToA; AoA.

[0068] In combination with some embodiments of the first aspect, in some embodiments, the reference signal includes at least one of the following: PRS; SRS; SRS-Pos.

[0069] In a second aspect, an embodiment of the present disclosure proposes a model selection method, which is executed by a second node and includes: sending a first message to a first node, wherein the first message is used to indicate first data for model selection, and the first data is used by the first node to determine a first AI model among multiple AI models for positioning the terminal.

[0070] In the above embodiment, the second node can provide the first data to the first node, so that the first node can determine the first AI model used for positioning the terminal among multiple AI models based on the first data, which can improve the accuracy of terminal positioning and ensure higher terminal positioning accuracy.

[0071] In combination with some embodiments of the second aspect, in some embodiments, the above method further includes: the second node receives a first request message sent by the first node, wherein the first request message is used to request to obtain the first data.

[0072] In combination with some embodiments of the second aspect, in some embodiments, the above method also includes: the second node sends a second message to the first node, wherein the second message is used to indicate second data, and the second data is used by the first node to determine the positioning result of the terminal based on the first AI model.

[0073] In combination with some embodiments of the second aspect, in some embodiments, the above method further includes: the second node receives a second request message sent by the first node, wherein the second request message is used to request to obtain the second data.

[0074] In combination with some embodiments of the second aspect, in some embodiments, the above method also includes: the second node receives indication information sent by the first node, wherein the indication information is used to indicate the determined first AI model; and determines the first AI model according to the indication information.

[0075] In combination with some embodiments of the second aspect, in some embodiments, the above method also includes: the second node determines the second data; and determines the positioning result of the terminal based on the second data and the first AI model.

[0076] In the above embodiment, the second node can determine the second data. When receiving the indication information sent by the first node and determining the first AI model, the second data and the first AI model can be used to locate the terminal to determine the positioning result of the terminal.

[0077] In combination with some embodiments of the second aspect, in some embodiments, the second node determines the positioning result of the terminal based on the second data and the first AI model, including: determining the first parameter based on the second data and the first AI model; and determining the positioning result of the terminal based on the first parameter.

[0078] In the above embodiment, the second node can determine the first parameter based on the second data and the first AI model, and then determine the positioning result of the terminal based on the first parameter to achieve positioning of the terminal.

[0079] In combination with some embodiments of the second aspect, in some embodiments, the second node determines the second data, including: receiving a third message sent by the first node, wherein the third message is used to indicate the second data; and determining the second data according to the third message.

[0080] In combination with some embodiments of the second aspect, in some embodiments, the above method further includes: the second node sends a third request message to the first node, wherein the third request message is used to request to obtain the second data.

[0081] In combination with some embodiments of the second aspect, in some embodiments, the first node is any one of the following: a terminal; an access network device; or a LMF.

[0082] In combination with some embodiments of the second aspect, in some embodiments, the first node is a terminal, and the second node is an access network device or LMF; or the first node is an access network device, and the second node is a terminal or LMF; or the first node is an LMF, and the second node is a terminal or an access network device.

[0083] In combination with some embodiments of the second aspect, in some embodiments, the first data includes at least one of the following: a reference signal; the RSRP of the reference signal; a CIR determined based on the reference signal; the time domain sampling point number of the maximum power receiving path in the CIR determined based on the reference signal; and the power value of the maximum power receiving path in the CIR determined based on the reference signal.

[0084] In combination with some embodiments of the second aspect, in some embodiments, the second data includes at least one of the following: a reference signal; the RSRP of the reference signal; a CIR determined based on the reference signal; the time domain sampling point number of the maximum power receiving path in the CIR determined based on the reference signal; and the power value of the maximum power receiving path in the CIR determined based on the reference signal.

[0085] In combination with some embodiments of the second aspect, in some embodiments, the first parameter includes at least one of the following: ToA; AoA.

[0086] In combination with some embodiments of the second aspect, in some embodiments, the reference signal includes at least one of the following: PRS; SRS; SRS-Pos.

[0087] In a third aspect, an embodiment of the present disclosure proposes a model selection method, wherein a second node sends a first message to a first node, wherein the first message is used to indicate first data for model selection; the first node determines the first data for model selection; and the first node determines, based on the first data, a first AI model among multiple AI models for positioning the terminal.

[0088] In a fourth aspect, an embodiment of the present disclosure proposes a first node, which includes at least one of a transceiver module and a processing module; wherein the first node is used to execute the optional implementation method of the first aspect.

[0089] In a fifth aspect, an embodiment of the present disclosure proposes a second node, wherein the above-mentioned first node includes at least one of a transceiver module and a processing module; wherein the above-mentioned second node is used to execute the optional implementation method of the second aspect.

[0090] In a sixth aspect, an embodiment of the present disclosure proposes a first node, which includes: one or more processors; wherein the first node is used to execute an optional implementation method of the first aspect.

[0091] In a seventh aspect, an embodiment of the present disclosure proposes a second node, which includes: one or more processors; wherein the second node is used to execute an optional implementation method of the second aspect.

[0092] In an eighth 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 implementation manner of the first aspect, and the second node is configured to execute the method described in the optional implementation manner of the second aspect.

[0093] In a ninth 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 implementation of the first and second aspects.

[0094] In a tenth 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 implementation of the first and second aspects.

[0095] In an eleventh aspect, an embodiment of the present disclosure proposes a computer program, which, when executed on a computer, enables the computer to execute the method described in the optional implementation of the first and second aspects.

[0096] In a twelfth aspect, an embodiment of the present disclosure provides a chip or a chip system, wherein the chip or chip system includes a processing circuit configured to execute the method described in the optional implementation of the first and second aspects above.

[0097] It is understandable that the first node, the second node, the communication system, the storage medium, the program product, the computer program, the chip, or the chip system are all used to perform the method proposed in the embodiment of the present disclosure. Therefore, the beneficial effects that can be achieved can refer to the beneficial effects of the corresponding method and will not be repeated here.

[0098] The embodiments of the present disclosure provide a model selection method, node, and system. In some embodiments, the terms model selection method, information processing method, communication method, etc. can be used interchangeably.

[0099] 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 implementation methods 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 implementation methods of other embodiments.

[0100] 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.

[0101] 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.

[0102] In the embodiments of the present disclosure, unless otherwise specified, elements expressed in the singular, such as "a", "an", "the", "above", "said", "the", "the", etc., may mean "one and only one", or "one or more", "at least one", etc. For example, when using articles such as "a", "an", "the" in English in translation, the noun following the article may be understood as a singular expression or a plural expression.

[0103] In the embodiments of the present disclosure, “plurality” refers to two or more.

[0104] In some embodiments, the terms "at least one," "one or more," "a plurality of," "multiple," etc. may be used interchangeably.

[0105] 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.

[0106] 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.

[0107] 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 restriction on the position, order, priority, quantity or content of the description objects. For the statement of the description object, please refer to the description in the context of the claims or embodiments, and no unnecessary restriction should be constituted due to the use of prefixes. For example, if the description object is a "field", the ordinal number before the "field" in the "first field" and the "second field" does not limit the position or order between the "fields". "First" and "second" do not limit whether the "fields" they modify are in the same message, nor do they limit the order of the "first field" and the "second field". For another example, if the description object is a "level", the ordinal number before the "level" in the "first level" and the "second level" does not limit the priority between the "levels". For another example, the number of description objects is not limited by the ordinal number and can be one or more. Taking "first device" as an example, the number of "devices" can be one or more. In addition, the objects modified by different prefixes can be the same or different. For example, if the description object is "device", then the "first device" and the "second device" can be the same device or different devices, and their types can be the same or different; for another example, if the description object is "information", then the "first information" and the "second information" can be the same information or different information, and their contents can be the same or different.

[0108] 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.

[0109] In some embodiments, terms such as "time / frequency" and "time / frequency domain" refer to the time domain and / or the frequency domain.

[0110] 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.

[0111] 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", "above" and the like 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", "below" and the like can be replaced with each other.

[0112] In some embodiments, devices, etc. can be interpreted as physical or virtual, and their names are not limited to the names recorded in the embodiments. Terms such as "device", "equipment", "device", "circuit", "network element", "node", "function", "unit", "section", "system", "network", "chip", "chip system", "entity", and "subject" can be used interchangeably.

[0113] In some embodiments, "network" can be interpreted as devices included in the network (eg, access network equipment, core network equipment, etc.).

[0114] 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.

[0115] 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.

[0116] 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.

[0117] 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.

[0118] In some embodiments, obtaining data, information, etc. may comply with the laws and regulations of the country where the data is obtained.

[0119] In some embodiments, data, information, etc. may be obtained with the user's consent.

[0120] 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.

[0121] FIG1 is an architecture diagram of a communication system provided by an embodiment of the present disclosure.

[0122] As shown in FIG1 , a communication system 100 includes a terminal 101 , an access network device 102 , and a core network device 103 .

[0123] In some embodiments, the terminal 101 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.

[0124] In some embodiments, the terminal may also be referred to as a terminal device, a user device, etc., and the names are interchangeable, and the embodiments of the present disclosure do not impose specific limitations on this.

[0125] In some embodiments, the access network device 102 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.

[0126] In some embodiments, the access network device 102 may also be a satellite.

[0127] In some embodiments, the core network device 103 may be a device including multiple network elements such as a first network element and a second network element, or may be multiple devices or a group of devices, each including multiple network functions. A network element may also be referred to as a network function, which 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).

[0128] In some embodiments, the first network element is, for example, an access and mobility management function (AMF).

[0129] In some embodiments, the first network element is, for example, a location management function (LMF).

[0130] In some embodiments, the second network element is, for example, a unified data management (UDM).

[0131] In some embodiments, the first network element is used for access control and mobility management of the terminal accessing the operator network, including, for example, mobility status management, allocation of user temporary identity, authentication and authorization of users, etc., and its name is not limited thereto.

[0132] In some embodiments, the first network element is used to provide positioning services for terminals and other devices.

[0133] In some embodiments, the second network element is used to manage subscription information of the terminal.

[0134] 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.

[0135] 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.

[0136] The embodiments of the present disclosure may 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), and the like. band, UWB), Bluetooth (registered trademark), public land mobile network (PLMN) network, device-to-device (D2D) system, machine-to-machine (M2M) system, Internet of Things (IoT) system, vehicle-to-everything (V2X), systems using other communication methods, and next-generation systems based on them. In addition, multiple systems can also be combined (for example, a combination of LTE or LTE-A and 5G) for application.

[0137] In recent years, high-precision positioning technology has become a hot research topic to meet the demand for location-based services in various commercial service scenarios and industrial IoT scenarios. It facilitates services such as indoor navigation, augmented and virtual reality, and autonomous driving. Implementing high-precision positioning services based on wireless communication network infrastructure is a key area of ​​mobile communication research and a key component of wireless communication standardization research throughout history.

[0138] The 3rd Generation Partnership Project (3GPP) introduced a variety of methods, such as time measurement and angle-based methods, in the NR release-16 standard to achieve high-precision positioning in indoor and outdoor scenarios. With the continuous increase in related business needs, 3GPP launched a project in release-17 to enhance positioning accuracy for commercial scenarios and industrial internet of things (IIOT) scenarios, with the goal of achieving high-precision positioning at the decimeter level, and is committed to meeting the high-precision location service needs of the consumer and enterprise markets. However, the positioning algorithms in related technologies, such as the time difference of arrival (TDOA) and multi-round trip time (multi-RTT) methods specified in the 3GPP standard, are difficult to meet the very strict positioning accuracy requirements in scenarios such as IIoT.

[0139] With the continuous development of artificial intelligence technology in recent years, AI-based solutions have been widely used in the field of wireless communications. Deep neural network models are capable of effectively performing complex data processing and feature modeling processes and are now being applied to solve many key problems in wireless communications. AI-based terminal positioning is a key application case of AI technology in the communications field and is also a research direction for 3GPP standardization. AI-based positioning technology solutions utilize deep neural network models to model the mapping relationship between channel measurement data and terminal location coordinates, achieving higher positioning accuracy than traditional positioning methods.

[0140] In some embodiments of the present disclosure, as shown in FIG2 , the AI-based terminal positioning technology includes two implementation methods, direct positioning based on an AI model as shown in FIG2 (a), and indirect positioning assisted by an AI model as shown in FIG2 (b).

[0141] (1) Direct positioning based on AI models: The input of the AI ​​model is the channel measurement data used for positioning, and the output is the terminal location coordinates;

[0142] (2) Indirect positioning assisted by AI model: The input of the AI ​​model is the channel measurement data used for positioning, and the output is intermediate positioning parameters, which may include time of arrival (TOA), angle of arrival (AOA), etc. Based on the first parameter, the terminal location coordinates can be calculated using traditional positioning methods.

[0143] In the direct positioning and indirect positioning methods, the input of the AI ​​model is the channel measurement data used for positioning, which in some embodiments is the channel impulse response (CIR) calculated based on the received reference signal.

[0144] Exemplarily, the terminal can calculate and obtain the downlink CIR based on the positioning reference signal (PRS) sent by the access network device, or the access network device can calculate and obtain the uplink CIR based on the sounding reference signal (SRS) sent by the terminal, or the access network device can calculate and obtain the uplink CIR based on the sounding reference signal (SRS-Pos) sent by the terminal for positioning.

[0145] In some embodiments, depending on the specific device for implementing positioning, AI-based terminal positioning can be implemented at the terminal, access network device or LMF respectively.

[0146] In some embodiments, as shown in FIG3 , the AI-based terminal positioning solution includes five specific application modes.

[0147] Mode 1: Direct or indirect positioning on the terminal side: The terminal calculates the measurement value used for positioning, such as CIR, based on the PRS sent by the access network equipment (base station, BS). The calculation inputs the measurement value used for positioning into the AI ​​model to directly obtain the terminal's location coordinates. Alternatively, the terminal inputs the measurement value used for positioning into the AI ​​model to obtain the first positioning parameters such as ToA and AoA, and then uses traditional positioning methods such as TDOA to obtain the terminal's location coordinates. After obtaining the positioning result, i.e., the location coordinates, the terminal reports the result to the LMF.

[0148] Mode 2: Terminal-assisted indirect positioning on the LMF side: The terminal calculates the measurement value used for positioning, such as CIR, based on the PRS sent by the BS, inputs the AI ​​model to obtain the first positioning parameters such as ToA and AoA, and reports the intermediate positioning parameters to the LMF. The LMF uses traditional positioning methods such as TDOA to obtain the terminal's position coordinates.

[0149] Mode 3: Terminal-assisted direct positioning on the LMF side: The terminal calculates the measurement value used for positioning, such as CIR, based on the PRS sent by the BS, and reports the measurement value used for positioning to the LMF. The LMF inputs the received measurement value into the AI ​​model to obtain the terminal's location coordinates.

[0150] Mode 4: BS-assisted indirect positioning on the LMF side: The BS calculates the measurement values ​​used for positioning, such as CIR, based on the SRS sent by the terminal, inputs the positioning measurement values ​​into the AI ​​model to obtain the first positioning parameters such as ToA and AoA, and reports the intermediate positioning parameters to the LMF. The LMF uses traditional positioning methods such as TDOA to obtain the terminal's location coordinates.

[0151] Mode 5: BS-assisted direct positioning on the LMF side: The BS calculates the measurement values ​​used for positioning, such as CIR, based on the SRS sent by the terminal, and reports the measurement values ​​used for positioning to the LMF. The LMF inputs the positioning measurement values ​​into the AI ​​model to directly obtain the terminal's location coordinates.

[0152] It is understandable that the main application process of the terminal positioning solution based on deep learning is: after using training data to complete the network model training (model training) of the AI ​​model used for terminal positioning, the trained AI model is deployed on the terminal, access network equipment or LMF, and then the terminal positioning work in the actual system is completed, that is, model inference is performed.

