Communication method, terminal, network device, and storage medium

Abstract

The present disclosure relates to a communication method, a terminal, a network device, and a storage medium. The communication method comprises: receiving first information sent by a network device, wherein the first information is used for instructing a terminal to select an artificial intelligence (AI) model meeting a performance requirement. In the present disclosure, first information sent by a network device is received, such that a terminal can select, on the basis of the first information, a suitable AI model for activation, etc., and the activated AI model has a relatively good performance.

Description

Communication method, terminal, network device and storage medium Technical Field

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

[0002] In related technologies, for new radio networks (NR), especially when the communication frequency band is in frequency range 2, beam-based transmission and reception are required to ensure coverage due to the rapid attenuation of high-frequency channels.

[0003] In some beam management processes, in order to reduce the number of beams or beam pairs measured by the terminal, an artificial intelligence (AI) model can be used to perform beam prediction.

[0004] Summary of the Invention

[0005] AI models activated by network devices are often inappropriate or perform poorly.

[0006] The embodiments of the present disclosure provide a communication method, a terminal, a network device, and a storage medium.

[0007] According to a first aspect of an embodiment of the present disclosure, a communication method is proposed, comprising: a terminal receiving first information sent by a network device, wherein the first information is used to instruct the terminal to select an artificial intelligence (AI) model that meets performance requirements.

[0008] According to a second aspect of an embodiment of the present disclosure, a communication method is proposed, comprising: a network device sending first information to a terminal, wherein the first information is used to instruct the terminal to select an artificial intelligence (AI) model that meets performance requirements.

[0009] According to a third aspect of an embodiment of the present disclosure, a communication method is proposed, comprising: a network device sending first information to a terminal, wherein the first information is used to instruct the terminal to select an artificial intelligence (AI) model that meets performance requirements; and the terminal receives the first information.

[0010] According to a fourth aspect of an embodiment of the present disclosure, a terminal is proposed, comprising: a transceiver module for receiving first information sent by a network device, wherein the first information is used to instruct the terminal to select an artificial intelligence (AI) model that meets performance requirements.

[0011] According to a fifth aspect of an embodiment of the present disclosure, a network device is proposed, including: a transceiver module, used to send first information to a terminal, wherein the first information is used to instruct the terminal to select an artificial intelligence (AI) model that meets performance requirements.

[0012] According to a sixth aspect of an embodiment of the present disclosure, a terminal is proposed, comprising: one or more processors; wherein the terminal is configured to execute the first aspect and any one of the communication methods in the first aspect.

[0013] According to a seventh aspect of an embodiment of the present disclosure, a network device is proposed, comprising: one or more processors; wherein the network device is used to execute the second aspect and any one of the communication methods in the second aspect.

[0014] According to the eighth aspect of an embodiment of the present disclosure, a communication system is proposed, comprising a terminal and a network device, wherein the terminal is configured to implement the first aspect and any one of the communication methods in the first aspect, and the network device is configured to implement the first aspect and any one of the communication methods in the first aspect.

[0015] According to the ninth aspect of the embodiment of the present disclosure, a storage medium is proposed, which stores instructions. When the instructions are executed on a communication device, the communication device executes a communication method such as the first aspect and any one of the first aspects or the first aspect and any one of the first aspects.

[0016] The present disclosure can facilitate the terminal to select a suitable AI model for activation based on the first information by receiving the first information sent by the network device, and the performance of the activated AI model is better. BRIEF DESCRIPTION OF THE DRAWINGS

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

[0018] FIG1 is a schematic diagram showing a communication system architecture according to an embodiment of the present disclosure.

[0019] FIG2 is a schematic diagram showing an interaction of a communication method according to an embodiment of the present disclosure.

[0020] FIG3 a is a flow chart of a communication method according to an embodiment of the present disclosure.

[0021] FIG3 b is a flow chart of a communication method according to an embodiment of the present disclosure.

[0022] FIG3 c is a flow chart of a communication method according to an embodiment of the present disclosure.

[0023] FIG4 a is a flow chart of a communication method according to an embodiment of the present disclosure.

[0024] FIG4 b is a flow chart of a communication method according to an embodiment of the present disclosure.

[0025] FIG5 is a flow chart showing a communication method according to an embodiment of the present disclosure.

[0026] FIG6 a is a schematic diagram of a terminal according to an embodiment of the present disclosure.

[0027] FIG6 b is a schematic diagram of a network device according to an embodiment of the present disclosure.

