Artificial intelligence model determination method and apparatus, communication device, and storage medium

Abstract

The embodiment of the disclosure provides an AI model determination method and device, a communication device and a storage medium. The AI model determination method is executed by a UE and includes: sending AI capability information of the UE, wherein the AI capability information is used for a base station to determine an AI model of CSI used by the UE; and wherein the AI capability information includes at least one of AI capability indication information, AI level indication information, identification information of an AI model, identification information of an AI platform, AI inference indication information and AI training indication information.

Description

TECHNICAL FIELD

[0001] The present disclosure relates to, but is not limited to, the technical field of wireless communication, and particularly relates to an AI model determination method and device, a communication device, and a storage medium. BACKGROUND

[0002] At present, the performance of an air interface can be improved by using artificial intelligence (AI) technology, for example, AI technology can be used to reduce channel state information (CSI) feedback overhead and improve the accuracy of channel estimation. A mainstream approach is to use a 'two-sided' AI structure: an AI-based CSI compression encoder is on the user equipment (UE) side, and the UE compresses the measured CSI according to the AI-based CSI compression encoder and sends the compressed CSI information to the base station; an AI-based CSI decompression encoder is on the base station side, and the base station uses a CSI decompression encoder corresponding to the AI-based CSI compression encoder to decompress and restore the compressed CSI information sent by the UE. Compression and decompression are two parts of an AI model and occur in pairs, so it is necessary to ensure that the AI models used by the UE and the base station are consistent.

[0003] However, for CSI compression, which is an AI model that can only be implemented on the UE side and the base station side, if the AI model is issued by the base station to the UE or the AI model is reported by the UE to the base station, the AI model needs to be exchanged between the UE and the base station, resulting in increased signaling and increased power consumption. SUMMARY

[0004] Embodiments of the present disclosure provide an AI model determination method and device, a communication device, and a storage medium.

[0005] According to a first aspect of the present disclosure, an AI model determination method is provided, executed by a UE, comprising:

[0006] sending AI capability information of the UE, wherein the AI capability information is used by a base station to determine an AI model of CSI used by the UE; and wherein the AI capability information comprises at least one of the following:

[0007] AI capability indication information, used to indicate whether the UE supports AI capability;

[0008] AI level indication information, used to indicate a level to which the AI capability supported by the UE belongs;

[0009] identification information of an AI model, used to indicate an AI model supported by the UE;

[0010] identification information of an AI platform, used to indicate an AI platform supported by the UE;

[0011] AI inference indication information, used for indicating whether the UE supports an inference capability of AI;

[0012] and AI training indication information, used for indicating whether the UE supports a training capability of an AI model.

[0013] In some embodiments, the AI capability information is reported per UE.

[0014] In some embodiments, the AI capability information is reported non-mandatorily or mandatorily conditionally.

[0015] In some embodiments, the method comprises:

[0016] receiving CSI reporting configuration information; wherein the CSI reporting configuration information is determined by a base station based on the AI capability information;

[0017] determining at least one AI model used by the UE based on the CSI reporting configuration information.

[0018] In some embodiments, determining the at least one AI model used by the UE based on the CSI reporting configuration information comprises:

[0019] determining, based on the identification information of the AI model not being included in the CSI reporting configuration information, that the UE uses one AI model supported by the UE; or

[0020] determining, based on the identification information of the at least one CSI reporting configuration and the identification information of the corresponding AI model included in the CSI reporting configuration information, that different CSI reporting configurations use corresponding AI models.

[0021] In some embodiments, the method comprises: sending AI model usage information; wherein the AI model usage information is used to determine the AI model used by the UE.

[0022] In some embodiments, the AI model usage information comprises at least one of:

[0023] identification information of the AI model;

[0024] identification information of a CSI reporting configuration corresponding to the identification information of the AI model.

[0025] In some embodiments, sending the AI model usage information comprises:

[0026] sending the AI model usage information based on receiving reporting request information from a network device; wherein the reporting request information is used to request the AI model used by the UE.

[0027] According to a second aspect of the present disclosure, an AI model determination method is provided, performed by a base station, comprising:

[0028] receiving AI capability information of the UE;

[0029] determining an AI model of at least one channel state information (CSI) used by the UE based on the AI capability information;

[0030] The AI capability information comprises at least one of the following:

[0031] AI capability indication information, used to indicate whether the UE supports AI capability;

[0032] AI level indication information, used to indicate a level to which the AI capability supported by the UE belongs;

[0033] identification information of the AI model, used to indicate the AI model supported by the UE;

[0034] identification information of an AI platform, used to indicate the AI platform supported by the UE;

[0035] AI inference indication information, used to indicate whether the UE supports inference capability of AI;

[0036] and AI training indication information, used to indicate whether the UE supports training capability of the AI model.

[0037] In some embodiments, the method comprises: sending CSI reporting configuration information, wherein the CSI reporting configuration information is used to indicate that the UE uses one AI model supported by the UE.

[0038] In some embodiments, sending the CSI reporting configuration information comprises:

[0039] In response to determining that the UE supports one AI model, determining to send CSI reporting configuration information that does not include identification information of the AI model; wherein the CSI reporting configuration information is used to indicate that the UE uses the one AI model supported by the UE.

[0040] In some embodiments, sending the CSI reporting configuration information comprises:

[0041] In response to determining that the UE supports multiple AI models, sending CSI reporting configuration information, wherein the CSI reporting configuration information comprises: identification information of at least one CSI reporting configuration and identification information of a corresponding AI model.

[0042] In some embodiments, the method comprises:

[0043] receiving AI model usage information sent by the UE;

[0044] The AI model usage information is used to determine an AI model of CSI used by the base station.

[0045] In some embodiments, the AI model usage information includes at least one of:

[0046] identification information of the AI model;

[0047] identification information of CSI reporting configuration corresponding to the identification information of the AI model.

[0048] In some embodiments, the method includes: sending reporting request information; wherein the reporting request information is used to request an AI model used by the UE.

[0049] According to a third aspect of the present disclosure, an AI model determination apparatus is provided, including:

[0050] A first sending module configured to send AI capability information of the UE, wherein the AI capability information is used by the base station to determine an AI model of CSI used by the UE; and wherein the AI capability information includes at least one of:

[0051] AI capability indication information used to indicate whether the UE supports AI capability;

[0052] AI level indication information used to indicate a level to which the AI capability supported by the UE belongs;

[0053] identification information of the AI model used to indicate an AI model supported by the UE;

[0054] identification information of an AI platform used to indicate an AI platform supported by the UE;

[0055] AI inference indication information used to indicate whether the UE supports inference capability of AI;

[0056] and AI training indication information used to indicate whether the UE supports training capability of the AI model.

[0057] In some embodiments, the AI capability information is reported per UE.

[0058] In some embodiments, the AI capability information is reported on a non-mandatory basis or on a conditional mandatory basis.

[0059] In some embodiments, the apparatus includes:

[0060] A first receiving module configured to receive CSI reporting configuration information; wherein the CSI reporting configuration information is determined by the base station based on AI capability information;

[0061] A first processing module configured to determine at least one AI model used by the UE based on the CSI reporting configuration information.

[0062] In some embodiments, the first processing module is configured to determine that the UE uses one AI model supported by the UE based on the fact that the identification information of the AI model is not included in the CSI reporting configuration information.

[0063] The first processing module is configured to determine that different CSI reporting configurations use corresponding AI models based on the fact that the identification information of at least one CSI reporting configuration and the identification information of the corresponding AI model are included in the CSI reporting configuration information.

[0064] In some embodiments, the first sending module is configured to send AI model usage information, wherein the AI model usage information is used to determine the AI model used by the UE.

[0065] In some embodiments, the AI model usage information includes at least one of the following:

[0066] The identification information of the AI model;

[0067] The identification information of the CSI reporting configuration corresponding to the identification information of the AI model.

[0068] In some embodiments, the first sending module is configured to send the AI model usage information based on receiving reporting request information from the network device, wherein the reporting request information is used to request the AI model used by the UE.

[0069] According to a fourth aspect of the present disclosure, an AI model determination apparatus is provided, comprising:

[0070] The second receiving module is configured to receive AI capability information of the UE.

[0071] The second processing module is configured to determine at least one AI model of channel state information (CSI) used by the UE based on the AI capability information.