[0153] Because the storage and computing power of relevant devices in actual communication systems are relatively limited, the scale and computational complexity of the neural network models required to solve problems in wireless communication systems are also limited. In this case, the generalization problem of the neural network model is more serious.

[0154] The generalization capability of a neural network model refers to its performance when processing unknown data that differs from the training data. Generally, a model is able to effectively process data that follows the same or similar distribution as the training dataset. However, when the characteristic distribution of the data the model needs to process differs significantly from that of the training dataset, the model performance will be significantly reduced. Actual communication systems have diverse channel scenarios or channel conditions. Under different channel scenarios or channel conditions, the characteristic distribution of the channel measurement data used to complete terminal positioning may vary significantly. Therefore, an AI model applied to a certain channel scenario or channel condition will find it difficult to maintain good model performance in other situations.

[0155] In some embodiments, in order to effectively solve the generalization problem of neural network models in actual system applications, three solutions are proposed:

[0156] (1) Using only one AI model for different channel scenarios / channel conditions: This method usually requires using mixed data sets from different channel scenarios / channel conditions to complete AI model training, so that the AI ​​model can learn the data distribution under different channel conditions. Advantages: Using one model to process data under different conditions simplifies the model application process and reduces the overall model size. Disadvantages: If the data distribution under different channel scenarios / channel conditions varies greatly, using only one AI model will make it difficult to guarantee model performance in all cases.

[0157] (2) Using a model and fine-tuning or updating model parameters: After deploying the pre-trained model on the device, fine-tune or update the model parameters using actual channel data during the model application process to adapt the model to the current channel. Advantages: The overall model size is relatively low, which can achieve good model performance. Disadvantages: The overhead of data collection and model parameter fine-tuning or updating in the actual system is high, which in turn causes problems such as latency and high device power consumption.

[0158] (3) Use multiple models and implement model switching: To ensure model performance in different situations, different models are trained and deployed in different channel scenarios or channel conditions. Before model inference is applied, AI model selection is first completed, and the AI ​​model suitable for the current situation is selected and activated. Advantages: Ability to achieve good model performance in various situations; Disadvantages: The overall model size is high, and model selection needs to be completed.

[0159] In some embodiments, AI-based terminal positioning technology, as a third solution to the generalization problem of AI models, adopts a method of training and storing multiple sets of positioning AI models for different channel scenarios or channel conditions to ensure higher positioning accuracy. Appropriate AI models are used to complete terminal positioning in different channel scenarios or channel conditions, and the AI ​​model selection problem needs to be considered at the same time.

[0160] In some embodiments, as shown in FIG4 , to address the model selection issue, a model selection module (which may be an AI model for model selection) is introduced. Its input is channel measurement data, and its output is the model selection result. Based on the model selection result, the corresponding AI model (the AI ​​positioning model used for terminal positioning) is activated, and the activated AI model is then used to complete terminal (UE) positioning.

[0161] In the embodiments of the present disclosure, for application scenarios in which terminal positioning is completed based on a deep neural network model (AI model), it is considered to train and store different AI models for different channel scenarios or channel conditions to ensure positioning accuracy in various situations.

[0162] In some embodiments, before performing AI model positioning inference, it is necessary to first select an AI model that matches the input data. In the disclosed embodiments, an AI model for model selection (model selection module) is used to complete the selection and activation of the AI ​​model with high accuracy and low overhead, and then use the AI ​​model suitable for the current channel scenario or channel conditions to achieve terminal positioning to ensure high positioning accuracy.

[0163] The present disclosure provides a model selection method, wherein the method, performed by a first node, includes: determining first data for model selection; and determining, based on the first data, a first AI model from among multiple AI models for positioning a terminal. Thus, the first node can determine the first AI model from among the multiple AI models for positioning the terminal, and then use the first AI model to position the terminal, thereby improving the accuracy of terminal positioning and ensuring high terminal positioning accuracy.

[0164] FIG5A is an interactive diagram of a model selection method according to an embodiment of the present disclosure. As shown in FIG5A , the embodiment of the present disclosure relates to a model selection method, which includes:

[0165] S501A: The first node sends a first request message to the second node.

[0166] In some embodiments, the second node receives the first request message sent by the first node.

[0167] In some embodiments, the first request message is used to request obtaining first data for model selection.

[0168] In some embodiments, the first request message is used to request to obtain first data input into the first module.

[0169] In some embodiments, the first module may be used for model selection. Optionally, the first module is an AI-based module, for example, a second AI model.

[0170] Alternatively, a module can be physical or virtual. Alternatively, the module can be replaced by other terms such as model.

[0171] Exemplarily, the first module is the second AI model, the first data is input into the second AI model, and the second AI model can output the first AI model selected from multiple AI models.

[0172] In some embodiments, the first request message is used to request acquisition of first data.

[0173] In some embodiments, the name of the first request message is not limited, and may be, for example, "first message", "first information", etc.

[0174] In an embodiment of the present disclosure, the first node may send a first request message to the second node, requesting to obtain first data for model selection.

[0175] It can be understood that the first data is used for model selection, and the first node can request to obtain the first data. When the first data is obtained, the model selection can be performed based on the first data.

[0176] In some embodiments, the name of the first data is not limited, and it can be, for example, “model input data”, “measurement data”, etc.

[0177] In some embodiments, the first data includes at least one of the following:

[0178] Reference signal;

[0179] Reference signal received power RSRP of the reference signal;

[0180] A channel impulse response (CIR) determined based on a reference signal;

[0181] The time domain sampling point number of the maximum power receiving path in the CIR determined based on the reference signal;

[0182] The power value of the receiving path with the highest power in the CIR determined based on the reference signal.

[0183] In some embodiments, the reference signal includes at least one of PRS, SRS, and SRS-Pos.

[0184] In some embodiments, the first data includes a PRS.

[0185] In some embodiments, the first data includes an SRS.

[0186] In some embodiments, the first data includes SRS-Pos (sounding reference signal-position, a sounding reference signal used for positioning).

[0187] In some embodiments, the first data includes a reference signal received power (RSRP) of a reference signal.

[0188] In some embodiments, the first data includes a CIR determined based on the PRS.

[0189] In some embodiments, the first data includes a CIR determined based on the SRS.

[0190] In some embodiments, the first data includes a CIR determined based on the SRS-Pos.

[0191] In some embodiments, the first data includes a time-domain sampling point number of a maximum-power receiving path in a CIR determined based on a reference signal.

[0192] The transmission of the first data including the time domain sampling point number of the maximum power receiving path in the CIR determined based on the reference signal can be transmitted using a bitmap encoding method. For example, the encoding method is: when there are N sampling points in total, log2N bits are used to represent the time domain sampling point number to be transmitted.

[0193] In some embodiments, according to the data processing results, for a case with 256 sampling points, the maximum power receiving path in the CIR determined based on the reference signal usually appears in the first 100 sampling points. Therefore, in order to reduce the transmission overhead, the first data including the time domain sampling point number of the maximum power receiving path in the CIR determined based on the reference signal may only use The setting can be realized according to the actual communication transmission requirements.

[0194] In some embodiments, the first data includes a time-domain sampling point number of a maximum-power receiving path in a CIR determined based on the PRS.

[0195] In some embodiments, the first data includes a time-domain sampling point number of a maximum-power receiving path in a CIR determined based on the SRS.

[0196] In some embodiments, the first data includes a time-domain sampling point number of a maximum-power receiving path in a CIR determined based on SRS-Pos.

[0197] In some embodiments, the first data includes a power value of a maximum-power receiving path in a CIR determined based on a reference signal.

[0198] In some embodiments, the first data includes a power value of a maximum power receiving path in a CIR determined based on the PRS.

[0199] In some embodiments, the first data includes a power value of a maximum power receiving path in a CIR determined based on the SRS.

[0200] In some embodiments, the first data includes a power value of a maximum power receiving path in a CIR determined based on SRS-Pos.

[0201] In some embodiments, the first node is at least one of a terminal, an access network device, and a LMF.

[0202] Of course, the first node may also be a core network element other than LMF, and the embodiment of the present disclosure does not impose any specific restrictions on this.

[0203] In some embodiments, the first node is a terminal and the second node is an access network device or LMF; or the first node is an access network device and the second node is a terminal or LMF; or the first node is an LMF and the second node is a terminal or an access network device.

[0204] In some embodiments, the first node is a terminal and the second node is an access network device, so that the terminal can send a first request message to the access network device to request to obtain first data for model selection.

[0205] In some embodiments, the first node is a terminal and the second node is a LMF, so that the terminal can send a first request message to the LMF to request to obtain first data for model selection.

[0206] In a possible implementation, the terminal sends a first request message to the LMF through the AMF, requesting to obtain first data for model selection.

[0207] In some embodiments, the first node is an access network device and the second node is a terminal, so that the access network device can send a first request message to the terminal to request first data for model selection.

[0208] In some embodiments, the first node is an access network device and the second node is a LMF, so that the access network device can send a first request message to the LMF to request first data for model selection.

[0209] In some embodiments, the first node is an LMF and the second node is a terminal, so that the LMF can send a first request message to the terminal to request to obtain first data for model selection.

[0210] In a possible implementation, the LMF sends a first request message to the terminal through the AMF, requesting to obtain first data for model selection.

[0211] In some embodiments, the first node is an LMF and the second node is an access network device, so that the LMF can send a first request message to the access network device to request to obtain first data for model selection.

[0212] In some embodiments, the first node may send the first request message to the second node on its own, or may send the first request message to the second node when it is determined that a specific condition is met.

[0213] Exemplarily, when determining that the terminal needs to be located, the first node sends a first request message to the second node.

[0214] Exemplarily, when determining that model selection is required, the first node sends a first request message to the second node.

[0215] Exemplarily, when determining that model selection is required for positioning the terminal, the first node sends a first request message to the second node.

[0216] S502A: The second node sends a first message to the first node.

[0217] In some embodiments, the first node receives a first message sent by the second node.

[0218] In some embodiments, the first message is used to indicate first data for model selection.

[0219] In some embodiments, the first message is used to indicate first data requested by the first request message.

[0220] In some embodiments, the name of the first message is not limited, and it can be, for example, "first response message", "first feedback information", etc.

[0221] In the embodiment of the present disclosure, the second node may send a first message to the first node to provide the first node with first data.

[0222] In some embodiments, upon receiving a first request message sent by the first node, the second node sends a first message to the first node, where the first request message is used to request first data for model selection, and the first message is used to indicate the first data, so that the first node can obtain the first data from the second node to use the first data for model selection.

[0223] In some embodiments, when the first node is a terminal and the second node is an access network device, the terminal can send a first request message to the access network device, requesting to obtain first data for model selection. Further, the terminal can receive a first message sent by the access network device, where the first message is used to indicate the first data. Thus, the terminal can obtain the first data for model selection from the access network device to implement model selection at the terminal.

[0224] In which, when the first node is a terminal and the second node is an access network device, the first data can be at least one of the following: PRS; CIR determined based on SRS; time domain sampling point number of the maximum power receiving path in the CIR determined based on SRS; power value of the maximum power receiving path in the CIR determined based on SRS; CIR determined based on SRS-Pos; time domain sampling point number of the maximum power receiving path in the CIR determined based on SRS-Pos; power value of the maximum power receiving path in the CIR determined based on SRS-Pos.

[0225] In one possible implementation, when the first node is a terminal and the second node is an access network device, the first data is a PRS. The terminal obtains the PRS from the access network device and can determine the CIR determined based on the PRS. Then, the terminal can implement model selection at the terminal based on the CIR determined based on the PRS.

[0226] In one possible implementation, when the first node is a terminal and the second node is an access network device, the first data is a PRS. The terminal obtains the PRS from the access network device and can determine the time domain sampling point number of the maximum power receiving path in the CIR determined based on the PRS. Then, the terminal can implement model selection at the terminal based on the time domain sampling point number of the maximum power receiving path in the CIR determined based on the PRS.

[0227] In one possible implementation, when the first node is a terminal and the second node is an access network device, the first data is a PRS. The terminal obtains the PRS from the access network device and can determine the power value of the maximum power receiving path in the CIR determined based on the PRS. Then, the terminal can implement model selection at the terminal based on the power value of the maximum power receiving path in the CIR determined based on the PRS.

[0228] In some embodiments, when the first node is an access network device and the second node is a terminal, the access network device can send a first request message to the terminal, requesting to obtain first data for model selection. Further, the access network device can receive the first message sent by the terminal, and the first message is used to indicate the first data. Thus, the access network device can obtain the first data for model selection from the terminal to implement model selection at the access network device.

[0229] In some embodiments, when the first node is an access network device and the second node is a terminal, the first data may be at least one of the following: SRS; SRS-Pos; CIR determined based on PRS; time domain sampling point number of the maximum power receiving path in the CIR determined based on PRS; power value of the maximum power receiving path in the CIR determined based on PRS.

[0230] In one possible implementation, when the first node is an access network device and the second node is a terminal, the first data is SRS or SRS-Pos. The access network device obtains the SRS or SRS-Pos from the terminal and can determine the CIR determined based on the SRS or SRS-Pos. Then, the access network device can implement model selection at the access network device based on the CIR determined based on the SRS or SRS-Pos.

[0231] In one possible implementation, when the first node is an access network device and the second node is a terminal, the first data is SRS or SRS-Pos. The access network device obtains the SRS or SRS-Pos from the terminal and can determine the time domain sampling point number of the maximum power receiving path in the CIR determined based on the SRS or SRS-Pos. Then, the access network device can implement model selection at the access network device based on the time domain sampling point number of the maximum power receiving path in the CIR determined based on the SRS or SRS-Pos.

[0232] In one possible implementation, when the first node is an access network device and the second node is a terminal, the first data is SRS or SRS-Pos. The access network device obtains SRS or SRS-Pos from the terminal and can determine the power value of the maximum power receiving path in the CIR determined based on SRS or SRS-Pos. Then, the access network device can implement model selection at the access network device based on the power value of the maximum power receiving path in the CIR determined based on SRS or SRS-Pos.

[0233] In some embodiments, when the first node is an LMF and the second node is a terminal, the LMF can send a first request message to the terminal, requesting to obtain first data for model selection. Further, the LMF can receive the first message sent by the terminal, and the first message is used to indicate the first data. Thus, the LMF can obtain the first data for model selection from the terminal to implement model selection at the LMF.

[0234] In some embodiments, when the first node is an LMF and the second node is a terminal, the first data may be at least one of the following: a CIR determined based on a PRS; a time domain sampling point number of a receiving path with the maximum power in the CIR determined based on the PRS; or a power value of a receiving path with the maximum power in the CIR determined based on the PRS.

[0235] In some embodiments, when the first node is LMF and the second node is an access network device, the LMF can send a first request message to the access network device, requesting to obtain first data for model selection. Further, the LMF can receive a first message sent by the access network device, where the first message is used to indicate the first data. Thus, the LMF can obtain the first data for model selection from the access network device to implement model selection at the LMF.

[0236] In some embodiments, when the first node is an LMF and the second node is an access network device, the first data may be at least one of the following: a CIR determined based on SRS; a time domain sampling point number of the maximum power receiving path in the CIR determined based on SRS; a power value of the maximum power receiving path in the CIR determined based on SRS; a CIR determined based on SRS-Pos; a time domain sampling point number of the maximum power receiving path in the CIR determined based on SRS-Pos; a power value of the maximum power receiving path in the CIR determined based on SRS-Pos.

[0237] S503A: The first node determines first data for model selection.

[0238] In some embodiments, the first node may determine the first data for model selection by itself, or the first node may obtain the first data for model selection from other nodes to determine the first data for model selection.