[0028] Fig. 7a is a schematic diagram showing a communication device according to an exemplary embodiment.

[0029] FIG7 b is a schematic diagram showing a chip structure according to an exemplary embodiment. DETAILED DESCRIPTION

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

[0031] In a first aspect, an embodiment of the present disclosure proposes a communication method, which includes: a terminal receives first information sent by a network device, where the first information is used to instruct the terminal to select an artificial intelligence (AI) model that meets performance requirements.

[0032] In the above embodiment, by receiving the first information sent by the network device, the terminal can select a suitable AI model for activation according to the first information, and the performance of the activated AI model is better.

[0033] In combination with the embodiments of the first aspect, in some embodiments, the first information includes at least one of the following: AI function identifier; AI model identifier; performance requirement.

[0034] In the above embodiment, the network device can selectively send at least one of the above-mentioned AI function identifier, AI model identifier and performance requirement according to different situations, so that the terminal can more accurately select the appropriate AI model and improve communication efficiency.

[0035] In combination with the embodiments of the first aspect, in some embodiments, the first information includes an AI function identifier and performance requirements; the AI ​​function identified by the AI ​​function identifier is an AI function configured, activated, or deactivated by the network device.

[0036] In the above embodiment, the first information may include an AI function identifier and performance requirements. The AI ​​function identifier may indicate the AI ​​function, and the performance requirements may facilitate the terminal to select an AI model from multiple AI models corresponding to the AI ​​function, so as to more accurately select an AI model that meets the requirements and improve communication efficiency.

[0037] In combination with the embodiments of the first aspect, in some embodiments, the first information includes an AI model identifier, and the method further includes: the terminal sends the performance of each AI model to the network device.

[0038] In the above embodiment, the performance of the AI ​​model is sent to the network device so that the network device can indicate the AI ​​model identifier, so that the terminal can quickly select an AI model that meets the needs.

[0039] In combination with the embodiments of the first aspect, in some embodiments, in response to lifecycle management based on an AI model, the first information includes the AI ​​model identifier and the performance requirement.

[0040] In the above embodiment, the first information may include an AI model identifier and performance requirements, so as to instruct the terminal to select an AI model that meets the performance requirements when performing lifecycle management based on the AI ​​model, thereby improving communication efficiency.

[0041] In combination with the embodiments of the first aspect, in some embodiments, the number of AI model identifiers is one or more.

[0042] In the above embodiment, the number of AI model identifiers may be one or more, and the number of AI models being one can quickly instruct the terminal to select an AI model that meets the performance requirements. If there are multiple AI models, the terminal can select an AI model that meets the performance requirements from the AI ​​models identified by the multiple AI model identifiers, thereby saving power consumption on the network device side.

[0043] In combination with the embodiments of the first aspect, in some embodiments, the performance requirements include different types of performance requirements, and the performance requirements include at least one of the following: the AI ​​function is used for spatial beam prediction, and each type of different types of performance requirements corresponds to a performance requirement value; the AI ​​function is used for time domain beam prediction, and each type of different types of performance requirements corresponds to one or more performance requirement values, and the multiple performance requirement values ​​include a performance requirement value corresponding to each prediction instance.

[0044] In the above embodiment, different performances are sent for different situations, and the performances corresponding to different prediction instances of the AI ​​function or AI model can be sent, thereby improving communication efficiency.

[0045] In combination with the embodiments of the first aspect, in some embodiments, the performance requirements include at least one of the following types: beam or beam pair prediction accuracy; beam or beam pair prediction accuracy with an L1-RSRP difference within a first threshold, the L1-RSRP difference being the difference between the measured L1-RSRP of the best predicted beam or beam pair and the measured L1-RSRP of the best beam or beam pair; L1-RSRP difference, the L1-RSRP difference being the difference between the measured L1-RSRP of the best predicted beam or beam pair and the measured L1-RSRP of the best beam or beam pair, wherein the difference includes at least one of the following: the average value of the L1-RSRP difference, the cumulative distribution function of the L1-RSRP difference, the proportion of the L1-RSRP difference less than or equal to the second threshold, and the proportion of the L1-RSRP difference greater than the third threshold, wherein the L1-RSRP difference is the best predicted beam or beam pair. The difference between the measured L1-RSRP of a beam or a beam pair and the measured L1-RSRP of the best beam or beam pair; a predicted L1-RSRP difference, wherein the predicted L1-RSRP difference is the difference between the predicted L1-RSRP of the best predicted beam or beam pair and the measured L1-RSRP of the best predicted beam or beam pair, wherein the predicted L1-RSRP difference includes at least one of the following: an average value of the predicted L1-RSRP difference, a cumulative distribution function of the predicted L1-RSRP difference, a proportion of the predicted L1-RSRP difference less than or equal to the second threshold, and a proportion of the L1-RSRP difference greater than a third threshold, wherein the predicted L1-RSRP difference is the difference between the predicted L1-RSRP of the best predicted beam or beam pair and the measured L1-RSRP of the best predicted beam or beam pair; terminal throughput; reference signal overhead; uplink control information overhead; predicted delay.