[0072] The AI capability information includes at least one of the following:

[0073] The AI capability indication information is used to indicate whether the UE supports AI capability;

[0074] The AI level indication information is used to indicate the level to which the AI capability supported by the UE belongs;

[0075] The identification information of the AI model is used to indicate the AI model supported by the UE;

[0076] The identification information of the AI platform is used to indicate the AI platform supported by the UE;

[0077] The AI inference indication information is used to indicate whether the UE supports the inference capability of AI;

[0078] and AI training indication information used for indicating whether the UE supports a training capability of the AI model.

[0079] In some embodiments, the apparatus comprises a second sending module configured to send CSI reporting configuration information, wherein the CSI reporting configuration information is used to indicate that the UE uses one AI model supported by the UE.

[0080] In some embodiments, the second sending module is configured to, in response to determining that the UE supports one AI model, determine to send CSI reporting configuration information that does not include identification information of the AI model, wherein the CSI reporting configuration information is used to indicate that the UE uses one AI model supported by the UE.

[0081] In some embodiments, the second sending module is configured to, in response to determining that the UE supports multiple AI models, send CSI reporting configuration information, wherein the CSI reporting configuration information includes identification information of at least one CSI reporting configuration and identification information of a corresponding AI model.

[0082] In some embodiments, the second receiving module is configured to receive AI model usage information sent by the UE.

[0083] The second processing module is configured to determine, based on the AI model usage information, an AI model of CSI used by the base station.

[0084] In some embodiments, the AI model usage information includes at least one of the following:

[0085] identification information of the AI model;

[0086] identification information of a CSI reporting configuration corresponding to the identification information of the AI model.

[0087] In some embodiments, the second sending module is configured to send reporting request information, wherein the reporting request information is used to request an AI model used by the UE.

[0088] According to a fifth aspect of the present disclosure, a communication device is provided, the communication device comprising:

[0089] a processor;

[0090] a memory for storing processor-executable instructions;

[0091] wherein the processor is configured to, when executing the executable instructions, implement the AI model determination method of any of the embodiments of the present disclosure.

[0092] According to a sixth aspect of the present disclosure, a computer storage medium is provided, the computer storage medium storing a computer-executable program, the executable program being executed by a processor to implement the AI model determination method of any of the embodiments of the present disclosure.

[0093] The technical solutions provided by the embodiments of the present disclosure may have the following beneficial effects:

[0094] In an embodiment of the present disclosure, the UE sends the AI ​​capability information of the UE, wherein the AI ​​capability information is used by the base station to determine the AI ​​model of the CSI used by the UE; wherein the AI ​​capability information includes at least one of AI capability indication information, AI level indication information, identification information of the AI ​​model, identification information of the AI ​​platform, AI reasoning indication information, and AI training indication information. In this way, the base station can know which AI model the UE uses to compress the CSI, which is beneficial for the base station to decompress the compressed CSI reported by the UE based on the AI ​​model to ensure that the compressed CSI reported by the UE can be correctly decompressed. In addition, since there is no need for interaction of the AI ​​model between the base station and the UE, the signaling of the interactive AI model can be reduced, and the power consumption of the UE and the base station can be reduced.

[0095] It should be understood that the foregoing general description and the following detailed description are merely exemplary and explanatory and are not restrictive of the embodiments of the present disclosure. BRIEF DESCRIPTION OF THE DRAWINGS

[0096] Figure 1 The figure is a schematic structural diagram of a wireless communication system according to an exemplary embodiment.

[0097] Figure 2 It is a schematic diagram of an AI model determination method according to an exemplary embodiment.

[0098] Figure 3 It is a schematic diagram of an AI model determination method according to an exemplary embodiment.

[0099] Figure 4 It is a schematic diagram of an AI model determination method according to an exemplary embodiment.

[0100] Figure 5 It is a schematic diagram of an AI model determination method according to an exemplary embodiment.

[0101] Figure 6 It is a schematic diagram of an AI model determination method according to an exemplary embodiment.

[0102] Figure 7 It is a block diagram of an AI model determination device according to an exemplary embodiment.

[0103] Figure 8 It is a block diagram of an AI model determination device according to an exemplary embodiment.

[0104] Figure 9is a block diagram of a UE according to an exemplary embodiment.

[0105] Figure 10 is a block diagram of a base station according to an exemplary embodiment. DETAILED DESCRIPTION

[0106] The exemplary embodiments will be described in detail herein with reference to the attached drawings. The following description is made with reference to the accompanying drawings in which like reference numerals refer to like elements, and redundant description is omitted. The following exemplary embodiments are not representative of all embodiments consistent with the present disclosure. Rather, they are merely examples of apparatuses and methods consistent with some aspects of the present disclosure as detailed in the appended claims.

[0107] The terminology used in the present disclosure is for the purpose of describing particular embodiments only and is not intended to be limiting of the present disclosure. As used in the present disclosure and the appended claims, the singular forms "a," "an" and "the" are intended to include the plural forms as well, unless the context clearly indicates otherwise. It will also be understood that the term "and / or" as used herein refers to and encompasses any and all possible combinations of one or more of the associated listed items.

[0108] It will be understood that, although the terms first, second, third, etc. can be used herein to describe various information, these terms are not intended to denote a temporal or chronological order. Rather, these terms are used only to distinguish different sets of information from one another. For example, a first information can be termed a second information, and similarly, a second information can be termed a first information, without departing from the scope of the present disclosure. As used herein, the term "if' can be interpreted to mean "when" or "upon" or "in response to determining" depending on the context.

[0109] Reference will now be made to Figure 1 which shows a structure diagram of a wireless communication system provided by the present disclosure. As shown in Figure 1 , the wireless communication system is a communication system based on cellular mobile communication technology, and the wireless communication system can include a plurality of user equipment 110 and a plurality of base stations 120.

[0110] The user equipment 110 can be a device that provides voice and / or data connectivity to a user. The user equipment 110 can communicate with one or more core networks via a Radio Access Network (RAN), and the user equipment 110 can be an Internet of Things user equipment, such as a sensor device, a mobile phone (also known as a "cellular" phone), and a computer with an Internet of Things user equipment, for example, which can be fixed, portable, pocket, hand-held, computer-embedded, or vehicle-mounted. For example, a Station (STA), a subscriber unit, a subscriber station, a mobile station, a mobile, a remote station, an access point, a remote terminal, an access terminal, a user terminal, a user agent, a user device, or a user equipment. Alternatively, the user equipment 110 can also be a device of an unmanned aerial vehicle. Alternatively, the user equipment 110 can also be a vehicle-mounted device, for example, it can be a vehicle-mounted computer with wireless communication function or a wireless user equipment externally connected to the vehicle-mounted computer. Alternatively, the user equipment 110 can also be a roadside device, for example, it can be a street lamp, a signal lamp, or other roadside devices with wireless communication function, etc.

[0111] The base station 120 can be a network-side device in a wireless communication system. The wireless communication system can be a 4th generation mobile communication (4G) system, also known as a Long Term Evolution (LTE) system, or the wireless communication system can also be a 5G system, also known as a New Radio system or a 5G NR system. Alternatively, the wireless communication system can also be a next generation of 5G system. In the 5G system, the access network can be referred to as a New Generation-Radio Access Network (NG-RAN).

[0112] The base station 120 can be an evolved NodeB (eNB) used in a 4G system. Alternatively, the base station 120 can also be a base station (gNB) using a centralized and distributed architecture in a 5G system. When the base station 120 uses a centralized and distributed architecture, it usually includes a central unit (CU) and at least two distributed units (DUs). The central unit is provided with a protocol stack of a packet data convergence protocol (PDCP) layer, a radio link control (RLC) layer, and a medium access control (MAC) layer; and the distributed unit is provided with a protocol stack of a physical (PHY) layer. The specific implementation of the base station 120 is not limited in the embodiments of the present disclosure.

[0113] The base station 120 and the user equipment 110 can establish a wireless connection through a wireless air interface. In different embodiments, the wireless air interface is a wireless air interface based on a fourth generation mobile communication network technology (4G) standard; or the wireless air interface is a wireless air interface based on a fifth generation mobile communication network technology (5G) standard, such as a new radio (NR); or the wireless air interface can also be a wireless air interface based on a more next generation mobile communication network technology standard of 5G.

[0114] In some embodiments, the user equipment 110 can also establish an E2E (End to End) connection. For example, vehicle to vehicle (V2V) communication, vehicle to infrastructure (V2I) communication, and vehicle to pedestrian (V2P) communication in vehicle to everything (V2X) communication, and the like.