[0239] In some embodiments, when the first node is a terminal, the terminal determines the first data for model selection by itself, and the first data can be at least one of the following: PRS; CIR determined based on PRS; time domain sampling point number of the maximum power receiving path in the CIR determined based on PRS; power value of the maximum power receiving path in the CIR determined based on PRS.

[0240] In some embodiments, when the first node is an access network device, the access network device determines the first data for model selection by itself, and the first data may be at least one of the following: SRS; SRS-Pos; CIR determined based on SRS; time domain sampling point number of the maximum power receiving path in the CIR determined based on SRS; power value of the maximum power receiving path in the CIR determined based on SRS; CIR determined based on SRS-Pos; time domain sampling point number of the maximum power receiving path in the CIR determined based on SRS-Pos; power value of the maximum power receiving path in the CIR determined based on SRS-Pos; CIR determined based on PRS; time domain sampling point number of the maximum power receiving path in the CIR determined based on PRS; power value of the maximum power receiving path in the CIR determined based on PRS.

[0241] In some embodiments, the first node determines first data for model selection, including the first node receiving a first message sent by the second node, where the first message is used to indicate the first data, and the first node determines the first data according to the first message.

[0242] In some embodiments, the first node determines the first data for model selection, including the first node sending a first request message to the second node, the first request message requesting to obtain the first data, further, the first node receives the first message sent by the second node, the first message is used to indicate the first data, and the first node determines the first data based on the first message.

[0243] In some embodiments, the first node is a terminal and the second node is an access network device or LMF; or the first node is an access network device and the second node is a terminal or LMF; or the first node is an LMF and the second node is a terminal or an access network device.

[0244] S504A: The first node determines, based on the first data, a first AI model among multiple AI models for positioning the terminal.

[0245] In some embodiments, when the first node determines the first data, it can determine a first AI model for positioning the terminal from among multiple AI models based on the first data.

[0246] In some embodiments, after determining the first data and the first module, the first node may determine a first AI model among multiple AI models for locating the terminal.

[0247] In some embodiments, the first module is configured at a first node, and the first node may determine the first module.

[0248] In some embodiments, the first module is capable of performing model selection. Optionally, the first module is an AI-based module, for example, a second AI model.

[0249] Alternatively, a module can be physical or virtual. Alternatively, the module can be replaced by other terms such as model.

[0250] Exemplarily, the first node inputs the first data into the second AI model, and the output result of the second AI model can indicate a first AI model selected from multiple AI models for positioning the terminal.

[0251] In some embodiments, before determining a first AI model for locating the terminal from among multiple AI models based on the first data and the second AI model, the second AI model may be trained.

[0252] Among them, the training of the second AI model can be completed at the first node, or it can also be completed at other nodes, and the trained second AI model is configured at the first node.

[0253] In some embodiments, the second AI model can be trained using a training data set, where the training data set includes sample input data and corresponding sample output data. When the sample input data is input into the second AI model to obtain predicted output data, the parameters of the second AI model can be updated based on the predicted output data and the sample output data. When the conditions are met, the training of the second AI model is determined to be completed to obtain a trained second AI model.

[0254] In an embodiment of the present disclosure, the first node can determine the first AI model among multiple AI models for positioning the terminal based on the first data and the second AI model. The first data can reflect the channel scenario or channel condition. The selected first AI model can be applicable to the current channel scenario or channel condition. Therefore, when the first AI model is used to position the terminal, the accuracy of the terminal positioning can be improved, thereby ensuring a higher terminal positioning accuracy.

[0255] S505A: The first node sends a second request message to the second node.

[0256] In some embodiments, the second node receives the second request message sent by the first node.

[0257] In some embodiments, the second request message is used to request acquisition of second data.

[0258] In some embodiments, the second request message is used to request acquisition of second data for locating the terminal.

[0259] In some embodiments, the second request message is used to request obtaining second data as input to the first AI model.

[0260] In some embodiments, the name of the second request message is not limited, and may be, for example, "second message", "second information", etc.

[0261] It can be understood that the second data is the input data of the first AI model, and the first AI model is used to locate the terminal. When the second data is input into the first AI model, the positioning result of the terminal can be output.

[0262] In some embodiments, the second data is used by the first node to determine the positioning result of the terminal based on the first AI model.

[0263] In some embodiments, the second data includes at least one of the following:

[0264] Reference signal;

[0265] RSRP of the reference signal;

[0266] A channel impulse response (CIR) determined based on a reference signal;

[0267] The time domain sampling point number of the maximum power receiving path in the CIR determined based on the reference signal;

[0268] The power value of the receiving path with the highest power in the CIR determined based on the reference signal.

[0269] In some embodiments, the reference signal includes at least one of a PRS, an SRS, and an SRS-Pos.

[0270] In some embodiments, the second data includes a PRS.

[0271] In some embodiments, the second data includes an SRS.

[0272] In some embodiments, the second data includes SRS-Pos (sounding reference signal-position, a sounding reference signal used for positioning).

[0273] In some embodiments, the second data includes a CIR determined based on the PRS.

[0274] In some embodiments, the second data includes a CIR determined based on the SRS.

[0275] In some embodiments, the second data includes a CIR determined based on the SRS-Pos.

[0276] In some embodiments, the second data includes a time-domain sampling point number of a maximum-power receiving path in a CIR determined based on the PRS.

[0277] In some embodiments, the second data includes a time-domain sampling point number of a maximum-power receiving path in a CIR determined based on the SRS.

[0278] In some embodiments, the second data includes a time-domain sampling point number of a maximum-power receiving path in a CIR determined based on SRS-Pos.

[0279] In some embodiments, the second data includes a power value of a maximum-power receiving path in a CIR determined based on the reference signal.

[0280] In some embodiments, the second data includes a power value of a maximum power receiving path in a CIR determined based on the PRS.

[0281] In some embodiments, the second data includes a power value of a maximum power receiving path in a CIR determined based on the SRS.

[0282] In some embodiments, the second data includes a power value of a maximum power receiving path in a CIR determined based on SRS-Pos.

[0283] In some embodiments, the first node is a terminal and the second node is an access network device, so that the terminal can send a second request message to the access network device to request to obtain the second data.

[0284] In some embodiments, the first node is an access network device and the second node is a terminal, so that the access network device can send a second request message to the terminal to request to obtain the second data.

[0285] In some embodiments, the first node is an LMF and the second node is a terminal, so that the LMF can send a second request message to the terminal to request to obtain the second data.

[0286] In a possible implementation, the LMF sends a second request message to the terminal through the AMF, requesting to obtain the second data.

[0287] In some embodiments, the first node is an LMF and the second node is an access network device, so that the LMF can send a second request message to the access network device to request to obtain the second data.

[0288] In some embodiments, the first node may send the second request message to the second node on its own, or may send the second request message to the second node when it is determined that a specific condition is met.

[0289] Exemplarily, when determining that the terminal needs to be located, the first node sends a second request message to the second node.

[0290] S506A: The second node sends a second message to the first node.

[0291] In some embodiments, the first node receives a second message sent by the second node.

[0292] In some embodiments, the second message is used to indicate second data.

[0293] In some embodiments, the second message is used to indicate second data requested by the second request message.

[0294] In some embodiments, the second message is used to indicate second data for locating the terminal.

[0295] In some embodiments, the second message is used to indicate second data serving as input data of the first AI model.

[0296] In some embodiments, the name of the second message is not limited, and it can be, for example, "second response message", "second feedback information", etc.

[0297] In the embodiment of the present disclosure, the second node may send a second message to the first node to provide the first node with second data.

[0298] In some embodiments, the second data is used by the first node to determine the positioning result of the terminal based on the first AI model.

[0299] In some embodiments, upon receiving a second request message sent by the first node, the second node sends a second message to the first node, where the second request message is used to request the acquisition of second data, and the second message is used to indicate the second data, so that the first node can obtain the second data from the second node, and use the second data and the first AI model at the first node to determine the positioning result of the terminal.

[0300] In some embodiments, when the first node is a terminal and the second node is an access network device, the terminal can send a second request message to the access network device to request to obtain the second data. Furthermore, the terminal can receive a second message sent by the access network device, and the second message is used to indicate the second data. Thus, the terminal can obtain the second data from the access network device to determine the positioning result of the terminal at the terminal based on the second data and the first AI model.

[0301] In which, when the first node is a terminal and the second node is an access network device, the second data can be at least one of the following: PRS; CIR determined based on SRS; time domain sampling point number of the maximum power receiving path in the CIR determined based on SRS; power value of the maximum power receiving path in the CIR determined based on SRS; CIR determined based on SRS-Pos; time domain sampling point number of the maximum power receiving path in the CIR determined based on SRS-Pos; power value of the maximum power receiving path in the CIR determined based on SRS-Pos.

[0302] In one possible implementation, when the first node is a terminal and the second node is an access network device, the second data is a PRS. The terminal obtains the PRS from the access network device and can determine the CIR determined based on the PRS. Then, the positioning result of the terminal can be determined based on the CIR determined based on the PRS and the first AI model.

[0303] In one possible implementation, when the first node is a terminal and the second node is an access network device, the second data is a PRS. The terminal obtains the PRS from the access network device and can determine the time domain sampling point number of the maximum power receiving path in the CIR determined based on the PRS. Then, the positioning result of the terminal can be determined based on the time domain sampling point number of the maximum power receiving path in the CIR determined based on the PRS and the first AI model.

[0304] In one possible implementation, when the first node is a terminal and the second node is an access network device, the second data is a PRS. The terminal obtains the PRS from the access network device and can determine the power value of the maximum power receiving path in the CIR determined based on the PRS. Then, the positioning result of the terminal can be determined based on the power value of the maximum power receiving path in the CIR determined based on the PRS and the first AI model.

[0305] In some embodiments, when the first node is an access network device and the second node is a terminal, the access network device can send a second request message to the terminal to request to obtain the second data. Furthermore, the access network device can receive the second message sent by the terminal, and the second message is used to indicate the second data. Thus, the access network device can obtain the second data from the terminal to determine the positioning result of the terminal at the access network device based on the second data and the first AI model.

[0306] In some embodiments, when the first node is an access network device and the second node is a terminal, the second data may be at least one of the following: SRS; SRS-Pos; CIR determined based on PRS; time domain sampling point number of the maximum power receiving path in the CIR determined based on PRS; power value of the maximum power receiving path in the CIR determined based on PRS.

[0307] In one possible implementation, when the first node is an access network device and the second node is a terminal, the second data is SRS or SRS-Pos. The access network device obtains the SRS or SRS-Pos from the terminal and can determine the CIR determined based on the SRS or SRS-Pos. Then, the positioning result of the terminal can be determined based on the CIR determined based on the SRS or SRS-Pos and the first AI model.

[0308] In one possible implementation, when the first node is an access network device and the second node is a terminal, the second data is SRS or SRS-Pos. The access network device obtains the SRS or SRS-Pos from the terminal, and can determine the time domain sampling point number of the maximum power receiving path in the CIR determined based on the SRS or SRS-Pos, and then can determine the positioning result of the terminal based on the time domain sampling point number of the maximum power receiving path in the CIR determined based on the SRS or SRS-Pos and the first AI model.

[0309] In one possible implementation, when the first node is an access network device and the second node is a terminal, the second data is SRS or SRS-Pos. The access network device obtains SRS or SRS-Pos from the terminal and can determine the power value of the maximum power receiving path in the CIR determined based on SRS or SRS-Pos. Then, the positioning result of the terminal can be determined based on the power value of the maximum power receiving path in the CIR determined based on SRS or SRS-Pos and the first AI model.

[0310] In some embodiments, when the first node is an LMF and the second node is a terminal, the LMF can send a second request message to the terminal to request to obtain the second data. Further, the LMF can receive the second message sent by the terminal, and the second message is used to indicate the second data. Thus, the LMF can obtain the second data from the terminal to determine the positioning result of the terminal at the LMF based on the second data and the first AI model.

[0311] In some embodiments, when the first node is an LMF and the second node is a terminal, the second data may be at least one of the following: a CIR determined based on a PRS; a time domain sampling point number of a receiving path with the maximum power in the CIR determined based on the PRS; or a power value of a receiving path with the maximum power in the CIR determined based on the PRS.

[0312] In some embodiments, when the first node is LMF and the second node is an access network device, the LMF can send a second request message to the access network device to request to obtain the second data. Further, the LMF can receive the second message sent by the access network device, and the second message is used to indicate the second data. Thus, the LMF can obtain the second data from the access network device to determine the positioning result of the terminal at the LMF based on the second data and the first AI model.

[0313] In some embodiments, when the first node is an LMF and the second node is an access network device, the second data may be at least one of the following: a CIR determined based on SRS; a time domain sampling point number of the maximum power receiving path in the CIR determined based on SRS; a power value of the maximum power receiving path in the CIR determined based on SRS; a CIR determined based on SRS-Pos; a time domain sampling point number of the maximum power receiving path in the CIR determined based on SRS-Pos; a power value of the maximum power receiving path in the CIR determined based on SRS-Pos.

[0314] S507A, the first node determines the second data.

[0315] In some embodiments, the second data is used by the first node to determine the positioning result of the terminal based on the first AI model.

[0316] In some embodiments, the first node may determine the second data by itself, or the first node may obtain the second data from other nodes to determine the second data.

[0317] In some embodiments, when the first node is a terminal, the terminal determines the second data by itself, and the second data can be at least one of the following: PRS; CIR determined based on PRS; time domain sampling point number of the maximum power receiving path in the CIR determined based on PRS; power value of the maximum power receiving path in the CIR determined based on PRS.

[0318] In some embodiments, when the first node is an access network device, the access network device determines the second data by itself, and the second data may be at least one of the following: SRS; SRS-Pos; CIR determined based on SRS; time domain sampling point number of the maximum power receiving path in the CIR determined based on SRS; power value of the maximum power receiving path in the CIR determined based on SRS; CIR determined based on SRS-Pos; time domain sampling point number of the maximum power receiving path in the CIR determined based on SRS-Pos; power value of the maximum power receiving path in the CIR determined based on SRS-Pos; CIR determined based on PRS; time domain sampling point number of the maximum power receiving path in the CIR determined based on PRS; power value of the maximum power receiving path in the CIR determined based on PRS.

[0319] In some embodiments, the first node determines the second data, including the first node receiving a second message sent by the second node, where the second message is used to indicate the second data, and the first node determines the second data according to the second message.

[0320] In some embodiments, the first node determines the second data, including the first node sending a second request message to the second node, the second request message requests to obtain the second data, further, the first node receives a second message sent by the second node, the second message is used to indicate the second data, and the first node determines the second data based on the second message.

[0321] In some embodiments, the first node is a terminal and the second node is an access network device or LMF; or the first node is an access network device and the second node is a terminal or LMF; or the first node is an LMF and the second node is a terminal or an access network device.

[0322] S508A: The first node determines a positioning result of the terminal based on the second data and the first AI model.

[0323] In the embodiment of the present disclosure, the first node can determine the positioning result of the terminal by determining the second data and the first AI model.

[0324] In some embodiments, the positioning result of the terminal is the location coordinates of the terminal.

[0325] In some embodiments, the positioning result of the terminal is the absolute position coordinates or relative position coordinates of the terminal.

[0326] In some embodiments, the first node determines a first AI model based on the first data and the first module.

[0327] In some embodiments, the first AI model is configured at the first node, and the first node can determine the first AI model based on the first data and the first module.

[0328] In some embodiments, the first AI model is capable of locating the terminal.

[0329] Exemplarily, the first node inputs the second data into the first AI model, and the output result of the first AI model can indicate the positioning result of the terminal.

[0330] In some embodiments, before determining the positioning result of the terminal based on the second data and the first AI model, the first AI model may be trained.