[0046] In the above embodiment, the performance requirement may be at least one of the above items, which enables the terminal to quickly select an AI model that meets the performance requirement based on the performance requirement, thereby improving efficiency.

[0047] In combination with the embodiments of the first aspect, in some embodiments, the first information includes the environment of the AI ​​function or the environment of the AI ​​model, and the environment includes at least one of the following: the number of beams or beam pairs in the first beam set, and the measurement value of the first beam set is used as the input of the AI ​​model; the beam pattern of the beams or beam pairs in the first beam set; the number of beams or beam pairs in the second beam set, wherein the output of the AI ​​model is used to obtain the beam information in the second beam set; the beam pattern of the beams or beam pairs in the second beam set; the relationship between the first beam set and the second beam set; the content of the AI ​​model input; the content of the AI ​​model output; AI function or model performance monitoring information; auxiliary information; applicable deployment scenarios; beam codebook of applicable network equipment; beam codebook of applicable terminals; applicable terminal distribution information; the number of measurement instances input to the AI ​​model; the number of prediction instances output by the AI ​​model; and the moving speed of applicable terminals.

[0048] In the above embodiment, various different environments can help the terminal quickly select an AI model that meets performance requirements, thereby improving efficiency.

[0049] In conjunction with the embodiments of the first aspect, in some embodiments, the first information is carried by any one of the following: unlimited resource control RRC;

[0050] Media Access Control Element MAC CE; Downlink Control Information DCI.

[0051] In the above embodiment, the first information can be carried in a variety of ways, so that the first information can be sent flexibly and practically.

[0052] According to a second aspect of an embodiment of the present disclosure, a communication method is provided, comprising: a network device sending first information to a terminal, wherein the first information is used to instruct the terminal to select an artificial intelligence (AI) model that meets performance requirements.

[0053] In combination with the embodiments of the second aspect, in some embodiments, the first information includes at least one of the following: AI function identifier; AI model identifier; performance requirement.

[0054] In combination with the embodiments of the second aspect, in some embodiments, the first information includes an AI function identifier and performance requirements; the AI ​​function identified by the AI ​​function identifier is an AI function configured, activated, or deactivated by the network device.

[0055] In combination with the embodiments of the second aspect, in some embodiments, the first information includes an AI model identifier, and the method further includes: the network device receives the performance of each AI model sent by the terminal.

[0056] In the above embodiment, by receiving the performance of each AI model, the network device can indicate the AI ​​model to the terminal, without the terminal having to select an AI model that meets the performance requirements based on the performance requirements, which is more efficient.

[0057] In combination with the embodiments of the second aspect, in some embodiments, in response to lifecycle management based on an AI model, the first information includes the AI ​​model identifier and the performance requirement.

[0058] In combination with the embodiments of the second aspect, in some embodiments, the number of AI model identifiers is one or more.

[0059] In combination with the embodiments of the second aspect, in some embodiments, the performance requirements include different types of performance requirements, and the performance requirements include at least one of the following: the AI ​​function is used for spatial beam prediction, and each type of different types of performance requirements corresponds to a performance requirement value; the AI ​​function is used for time domain beam prediction, and each type of different types of performance requirements corresponds to one or more performance requirement values, and the multiple performance requirement values ​​include a performance requirement value corresponding to each prediction instance.