[0115] Here, the user equipment described above can be considered as a terminal device in the following embodiments.

[0116] In some embodiments, the wireless communication system described above can also include a network management device 130.

[0117] Several base stations 120 are respectively connected to a network management device 130. The network management device 130 may be a core network device in a wireless communication system. For example, the network management device 130 may be a mobility management entity (MME) in an evolved packet core (EPC). Alternatively, the network management device may be other core network devices, such as a serving gateway (SGW), a public data network gateway (PGW), a policy and charging rules function (PCRF), or a home subscriber server (HSS). The embodiments of the present disclosure do not limit the implementation form of the network management device 130.

[0118] To facilitate understanding by those skilled in the art, the embodiments of the present disclosure list multiple implementation methods to clearly illustrate the technical solutions of the embodiments of the present disclosure. Of course, those skilled in the art will understand that the multiple embodiments provided in the embodiments of the present disclosure can be implemented individually, or can be implemented together with the methods of other embodiments in the embodiments of the present disclosure, or can be implemented together with some methods in other related technologies individually or in combination; the embodiments of the present disclosure do not limit this.

[0119] In order to better understand the technical solutions described in any embodiment of the present disclosure, first, some related technologies are partially explained:

[0120] In one embodiment, AI software implementation is significantly more complex than AI hardware implementation. For example, AI software implementation can involve building some basic models into a chip; the base station changes some parameters, and the UE refines the model using C language. AI hardware implementation can involve directly building the AI ​​model into the chip. This can be achieved by embedding the AI ​​model into the hardware using Verilog.

[0121] like Figure 2 As shown, an embodiment of the present disclosure provides an AI model determination method, which is executed by a UE and includes:

[0122] Step S21: Sending the UE's AI capability information, where the AI ​​capability information is used by the base station to determine the AI ​​model of the CSI used by the UE;

[0123] The AI ​​capability information includes at least one of the following:

[0124] AI capability indication information, used to indicate whether the UE supports AI capability;

[0125] AI level indication information, used to indicate a level to which the AI capability supported by the UE belongs;

[0126] AI model identification information, used to indicate an AI model supported by the UE;

[0127] AI platform identification information, used to indicate an AI platform supported by the UE;

[0128] AI inference indication information, used to indicate whether the UE supports inference capability of AI;

[0129] and AI training indication information, used to indicate whether the UE supports training capability of AI model.

[0130] Here, the UE can be various mobile terminals or fixed terminals. For example, the UE can be, but is not limited to, a mobile phone, a computer, a server, a wearable device, a vehicle-mounted terminal, a road side unit (RSU), a game control platform, a multimedia device, etc.

[0131] In one embodiment, step S21 can be: sending AI capability information of the UE to a base station.

[0132] Here, the base station can be various types of base stations. For example, the base station can be a 2G base station, a 3G base station, a 4G base station, a 5G base station or other evolved base stations.

[0133] In another embodiment, step S21 can be: sending the AI capability information to a network device.

[0134] Here, the network device can be an access network device or a core network device. The access network device can be various base stations. The core network device can be various logical nodes or functions of the core network; for example, the core network device can be an access and mobility management function (AMF) or a network function (NF). If the UE sends the AI capability information of the UE to the core network device, it can be that the UE sends the AI capability information of the UE to the base station, and the base station forwards the AI capability information of the UE to the core network device.

[0135] In one embodiment, step S21 can be: reporting AI capability information of the UE. Illustratively, the UE reports the AI capability information of the UE to the base station.

[0136] Here, the AI capability indication information, the AI level indication information, the identification information of the AI model, the identification information of the AI platform, the AI inference indication information, and the AI training indication information can be respectively carried or indicated by at least one bit of the AI capability information.

[0137] In some embodiments, the A capability information includes at least one of the following:

[0138] The AI capability indication information can be used to indicate whether the chip of the UE supports the AI capability.

[0139] The AI level indication information can be used to indicate the level to which the AI capability supported by the chip of the UE belongs.

[0140] For example, when the AI capability information indicates a first value, such as "0", it is used to indicate that the UE supports the AI capability; and when the AI capability information indicates a second value, such as "1", it is used to indicate that the UE does not support the AI capability.

[0141] Here, the AI capability can be any AI capability; for example, the AI capability can be but is not limited to the AI capability of CSI compression or the AI positioning capability.

[0142] For example, the protocol stipulates that the level to which the AI capability supported by the chip of the UE belongs can be x, y, and z; or the base station and the UE negotiate that the level to which the AI capability supported by the chip of the UE belongs can be x, y, and z. Here, x, y, and z correspond to different computing power capabilities and / or storage capabilities of the UE, respectively. Thus, based on the computing power capability and / or the storage capability of the UE, it can be determined which of the three levels x, y, and z the AI capability supported by the UE belongs to.

[0143] Here, the AI level indication information can take different values to indicate the level to which the AI capability supported by the UE or the chip of the UE belongs.

[0144] For example, the AI model can be any AI model; for example, the AI model can be but is not limited to a CNN model, an RNN model, or a transformer model.

[0145] Here, the identification information of the AI model is used to uniquely identify the AI model. Thus, the UE can report the AI model indication information to inform the base station of the AI model supported by the UE, thereby facilitating the base station to determine the AI model used by the UE.

[0146] Exemplarily, the AI platform can be any AI platform. For example, the AI platform can be, but is not limited to, a TensorFlow platform or a Pytorch platform, etc.

[0147] Exemplarily, when the AI inference indication information takes a first value, for example, "0", it is used to indicate that the UE supports the inference capability of AI; and when the AI inference indication information takes a second value, for example, "1", it is used to indicate that the UE does not support the inference capability of AI.

[0148] Exemplarily, when the AI training indication information takes a first value, for example, "0", it is used to indicate that the UE supports the training capability of the AI model; and when the AI training indication information takes a second value, for example, "1", it is used to indicate that the UE does not support the training capability of the AI model.

[0149] In an embodiment, the AI capability information can be used to indicate the AI platform used by the AI model; and / or, the AI capability information can be used to indicate that the UE or the chip of the UE supports the AI platform corresponding to the AI capability level. Thus, in the embodiments of the present disclosure, the AI capability information can also be used by the base station to determine the AI platform corresponding to the UE when supporting different AI models, and / or to determine the AI platform corresponding to the UE or the chip of the UE when supporting different AI capabilities belonging to different levels.

[0150] Thus, it can be ensured that different AI platforms are used when the UE performs CSI compression and the base station performs CSI decompression.

[0151] Here, the AI capability information is used by the base station to determine the AI model of the CSI compression used by the UE; and / or, the AI capability information can also be used by the base station to determine the AI model of the CSI decompression used.

[0152] In the embodiments of the present disclosure, the UE sends AI capability information of the UE, wherein the AI capability information is used by the base station to determine the AI model of the CSI used by the UE; and the AI capability information includes at least one of AI capability indication information, AI level indication information, identification information of the AI model, identification information of the AI platform, AI inference indication information, and AI training indication information. Thus, the base station can know which AI model is used by the UE to perform CSI compression, thereby facilitating the base station to also decompress the compressed CSI reported by the UE based on the AI model, so as to ensure that the compressed CSI reported by the UE can be correctly decompressed. Moreover, since there is no need for interaction of the AI model between the base station and the UE, the signaling of the interactive AI model can be reduced, and the power consumption of the UE and the base station can be reduced, etc.

[0153] In some embodiments, AI capability information is reported per UE or per feature. For example, per UE reporting means that the UE only needs to report the AI ​​capability information once, regardless of the number of frequency bands supported by the UE. For example, per function reporting means that the UE reports the AI ​​capability information for each frequency band and each frequency band group separately.

[0154] In some embodiments, AI capability information is reported non-mandatory or conditionally mandatory.

[0155] Here, the non-mandatory reporting of the AI ​​capability information means that when the UE capability is reported, the UE is forced to report the AI ​​capability information included in the AI ​​capability.

[0156] Here, the conditional mandatory reporting of the AI ​​capability information means that, when the UE supports a specific AI capability, the UE needs to report the AI ​​capability information corresponding to the AI ​​capability supported by the UE.

[0157] Exemplarily, if the UE supports at least one of the following AI capabilities, then the AI ​​capability information of at least one of the following AI capabilities is reported: the UE supports reporting of CSI for AI model compression, the UE supports AI reasoning capability, and supports AI model training capability.