[0331] Among them, the training of the first AI model can be completed at the first node, or it can also be completed at other nodes, and the trained first AI model is configured at the first node.

[0332] In some embodiments, the first AI model can be trained using a training data set, where the training data set includes sample input data and corresponding sample output data. When the sample input data is input into the first AI model to obtain predicted output data, the parameters of the first AI model can be updated based on the predicted output data and the sample output data. When the conditions are met, the training of the first AI model is determined to be completed to obtain a trained first AI model.

[0333] In an embodiment of the present disclosure, the first node can determine the first AI model among multiple AI models for positioning the terminal based on the first data and the first module. The first data can reflect the channel scenario or channel condition, and the selected first AI model can be applicable to the current channel scenario or channel condition, so that when the first node determines the second data and uses the second data and the first AI model to position the terminal, it can obtain a more accurate terminal positioning result.

[0334] In some embodiments, the first node determines the positioning result of the terminal based on the second data and the first AI model, including: determining the first parameter based on the second data and the first AI model; and determining the positioning result of the terminal based on the first parameter.

[0335] In an embodiment of the present disclosure, the first node determines the positioning result of the terminal based on the second data and the first AI model, and can determine the first parameter based on the second data and the first AI model, and then determine the positioning result of the terminal based on the first parameter.

[0336] In some embodiments, the first parameter includes at least one of ToA and AoA.

[0337] In some embodiments, the first node determines the positioning result of the terminal based on the first parameter, and can use traditional positioning methods such as TDOA to determine the positioning result of the terminal based on the first parameter, for example, determine the position coordinates of the terminal.

[0338] 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.

[0339] 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.

[0340] In some embodiments, terms such as "send", "transmit", "report", "download", "transmit", "bidirectional transmission", "send and / or receive" can be used interchangeably.

[0341] In some embodiments, terms such as "certain", "preset", "preset", "setting", "indicated", "a certain", "any", and "first" can be interchangeable. "Specific A", "preset A", "preset A", "setting A", "indicated A", "a certain A", "any A", and "first A" can be interpreted as A pre-specified in a protocol, etc., or as A obtained through setting, configuration, or indication, etc., or as specific A, a certain A, any A, or first A, etc., but not limited to this.

[0342] The communication method involved in the embodiments of the present disclosure may include at least one of S501A to S508A. For example, S501A may be implemented as an independent embodiment, S502A may be implemented as an independent embodiment, S503A may be implemented as an independent embodiment, S504A may be implemented as an independent embodiment, S505A may be implemented as an independent embodiment, S506A may be implemented as an independent embodiment, S507A may be implemented as an independent embodiment, S508A may be implemented as an independent embodiment, S503A+S504A may be implemented as an independent embodiment, S502A+S503A+S508A may be implemented as an independent embodiment. 504A can be implemented as an independent embodiment, S501A+S502A+S503A+S504A can be implemented as an independent embodiment, S507A+S508A can be implemented as an independent embodiment, S506A+S507A+S508A can be implemented as an independent embodiment, S505A+S506A+S507A+S508A can be implemented as an independent embodiment, and S503A+S504A+S507A+S508A can be implemented as an independent embodiment, but are not limited to this.

[0343] In some embodiments, S503A and S507A may be executed in an exchanged order or simultaneously, and S504A and S508A may be executed in an exchanged order or simultaneously.

[0344] In some embodiments, S502A and S506A may be executed in an exchanged order or simultaneously, and S501A and S505A may be executed in an exchanged order or simultaneously.

[0345] In some embodiments, S501A, S502A, S505A, S506A, S507A, and S508A are optional, and one or more of these steps may be omitted or replaced in different embodiments.

[0346] In some embodiments, S501A, S502A, S507A, and S508A are optional, and one or more of these steps may be omitted or replaced in different embodiments.

[0347] In some embodiments, S501A, S505A, S506A, S507A, and S508A are optional, and one or more of these steps may be omitted or replaced in different embodiments.

[0348] In some embodiments, S505A, S506A, S507A, and S508A are optional, and one or more of these steps may be omitted or replaced in different embodiments.

[0349] In some embodiments, S505A and S506A are optional, and one or more of these steps may be omitted or replaced in different embodiments.

[0350] In some embodiments, S505A is optional, and one or more of these steps may be omitted or replaced in different embodiments.

[0351] In some embodiments, reference may be made to other optional implementations described before or after the description corresponding to FIG. 5A .

[0352] FIG5B is an interactive diagram of a model selection method according to an embodiment of the present disclosure. As shown in FIG5B , the embodiment of the present disclosure relates to a model selection method, which includes:

[0353] S501B: The first node sends a first request message to the second node.

[0354] In some embodiments, the first request message is used to request obtaining first data for model selection.

[0355] S502B: The second node sends a first message to the first node.

[0356] In some embodiments, the first message is used to indicate first data for model selection.

[0357] S503B: The first node determines first data for model selection.

[0358] S504B: The first node determines, based on the first data, a first AI model among multiple AI models for positioning the terminal.

[0359] For the related descriptions of S501B to S504B, reference may be made to the related descriptions of S501A to S504A in FIG5A , which will not be repeated here.

[0360] Among them, the optional implementation methods of S501B to S504B can refer to the optional implementation methods of S501A to S504A in Figure 5A and other related parts in the embodiment involved in Figure 2, and will not be repeated here.

[0361] S505B: The first node sends indication information to the second node.

[0362] In some embodiments, the second node receives the indication information sent by the first node.

[0363] In some embodiments, the indication information is used to indicate the determined first AI model, and the first AI model is used by the second node to locate the terminal based on the second data.

[0364] In some embodiments, the first AI model is configured at the second node.

[0365] In some embodiments, the indication information is used to indicate an identifier corresponding to the determined first AI model, and the second node determines the first AI model according to the identifier.

[0366] In some embodiments, the name of the indication information is not limited.

[0367] In the embodiment of the present disclosure, the second node receives the indication information sent by the first node, can determine the first AI model, and further determine the first AI model used when positioning the terminal, thereby using the first AI model that matches the current channel scenario or channel condition, which can improve the accuracy of terminal positioning and ensure a higher terminal positioning accuracy.

[0368] S506B: The second node determines the first AI model.

[0369] In some embodiments, the second node determines the first AI model based on its own configuration, or determines the first AI model based on instructions from other nodes, or determines the first AI model based on protocol agreement.

[0370] In some embodiments, the second node determines the first AI model based on the indication information, wherein the indication information is sent by the first node to the second node, and the indication information is used to indicate the first AI model.

[0371] In some embodiments, the indication information is used to indicate a first AI model determined by the first node, and the first AI model is used by the second node to locate the terminal based on the second data.

[0372] In some embodiments, the indication information is used to indicate an identifier corresponding to the first AI model, and the second node determines the first AI model based on the indication information, that is, the identifier.

[0373] S507B: The second node sends a third request message to the first node.

[0374] In some embodiments, the first node receives a third request message sent by the second node.

[0375] In some embodiments, the third request message is used to request acquisition of the second data.

[0376] In some embodiments, the third request message is used to request acquisition of second data for positioning the terminal.

[0377] In some embodiments, the third request message is used to request obtaining second data as input to the first AI model.

[0378] In some embodiments, the name of the third request message is not limited, and it can be, for example, "third message", "third information", etc.

[0379] It can be understood that the second data is the input data of the first AI model, and the first AI model is used to locate the terminal. When the second data is input into the first AI model, the positioning result of the terminal can be output.

[0380] In some embodiments, the second data is used by the second node to determine the positioning result of the terminal based on the first AI model.

[0381] It should be noted that, for the relevant description of the second data, reference can be made to the relevant description in the above embodiment, which will not be repeated here.

[0382] In some embodiments, the first node is a terminal and the second node is an access network device, so that the access network device can send a third request message to the terminal to request to obtain the second data.

[0383] In some embodiments, the first node is an access network device, and the second node is a terminal, so that the terminal can send a third request message to the access network device to request to obtain the second data.

[0384] In some embodiments, the first node is a LMF and the second node is a terminal, so that the terminal can send a third request message to the LMF to request to obtain the second data.

[0385] In one possible implementation, at least a third request message is sent to the LMF through the AMF to request the second data.

[0386] In some embodiments, the first node is an LMF and the second node is an access network device, so that the access network device can send a third request message to the LMF to request to obtain the second data.

[0387] In some embodiments, the second node may send the third request message to the first node on its own, or may send the third request message to the first node when it is determined that a specific condition is met.

[0388] Exemplarily, when determining that the terminal needs to be located, the second node sends a third request message to the first node.

[0389] S508B: The first node sends a third message to the second node.

[0390] In some embodiments, the second node receives the third message sent by the first node.

[0391] In some embodiments, the third message is used to indicate second data, and the second data is used by the second node to locate the terminal based on the first AI model.

[0392] In some embodiments, the third message is used to indicate the second data requested by the second request message.

[0393] In some embodiments, the third message is used to indicate second data for positioning the terminal.

[0394] In some embodiments, the third message is used to indicate second data serving as input data of the first AI model.

[0395] In some embodiments, the name of the third message is not limited, and it can be, for example, "third response message", "third feedback information", etc.

[0396] In the embodiment of the present disclosure, the first node may send a third message to the second node to provide the second node with second data.

[0397] In some embodiments, the second data is used by the second node to determine the positioning result of the terminal based on the first AI model.

[0398] In some embodiments, upon receiving a third request message sent by the second node, the first node sends a third message to the second node, where the third request message is used to request the acquisition of the second data, and the third message is used to indicate the second data, so that the second node can obtain the second data from the first node, and use the second data and the first AI model at the second node to determine the positioning result of the terminal.

[0399] In some embodiments, when the first node is an access network device and the second node is a terminal, the terminal can send a third request message to the access network device to request to obtain the second data. Furthermore, the terminal can receive a third message sent by the access network device, and the third message is used to indicate the second data. Thus, the terminal can obtain the second data from the access network device to determine the positioning result of the terminal at the terminal based on the second data and the first AI model.

[0400] In which, when the first node is an access network device and the second node is a terminal, the second data can be at least one of the following: PRS; CIR determined based on SRS; time domain sampling point number of the maximum power receiving path in the CIR determined based on SRS; power value of the maximum power receiving path in the CIR determined based on SRS; CIR determined based on SRS-Pos; time domain sampling point number of the maximum power receiving path in the CIR determined based on SRS-Pos; power value of the maximum power receiving path in the CIR determined based on SRS-Pos.

[0401] In one possible implementation, when the first node is an access network device and the second node is a terminal, the second data is a PRS. The terminal obtains the PRS from the access network device and can determine the CIR determined based on the PRS. Then, the positioning result of the terminal can be determined based on the CIR determined based on the PRS and the first AI model.

[0402] In one possible implementation, when the first node is an access network device and the second node is a terminal, the second data is a PRS. The terminal obtains the PRS from the access network device and can determine the time domain sampling point number of the maximum power receiving path in the CIR determined based on the PRS. Then, the positioning result of the terminal can be determined based on the time domain sampling point number of the maximum power receiving path in the CIR determined based on the PRS and the first AI model.

[0403] In one possible implementation, when the first node is an access network device and the second node is a terminal, the second data is a PRS. The terminal obtains the PRS from the access network device and can determine the power value of the maximum power receiving path in the CIR determined based on the PRS. Then, the positioning result of the terminal can be determined based on the power value of the maximum power receiving path in the CIR determined based on the PRS and the first AI model.

[0404] In some embodiments, when the first node is a terminal and the second node is an access network device, the access network device can send a third request message to the terminal to request to obtain the second data. Furthermore, the access network device can receive the third message sent by the terminal, and the third message is used to indicate the second data. Thus, the access network device can obtain the second data from the terminal to determine the positioning result of the terminal at the access network device based on the second data and the first AI model.

[0405] In some embodiments, when the first node is a terminal and the second node is an access network device, the second data may be at least one of the following: SRS; SRS-Pos; CIR determined based on PRS; time domain sampling point number of the maximum power receiving path in the CIR determined based on PRS; power value of the maximum power receiving path in the CIR determined based on PRS.

[0406] In one possible implementation, when the first node is a terminal and the second node is an access network device, the second data is SRS or SRS-Pos. The access network device obtains the SRS or SRS-Pos from the terminal and can determine the CIR determined based on the SRS or SRS-Pos. Then, the positioning result of the terminal can be determined based on the CIR determined based on the SRS or SRS-Pos and the first AI model.

[0407] In one possible implementation, when the first node is a terminal and the second node is an access network device, the second data is SRS or SRS-Pos. The access network device obtains the SRS or SRS-Pos from the terminal and can determine the time domain sampling point number of the maximum power receiving path in the CIR determined based on the SRS or SRS-Pos. Then, the positioning result of the terminal can be determined based on the time domain sampling point number of the maximum power receiving path in the CIR determined based on the SRS or SRS-Pos and the first AI model.

[0408] In one possible implementation, when the first node is a terminal and the second node is an access network device, the second data is SRS or SRS-Pos. The access network device obtains SRS or SRS-Pos from the terminal and can determine the power value of the maximum power receiving path in the CIR determined based on SRS or SRS-Pos. Then, the positioning result of the terminal can be determined based on the power value of the maximum power receiving path in the CIR determined based on SRS or SRS-Pos and the first AI model.

[0409] In some embodiments, when the first node is a terminal and the second node is an LMF, the LMF can send a third request message to the terminal to request to obtain the second data. Further, the LMF can receive the third message sent by the terminal, and the third message is used to indicate the second data. Thus, the LMF can obtain the second data from the terminal to determine the positioning result of the terminal at the LMF based on the second data and the first AI model.

[0410] In some embodiments, when the first node is a terminal and the second node is an LMF, the second data may be at least one of the following: a CIR determined based on a PRS; a time domain sampling point number of the maximum power receiving path in the CIR determined based on the PRS; or a power value of the maximum power receiving path in the CIR determined based on the PRS.

[0411] In some embodiments, when the first node is an access network device and the second node is LMF, the LMF can send a third request message to the access network device to request to obtain the second data. Further, the LMF can receive the third message sent by the access network device, and the third message is used to indicate the second data. Thus, the LMF can obtain the second data from the access network device to determine the positioning result of the terminal at the LMF based on the second data and the first AI model.

[0412] In some embodiments, when the first node is an access network device and the second node is an LMF, the second data may be at least one of the following: a CIR determined based on SRS; a time domain sampling point number of the maximum power receiving path in the CIR determined based on SRS; a power value of the maximum power receiving path in the CIR determined based on SRS; a CIR determined based on SRS-Pos; a time domain sampling point number of the maximum power receiving path in the CIR determined based on SRS-Pos; a power value of the maximum power receiving path in the CIR determined based on SRS-Pos.

[0413] S509B: The second node determines the second data.

[0414] In some embodiments, the second data is used by the second node to determine the positioning result of the terminal based on the first AI model.

[0415] In some embodiments, the second node may determine the second data by itself, or the second node may obtain the second data from other nodes to determine the second data.

[0416] In some embodiments, when the second node is a terminal, the terminal determines the second data by itself, and the second data can be at least one of the following: PRS; CIR determined based on PRS; time domain sampling point number of the maximum power receiving path in the CIR determined based on PRS; power value of the maximum power receiving path in the CIR determined based on PRS.

[0417] In some embodiments, when the second node is an access network device, the access network device determines the second data by itself, and the second data may be at least one of the following: SRS; SRS-Pos; CIR determined based on SRS; time domain sampling point number of the maximum power receiving path in the CIR determined based on SRS; power value of the maximum power receiving path in the CIR determined based on SRS; CIR determined based on SRS-Pos; time domain sampling point number of the maximum power receiving path in the CIR determined based on SRS-Pos; power value of the maximum power receiving path in the CIR determined based on SRS-Pos; CIR determined based on PRS; time domain sampling point number of the maximum power receiving path in the CIR determined based on PRS; power value of the maximum power receiving path in the CIR determined based on PRS.