[0060] In combination with the embodiments of the second aspect, in some embodiments, the performance requirements include at least one of the following types: beam or beam pair prediction accuracy; beam or beam pair prediction accuracy with an L1-RSRP difference within a first threshold, the L1-RSRP difference being the difference between the measured L1-RSRP of the best predicted beam or beam pair and the measured L1-RSRP of the best beam or beam pair; L1-RSRP difference, the L1-RSRP difference being the difference between the measured L1-RSRP of the best predicted beam or beam pair and the measured L1-RSRP of the best beam or beam pair, wherein the difference includes at least one of the following: the average value of the L1-RSRP difference, the cumulative distribution function of the L1-RSRP difference, the proportion of the L1-RSRP difference less than or equal to the second threshold, and the proportion of the L1-RSRP difference greater than a third threshold, wherein the L1-RSRP difference is the best predicted beam or beam pair. The difference between the measured L1-RSRP of a beam or a beam pair and the measured L1-RSRP of the best beam or beam pair; a predicted L1-RSRP difference, wherein the predicted L1-RSRP difference is the difference between the predicted L1-RSRP of the best predicted beam or beam pair and the measured L1-RSRP of the best predicted beam or beam pair, wherein the predicted L1-RSRP difference includes at least one of the following: an average value of the predicted L1-RSRP difference, a cumulative distribution function of the predicted L1-RSRP difference, a proportion of the predicted L1-RSRP difference less than or equal to the second threshold, and a proportion of the L1-RSRP difference greater than a third threshold, wherein the predicted L1-RSRP difference is the difference between the predicted L1-RSRP of the best predicted beam or beam pair and the measured L1-RSRP of the best predicted beam or beam pair; terminal throughput; reference signal overhead; uplink control information overhead; predicted delay.

[0061] In combination with the embodiments of the second aspect, in some embodiments, the first information includes the environment of the AI ​​function or the environment of the AI ​​model, and the environment includes at least one of the following: the number of beams or beam pairs in the first beam set, and the measurement value of the first beam set is used as the input of the AI ​​model; the beam pattern of the beams or beam pairs in the first beam set; the number of beams or beam pairs in the second beam set, wherein the output of the AI ​​model is used to obtain the beam information in the second beam set; the beam pattern of the beams or beam pairs in the second beam set; the relationship between the first beam set and the second beam set; the content of the AI ​​model input; the content of the AI ​​model output; AI function or model performance monitoring information; auxiliary information; applicable deployment scenarios; beam codebook of applicable network equipment; beam codebook of applicable terminals; applicable terminal distribution information; the number of measurement instances input to the AI ​​model; the number of prediction instances output by the AI ​​model; and the moving speed of applicable terminals.

[0062] In conjunction with the embodiments of the second aspect, in some embodiments, the first information is carried by any one of the following: unlimited resource control RRC;

[0063] Media Access Control Element MAC CE; Downlink Control Information DCI.

[0064] According to a third aspect of an embodiment of the present disclosure, a communication method is provided, comprising: a network device sending first information to a terminal, wherein the first information is used to instruct the terminal to select an artificial intelligence (AI) model that meets performance requirements; and the terminal receives the first information.

[0065] According to a fourth aspect of an embodiment of the present disclosure, a terminal is provided, comprising: a transceiver module for receiving first information sent by a network device, wherein the first information is used to instruct the terminal to select an artificial intelligence (AI) model that meets performance requirements.

[0066] According to a fifth aspect of an embodiment of the present disclosure, a network device is provided, including: a transceiver module, used to send first information to a terminal, wherein the first information is used to instruct the terminal to select an artificial intelligence (AI) model that meets performance requirements.

[0067] According to a sixth aspect of an embodiment of the present disclosure, a terminal is provided, comprising: one or more processors; wherein the terminal is configured to execute the first aspect and any one of the communication methods in the first aspect.

[0068] According to a seventh aspect of an embodiment of the present disclosure, a network device is provided, comprising: one or more processors; wherein the network device is configured to execute the second aspect and any one of the communication methods in the second aspect.

[0069] According to the eighth aspect of an embodiment of the present disclosure, a communication system is provided, including a terminal and a network device, wherein the terminal is configured to implement the first aspect and any one of the communication methods in the first aspect, and the network device is configured to implement the first aspect and any one of the communication methods in the first aspect.

[0070] According to the ninth aspect of an embodiment of the present disclosure, a storage medium is provided, which stores instructions. When the instructions are executed on a communication device, the communication device executes a communication method such as any one of the first aspect and the first aspect or any one of the first aspect and the first aspect.

[0071] According to a tenth aspect of an embodiment of the present disclosure, an embodiment of the present disclosure proposes a program product. When the program product is executed by a communication device, the communication device executes the method described in the optional implementation manner of the first aspect or the second aspect.