[0158] In this way, for the AI ​​capabilities supported by the UE, the AI ​​capability information of the AI ​​capabilities can be conditionally and compulsorily reported.

[0159] It should be noted that those skilled in the art will understand that the method provided in the embodiments of the present disclosure may be executed alone or together with some methods in the embodiments of the present disclosure or some methods in related technologies.

[0160] like Figure 3 As shown, an embodiment of the present disclosure provides an AI model determination method, which is executed by a UE and includes:

[0161] Step S31: Receive CSI reporting configuration information; wherein the CSI reporting configuration information is determined by the base station based on AI capability information;

[0162] Step S32: Determine at least one AI model used by the UE based on the CSI reporting configuration information.

[0163] In some embodiments of the present disclosure, the AI ​​capability information may be the AI ​​capability information in step S21; the AI ​​model may be the AI ​​model in step S21. Exemplarily, the AI ​​capability information includes at least one of AI capability indication information, AI level indication information, AI model identification information, AI platform identification information, AI reasoning indication information, and AI training indication information.

[0164] In an embodiment, the CSI reporting configuration information received in step S31 can be CSI reporting configuration information sent by the base station.

[0165] Here, the CSI reporting configuration can be any CSI reporting configuration. For example, the CSI reporting configuration can be a periodic CSI reporting configuration or an aperiodic CSI reporting configuration; for another example, the CSI reporting configuration can be a CSI reporting configuration based on a predetermined frequency band; for yet another example, the CSI reporting configuration can be a CSI reporting configuration based on a certain PUCCH resource; for yet another example, the CSI reporting configuration can be a CSI reporting configuration based on a certain beam; and so on.

[0166] Here, the identification information of the CSI reporting configuration is used to uniquely identify the CSI reporting configuration. For example, when the identification information of the reporting configuration is "00", it can be used to identify a specific CSI reporting configuration.

[0167] In some embodiments, step S32 comprises:

[0168] Based on the fact that the identification information of the AI model is not included in the CSI reporting configuration information, it is determined that the UE uses one AI model supported by the UE; or, based on the fact that the identification information of at least one CSI reporting configuration and the identification information of the corresponding AI model are included in the CSI reporting configuration information, it is determined that different CSI reporting configurations use corresponding AI models.

[0169] The embodiments of the present disclosure provide an AI model determination method, executed by a UE, comprising:

[0170] Based on the fact that the identification information of the AI model is not included in the CSI reporting configuration information, it is determined that the UE uses one AI model supported by the UE; or, based on the fact that the identification information of at least one CSI reporting configuration and the identification information of the corresponding AI model are included in the CSI reporting configuration information, it is determined that different CSI reporting configurations use corresponding AI models.

[0171] The embodiments of the present disclosure provide an AI model determination method, executed by a UE, comprising:

[0172] Based on the identification information of the AI model included in the CSI reporting configuration information, it is determined that the UE uses the AI model indicated by the identification information of the AI model.

[0173] For example, the UE supports one AI model, and the UE receives CSI reporting configuration information sent by the base station; if the UE determines that the identification information of the AI model is not included in the CSI reporting configuration information, it is determined that the UE uses the one AI model supported by the UE.

[0174] For example, the UE supports one or more AI models, and the UE receives CSI reporting configuration information sent by the base station; if the UE determines that the CSI reporting configuration information includes identification information of an AI model, the UE determines that the AI model indicated by the identification information of the AI model is used by the UE.

[0175] For example, the UE supports multiple AI models, and the UE receives CSI reporting configuration information sent by the base station; if the UE determines that the CSI reporting configuration information includes: identification information "00" of a CSI reporting configuration and identification information of a first AI model, and identification information "01" of a CSI reporting configuration and identification information of a second AI model. If the UE determines that the CSI reporting configuration indicated by the identification information "00" of the CSI reporting configuration is currently used, the UE determines that the AI model used by the UE is the first AI model; or if the UE determines that the CSI reporting configuration indicated by the identification information "01" of the CSI reporting configuration is currently used, the UE determines that the AI model used by the UE is the second AI model.

[0176] In the embodiments of the present disclosure, the UE can accurately determine that the AI model used by the UE for CSI compression is corresponding to the AI model used by the base station for CSI decompression by receiving the CSI reporting configuration information sent by the base station; in this way, the corresponding AI models can be used between the UE and the base station without the need for the UE and the base station to interact with the specific AI parameter information of the AI model.

[0177] Here, the AI models between the base station and the UE can be corresponding. The UE uses the AI compression model to compress the CSI, and sends the compressed CSI to the base station; the base station uses the AI decompression model corresponding to the UE to decompress the compressed CSI.

[0178] As shown in Figure 4 The embodiments of the present disclosure provide an AI model determination method, executed by a UE, comprising:

[0179] Step S41: sending AI model usage information; wherein the AI model usage information is used to determine the AI model used by the UE.

[0180] The embodiments of the present disclosure provide an AI model determination method, executed by a UE, comprising: after sending the AI capability information, sending AI model usage information.

[0181] In one embodiment, the AI model usage information is used to indicate the AI model used by the UE.

[0182] In one embodiment, the AI model usage information can be used by the base station to determine the AI model used by the UE; and / or the AI model usage information can be used by the base station to determine the AI model used by the base station.

[0183] In an embodiment, the AI model usage information is used by the UE to determine the AI model used by the UE.

[0184] In some embodiments, the AI model usage information comprises at least one of:

[0185] identification information of the AI model;

[0186] identification information of a CSI reporting configuration corresponding to the identification information of the AI model.

[0187] For example, the UE sends AI model usage information to the base station, wherein the AI model usage information comprises identification information of the AI model, and the AI model usage information is used to indicate the AI model used by the UE. In this way, the base station can be directly informed of the AI model used by the UE.

[0188] For example, the UE sends AI model usage information to the base station, wherein the AI model usage information comprises identification information of a CSI reporting configuration; and the base station, after receiving the identification information of the CSI reporting configuration, can determine the identification information of the AI model used by the UE based on the correspondence between the received identification information of the CSI reporting configuration and the stored correspondence between the identification information of the AI model and the identification information of the CSI reporting configuration. In this way, the AI model used by the UE can also be determined based on the received identification information of the CSI reporting configuration.

[0189] In this way, in the embodiments of the present disclosure, the UE can report AI model usage information, if the AI model usage information carries identification information of the AI model, the base station can be directly informed of the AI model used by the UE; and / or if the AI model usage information carries CSI reporting configuration information, the base station can determine the identification information of the AI model based on the identification information of the CSI reporting configuration information, so that the base station can also determine the AI model used by the UE. In this way, the base station can be informed of the AI model used by the UE in various ways, so that more application scenarios can be applied.

[0190] The embodiments of the present disclosure provide an AI model determination method, executed by a UE, comprising: determining an AI model used by the UE.

[0191] The embodiments of the present disclosure provide an AI model determination method, executed by a UE, comprising: determining an AI model used by the UE based on a scenario in which the UE is located.

[0192] The embodiments of the present disclosure provide an AI model determination method, executed by a UE, comprising at least one of:

[0193] determining an AI model used by the UE based on AI capability information of the UE;

[0194] determine the AI model used by the UE based on the AI model supported by the UE.

[0195] For example, if the UE supports one AI model, the AI model used by the UE is determined as the AI model supported by the UE; or if the UE supports multiple AI models, the AI model used by the UE is determined as any one of the multiple AI models; and the like.

[0196] In some embodiments, the AI model used by the UE is determined based on a scenario in which the UE is located, including:

[0197] determine that the UE uses an AI model of a first level based on the UE being in a first speed scenario and / or an urban scenario; or

[0198] determine that the UE uses an AI model of a second level based on the UE being in a second speed scenario and / or a rural scenario; wherein the first speed is less than or equal to the second speed.

[0199] The embodiments of the present disclosure provide an AI model determination method, executed by a UE, including: determining that the UE uses an AI model of a first level based on the UE being in a first speed scenario and / or an urban scenario; or determining that the UE uses an AI model of a second level based on the UE being in a second speed scenario and / or a rural scenario; wherein the first speed is less than or equal to the second speed.