[0418] In some embodiments, the second node determines the second data, including the second node receiving a third message sent by the first node, where the third message is used to indicate the second data, and the second node determines the second data according to the third message.

[0419] In some embodiments, the second node determines the second data, including the second node sending a third request message to the first node, the third request message requests to obtain the second data, further, the second node receives the third message sent by the first node, the third message is used to indicate the second data, and the second node determines the second data based on the third message.

[0420] In some embodiments, the first node is an access network device, and the second node is a terminal or LMF; or the first node is a terminal, and the second node is an access network device or LMF; or the first node is an LMF, and the second node is a terminal or an access network device.

[0421] S510B: The second node determines the positioning result of the terminal based on the second data and the first AI model.

[0422] In some embodiments, after determining the second data and the first AI model, the second node may determine the positioning result of the terminal based on the second data and the first AI model.

[0423] In some embodiments, the positioning result of the terminal is the location coordinates of the terminal.

[0424] In some embodiments, the positioning result of the terminal is the absolute position coordinates or relative position coordinates of the terminal.

[0425] In some embodiments, the second node determines the first AI model based on the indication information sent by the first node.

[0426] In some embodiments, the first AI model is configured at the second node, and the second node may determine the first AI model based on the indication information sent by the first node.

[0427] In some embodiments, the first AI model is capable of locating the terminal.

[0428] Exemplarily, the second node inputs the second data into the first AI model, and the output result of the first AI model can indicate the positioning result of the terminal.

[0429] In some embodiments, before determining the positioning result of the terminal based on the second data and the first AI model, the first AI model may be trained.

[0430] Among them, the training of the first AI model can be completed at the second node, or it can also be completed at other nodes, and the trained first AI model is configured at the second node.

[0431] In some embodiments, the first AI model can be trained using a training data set, where the training data set includes sample input data and corresponding sample output data. When the sample input data is input into the first AI model to obtain predicted output data, the parameters of the first AI model can be updated based on the predicted output data and the sample output data. When the conditions are met, the training of the first AI model is determined to be completed to obtain a trained first AI model.

[0432] In an embodiment of the present disclosure, the second node can determine the first AI model for positioning the terminal from multiple AI models based on the indication information sent by the first node. Since the first node determines the first AI model based on the first data and the first module, the first data can reflect the channel scenario or channel conditions, and the selected first AI model can be applicable to the current channel scenario or channel conditions. Therefore, when the second node determines the second data and uses the second data and the first AI model to position the terminal, it can obtain a more accurate terminal positioning result.

[0433] In some embodiments, the second node determines the positioning result of the terminal based on the second data and the first AI model, including: determining the first parameter based on the second data and the first AI model; and determining the positioning result of the terminal based on the first parameter.

[0434] In an embodiment of the present disclosure, the second node determines the positioning result of the terminal based on the second data and the first AI model, and can determine the first parameter based on the second data and the first AI model, and then determine the positioning result of the terminal based on the first parameter.

[0435] In some embodiments, the first parameter includes at least one of ToA and AoA.

[0436] In some embodiments, the second node determines the positioning result of the terminal based on the first parameter, and can use traditional positioning methods such as TDOA to determine the positioning result of the terminal based on the first parameter, for example, determine the position coordinates of the terminal.

[0437] It should be noted that, for the relevant description of the first node and the second node, reference can be made to the relevant description in the above embodiment, which will not be repeated here.

[0438] The communication method involved in the embodiments of the present disclosure may include at least one of S501B to S510B. For example, S501B can be implemented as an independent embodiment, S502B can be implemented as an independent embodiment, S503B can be implemented as an independent embodiment, S504B can be implemented as an independent embodiment, S505B can be implemented as an independent embodiment, S506B can be implemented as an independent embodiment, S507B can be implemented as an independent embodiment, S508B can be implemented as an independent embodiment, S509B can be implemented as an independent embodiment, S510B can be implemented as an independent embodiment, S503B+S504B can be implemented as an independent embodiment, S503B+S504B+S505B can be implemented as an independent embodiment, S502B+S503B+S 504B can be implemented as an independent embodiment, S501B+S502B+S503B+S504B can be implemented as an independent embodiment, S509B+S510B can be implemented as an independent embodiment, S508B+S509B+S510B can be implemented as an independent embodiment, S507B+S508B+S509B+S510B can be implemented as an independent embodiment, S506B+S509B+S510B can be implemented as an independent embodiment, S505B+S509B+S510B can be implemented as an independent embodiment, and S503B+S504B+S505B+S509B+S510B can be implemented as an independent embodiment, but are not limited to this.

[0439] In some embodiments, S501B, S502B, S505B, S506B, S507B, S508B, S509B, and S510B are optional, and one or more of these steps may be omitted or replaced in different embodiments.

[0440] In some embodiments, S501B, S502B, S506B, S507B, S508B, S509B, and S510B are optional, and one or more of these steps may be omitted or replaced in different embodiments.

[0441] In some embodiments, S501B, S505B, S506B, S507B, S508B, S509B, and S510B are optional, and one or more of these steps may be omitted or replaced in different embodiments.

[0442] In some embodiments, S505B, S506B, S507B, S508B, S509B, and S510B are optional, and one or more of these steps may be omitted or replaced in different embodiments.

[0443] In some embodiments, S501B, S502B, S506B, S507B, and S508B are optional, and one or more of these steps may be omitted or replaced in different embodiments.

[0444] In some embodiments, S501B, S502B, S506B, and S507B are optional, and one or more of these steps may be omitted or replaced in different embodiments.

[0445] In some embodiments, S501B, S502B, and S506B are optional, and one or more of these steps may be omitted or replaced in different embodiments.

[0446] In some embodiments, reference may be made to other optional implementations described before or after the description corresponding to FIG. 5B .

[0447] FIG5C is an interactive diagram of a model selection method according to an embodiment of the present disclosure. As shown in FIG5C , the embodiment of the present disclosure relates to a model selection method, which includes:

[0448] S501C: The first node sends a first request message to the second node.

[0449] In some embodiments, the first request message is used to request obtaining first data for model selection.

[0450] S502C: The second node sends a first message to the first node.

[0451] In some embodiments, the first message is used to indicate first data for model selection.

[0452] S503C: The first node determines first data for model selection.

[0453] S504C: The first node determines, based on the first data, a first AI model from among multiple AI models for positioning the terminal.

[0454] For the related descriptions of S501C to S504C, reference may be made to the related descriptions of S501A to S504A in FIG5A , which will not be repeated here.

[0455] Among them, the optional implementation methods of S501C to S504C can refer to the optional implementation methods of S501A to S504A in Figure 5A and other related parts in the embodiment involved in Figure 2, and will not be repeated here.

[0456] S505C: The first node sends indication information to the third node.

[0457] In some embodiments, the third node receives the indication information sent by the first node.

[0458] In some embodiments, the indication information is used to indicate the determined first AI model, and the first AI model is used by the third node to locate the terminal based on the second data.

[0459] In some embodiments, the first AI model is configured at the third node.

[0460] In some embodiments, the indication information is used to indicate an identifier corresponding to the determined first AI model, and the third node determines the first AI model according to the identifier.

[0461] In some embodiments, the name of the indication information is not limited.

[0462] In the embodiment of the present disclosure, the third node receives the indication information sent by the first node, can determine the first AI model, and further determine the first AI model used when positioning the terminal, thereby using the first AI model that matches the current channel scenario or channel condition, which can improve the accuracy of terminal positioning and ensure a higher terminal positioning accuracy.

[0463] S506C: The third node determines the first AI model.

[0464] In some embodiments, the third node determines the first AI model based on its own configuration, or determines the first AI model based on instructions from other nodes, or determines the first AI model based on protocol agreement.

[0465] In some embodiments, the third node determines the first AI model based on the indication information, wherein the indication information is sent by the first node to the third node, and the indication information is used to indicate the first AI model.

[0466] In some embodiments, the indication information is used to indicate a first AI model determined by the first node, and the first AI model is used by the third node to locate the terminal based on the second data.

[0467] In some embodiments, the indication information is used to indicate an identifier corresponding to the first AI model, and the second node determines the first AI model based on the indication information, that is, the identifier.

[0468] S507C: The third node sends a third request message to the first node.

[0469] In some embodiments, the first node receives a third request message sent by the third node.

[0470] In some embodiments, the third request message is used to request acquisition of the second data.

[0471] In some embodiments, the third request message is used to request acquisition of second data for positioning the terminal.

[0472] In some embodiments, the third request message is used to request obtaining second data as input to the first AI model.

[0473] In some embodiments, the name of the third request message is not limited, and it can be, for example, "third message", "third information", etc.

[0474] It can be understood that the second data is the input data of the first AI model, and the first AI model is used to locate the terminal. When the second data is input into the first AI model, the positioning result of the terminal can be output.

[0475] In some embodiments, the second data is used by the third node to determine the positioning result of the terminal based on the first AI model.

[0476] It should be noted that, for the relevant description of the second data, reference can be made to the relevant description in the above embodiment, which will not be repeated here.

[0477] In some embodiments, the first node is a terminal, and the third node is an access network device, so that the access network device can send a third request message to the terminal to request to obtain the second data.

[0478] In some embodiments, the first node is an access network device, and the third node is a terminal, so that the terminal can send a third request message to the access network device to request to obtain the second data.

[0479] In some embodiments, the first node is an LMF and the third node is a terminal, so that the terminal can send a third request message to the LMF to request to obtain the second data.

[0480] In a possible implementation, the terminal sends a third request message to the LMF through the AMF, requesting to obtain the second data.

[0481] In some embodiments, the first node is an LMF and the third node is an access network device, so that the access network device can send a third request message to the LMF to request to obtain the second data.

[0482] In some embodiments, the third node may send the third request message to the first node on its own, or may send the third request message to the first node when it is determined that a specific condition is met.

[0483] Exemplarily, when determining that the terminal needs to be positioned, the third node sends a third request message to the first node.

[0484] In some embodiments, the first node is a terminal and the third node is a LMF; or

[0485] The first node is a terminal, the second node is an access network device, and the third node is a LMF; or

[0486] The first node is an access network device, and the third node is a LMF; or

[0487] The first node is an access network device, the second node is a terminal, and the third node is a LMF; or

[0488] The first node is an LMF, and the third node is a terminal or an access network device; or

[0489] The first node is an LMF, the second node is a terminal, and the third node is an access network device; or

[0490] The first node is the LMF, the second node is the access network device, and the third node is the terminal.

[0491] S508C: The first node sends a third message to the third node.

[0492] In some embodiments, the third node receives the third message sent by the first node.

[0493] In some embodiments, the third message is used to indicate second data, and the second data is used by the third node to locate the terminal based on the first AI model.

[0494] In some embodiments, the third message is used to indicate the second data requested by the second request message.

[0495] In some embodiments, the third message is used to indicate second data for positioning the terminal.

[0496] In some embodiments, the third message is used to indicate second data serving as input data of the first AI model.

[0497] In some embodiments, the name of the third message is not limited, and it can be, for example, "third response message", "third feedback information", etc.

[0498] In the embodiment of the present disclosure, the first node may send a third message to the third node to provide the third node with second data.

[0499] In some embodiments, the second data is used by the third node to determine the positioning result of the terminal based on the first AI model.

[0500] In some embodiments, upon receiving a third request message sent by a third node, the first node sends a third message to the third node, where the third request message is used to request the acquisition of the second data, and the third message is used to indicate the second data, so that the third node can obtain the second data from the first node, and use the second data and the first AI model at the third node to determine the positioning result of the terminal.

[0501] In some embodiments, when the first node is an access network device and the third node is a terminal, the terminal can send a third request message to the access network device to request to obtain the second data. Furthermore, the terminal can receive the third message sent by the access network device, and the third message is used to indicate the second data. Thus, the terminal can obtain the second data from the access network device to determine the positioning result of the terminal at the terminal based on the second data and the first AI model.

[0502] In which, when the first node is an access network device and the third node is a terminal, the second data can be at least one of the following: PRS; CIR determined based on SRS; time domain sampling point number of the maximum power receiving path in the CIR determined based on SRS; power value of the maximum power receiving path in the CIR determined based on SRS; CIR determined based on SRS-Pos; time domain sampling point number of the maximum power receiving path in the CIR determined based on SRS-Pos; power value of the maximum power receiving path in the CIR determined based on SRS-Pos.

[0503] In one possible implementation, when the first node is an access network device and the third node is a terminal, the second data is a PRS. The terminal obtains the PRS from the access network device and can determine the CIR determined based on the PRS. Then, the positioning result of the terminal can be determined based on the CIR determined based on the PRS and the first AI model.

[0504] In one possible implementation, when the first node is an access network device and the third node is a terminal, the second data is a PRS. The terminal obtains the PRS from the access network device and can determine the time domain sampling point number of the maximum power receiving path in the CIR determined based on the PRS. Then, the positioning result of the terminal can be determined based on the time domain sampling point number of the maximum power receiving path in the CIR determined based on the PRS and the first AI model.

[0505] In one possible implementation, when the first node is an access network device and the third node is a terminal, the second data is a PRS. The terminal obtains the PRS from the access network device and can determine the power value of the maximum power receiving path in the CIR determined based on the PRS. Then, the positioning result of the terminal can be determined based on the power value of the maximum power receiving path in the CIR determined based on the PRS and the first AI model.

[0506] In some embodiments, when the first node is a terminal and the third node is an access network device, the access network device can send a third request message to the terminal to request to obtain the second data. Furthermore, the access network device can receive the third message sent by the terminal, and the third message is used to indicate the second data. Thus, the access network device can obtain the second data from the terminal to determine the positioning result of the terminal at the access network device based on the second data and the first AI model.

[0507] In some embodiments, when the first node is a terminal and the third node is an access network device, the second data may be at least one of the following: SRS; SRS-Pos; CIR determined based on PRS; time domain sampling point number of the maximum power receiving path in the CIR determined based on PRS; power value of the maximum power receiving path in the CIR determined based on PRS.

[0508] In one possible implementation, when the first node is a terminal and the third node is an access network device, the second data is SRS or SRS-Pos. The access network device obtains the SRS or SRS-Pos from the terminal and can determine the CIR determined based on the SRS or SRS-Pos. Then, the positioning result of the terminal can be determined based on the CIR determined based on the SRS or SRS-Pos and the first AI model.

[0509] In one possible implementation, when the first node is a terminal and the third node is an access network device, the second data is SRS or SRS-Pos. The access network device obtains the SRS or SRS-Pos from the terminal and can determine the time domain sampling point number of the maximum power receiving path in the CIR determined based on the SRS or SRS-Pos. Then, the positioning result of the terminal can be determined based on the time domain sampling point number of the maximum power receiving path in the CIR determined based on the SRS or SRS-Pos and the first AI model.

[0510] In one possible implementation, when the first node is a terminal and the third node is an access network device, the second data is SRS or SRS-Pos. The access network device obtains SRS or SRS-Pos from the terminal and can determine the power value of the maximum power receiving path in the CIR determined based on SRS or SRS-Pos. Then, the positioning result of the terminal can be determined based on the power value of the maximum power receiving path in the CIR determined based on SRS or SRS-Pos and the first AI model.

[0511] In some embodiments, when the first node is a terminal and the third node is an LMF, the LMF can send a third request message to the terminal to request to obtain the second data. Further, the LMF can receive the third message sent by the terminal, and the third message is used to indicate the second data. Thus, the LMF can obtain the second data from the terminal to determine the positioning result of the terminal at the LMF based on the second data and the first AI model.