[0072] According to an eleventh aspect of the embodiments of the present disclosure, the embodiments of the present disclosure propose a computer program, which, when executed on a computer, enables the computer to execute the method described in the optional implementation of the first aspect or the second aspect.

[0073] According to a twelfth aspect of the embodiments of the present disclosure, the embodiments of the present disclosure provide a chip or a chip system, wherein the chip or chip system includes a processing circuit configured to execute the method described in the optional implementation of the first or second aspect.

[0074] It is understandable that the terminal, access network device, first network element, other network elements, core network device, communication system, storage medium, program product, computer program, chip, or chip system involved in each embodiment of the present disclosure are all used to perform the method proposed in the embodiment of the present disclosure. Therefore, the beneficial effects that can be achieved can refer to the beneficial effects of the corresponding method and will not be repeated here.

[0075] The present disclosure provides communication methods, devices, equipment, and storage media. In some embodiments, the terms "communication method," "information processing method," and "communication method" are interchangeable; the terms "communication device," "information processing device," and "communication device" are interchangeable; and the terms "information processing system," "communication system," and "communication system" are interchangeable.

[0076] The embodiments of the present disclosure are not exhaustive and are merely illustrative of some embodiments, and are not intended to be a specific limitation on the scope of protection of the present disclosure. In the absence of contradiction, each step in a certain embodiment can be implemented as an independent embodiment, and the steps can be arbitrarily combined. For example, a solution after removing some steps in a certain embodiment can also be implemented as an independent embodiment, and the order of the steps in a certain embodiment can be arbitrarily exchanged. In addition, the optional implementation methods in a certain embodiment can be arbitrarily combined; in addition, the embodiments can be arbitrarily combined. For example, some or all steps of different embodiments can be arbitrarily combined, and a certain embodiment can be arbitrarily combined with the optional implementation methods of other embodiments.

[0077] In each embodiment of the present disclosure, unless otherwise specified or provided for, the terms and / or descriptions between the embodiments are consistent and may be referenced by each other. The technical environments in different embodiments may be combined to form new embodiments based on their inherent logical relationships.

[0078] The terms used in the embodiments of the present disclosure are only for the purpose of describing specific embodiments and are not intended to limit the present disclosure.

[0079] In the embodiments of the present disclosure, unless otherwise specified, elements expressed in the singular, such as "a", "an", "the", "above", "said", "the", "the", etc., may mean "one and only one", or "one or more", "at least one", etc. For example, when using articles such as "a", "an", "the" in English in translation, the noun following the article may be understood as a singular expression or a plural expression.

[0080] In the embodiments of the present disclosure, “plurality” refers to two or more.

[0081] In some embodiments, the terms "at least one," "one or more," "a plurality of," "multiple," etc. may be used interchangeably.

[0082] In some embodiments, descriptions such as "at least one of A and B," "A and / or B," "A in one case, B in another case," or "in response to one case A, in response to another case B" may include the following technical solutions depending on the situation: in some embodiments, A (A is executed independently of B); in some embodiments, B (B is executed independently of A); in some embodiments, execution is selected from A and B (A and B are selectively executed); and in some embodiments, A and B (both A and B are executed). The above is also applicable when there are more branches such as A, B, and C.

[0083] In some embodiments, "A or B" and other descriptions may include the following technical solutions depending on the situation: in some embodiments, A (A is executed independently of B); in some embodiments, B (B is executed independently of A); in some embodiments, execution is selected from A and B (A and B are selectively executed). The above is also applicable when there are more branches such as A, B, C, etc.

[0084] The prefixes such as "first" and "second" in the embodiments of the present disclosure are only used to distinguish different description objects and do not constitute any restriction on the position, order, priority, quantity or content of the description objects. For the statement of the description object, please refer to the description in the context of the claims or embodiments, and no unnecessary restriction should be constituted due to the use of prefixes. For example, if the description object is a "field", the ordinal number before the "field" in the "first field" and the "second field" does not limit the position or order between the "fields". "First" and "second" do not limit whether the "fields" they modify are in the same message, nor do they limit the order of the "first field" and the "second field". For another example, if the description object is a "level", the ordinal number before the "level" in the "first level" and the "second level" does not limit the priority between the "levels". For another example, the number of description objects is not limited by the ordinal number and can be one or more. Taking "first device" as an example, the number of "devices" can be one or more. In addition, the objects modified by different prefixes can be the same or different. For example, if the description object is "device", then the "first device" and the "second device" can be the same device or different devices, and their types can be the same or different; for example, if the description object is "information", then the "first information" and "the performance of each AI model" can be the same information or different information, and their contents can be the same or different.