[0200] Here, the AI capability of the UE can be divided into the first level or the second level through protocol agreement or negotiation between the base station and the UE; or the AI capability of the UE can be divided into the 1st to the Nth level, wherein N is an integer greater than 1; or the AI capability of the UE can be divided into the x, y or z level. Here, the computing power and / or storage capacity of the UE corresponding to different levels are different. For example, the AI capability of the UE is divided into the first level or the second level, and the computing power and / or storage capacity corresponding to the first level is less than the computing power and / or storage capacity corresponding to the second level.

[0201] In this way, in the embodiments of the present disclosure, the UE can select a suitable AI model for CSI compression based on the scenario in which the UE is located. In this way, when the AI model used by the UE is sent to the base station, the base station can perform CSI decompression based on the corresponding AI model.

[0202] In some embodiments, the AI model usage information is sent in step S41, including:

[0203] The AI model usage information is sent based on receiving reporting request information from the network device; wherein the reporting request information is used to request the AI model used by the UE.

[0204] The embodiments of the present disclosure provide an AI model determination method, executed by a UE, including:

[0205] The AI model usage information is sent based on receiving report request information from the network device, wherein the report request information is used to request the AI model used by the UE.

[0206] For example, the UE receives the report request information sent by the base station, and sends the identification information of the AI model and / or the identification information of the CSI report configuration corresponding to the AI model identification information; the report request information is used to request the AI model used by the UE.

[0207] Therefore, in the embodiments of the present disclosure, the UE can be triggered by the base station, i.e., the base station sends the report request information, and the AI model is used as the usage information; therefore, the base station can accurately determine the AI model used by the UE.

[0208] It should be noted that those skilled in the art can understand that the method provided by the embodiments of the present disclosure can be executed alone or together with some methods in some methods or related technologies in the embodiments of the present disclosure.

[0209] The following AI model determination method is executed by the base station, which is similar to the description of the AI model determination method executed by the UE; and for the technical details not disclosed in the AI model determination method executed by the base station, please refer to the description of the AI model determination method executed by the UE, which will not be described in detail here.

[0210] As shown in Figure 5 The embodiments of the present disclosure provide an AI model determination method executed by a base station, comprising:

[0211] Step S51: receiving AI capability information of the UE;

[0212] Step S52: determining at least one AI model of the CSI used by the UE based on the AI capability information;

[0213] The AI capability information comprises at least one of the following:

[0214] The AI capability indication information is used to indicate whether the UE supports the AI capability;

[0215] The AI level indication information is used to indicate the level to which the AI capability supported by the UE belongs;

[0216] The identification information of the AI model is used to indicate the AI model supported by the UE;

[0217] The identification information of the AI platform is used to indicate the AI platform supported by the UE;

[0218] The AI inference indication information is used to indicate whether the UE supports the inference capability of the AI.

[0219] and AI training indication information, used for indicating whether the UE supports the training capability of the AI model.

[0220] The AI model determination method related to the embodiments of the present disclosure can also be executed by a network device.

[0221] In some embodiments of the present disclosure, the AI capability information can be the AI capability information in step S21, and the AI model can be the AI model in the above embodiments.

[0222] In one embodiment, step S51 can be: receiving AI capability information of the UE reported by the UE.

[0223] In some embodiments, the AI capability information includes but is not limited to at least one of the following:

[0224] The AI capability indication information can be used to indicate whether the chip of the UE supports the AI capability.

[0225] The AI level indication information can be used to indicate the level to which the AI capability supported by the chip of the UE belongs.

[0226] In some embodiments, step S52 can be: determining the AI model of at least one CSI used by the UE based on at least one of the AI capability indication information, the AI level indication information, the identification information of the AI model, the identification information of the AI platform, the AI inference indication information and the AI training indication information.

[0227] For example, the base station receives AI capability information sent by the UE, wherein the AI capability information includes AI capability indication information and identification information of an AI model; if the base station determines that the AI capability indication information indicates that the UE supports the AI capability information, the base station can determine the AI model supported by the UE based on the identification information of the AI model; and the base station selects one or more AI models from the AI model supported by the UE as the AI model used by the UE.

[0228] For example, the base station receives AI capability information sent by the UE, wherein the AI capability information includes AI capability indication information and AI level indication information; if the base station determines that the AI capability indication information indicates that the UE supports the AI capability information, the base station can determine the level to which the AI capability supported by the UE belongs based on the AI level indication information; and the base station determines the AI model used by the UE as one or more AI models included in the level to which the AI capability belongs.

[0229] For example, the base station receives AI capability information sent by the UE, wherein the AI capability information includes identification information of an AI platform; the base station can determine the AI platform supported by the UE based on the identification information of the AI platform; and the base station determines that the AI model used by the UE is one or more AI models corresponding to the AI platform supported by the UE.

[0230] In this way, the AI model suitable for the UE can be determined through the AI capability information of the UE sent by the UE in the embodiments of the present disclosure. Moreover, the AI model used by the UE can be determined in various ways, so that more application scenarios can be adapted.

[0231] The above embodiments can be specifically referred to the description of the UE side, which will not be described here.

[0232] It should be noted that those skilled in the art can understand that the method provided by the embodiments of the present disclosure can be executed alone or together with some methods in some methods or related technologies in the embodiments of the present disclosure.

[0233] As shown in Figure 6 The embodiments of the present disclosure provide an AI model determination method, executed by a base station, comprising:

[0234] Step S61: sending CSI reporting configuration information, wherein the CSI reporting configuration information is used to instruct the UE to use a supported AI model.

[0235] In some embodiments of the present disclosure, the CSI reporting configuration information can be the CSI reporting configuration information in step S31; and the identification information of the CSI reporting configuration information can be the identification information of the CSI reporting configuration information in the above embodiments.

[0236] In one embodiment, the CSI reporting configuration information is determined based on the AI capability information of the UE.

[0237] In some embodiments, the sending of the CSI reporting configuration information in step S61 comprises:

[0238] In response to determining that the UE supports one AI model, it is determined to send CSI reporting configuration information that does not include identification information of an AI model; wherein the CSI reporting configuration information is used to instruct the UE to use the one AI model supported by the UE.

[0239] The embodiments of the present disclosure provide an AI model determination method, executed by a base station, comprising: in response to determining that the UE supports one AI model, determining to send CSI reporting configuration information that does not include identification information of an AI model; wherein the CSI reporting configuration information is used to instruct the UE to use the one AI model supported by the UE.

[0240] In other embodiments, the base station can also carry identification information of the AI model in the CSI reporting configuration information if it is determined that the UE supports one AI model.

[0241] In other embodiments, the base station can also carry identification information of the AI model in the CSI reporting configuration information if it is determined that the UE supports one AI model.

[0242] In this way, in the embodiments of the present disclosure, the base station sends the CSI reporting configuration information to the UE to indicate that the CSI reported by the UE can be compressed by using the AI model indicated by the base station for the UE to use.

[0243] In some embodiments, the CSI reporting configuration information sent in step S61 comprises:

[0244] In response to determining that the UE supports multiple AI models, the CSI reporting configuration information is sent, wherein the CSI reporting configuration information comprises identification information of at least one CSI reporting configuration and identification information of a corresponding AI model.

[0245] The embodiments of the present disclosure provide an AI model determination method, which is executed by a base station and comprises:

[0246] In response to determining that the UE supports multiple AI models, the CSI reporting configuration information is sent, wherein the CSI reporting configuration information comprises identification information of at least one CSI reporting configuration and identification information of a corresponding AI model.

[0247] Here, the identification information of the same CSI reporting configuration corresponds to the identification information of one AI model.

[0248] In this way, in the embodiments of the present disclosure, the base station can configure multiple AI models for the UE to use, and different AI models are configured for different CSI reporting configurations, so that the UE can use appropriate AI models to compress the CSI of different CSI reporting configurations.

[0249] The above embodiments can be specifically referred to the description of the UE side, which will not be repeated here.

[0250] It should be noted that those skilled in the art can understand that the method provided by the embodiments of the present disclosure can be executed alone or together with some methods in some methods or related technologies in the embodiments of the present disclosure.

[0251] The embodiments of the present disclosure provide an AI model determination method, which is executed by a base station and comprises:

[0252] Receiving AI model usage information sent by the UE;

[0253] The AI model usage information is used to determine an AI model of CSI used by the base station.

[0254] In some embodiments of the present disclosure, the AI model usage information can be the AI model usage information in step S41.

[0255] For example, the AI model usage information includes at least one of the following:

[0256] identification information of the AI model;

[0257] identification information of CSI reporting configuration corresponding to the identification information of the AI model.