[0512] In some embodiments, when the first node is a terminal and the third node is an LMF, the second data may be at least one of the following: a CIR determined based on a PRS; a time domain sampling point number of a receiving path with the maximum power in the CIR determined based on the PRS; or a power value of a receiving path with the maximum power in the CIR determined based on the PRS.

[0513] In some embodiments, when the first node is an access network device and the third node is LMF, the LMF can send a third request message to the access network device to request to obtain the second data. Further, the LMF can receive the third message sent by the access network device, and the third message is used to indicate the second data. Thus, the LMF can obtain the second data from the access network device to determine the positioning result of the terminal at the LMF based on the second data and the first AI model.

[0514] In some embodiments, when the first node is an access network device and the third node is an LMF, the second data may be at least one of the following: a CIR determined based on SRS; a time domain sampling point number of the maximum power receiving path in the CIR determined based on SRS; a power value of the maximum power receiving path in the CIR determined based on SRS; a CIR determined based on SRS-Pos; a time domain sampling point number of the maximum power receiving path in the CIR determined based on SRS-Pos; a power value of the maximum power receiving path in the CIR determined based on SRS-Pos.

[0515] S509C, the third node determines the second data.

[0516] In some embodiments, the second data is used by the third node to determine the positioning result of the terminal based on the first AI model.

[0517] In some embodiments, the third node may determine the second data by itself, or the third node may obtain the second data from other nodes to determine the second data.

[0518] In some embodiments, when the third node is a terminal, the terminal determines the second data by itself, and the second data can be at least one of the following: PRS; CIR determined based on PRS; time domain sampling point number of the maximum power receiving path in the CIR determined based on PRS; power value of the maximum power receiving path in the CIR determined based on PRS.

[0519] In some embodiments, when the third node is an access network device, the access network device determines the second data by itself, and the second data may be at least one of the following: SRS; SRS-Pos; CIR determined based on SRS; time domain sampling point number of the maximum power receiving path in the CIR determined based on SRS; power value of the maximum power receiving path in the CIR determined based on SRS; CIR determined based on SRS-Pos; time domain sampling point number of the maximum power receiving path in the CIR determined based on SRS-Pos; power value of the maximum power receiving path in the CIR determined based on SRS-Pos; CIR determined based on PRS; time domain sampling point number of the maximum power receiving path in the CIR determined based on PRS; power value of the maximum power receiving path in the CIR determined based on PRS.

[0520] In some embodiments, the third node determines the second data, including the third node receiving a third message sent by the first node, where the third message is used to indicate the second data, and the third node determines the second data according to the third message.

[0521] In some embodiments, the third node determines the second data, including the third node sending a third request message to the first node, the third request message requests to obtain the second data, further, the third node receives a third message sent by the first node, the third message is used to indicate the second data, and the third node determines the second data based on the third message.

[0522] In some embodiments, the first node is an access network device, and the third node is a terminal or LMF; or the first node is a terminal, and the third node is an access network device or LMF; or the first node is an LMF, and the third node is a terminal or an access network device.

[0523] S510C: The third node determines a positioning result of the terminal based on the second data and the first AI model.

[0524] In some embodiments, when determining the second data and the first AI model, the third node may determine the positioning result of the terminal based on the second data and the first AI model.

[0525] In some embodiments, the positioning result of the terminal is the location coordinates of the terminal.

[0526] In some embodiments, the positioning result of the terminal is the absolute position coordinates or relative position coordinates of the terminal.

[0527] In some embodiments, the third node determines the first AI model based on the indication information sent by the first node.

[0528] In some embodiments, the first AI model is configured at a third node, and the third node may determine the first AI model based on the indication information sent by the first node.

[0529] In some embodiments, the first AI model is capable of locating the terminal.

[0530] Exemplarily, the third node inputs the second data into the first AI model, and the output result of the first AI model can indicate the positioning result of the terminal.

[0531] In some embodiments, before determining the positioning result of the terminal based on the second data and the first AI model, the first AI model may be trained.

[0532] Among them, the training of the first AI model can be completed at the third node, or it can also be completed at other nodes, and the trained first AI model is configured at the third node.

[0533] In some embodiments, the first AI model can be trained using a training data set, where the training data set includes sample input data and corresponding sample output data. When the sample input data is input into the first AI model to obtain predicted output data, the parameters of the first AI model can be updated based on the predicted output data and the sample output data. When the conditions are met, the training of the first AI model is determined to be completed to obtain a trained first AI model.

[0534] In an embodiment of the present disclosure, the third node can determine the first AI model for positioning the terminal from multiple AI models based on the indication information sent by the first node. Since the first node determines the first AI model based on the first data and the first module, the first data can reflect the channel scenario or channel condition, and the selected first AI model can be applicable to the current channel scenario or channel condition. Therefore, when the third node determines the second data and uses the second data and the first AI model to position the terminal, it can obtain a more accurate terminal positioning result.

[0535] In some embodiments, the third node determines the positioning result of the terminal based on the second data and the first AI model, including: determining the first parameter based on the second data and the first AI model; and determining the positioning result of the terminal based on the first parameter.

[0536] In the embodiment of the present disclosure, the third node determines the positioning result of the terminal based on the second data and the first AI model, and can determine the first parameter based on the second data and the first AI model, and then determine the positioning result of the terminal based on the first parameter.

[0537] In some embodiments, the first parameter includes at least one of ToA and AoA.

[0538] In some embodiments, the third node determines the positioning result of the terminal based on the first parameter, and can use traditional positioning methods such as TDOA to determine the positioning result of the terminal based on the first parameter, for example, determine the location coordinates of the terminal.

[0539] It should be noted that, for the relevant descriptions of the first node, the second node and the third node, reference can be made to the relevant descriptions in the above embodiments, which will not be repeated here.

[0540] The communication method involved in the embodiments of the present disclosure may include at least one of S501C to S510C. For example, S501C can be implemented as an independent embodiment, S502C can be implemented as an independent embodiment, S503C can be implemented as an independent embodiment, S504C can be implemented as an independent embodiment, S505C can be implemented as an independent embodiment, S506C can be implemented as an independent embodiment, S507C can be implemented as an independent embodiment, S508C can be implemented as an independent embodiment, S509C can be implemented as an independent embodiment, S510C can be implemented as an independent embodiment, S503C+S504C can be implemented as an independent embodiment, S503C+S504C+S505C can be implemented as an independent embodiment, S502C+S503C+S504C can be implemented as an independent embodiment. 504C can be implemented as an independent embodiment, S501C+S502C+S503C+S504C can be implemented as an independent embodiment, S509C+S510C can be implemented as an independent embodiment, S508C+S509C+S510C can be implemented as an independent embodiment, S507C+S508C+S509C+S510C can be implemented as an independent embodiment, S506C+S509C+S510C can be implemented as an independent embodiment, S505C+S509C+S510C can be implemented as an independent embodiment, and S503C+S504C+S505C+S509C+S510C can be implemented as an independent embodiment, but are not limited to this.

[0541] In some embodiments, S501C, S502C, S505C, S506C, S507C, S508C, S509C, and S510C are optional, and one or more of these steps may be omitted or replaced in different embodiments.

[0542] In some embodiments, S501C, S502C, S506C, S507C, S508C, S509C, and S510C are optional, and one or more of these steps may be omitted or replaced in different embodiments.

[0543] In some embodiments, S501C, S505C, S506C, S507C, S508C, S509C, and S510C are optional, and one or more of these steps may be omitted or replaced in different embodiments.

[0544] In some embodiments, S505C, S506C, S507C, S508C, S509C, and S510C are optional, and one or more of these steps may be omitted or replaced in different embodiments.

[0545] In some embodiments, S501C, S502C, S506C, S507C, and S508C are optional, and one or more of these steps may be omitted or replaced in different embodiments.

[0546] In some embodiments, S501C, S502C, S506C, and S507C are optional, and one or more of these steps may be omitted or replaced in different embodiments.

[0547] In some embodiments, S501C, S502C, and S506C are optional, and one or more of these steps may be omitted or replaced in different embodiments.

[0548] In some embodiments, reference may be made to other optional implementations described before or after the description corresponding to FIG. 5C .

[0549] FIG6A is a flow chart of a model selection method according to an embodiment of the present disclosure. As shown in FIG6A , the embodiment of the present disclosure relates to a model selection method, which is executed by a first node and includes:

[0550] S601A, obtain first data.

[0551] Among them, the optional implementation of S601A can refer to the optional implementation of S503A in Figure 5A and other related parts in the embodiment involved in Figure 5A, which will not be repeated here.

[0552] In some embodiments, the first node determines the first data by itself, or receives the first data sent by other nodes.

[0553] In some embodiments, the first node receives a first message sent by the second node, where the first message is used to indicate first data for model selection, thereby obtaining the first data. However, this is not limited to the above, and the first node may also receive a first message sent by other entities to obtain the first data.

[0554] In some embodiments, the first node obtains first data specified by a protocol.

[0555] In some embodiments, the first node obtains the first data from an upper layer(s).

[0556] In some embodiments, the first node performs processing to obtain first data.

[0557] In some embodiments, S601A is omitted, and the first node autonomously implements the function indicated by the first data, or the above function is default or by default.

[0558] In some embodiments, the first node receives a first message sent by the second node, wherein the first message is used to indicate first data for model selection; and the first data is determined according to the first message.

[0559] In some embodiments, the first node sends a first request message to the second node, where the first request message is used to request to obtain first data.

[0560] It should be noted that, for the relevant descriptions of the first node, the second node, and the first data, reference can be made to the relevant descriptions in the above embodiments, which will not be repeated here.

[0561] S602A: Determine, based on the first data, a first AI model among multiple AI models for positioning the terminal.

[0562] Among them, the optional implementation of S602A can refer to the optional implementation of S504A in Figure 5A and other related parts in the embodiment involved in Figure 5A, which will not be repeated here.

[0563] In some embodiments, the first node is configured with the first module, and the first node may determine the first module.

[0564] In some embodiments, the first node determines a first AI model for positioning the terminal from among multiple AI models based on the first data and the first module.

[0565] In the embodiments of the present disclosure, some or all of the steps and their optional implementations may be arbitrarily combined with some or all of the steps in other embodiments, or may be arbitrarily combined with the optional implementations of other embodiments.

[0566] FIG6B is a flow chart of a model selection method according to an embodiment of the present disclosure. As shown in FIG6B , the embodiment of the present disclosure relates to a model selection method, which is executed by a first node and includes:

[0567] S601B, obtain second data.

[0568] Among them, the optional implementation of S601B can refer to the optional implementation of S507A in Figure 5A and other related parts in the embodiment involved in Figure 5A, which will not be repeated here.

[0569] In some embodiments, the first node determines the second data by itself, or receives the second data sent by other nodes.

[0570] In some embodiments, the first node receives a second message sent by the second node, the second message is used to indicate second data, and the first node obtains the second data, but is not limited to this. The first node can also receive a second message sent by other entities to obtain the second data.

[0571] In some embodiments, the first node obtains second data specified by the protocol.

[0572] In some embodiments, the first node obtains the second data from an upper layer(s).

[0573] In some embodiments, the first node performs processing to obtain the second data.

[0574] In some embodiments, S601B is omitted, and the first node autonomously implements the function indicated by the second data, or the above function is default or by default.

[0575] In some embodiments, the first node determines the second data, including: receiving a second message sent by the second node, where the second message is used to indicate the second data; and determining the second data according to the second message.

[0576] In some embodiments, the first node sends a second request message to the second node, where the second request message is used to request to obtain second data.

[0577] It should be noted that, for the relevant description of the second data, reference can be made to the relevant description in the above embodiment, which will not be repeated here.

[0578] It should be noted that, for the relevant description of the first node and the second node, reference can be made to the relevant description in the above embodiment, which will not be repeated here.

[0579] S602B: Determine a positioning result of the terminal based on the second data and the first AI model.

[0580] Among them, the optional implementation of S602B can refer to the optional implementation of S508A in Figure 5A and other related parts in the embodiment involved in Figure 5A, which will not be repeated here.

[0581] In some embodiments, the first node determines the positioning result of the terminal based on the second data and the first AI model, including: determining the first parameter based on the second data and the first AI model; and determining the positioning result of the terminal based on the first parameter.

[0582] In some embodiments, the first parameter includes at least one of ToA and AoA.

[0583] In some embodiments, the first node uses the method shown in S601A and S602A of Figure 6A to determine the first AI model.

[0584] In some embodiments, S601B and S602B are implemented together with S601A and S602A of FIG. 6A .

[0585] In the embodiments of the present disclosure, some or all of the steps and their optional implementations may be arbitrarily combined with some or all of the steps in other embodiments, or may be arbitrarily combined with the optional implementations of other embodiments.

[0586] FIG6C is a flow chart of a model selection method according to an embodiment of the present disclosure. As shown in FIG6C , the embodiment of the present disclosure relates to a model selection method, which is executed by a first node and includes:

[0587] S601C, sending instruction information.

[0588] Among them, the optional implementation of S601C can refer to the optional implementation of S505B in Figure 5B and other related parts in the embodiment involved in Figure 5B, which will not be repeated here.

[0589] In some embodiments, the first node sends the indication information to the second node, but is not limited thereto, and the indication information may also be sent to other entities.

[0590] In some embodiments, the indication information is used to indicate the determined first AI model, and the first AI model is used by the second node to locate the terminal based on the second data.

[0591] In some embodiments, the indication information is used to indicate an identifier corresponding to the first AI model.

[0592] Optionally, the above-mentioned indication information is used by the second node to determine the first AI model. Its optional implementation method can be referred to the optional implementation method of S506B in Figure 5B and other related parts in the embodiment involved in Figure 5B, which will not be repeated here.

[0593] Among them, the optional implementation of S601C can refer to the optional implementation of S505C in Figure 5C and other related parts in the embodiment involved in Figure 5C, which will not be repeated here.

[0594] In some embodiments, the first node sends indication information to the third node, but is not limited thereto, and the first node may also send indication information to other entities.

[0595] In some embodiments, the indication information is used to indicate the determined first AI model, and the first AI model is used by the third node to locate the terminal based on the second data.

[0596] Optionally, the above-mentioned indication information is used by the third node to determine the first AI model. For optional implementations thereof, please refer to the optional implementation of S506C in FIG5C and other related parts in the embodiment involved in FIG5C , which will not be repeated here.

[0597] S602C: Receive a third request message.

[0598] Among them, the optional implementation of S602C can refer to the optional implementation of S507B in Figure 5B and other related parts in the embodiment involved in Figure 5B, which will not be repeated here.

[0599] In some embodiments, the first node receives the third request message sent by the second node, but is not limited thereto and may also receive the third request message sent by other entities.

[0600] Among them, the optional implementation of S602C can refer to the optional implementation of S507C in Figure 5C and other related parts in the embodiment involved in Figure 5C, which will not be repeated here.

[0601] In some embodiments, the first node receives the third request message sent by the third node, but is not limited thereto and may also receive the third request message sent by other entities.

[0602] In some embodiments, the first node obtains a third request message specified by the protocol.

[0603] In some embodiments, the first node obtains the third request message from an upper layer(s).

[0604] In some embodiments, the first node performs processing to obtain the third request message.

[0605] In some embodiments, S602C is omitted, and the first node autonomously implements the function indicated by the third request message, or the above function is default or by default.

[0606] In some embodiments, the third request message is used to request acquisition of the second data.

[0607] S603C, sending a third message.

[0608] Among them, the optional implementation of S603C can refer to the optional implementation of S508B in Figure 5B and other related parts in the embodiment involved in Figure 5B, which will not be repeated here.

[0609] In some embodiments, the first node sends the third message to the second node, but is not limited thereto, and the third message may also be sent to other entities.