[0258] The AI model determination method provided by the embodiments of the present disclosure is executed by a base station, and includes: sending reporting request information; wherein the reporting request information is used to request an AI model used by a UE.

[0259] Here, the sending of the reporting request information includes: sending the reporting request information to the UE. The reporting request information is used to trigger the UE to report AI model usage information.

[0260] The above embodiments can be specifically referred to the description of the UE side, which will not be repeated here.

[0261] It should be noted that those skilled in the art can understand that the method provided by the embodiments of the present disclosure can be executed alone or together with some methods in some methods or related technologies in the embodiments of the present disclosure.

[0262] In order to further explain any embodiments of the present disclosure, a specific embodiment is provided below.

[0263] The AI model determination method provided by the embodiments of the present disclosure is executed by a communication device, and the communication device includes a UE and a base station; the AI model determination method includes at least one of the following:

[0264] Step S71: The UE reports AI capability information of the UE; wherein the AI capability information includes at least one of the following:

[0265] AI capability indication information, used to indicate whether the UE supports AI capability;

[0266] AI level indication information, used to indicate a level to which the AI capability supported by the UE belongs;

[0267] identification information of the AI model, used to indicate the AI model supported by the UE;

[0268] identification information of the AI platform, used to indicate the AI platform supported by the UE;

[0269] AI inference indication information, used to indicate whether the UE supports AI inference capability;

[0270] AI training indication information, used for indicating whether the UE supports the training capability of the AI model.

[0271] In an optional embodiment, the AI capability information is reported per UE or per feature.

[0272] In another optional embodiment, the AI capability information is reported optionally or conditionally. For example, if the UE supports at least one of the following capabilities, the UE reports the AI capability information of the at least one of the following capabilities: the UE supports the reporting of the CSI compressed by the AI model, the UE supports the inference capability of the AI, and the UE supports the training capability of the AI model.

[0273] Step S72: The base station receives the AI capability information and configures the AI model used by the UE; wherein, step S72 includes steps S72a and S72b.

[0274] Step S72a: The base station determines one or more AI models supported by the UE based on the AI capability information of the UE.

[0275] Step S72b: Based on the one or more AI models supported by the UE, determine the AI model used by the UE; and send the CSI reporting configuration information.

[0276] In an optional embodiment, if it is determined that the UE supports one AI model, the base station sends the CSI reporting configuration information which does not include the identification information of the AI model.

[0277] In another optional embodiment, if it is determined that the UE supports multiple AI models, the base station sends the CSI reporting configuration information; the CSI reporting configuration information includes the identification information of at least one CSI reporting configuration and the identification information of the corresponding AI model.

[0278] Here, the base station can indicate the AI model used by the UE according to the current channel state.

[0279] Here, the UE can use the AI model CSI compression configured by the base station, and the base station can use the corresponding AI model to decompress the compressed CSI.

[0280] In an optional embodiment, step S72 can also be replaced by step S73.

[0281] Step S73: The UE reports AI model usage information, wherein the AI model usage information is used to determine the AI model used by the UE.

[0282] In an optional embodiment, the UE determines the AI model used by the UE based on the scenario in which the UE is located.

[0283] For example, the UE determines to use an AI model of x level based on that the UE is in a first speed scenario and / or an urban scenario; or determines to use an AI model of y level based on that the UE is in a second speed scenario and / or a rural scenario; wherein the first speed is less than or equal to the second speed. Here, the computing power and / or storage capacity corresponding to the x level is less than the computing power and / or storage capacity corresponding to the y level.

[0284] In an optional embodiment, the AI model usage information sent by the UE includes at least one of the following: identification information of the AI model, and identification information of CSI reporting configuration information corresponding to the identification information of the AI model.

[0285] Here, the AI model usage information can be actively reported by the UE, or can be reported by the UE based on triggering of the base station. Here, the UE reports based on triggering of the base station can be that the UE receives reporting request information sent by the base station and reports.

[0286] It should be noted that those skilled in the art can understand that the method provided by the embodiments of the present disclosure can be executed alone or together with some methods in some methods or related technologies in the embodiments of the present disclosure.

[0287] As shown in Figure 7 The embodiments of the present disclosure provide an AI model determination apparatus, which includes:

[0288] The first sending module 51 is configured to send AI capability information of the UE, wherein the AI capability information is used by the base station to determine an AI model of CSI used by the UE; and wherein the AI capability information includes at least one of the following:

[0289] AI capability indication information, used to indicate whether the UE supports AI capability;

[0290] AI level indication information, used to indicate a level to which the AI capability supported by the UE belongs;

[0291] Identification information of the AI model, used to indicate the AI model supported by the UE;

[0292] Identification information of the AI platform, used to indicate the AI platform supported by the UE;

[0293] AI inference indication information, used to indicate whether the UE supports inference capability of AI;

[0294] and AI training indication information, used to indicate whether the UE supports training capability of the AI model.

[0295] The AI model determination apparatus provided by the embodiments of the present disclosure can be applied to the UE.

[0296] In some embodiments, the AI capability information is reported per UE.

[0297] In some embodiments, the AI capability information is reported non-mandatorily or conditionally mandatorily.

[0298] Embodiments of the present disclosure provide an AI model determination apparatus, comprising:

[0299] A first receiving module is configured to receive CSI reporting configuration information; wherein the CSI reporting configuration information is determined by a base station based on AI capability information;

[0300] A first processing module is configured to determine at least one AI model used by a UE based on the CSI reporting configuration information.

[0301] Embodiments of the present disclosure provide an AI model determination apparatus, comprising: a first processing module configured to determine one AI model supported by a UE based on identification information of an AI model not included in CSI reporting configuration information.

[0302] Embodiments of the present disclosure provide an AI model determination apparatus, comprising: a first processing module configured to determine that different CSI reporting configurations use corresponding AI models based on identification information of at least one CSI reporting configuration and identification information of corresponding AI models included in the CSI reporting configuration information.

[0303] Embodiments of the present disclosure provide an AI model determination apparatus, comprising: a first sending module 51 configured to send AI model usage information; wherein the AI model usage information is used to determine AI models used by a UE.

[0304] In some embodiments, the AI model usage information comprises at least one of:

[0305] identification information of an AI model;

[0306] identification information of a CSI reporting configuration corresponding to the identification information of the AI model.

[0307] Embodiments of the present disclosure provide an AI model determination apparatus, comprising: a first sending module 51 configured to send AI model usage information based on receiving reporting request information from a network device; wherein the reporting request information is used to request AI models used by a UE.

[0308] As shown in Figure 8 Embodiments of the present disclosure provide an AI model determination apparatus, comprising:

[0309] A second receiving module 61 is configured to receive AI capability information of a UE.

[0310] The second processing module 62 is configured to determine, based on the AI capability information, an AI model of at least one channel state information (CSI) used by the UE.

[0311] The AI capability information includes at least one of the following:

[0312] AI capability indication information for indicating whether the UE supports the AI capability;

[0313] AI level indication information for indicating a level to which the AI capability supported by the UE belongs;

[0314] AI model identification information for indicating an AI model supported by the UE;

[0315] AI platform identification information for indicating an AI platform supported by the UE;

[0316] AI inference indication information for indicating whether the UE supports an inference capability of the AI;

[0317] and AI training indication information for indicating whether the UE supports a training capability of the AI model.

[0318] The AI model determination apparatus provided by the embodiments of the present disclosure can be applied to a base station.

[0319] The embodiments of the present disclosure provide an AI model determination apparatus, which includes a second sending module configured to send CSI reporting configuration information, wherein the CSI reporting configuration information is used to indicate that the UE uses one AI model supported by the UE.

[0320] The embodiments of the present disclosure provide an AI model determination apparatus, which includes a second sending module configured to, in response to determining that the UE supports one AI model, determine to send CSI reporting configuration information that does not include identification information of the AI model; wherein the CSI reporting configuration information is used to indicate that the UE uses the one AI model supported by the UE.

[0321] The embodiments of the present disclosure provide an AI model determination apparatus, which includes a second sending module configured to, in response to determining that the UE supports multiple AI models, send CSI reporting configuration information, wherein the CSI reporting configuration information includes identification information of at least one CSI reporting configuration and identification information of a corresponding AI model.