[0610] In some embodiments, the third message is used to indicate second data, and the second data is used by the second node to locate the terminal based on the first AI model.

[0611] Optionally, the third message is used by the second node to determine the second data. Optional implementations thereof may refer to the optional implementations of S509B in FIG5B and other related parts of the embodiment involved in FIG5B , which will not be described in detail here.

[0612] Among them, the optional implementation of S603C can refer to the optional implementation of S508C in Figure 5C and other related parts in the embodiment involved in Figure 5C, which will not be repeated here.

[0613] In some embodiments, the first node sends the third message to the third node, but is not limited thereto, and the third message may also be sent to other entities.

[0614] In some embodiments, the third message is used to indicate second data, and the second data is used by the third node to locate the terminal based on the first AI model.

[0615] Optionally, the third message is used by the third node to determine the second data. Optional implementations thereof may refer to the optional implementations of S509C in FIG5C and other related parts of the embodiment involved in FIG5C , which will not be described in detail here.

[0616] It should be noted that, for the relevant descriptions of the first node, the second node, and the third node, reference can be made to the relevant descriptions in the above embodiments, which will not be repeated here.

[0617] In some embodiments, the first node uses the method shown in S601A and S602A of Figure 6A to determine the first AI model.

[0618] In some embodiments, S601B and S602B are implemented together with S601A and S602A of FIG. 6A .

[0619] The communication method involved in the embodiments of the present disclosure may include at least one of S601C to S603C. For example, S601C may be implemented as an independent embodiment, S602C may be implemented as an independent embodiment, and S603C may be implemented as an independent embodiment, but are not limited thereto.

[0620] In some embodiments, S602C and S603C are optional, and one or more of these steps may be omitted or replaced in different embodiments.

[0621] In some embodiments, S602C is optional, and one or more of these steps may be omitted or replaced in different embodiments.

[0622] In the embodiments of the present disclosure, some or all of the steps and their optional implementations may be arbitrarily combined with some or all of the steps in other embodiments, or may be arbitrarily combined with the optional implementations of other embodiments.

[0623] FIG7A is a flow chart of a model selection method according to an embodiment of the present disclosure. As shown in FIG7A , the embodiment of the present disclosure relates to a model selection method, which is executed by the second node and includes:

[0624] S701A, send a first message.

[0625] Among them, the optional implementation of S701A can refer to the optional implementation of S502A in Figure 5A and other related parts in the embodiment involved in Figure 5A, which will not be repeated here.

[0626] In some embodiments, the second node sends the first message to the first node, but is not limited thereto, and the first message may also be sent to other entities.

[0627] Optionally, the first message is used by the first node to determine the first data. Optional implementations thereof may refer to the optional implementations of S503A in FIG5A and other related parts of the embodiment involved in FIG5A , which will not be described in detail here.

[0628] In some embodiments, the first message is used to indicate first data for model selection, and the first data is used by the first node to determine a first AI model for positioning the terminal among multiple AI models based on the first module.

[0629] In some embodiments, the second node receives a first request message sent by the first node, where the first request message is used to request to obtain the first data.

[0630] It should be noted that, for the relevant descriptions of the first node, the second node, and the first data, reference can be made to the relevant descriptions in the above embodiments, which will not be repeated here.

[0631] In the embodiments of the present disclosure, some or all of the steps and their optional implementations may be arbitrarily combined with some or all of the steps in other embodiments, or may be arbitrarily combined with the optional implementations of other embodiments.

[0632] FIG7B is a flow chart of a model selection method according to an embodiment of the present disclosure. As shown in FIG7B , the embodiment of the present disclosure relates to a model selection method, which is executed by the second node and includes:

[0633] S701B, send a second message.

[0634] Among them, the optional implementation of S701B can refer to the optional implementation of S506A in Figure 5A and other related parts in the embodiment involved in Figure 5A, which will not be repeated here.

[0635] In some embodiments, the second node sends the second message to the first node, but is not limited thereto, and the second message may also be sent to other entities.

[0636] Optionally, the second message is used by the first node to determine the second data. Optional implementations thereof may refer to the optional implementations of S507A in FIG5A and other related parts of the embodiment involved in FIG5A , which will not be described in detail here.

[0637] In some embodiments, the second message is used to indicate second data, and the second data is used by the first node to determine the positioning result of the terminal based on the first AI model.

[0638] In some embodiments, the second node receives a second request message sent by the first node, where the second request message is used to request to obtain second data.

[0639] It should be noted that, for the relevant descriptions of the first node, the second node, and the second data, reference can be made to the relevant descriptions in the above embodiments, which will not be repeated here.

[0640] In some embodiments, the second node also uses the method shown in S701A of Figure 7A to send the first message.

[0641] In some embodiments, S701B is implemented together with S701A of FIG. 7A .

[0642] In the embodiments of the present disclosure, some or all of the steps and their optional implementations may be arbitrarily combined with some or all of the steps in other embodiments, or may be arbitrarily combined with the optional implementations of other embodiments.

[0643] FIG7C is a flow chart of a model selection method according to an embodiment of the present disclosure. As shown in FIG7C , the embodiment of the present disclosure relates to a model selection method, which is executed by the second node and includes:

[0644] S701C, obtain instruction information.

[0645] Among them, the optional implementation of S701C can refer to the optional implementation of S505B in Figure 5B and other related parts in the embodiment involved in Figure 5B, which will not be repeated here.

[0646] In some embodiments, the second node receives the indication information sent by the first node, but is not limited thereto, and may also receive the indication information sent by other entities.

[0647] In some embodiments, the second node obtains indication information specified by the protocol.

[0648] In some embodiments, the second node obtains the indication information from upper layer(s).

[0649] In some embodiments, the second node performs processing to obtain the indication information.

[0650] In some embodiments, S701C is omitted, and the second node autonomously implements the function indicated by the indication information, or the above function is default or acquiescent.

[0651] In some embodiments, the indication information is used to indicate the first AI model, but is not limited thereto. The indication information may also be used to indicate an identifier corresponding to the first AI model.

[0652] In some embodiments, the second node determines the first AI model based on the indication information.

[0653] S702C: Send a third request message.

[0654] Among them, the optional implementation of S702C can refer to the optional implementation of S507B in Figure 5B and other related parts in the embodiment involved in Figure 5B, which will not be repeated here.

[0655] In some embodiments, the second node sends the third request message to the first node, but is not limited thereto, and the third request message may also be sent to other entities.

[0656] In some embodiments, the third request message is used to request acquisition of the second data.

[0657] It should be noted that, for the relevant description of the second data, reference can be made to the relevant description in the above embodiment, which will not be repeated here.

[0658] S703C, obtain the third message.

[0659] Among them, the optional implementation of S703C can refer to the optional implementation of S508B in Figure 5B and other related parts in the embodiment involved in Figure 5B, which will not be repeated here.

[0660] In some embodiments, the second node receives the third message sent by the first node, but is not limited thereto and may also receive the third message sent by other entities.

[0661] In some embodiments, the second node obtains a third message specified by the protocol.

[0662] In some embodiments, the second node obtains the third message from an upper layer(s).

[0663] In some embodiments, the second node performs processing to obtain the third message.

[0664] In some embodiments, S703C is omitted, and the second node autonomously implements the function indicated by the third message, or the above function is default or by default.

[0665] In some embodiments, the third message is used to indicate the second data.

[0666] S704C, determine the second data.

[0667] Among them, the optional implementation of S704C can refer to the optional implementation of S509B in Figure 5B and other related parts in the embodiment involved in Figure 5B, which will not be repeated here.

[0668] In some embodiments, the second node determines the second data based on the third message.

[0669] S705C: Determine a positioning result of the terminal based on the second data and the first AI model.

[0670] Among them, the optional implementation of S705C can refer to the optional implementation of S510B in Figure 5B and other related parts in the embodiment involved in Figure 5B, which will not be repeated here.

[0671] In some embodiments, the second node determines the positioning result of the terminal based on the second data and the first AI model, including: determining the first parameter based on the second data and the first AI model; and determining the positioning result of the terminal based on the first parameter.

[0672] In some embodiments, the first parameter includes at least one of ToA and AoA.

[0673] It should be noted that, for the relevant description of the first node and the second node, reference can be made to the relevant description in the above embodiment, which will not be repeated here.

[0674] In some embodiments, the second node also uses the method shown in S701A of Figure 7A to send the first message.

[0675] In some embodiments, S701C to S705C are implemented together with S701A of FIG. 7A .

[0676] The communication method involved in the embodiments of the present disclosure may include at least one of S701C to S705C. For example, S701C may be implemented as an independent embodiment, S702C may be implemented as an independent embodiment, S703C may be implemented as an independent embodiment, S704C may be implemented as an independent embodiment, S705C may be implemented as an independent embodiment, S704C + S705C may be implemented as an independent embodiment, and S703C + S705C may be implemented as an independent embodiment, but the present invention is not limited thereto.

[0677] In some embodiments, S701C and S703C may be executed simultaneously or in a swapped order.

[0678] In some embodiments, S702C and S703C are optional, and one or more of these steps may be omitted or replaced in different embodiments.

[0679] In some embodiments, S702C is optional, and one or more of these steps may be omitted or replaced in different embodiments.

[0680] In the embodiments of the present disclosure, some or all of the steps and their optional implementations may be arbitrarily combined with some or all of the steps in other embodiments, or may be arbitrarily combined with the optional implementations of other embodiments.

[0681] In the embodiments of the present disclosure, for application scenarios in which terminal positioning is completed based on a deep neural network model, during actual system application, different AI models are trained and stored for different channel scenarios or channel conditions to ensure positioning accuracy in various situations.

[0682] In some embodiments, before performing AI model positioning inference, it is necessary to first select an AI model that matches the input data. Based on the first module (model selection module), the AI ​​model selection is completed with higher accuracy and lower overhead, and then the corresponding AI model is activated, and then the terminal positioning is implemented using the AI ​​model suitable for the current channel scenario or channel conditions to ensure higher positioning accuracy.

[0683] Generally, the characteristics of channel measurement data under different channel scenarios or channel conditions are different. Therefore, a machine learning algorithm or neural network model for data classification can be used as the first module (model selection module). The model selection module inputs the channel measurement data and outputs the corresponding model type information, or outputs information such as the channel scenario or channel condition type related to the model type, and then selects the corresponding AI model according to the output of the model selection module and performs subsequent model inference.

[0684] For application modes 1, 2, and 4 as shown in Figure 3, the measurement data required for input to the model selection module is measured and obtained at the terminal or access network device. The AI ​​model is deployed at the same device that obtains the channel measurement data. The terminal or access network device can directly select the model based on the channel measurement data it obtains. That is, the measurement node is the same as the model selection and inference node, and does not involve the transmission of channel measurement data for model selection between communication nodes.

[0685] For application modes 3 and 5 shown in Figure 3, the model selection module requires input measurement data acquired at the terminal or access network device, while the AI ​​model is applied at the LMF. This involves the transmission of channel measurement data between communication nodes for model selection. In application modes 3 and 5, the measurement node typically includes a terminal or access network device, and the model selection and inference node typically refers to the LMF.

[0686] In addition, in the application of AI models in actual systems, there are two methods for executing model selection and model inference:

[0687] (1) The measurement node first provides channel measurement data for completing model selection. After the model selection and inference node completes model selection, the measurement node then sends the channel measurement data for completing positioning and performs the subsequent model inference process.

[0688] (2) The measurement node also provides channel measurement data for completing model selection and model inference. After the model selection and inference node completes model selection based on the data used for model selection, it directly completes model inference using the corresponding AI positioning model.

[0689] This solution proposes the following two steps for different situations.

[0690] In an exemplary embodiment, as shown in FIG8A , the measurement node is a terminal or access network device, and the model selection and inference node is an LMF. Process 1: first complete the model selection and then perform positioning model inference.

[0691] 1. The model selection and inference node sends a data request to the measurement node to complete the AI ​​model selection, specifying the type of data to be reported. The data type may include: complete CIR data obtained by the measurement node based on reference signal measurement, or other types of measurement data.

[0692] 2. The measurement node receives data requests from the model selection and inference nodes, measures and reports the corresponding data.

[0693] 3. The model selection and inference node receives the measurement data sent by the measurement node, uses the model selection module to complete the AI ​​positioning model selection, and completes the corresponding model activation. The model selection module may include a machine learning algorithm or neural network model for completing data classification. Its input is the data received by the model selection and inference node, and its output is information such as the AI ​​positioning model number, channel scenario, channel configuration, etc. This information can indicate the specific AI model to be used in the current situation.

[0694] 4. The activated AI model is applied to complete terminal positioning. That is, the model selection and inference node completes AI positioning model inference based on the channel measurement data reported by the measurement node to obtain the terminal location coordinates.

[0695] In an exemplary embodiment, as shown in FIG8B , the measurement node is a terminal or access network device, and the model selection and inference node is an LMF. Process 2: Model selection and inference are completed simultaneously.

[0696] 1. The measurement node sends measurement data for completing AI model selection and model inference. The data may include: complete CIR data obtained by the measurement node based on reference signal measurement, or other types of measurement data.

[0697] 2. The model selection and inference node completes the selection and activation of the AI ​​positioning model based on the data used for model selection reported by the measurement node.

[0698] The model selection and inference node applies the activated AI model and uses the measurement data reported by the measurement node to complete the terminal positioning.

[0699] It should be noted that in the above process, the measurement node needs to report the channel measurement data used for model selection to the model selection and inference nodes. According to the reporting data type supported by existing technologies, the following main methods can be included:

[0700] (1) Complete CIR data contains a lot of channel characteristic information. Based on the complete CIR data, it can better distinguish the input data under different channel scenarios and channel conditions. Therefore, the measurement node can directly report the complete CIR data, which can achieve higher model selection accuracy. However, the complete CIR data has a high dimensionality and requires a more complex model selection module, which in turn results in higher model storage and computational overhead. At the same time, the measurement node reporting the complete CIR data for model selection will also incur a large data transmission overhead.

[0701] (2) Existing technologies support reporting of RSRP data, the average power of received signals. Therefore, the average power is calculated based on the original CIR measurement value, and this power value can also be used as the input of the model selection module. However, although RSRP data has a very low dimensionality compared to the complete CIR data, and the corresponding model storage and computational overhead is low, RSRP is the average power value of the received signal and cannot reflect the data characteristics under different channel scenarios or channel conditions, and cannot achieve high model selection accuracy.

[0702] To achieve high-precision, low-overhead model selection, this paper proposes a model selection method based on the strongest receive path. In CIR data, the path with the highest power and the corresponding time-domain sampling point number can better represent the positional relationship between the receiver and transmitter, as well as conditions such as obstructions in the channel environment, and can reflect the data distribution characteristics under different channel scenarios or conditions. Furthermore, by using the strongest receive path power and time-domain sampling point number as input to the model selection module, the model complexity is low, and the data transmission overhead required to be reported by the measurement node is also low.

[0703] In solution processes 1 and 2, the channel measurement data reported by the measurement node for completing the AI ​​positioning model selection is: the time domain sampling point number and power value of the maximum power receiving path in the CIR data obtained based on the reference signal measurement. Therefore, it is possible to consider defining new measurement values ​​in the information reported by the measurement node to the LMF:

[0704] -nr-StrongestPathRSRP-Result

[0705] -nr-TapIndex

[0706] The representation and transmission of the RSRP of the maximum power receiving path are the same as those specified in the existing standards. The RSRP unit is converted to a dBm integer and then represented using 8 bits. The transmission of TapIndex can be encoded as follows: when there are □ sampling points in total, log2N bits are used to represent the sampling point number to be transmitted. In addition, according to data processing results, for the case of 256 sampling points, the maximum power receiving path usually appears in the first 100 sampling points. Therefore, in order to reduce transmission overhead, TapIndex can be only used The specific settings can be implemented according to the actual communication transmission requirements.

[0707] By implementing the embodiments of the present disclosure, for application scenarios in which terminal positioning is completed based on a deep neural network model, an application mode in which the LMF receives channel measurement data reported by the terminal or access network device and inputs it into the AI ​​model to directly obtain the terminal location coordinates is implemented. In order to solve the problem of AI model selection under different channel scenarios or channel conditions, the embodiments of the present disclosure propose an AI model selection module and related communication processes. The model selection and inference nodes complete the AI ​​model selection with higher accuracy and lower overhead based on the channel measurement data reported by the measurement node, which can better guarantee the performance of the AI ​​model in the actual system application process.

[0708] The present disclosure also provides an apparatus for implementing any of the above methods. For example, a device is provided that includes units or modules for implementing each step performed by the first node in any of the above methods. For another example, another device is provided that includes units or modules for implementing each step performed by the second node in any of the above methods.

[0709] 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.

[0710] 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.

[0711] FIG9A is a schematic diagram of the structure of a first node proposed in an embodiment of the present disclosure. As shown in FIG9A , the first node 10 may include at least one of a transceiver module 11 and a processing module 12 .

[0712] In some embodiments, the processing module 12 is used to determine first data for model selection; the transceiver module 11 is used to determine a first AI model for positioning the terminal among multiple AI models based on the first data.

[0713] Optionally, the transceiver module 11 is configured to execute at least one of the communication steps (e.g., S501A to S508A, S501B to S510B, S501C to S510C, but not limited thereto) such as sending and / or receiving performed by the first node 10 in any of the above methods, which are not described in detail here. Optionally, the processing module 12 is configured to execute at least one of the other steps (e.g., S501A to S508A, S501B to S510B, S501C to S510C, but not limited thereto) performed by the first node 10 in any of the above methods, which are not described in detail here.

[0714] FIG9B is a schematic diagram of the structure of the second node proposed in an embodiment of the present disclosure. As shown in FIG9B , the second node 20 may include: at least one of a transceiver module 21 and a processing module 22 .

[0715] In some embodiments, the above-mentioned transceiver module 21 is used to send a first message to the first node, wherein the first message is used to indicate first data for model selection, and the first data is used by the first node to determine the first AI model among multiple AI models for positioning the terminal.

[0716] Optionally, the transceiver module 21 is configured to execute at least one of the communication steps (e.g., S501A to S508A, S501B to S510B, S501C to S510C, but not limited thereto) performed by the second node 20 in any of the above methods, which are not described in detail here. Optionally, the processing module 22 is configured to execute at least one of the other steps (e.g., S501A to S508A, S501B to S510B, S501C to S510C, but not limited thereto) performed by the second node 20 in any of the above methods, which are not described in detail here.

[0717] In some embodiments, the transceiver module may include a transmitting module and / or a receiving module, and the transmitting module and the receiving module may be separate or integrated. Optionally, the transceiver module may be interchangeable with the transceiver.

[0718] In some embodiments, the processing module can be a single module or can include multiple submodules. Optionally, the multiple submodules respectively execute all or part of the steps required to be executed by the processing module. Optionally, the processing module can be interchangeable with the processor.

[0719] Figure 10A is a schematic diagram of the structure of a communication device 8100 proposed in an embodiment of the present disclosure. Communication device 8100 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 8100 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.

[0720] As shown in Figure 10A, the communication device 8100 includes one or more processors 8101. The processor 8101 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 communication devices (such as base stations, baseband chips, terminal devices, terminal device chips, DUs or CUs, etc.), execute programs, and process program data. Optionally, the communication device 8100 is used to perform any of the above methods. Optionally, one or more processors 8101 are used to call instructions to enable the communication device 8100 to perform any of the above methods.

[0721] In some embodiments, the communication device 8100 further includes one or more transceivers 8102. When the communication device 8100 includes one or more transceivers 8102, the transceiver 8102 performs at least one of the communication steps (e.g., S501A-S508A, S501B-S510B, S501C-S510C, but not limited thereto) of transmitting and / or receiving in the above method, and the processor 8101 performs at least one of the other steps (e.g., S501A-S508A, S501B-S510B, S501C-S510C, but not limited thereto). In an optional embodiment, the transceiver may include a receiver and / or a transmitter, and the receiver and transmitter may be separate or integrated. Optionally, terms such as transceiver, transceiver unit, transceiver, transceiver circuit, interface circuit, and interface can be replaced with each other, terms such as transmitter, transmitting unit, transmitter, and transmitting circuit can be replaced with each other, and terms such as receiver, receiving unit, receiver, and receiving circuit can be replaced with each other.

[0722] In some embodiments, the communication device 8100 further includes one or more memories 8103 for storing data. Alternatively, all or part of the memories 8103 may be located outside the communication device 8100. In alternative embodiments, the communication device 8100 may include one or more interface circuits 8104. Optionally, the interface circuits 8104 are connected to the memory 8102 and may be configured to receive data from the memory 8102 or other devices, or to send data to the memory 8102 or other devices. For example, the interface circuits 8104 may read data stored in the memory 8102 and send the data to the processor 8101.

[0723] The communication device 8100 described in the above embodiment may be a first node or a second node, but the scope of the communication device 8100 described in the present disclosure is not limited thereto, and the structure of the communication device 8100 may not be limited by FIG. 10A. 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.

[0724] FIG10B is a schematic diagram of the structure of the chip 8200 proposed in an embodiment of the present disclosure. If the communication device 8100 can be a chip or a chip system, please refer to the schematic diagram of the structure of the chip 8200 shown in FIG10B , but the present disclosure is not limited thereto.

[0725] The chip 8200 includes one or more processors 8201. The chip 8200 is configured to execute any of the above methods.

[0726] In some embodiments, chip 8200 further includes one or more interface circuits 8202. Terms such as interface circuit, interface, and transceiver pins may be used interchangeably. In some embodiments, chip 8200 further includes one or more memories 8203 for storing data. Alternatively, all or part of memory 8203 may be located external to chip 8200. Optionally, interface circuit 8202 is connected to memory 8203 and may be used to receive data from memory 8203 or other devices, or may be used to send data to memory 8203 or other devices. For example, interface circuit 8202 may read data stored in memory 8203 and send the data to processor 8201.

[0727] In some embodiments, the interface circuit 8202 performs at least one of the communication steps (e.g., S501A-S508A, S501B-S510B, S501C-S510C, but not limited thereto) in the above method. The interface circuit 8202 performing the communication steps (e.g., S501A-S508A, S501B-S510B, S501C-S510C, but not limited thereto) in the above method means, for example, that the interface circuit 8202 performs data exchange between the processor 8201, the chip 8200, the memory 8203, or the transceiver device. In some embodiments, the processor 8201 performs at least one of the other steps (e.g., S501A-S508A, S501B-S510B, S501C-S510C, but not limited thereto).

[0728] The present disclosure also proposes a storage medium having instructions stored thereon, which, when executed on the communication device 8100, causes the communication device 8100 to execute 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.

[0729] The present disclosure also provides a program product, which, when executed by the communication device 8100, enables the communication device 8100 to perform any of the above methods. Optionally, the program product is a computer program product.

[0730] 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.

[0731] Those skilled in the art will appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professionals and technicians can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of this disclosure.

[0732] Those skilled in the art will clearly understand that, for the convenience and brevity of description, the specific working processes of the systems, devices and units described above can refer to the corresponding processes in the aforementioned method embodiments and will not be repeated here.

[0733] The above description is merely a specific embodiment of the present disclosure, but the scope of protection of the present disclosure is not limited thereto. Any changes or substitutions that can be easily conceived by a person skilled in the art within the technical scope disclosed in this disclosure should be included in the scope of protection of the present disclosure. Therefore, the scope of protection of the present disclosure should be based on the scope of protection of the claims.

Claims

1. A model selection method, characterized in that: The method is performed by a first node and includes: determining first data for model selection; According to the first data, a first AI model for positioning the terminal among multiple AI models is determined.

2. The method according to claim 1, characterized in that The determining of first data for model selection comprises: receiving a first message sent by the second node, wherein the first message is used to indicate the first data for model selection; The first data is determined according to the first message.

3. The method according to claim 1 or 2, characterized in that The method further comprises: A first request message is sent to the second node, wherein the first request message is used to request to obtain the first data.

4. The method according to any one of claims 1 to 3, characterized in that The method further comprises: determining second data; Determine the positioning result of the terminal according to the second data and the first AI model.

5. The method according to claim 4, characterized in that The determining, according to the second data and the first AI model, a positioning result of the terminal includes: Determine a first parameter according to the second data and the first AI model; The positioning result of the terminal is determined according to the first parameter.

6. The method according to claim 4 or 5, characterized in that The determining of the second data comprises: receiving a second message sent by the second node, wherein the second message is used to indicate the second data; The second data is determined according to the second message.

7. The method according to any one of claims 4 to 6, characterized in that The method further comprises: A second request message is sent to the second node, wherein the second request message is used to request to obtain the second data.

8. The method according to any one of claims 1 to 3, characterized in that The method further comprises: Sending indication information to the second node, wherein the indication information is used to indicate the determined first AI model, and the first AI model is used by the second node to determine a positioning result of the terminal based on the second data; or Send indication information to the third node, wherein the indication information is used to indicate the determined first AI model, and the first AI model is used by the third node to determine the positioning result of the terminal based on the second data.

9. The method according to claim 8, characterized in that The method further comprises: sending a third message to the second node, wherein the third message is used to indicate the second data, and the second data is used by the second node to determine a positioning result of the terminal based on the first AI model; or A third message is sent to the third node, wherein the third message is used to indicate the second data, and the second data is used by the third node to determine the positioning result of the terminal based on the first AI model.

10. The method according to claim 8 or 9, characterized in that The method further comprises: receiving a third request message sent by the second node, wherein the third request message is used to request to obtain the second data; or A third request message sent by the third node is received, wherein the third request message is used to request to obtain the second data.

11. The method according to any one of claims 1 to 10, characterized in that The first node is any one of the following: terminal; Access network equipment; Location management function LMF.

12. The method according to any one of claims 2, 3, 6 to 10, characterized in that The first node is a terminal, and the second node is an access network device or a LMF; or The first node is an access network device, and the second node is a terminal or a LMF; or The first node is a LMF, and the second node is a terminal or an access network device.

13. The method according to any one of claims 8 to 10, characterized in that The first node is a terminal, and the third node is a LMF; or The first node is a terminal, the second node is an access network device, and the third node is a LMF; or The first node is an access network device, and the third node is a LMF; or The first node is an access network device, the second node is a terminal, and the third node is a LMF; or The first node is an LMF, and the third node is a terminal or an access network device; or The first node is an LMF, the second node is a terminal, and the third node is an access network device; or The first node is an LMF, the second node is an access network device, and the third node is a terminal.

14. The method according to any one of claims 1 to 13, characterized in that The first data includes at least one of the following: Reference signal; Reference signal received power RSRP of the reference signal; A channel impulse response CIR determined based on a reference signal; The time domain sampling point number of the maximum power receiving path in the CIR determined based on the reference signal; The power value of the receiving path with the highest power in the CIR determined based on the reference signal.

15. The method according to any one of claims 4 to 10, characterized in that The second data includes at least one of the following: Reference signal; RSRP of the reference signal; A CIR determined based on a reference signal; The time domain sampling point number of the maximum power receiving path in the CIR determined based on the reference signal; The power value of the receiving path with the highest power in the CIR determined based on the reference signal.

16. The method according to claim 5, characterized in that The first parameter includes at least one of the following: Time of arrival ToA; Angle of arrival AoA.

17. The method according to claim 14 or 15, characterized in that The reference signal includes at least one of the following: Positioning reference signal PRS; Sounding reference signal SRS; Sounding reference signal SRS-Pos used for positioning.

18. A model selection method, characterized in that: The method is performed by the second node, comprising: A first message is sent to a first node, wherein the first message is used to indicate first data for model selection, and the first data is used by the first node to determine a first AI model among multiple AI models for positioning a terminal.

19. The method according to claim 18, characterized in that The method further comprises: A first request message sent by the first node is received, wherein the first request message is used to request to obtain the first data.

20. The method according to claim 18 or 19, characterized in that The method further comprises: A second message is sent to the first node, wherein the second message is used to indicate second data, and the second data is used by the first node to determine the positioning result of the terminal based on the first AI model.

21. The method of claim 20, wherein: The method further comprises: A second request message sent by the first node is received, wherein the second request message is used to request to obtain the second data.

22. The method according to claim 18 or 19, characterized in that The method further comprises: receiving indication information sent by the first node, wherein the indication information is used to indicate the determined first AI model; Determine the first AI model according to the indication information.

23. The method of claim 22, wherein: The method further comprises: determining second data; Determine the positioning result of the terminal according to the second data and the first AI model.

24. The method of claim 23, wherein: The determining, according to the second data and the first AI model, a positioning result of the terminal includes: Determine a first parameter according to the second data and the first AI model; The positioning result of the terminal is determined according to the first parameter.

25. The method according to claim 23 or 24, characterized in that The determining of the second data comprises: receiving a third message sent by the first node, wherein the third message is used to indicate the second data, and the second data is used by the second node to determine a positioning result of the terminal based on the first AI model; The second data is determined according to the third message.

26. The method according to any one of claims 23 to 25, characterized in that The method further comprises: A third request message is sent to the first node, wherein the third request message is used to request to obtain the second data.

27. The method according to any one of claims 18 to 26, characterized in that The first node is any one of the following: terminal; Access network equipment; LMF.

28. The method according to any one of claims 18 to 26, characterized in that The first node is a terminal, and the second node is an access network device or a LMF; or The first node is an access network device, and the second node is a terminal or a LMF; or The first node is a LMF, and the second node is a terminal or an access network device.

29. The method according to any one of claims 18 to 28, characterized in that The first data includes at least one of the following: Reference signal; RSRP of the reference signal; A CIR determined based on a reference signal; The time domain sampling point number of the maximum power receiving path in the CIR determined based on the reference signal; The power value of the receiving path with the highest power in the CIR determined based on the reference signal.

30. The method according to any one of claims 20, 21, 23 to 26, characterized in that The second data includes at least one of the following: Reference signal; RSRP of the reference signal; A CIR determined based on a reference signal; The time domain sampling point number of the maximum power receiving path in the CIR determined based on the reference signal; The power value of the receiving path with the highest power in the CIR determined based on the reference signal.

31. The method of claim 24, wherein: The first parameter includes at least one of the following: ToA; AoA.

32. The method according to claim 29 or 30, characterized in that The reference signal includes at least one of the following: PRS; SRS; SRS-Pos.

33. A first node, characterized in that: include: A processing module, configured to determine first data for model selection; The transceiver module is used to determine a first AI model for positioning the terminal from among multiple AI models based on the first data.

34. A second node, characterized in that: include: A transceiver module is used to send a first message to a first node, wherein the first message is used to indicate first data for model selection, and the first data is used by the first node to determine a first AI model among multiple AI models for positioning the terminal.

35. A first node, characterized in that: include: one or more processors; The first node is used to execute the method according to any one of claims 1 to 17.

36. A second node, characterized in that: include: one or more processors; The second node is used to execute the method according to any one of claims 18 to 32.

37. A communication system, characterized in that: The method comprises a first node and a second node, wherein the first node is configured to implement the method according to any one of claims 1 to 17, and the second node is configured to implement the method according to any one of claims 18 to 32.

38. A storage medium storing instructions, characterized in that: When the instructions are executed on a communication device, the communication device is caused to execute the method according to any one of claims 1 to 17 and 18 to 32.

Images