[0322] The embodiments of the present disclosure provide an AI model determination apparatus, which includes:

[0323] The second receiving module 61 is configured to receive AI model usage information sent by the UE;

[0324] The second processing module 62 is configured to determine, based on the AI model usage information, an AI model of CSI used by the base station.

[0325] In some embodiments, the AI model uses information, including at least one of:

[0326] identification information of the AI model;

[0327] identification information of a CSI reporting configuration corresponding to the identification information of the AI model.

[0328] The embodiments of the present disclosure provide an AI model determination apparatus, comprising: a second sending module configured to send reporting request information; wherein the reporting request information is used to request an AI model used by a UE.

[0329] It should be noted that those skilled in the art can understand that the apparatus provided by the embodiments of the present disclosure can be executed alone or together with some apparatuses in some embodiments or related technologies.

[0330] Regarding the apparatuses in the above embodiments, the specific manners in which each module performs operations have been described in detail in the embodiments related to the method, and will not be described in detail here.

[0331] The embodiments of the present disclosure provide a communication device, comprising:

[0332] a processor;

[0333] a memory for storing processor-executable instructions;

[0334] The processor is configured to implement the AI model determination method of any of the embodiments of the present disclosure when running the executable instructions.

[0335] In one embodiment, the communication device can include, but is not limited to, at least one of: a UE and a base station.

[0336] The processor can include various types of storage media, which is a non-transitory computer storage medium that can continue to store information on it after the user equipment is powered off.

[0337] The processor can be connected with the memory through a bus or the like, for reading the executable program stored on the memory, for example, at least one of the methods as shown in Figures 2 to 6

[0338] The embodiments of the present disclosure also provide a computer storage medium, which stores a computer executable program. The executable program is executed by the processor to implement the AI model determination method of any of the embodiments of the present disclosure. For example, at least one of the methods as shown in Figures 2 to 6

[0339] ​​With reference to the apparatus or the storage medium in the above embodiments, the specific manners in which various modules perform operations have been described in detail in the embodiments of the method, and thus will not be described here in detail.

[0340] Figure 9 is a block diagram of a user equipment 800 according to an exemplary embodiment. The user equipment 800 can be a mobile phone, computer, digital broadcast user equipment, messaging equipment, game console, tablet equipment, medical equipment, fitness equipment, personal digital assistant, etc.

[0341] With reference to Figure 9 , the user equipment 800 can include one or more of the following components: a processing component 802, a memory 804, a power supply component 806, a multimedia component 808, an audio component 810, an input / output (I / O) interface 812, a sensor component 814, and a communication component 816.

[0342] The processing component 802 usually controls overall operations of the user equipment 800, such as operations associated with displaying, making phone calls, data communications, camera operations and recording operations. The processing component 802 can include one or more processors 820 to execute instructions to complete all or part of steps of the methods described above. In addition, the processing component 802 can include one or more modules to facilitate interaction between the processing component 802 and other components. For example, the processing component 802 can include a multimedia module to facilitate the interaction between the multimedia component 808 and the processing component 802.

[0343] The memory 804 is configured to store various types of data to support operations of the user equipment 800. Examples of these data include instructions for any application or method operating on the user equipment 800, contact data, phonebook data, messages, pictures, videos, etc. The memory 804 can be implemented by any type of volatile or non-volatile storage devices or a combination thereof, such as static random access memory (SRAM), electrically erasable programmable read-only memory (EEPROM), erasable programmable read-only memory (EPROM), programmable read-only memory (PROM), read-only memory (ROM), magnetic storage, flash memory, magnetic disk or optical disk.

[0344] The power supply component 806 provides power for various components of the user equipment 800. The power supply component 806 can include a power supply management system, one or more power supplies, and other components associated with generating, managing and distributing power for the user equipment 800.

[0345] The multimedia component 808 includes a screen to provide an output interface between the user and the user device 800. In some embodiments, the screen can include a liquid crystal display (LCD) and a touch panel (TP). If the screen includes a touch panel, the screen can be implemented as a touch screen to receive input signals from a user. The touch panel includes one or more touch sensors to sense touch, swiping, and gestures on the touch panel. The touch sensors can not only sense a boundary of a touching or swiping action, but also detect duration and pressure related to the touching or swiping action. In some embodiments, the multimedia component 808 includes a front camera and / or a back camera. When the user device 800 is in an operation mode, such as a shooting mode or a video mode, the front camera and / or the back camera can receive external multimedia data. Each of the front and back cameras can be a fixed optical lens system or have a focal length and optical zoom capability.

[0346] The audio component 810 is configured to output and / or input audio signals. For example, the audio component 810 includes a microphone (MIC) to receive an external audio signal when the user device 800 is in an operation mode, such as a call mode, a recording mode, and a voice recognition mode. The received audio signal can be further stored in the memory 804 or transmitted via the communication component 816. In some embodiments, the audio component 810 also includes a speaker to output audio signals.

[0347] The I / O interface 812 provides an interface between the processing component 802 and peripheral interface modules, which can be a keypad, a click wheel, buttons, and the like. The buttons can include, but are not limited to, a home button, a volume button, a start button, and a lock button.

[0348] The sensor component 814 includes one or more sensors to provide various state assessments for the user device 800. For example, the sensor component 814 can detect an open / closed state of the device 800, relative positioning of components, such as a display and a keypad of the user device 800, a change in position of the user device 800 or a component of the user device 800, presence or absence of user contact with the user device 800, a change in orientation of the user device 800 or acceleration / deceleration of the user device 800, and a temperature change of the user device 800. The sensor component 814 can include a proximity sensor configured to detect presence of a nearby object without any physical touch. The sensor component 814 can further include a light sensor, such as a CMOS or CCD image sensor, for use in an imaging application. In some embodiments, the sensor component 814 can further include an acceleration sensor, a gyroscope sensor, a magnetic sensor, a pressure sensor, or a temperature sensor.

[0349] The communication component 816 is configured to facilitate wired or wireless communication between the user equipment 800 and other devices. The user equipment 800 can access a wireless network based on a communication standard, such as WiFi, 4G, or 5G, or a combination thereof. In an example embodiment, the communication component 816 receives a broadcast signal or broadcast related information from an external broadcast management system via a broadcast channel. In an example embodiment, the communication component 816 further includes a Near Field Communication (NFC) module to facilitate short-range communication. For example, the NFC module can be implemented based on Radio Frequency Identification (RFID) techniques, infrared data association (IrDA) techniques, ultra-wideband (UWB) techniques, Bluetooth (BT) techniques, and other techniques.

[0350] In an example embodiment, the user equipment 800 can be implemented by one or more application-specific integrated circuits (ASICs), digital signal processors (DSPs), digital signal processing devices (DSPDs), programmable logic devices (PLDs), field programmable gate arrays (FPGAs), controllers, micro-controllers, microprocessors, or other electronic elements, for performing the above-described methods.

[0351] In an example embodiment, a non-transitory computer-readable storage medium including instructions, such as the memory 804 including instructions, is also provided, which can be executed by the processor 820 of the user equipment 800 to complete the above-described methods. For example, the non-transitory computer-readable storage medium can be a ROM, a random access memory (RAM), a CD-ROM, a magnetic tape, a floppy disc, and an optical data storage device, etc.

[0352] As shown in Figure 10 , an embodiment of the present disclosure shows a structure of a base station. For example, the base station 900 can be provided as a network-side device. Referring to Figure 10 , the base station 900 includes a processing component 922, which further includes one or more processors, and memory resources represented by a memory 932, for storing instructions, such as application programs, executable by the processing component 922. The application programs stored in the memory 932 can include one or more modules each corresponding to a set of instructions. In addition, the processing component 922 is configured to execute the instructions to perform any of the above-described methods of the application on the base station.

[0353] The base station 900 can also include a power supply component 926 configured to perform power management for the base station 900, a wired or wireless network interface 950 configured to connect the base station 900 to a network, and an input output (I / O) interface 958. The base station 900 can operate based on an operating system stored in the memory 932, such as Windows Server™, Mac OS X™, Unix™, Linux™, FreeBSD™, or the like.

[0354] Other embodiments of the application will be apparent to those skilled in the art from consideration of the specification and practice of the application disclosed herein. Various modifications and changes can be made to the application without departing from its spirit. It is intended that the specification and examples be considered as exemplary only, with the true scope and spirit of the application being indicated by the following claims.

[0355] It should be understood that the application is not limited to the precise construction that has been described above and shown in the accompanying drawings, and that various modifications and changes can be made to the embodiments of the application without departing from the scope thereof. The scope of the application is limited only by the claims that follow.

Claims

1. A method for determining an AI model, wherein: Executed by user equipment UE, including: Determining an AI model to be used by the UE based on a scenario in which the UE is located; wherein determining the AI ​​model to be used by the UE based on the scenario in which the UE is located includes one of the following: determining that the UE uses a first-level AI model based on the UE being in a first speed scenario and / or an urban scenario; determining that the UE uses a second-level AI model based on the UE being in a second speed scenario and / or a rural scenario; the first speed is less than or equal to the second speed; the computing power and / or storage capacity corresponding to the first level is less than the computing power and / or storage capacity corresponding to the second level; Sending artificial intelligence (AI) capability information of the UE, where the AI ​​capability information is used by the base station to determine an AI model of channel state information (CSI) used by the UE; wherein the AI ​​capability information includes: AI level indication information, which is used to indicate the level of AI capability supported by the UE; the AI ​​capability information also includes at least one of the following: AI capability indication information, used to indicate whether the UE supports AI capabilities; AI model identification information, used to indicate the AI ​​model supported by the UE; AI platform identification information, used to indicate the AI ​​platform supported by the UE; AI reasoning indication information, used to indicate whether the UE supports AI reasoning capability; and AI training indication information, used to indicate whether the UE supports the training capability of the AI ​​model; The AI ​​capability information is reported by each UE.

2. The method according to claim 1, wherein The AI ​​capability information is reported non-mandatory or conditionally mandatory.

3. The method according to any one of claims 1 to 2, wherein: The method further comprises: receiving CSI reporting configuration information; wherein the CSI reporting configuration information is determined by the base station based on the AI ​​capability information; Determine at least one AI model used by the UE based on the CSI reporting configuration information.

4. The method according to claim 3, wherein: The determining, based on the CSI reporting configuration information, at least one AI model used by the UE includes: Determining, based on the fact that the CSI reporting configuration information does not include the identification information of the AI ​​model, that the UE uses one of the AI ​​models supported by the UE; or, Based on identification information of at least one CSI reporting configuration and identification information of a corresponding AI model included in the CSI reporting configuration information, it is determined that different CSI reporting configurations use the corresponding AI model.

5. The method according to claim 3, wherein The method further comprises: Send AI model usage information; wherein the AI ​​model usage information is used to determine the AI ​​model used by the UE.

6. The method according to claim 5, wherein: The AI ​​model usage information includes at least one of the following: Identification information of the AI ​​model; Identification information of the CSI reporting configuration corresponding to the identification information of the AI ​​model.

7. The method according to claim 5 or 6, wherein: The sending of AI model usage information includes: Based on the report request information received from the network device, the AI ​​model usage information is sent; wherein the report request information is used to request the AI ​​model used by the UE.

8. A method for determining an AI model, wherein: Executed by the base station, including: Receive artificial intelligence (AI) capability information of a user equipment (UE); wherein the AI ​​capability information includes: AI level indication information, which is used to indicate the level of the AI ​​capability supported by the UE; the AI ​​capability information includes at least one of the following: AI capability indication information, used to indicate whether the UE supports AI capabilities; AI model identification information, used to indicate the AI ​​model supported by the UE; AI platform identification information, used to indicate the AI ​​platform supported by the UE; AI reasoning indication information, used to indicate whether the UE supports AI reasoning capability; and AI training indication information, used to indicate whether the UE supports the training capability of the AI ​​model; Determining, based on the AI ​​capability information, at least one AI model of channel state information (CSI) used by the UE; wherein, determining, based on the AI ​​capability information, at least one AI model of channel state information (CSI) used by the UE includes one of the following: determining, based on the AI ​​capability information, that the UE uses a first-level AI model, wherein the UE is in a first speed scenario and / or an urban scenario; determining, based on the AI ​​capability information, that the UE uses a second-level AI model, wherein the UE is in a second speed scenario and / or an urban scenario; the first speed is less than or equal to the second speed; the computing power and / or storage capacity corresponding to the first level is less than the computing power and / or storage capacity corresponding to the second level; The AI ​​capability information is reported by each UE.

9. The method according to claim 8, wherein The method comprises: Send CSI reporting configuration information, where the CSI reporting configuration information is used to instruct the UE to use one of the AI ​​models.

10. The method according to claim 9, wherein: The sending the CSI reporting configuration information includes: In response to determining that the UE supports an AI model, determine to send CSI reporting configuration information that does not include identification information of the AI ​​model; wherein the CSI reporting configuration information is used to instruct the UE to use one of the AI ​​models supported by the UE.

11. The method according to claim 9, wherein The sending the CSI reporting configuration information includes: In response to determining that the UE supports multiple AI models, CSI reporting configuration information is sent, wherein the CSI reporting configuration information includes: identification information of at least one CSI reporting configuration and identification information of the corresponding AI model.

12. The method according to claim 9, wherein The method comprises: Receive AI model usage information sent by UE; Based on the AI ​​model usage information, determine the AI ​​model of the CSI used by the base station.

13. The method according to claim 12, wherein: The AI ​​model usage information includes at least one of the following: Identification information of the AI ​​model; Identification information of the CSI reporting configuration corresponding to the identification information of the AI ​​model.

14. The method according to claim 13, wherein: The method comprises: Sending a reporting request message; wherein the reporting request message is used to request the AI ​​model used by the UE.

15. An AI model determination device, wherein: include: The first processing module is configured to determine an AI model to be used by the UE based on a scenario in which the UE is located; wherein the first processing module is specifically configured to: determine that the UE uses a first-level AI model based on the UE being in a first speed scenario and / or an urban scenario; or determine that the UE uses a second-level AI model based on the UE being in a second speed scenario and / or a rural scenario; the first speed is less than or equal to the second speed; and the computing power and / or storage capacity corresponding to the first level is less than the computing power and / or storage capacity corresponding to the second level; A first sending module is configured to send artificial intelligence (AI) capability information of a user equipment (UE), wherein the AI ​​capability information is used by a base station to determine an AI model of channel state information (CSI) used by the UE; wherein the AI ​​capability information includes AI level indication information, which is used to indicate a level of AI capability supported by the UE; and the AI ​​capability information further includes at least one of the following: AI capability indication information, used to indicate whether the UE supports AI capabilities; AI model identification information, used to indicate the AI ​​model supported by the UE; AI platform identification information, used to indicate the AI ​​platform supported by the UE; AI reasoning indication information, used to indicate whether the UE supports AI reasoning capability; and AI training indication information, used to indicate whether the UE supports the training capability of the AI ​​model; The AI ​​capability information is reported by each UE.

16. An AI model determination device, wherein: include: The second receiving module is configured to receive artificial intelligence (AI) capability information of a user equipment (UE); wherein the AI ​​capability information includes: AI level indication information, which is used to indicate the level of the AI ​​capability supported by the UE; and the AI ​​capability information further includes at least one of the following: AI capability indication information, used to indicate whether the UE supports AI capabilities; AI model identification information, used to indicate the AI ​​model supported by the UE; AI platform identification information, used to indicate the AI ​​platform supported by the UE; AI reasoning indication information, used to indicate whether the UE supports AI reasoning capability; and AI training indication information, used to indicate whether the UE supports the training capability of the AI ​​model; a second processing module configured to determine, based on the AI ​​capability information, at least one AI model of channel state information (CSI) used by the UE; the second processing module being specifically configured to: determine, based on the AI ​​capability information, that the UE uses a first-level AI model, wherein the UE is in a first speed scenario and / or an urban scenario; or, based on the AI ​​capability information, determine that the UE uses a second-level AI model, wherein the UE is in a second speed scenario and / or an urban scenario; the first speed is less than or equal to the second speed; and the computing power and / or storage capacity corresponding to the first level is less than the computing power and / or storage capacity corresponding to the second level; The AI ​​capability information is reported by each UE.

17. A communication device, wherein: The communication device comprises: processor; a memory for storing instructions executable by the processor; The processor is configured to implement the AI ​​model determination method described in any one of claims 1 to 7 or claims 9 to 14 when running the executable instructions.

18. A computer storage medium, wherein: The computer storage medium stores a computer executable program, and when the executable program is executed by the processor, it implements the AI ​​model determination method described in any one of claims 1 to 7 or claims 9 to 14.

Images