[0085] In some embodiments, “including A,” “comprising A,” “used to indicate A,” and “carrying A” can be interpreted as directly carrying A or indirectly indicating A.

[0086] In some embodiments, terms such as "in response to...", "in response to determining...", "in the case of...", "at the time of...", "when...", "if...", "if...", etc. can be used interchangeably.

[0087] In some embodiments, terms such as "greater than", "greater than or equal to", "not less than", "more than", "more than or equal to", "not less than", "higher than", "higher than or equal to", "not less than", and "above" can be replaced with each other, and terms such as "less than", "less than or equal to", "not greater than", "less than", "less than or equal to", "not more than", "lower than", "lower than or equal to", "not higher than", and "below" can be replaced with each other.

[0088] In some embodiments, devices and equipment can be interpreted as physical or virtual, and their names are not limited to the names recorded in the embodiments. In some cases, they can also be understood as "equipment", "device", "circuit", "network element", "node", "function", "unit", "section", "system", "network", "chip", "chip system", "entity", "subject", etc.

[0089] In some embodiments, "network" can be interpreted as devices included in the network, such as access network equipment, core network equipment, etc.

[0090] In some embodiments, "access network device (AN device)" may also be referred to as "radio access network device (RAN device)", "base station (BS)", "radio base station", "fixed station", and in some embodiments may also be understood as "node", "access point", "transmission point (TP)", "reception point (RP)", "transmission and / or reception point (TRP)" "panel", "antenna panel", "antenna array", "cell", "macro cell", "small cell", "femto cell", "pico cell", "sector", "cell group", "serving cell", "carrier", "component carrier", "bandwidth part (BWP)", etc.

[0091] In some embodiments, "terminal" or "terminal device" may be referred to as "user equipment (UE)", "user terminal" "mobile station (MS)", "mobile terminal (MT)", subscriber station, mobile unit, subscriber unit, wireless unit, remote unit, mobile device, wireless device, wireless communication device, remote device, mobile subscriber station, access terminal, mobile terminal, wireless terminal, remote terminal, handset, user agent, mobile client, client, etc.

[0092] In some embodiments, obtaining data, information, etc. may comply with the laws and regulations of the country where the data is obtained.

[0093] In some embodiments, data, information, etc. may be obtained with the user's consent.

[0094] In addition, each element, each row, or each column in the table of the embodiment of the present disclosure can be implemented as an independent embodiment, and the combination of any elements, any rows, and any columns can also be implemented as an independent embodiment.

[0095] FIG1 is a schematic diagram showing a communication system architecture according to an embodiment of the present disclosure.

[0096] As shown in FIG1 , a communication system 100 includes a terminal 101 and a network device 102 .

[0097] In some embodiments, the terminal 101 includes, for example, a mobile phone, a wearable device, an Internet of Things device, a car with communication function, a smart car, a tablet computer, a computer with wireless transceiver function, a virtual reality (VR) terminal device, an augmented reality (AR) terminal device, a wireless terminal device in industrial control, a wireless terminal device in self-driving, a wireless terminal device in remote medical surgery, a wireless terminal device in a smart grid, a wireless terminal device in transportation safety, a wireless terminal device in a smart city, and at least one of a wireless terminal device in a smart home, but is not limited thereto.

[0098] In some embodiments, the network device 102 may include at least one of an access network device and a core network device.

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

[0100] In some embodiments, the technical solution of the present disclosure can be applied to the Open RAN architecture. In this case, the interfaces between or within the access network devices involved in the embodiments of the present disclosure can be transformed into internal interfaces of the Open RAN, and the processes and information interactions between these internal interfaces can be implemented through software or programs.

[0101] In some embodiments, the access network device can be composed of a centralized unit (CU) and a distributed unit (DU), where the CU can also be called a control unit. The CU-DU structure can be used to split the protocol layer of the access network device, with the functions of some protocol layers centrally controlled by the CU, and the functions of the remaining part or all of the protocol layers distributed in the DU, which is centrally controlled by the CU, but is not limited to this.

[0102] In some embodiments, a core network device may be a device including one or more network elements, or may be multiple devices or device groups, each including all or part of the one or more network elements. The network element may be virtual or physical. The core network may include, for example, at least one of an Evolved Packet Core (EPC), a 5G Core Network (5GCN), and a Next Generation Core (NGC).

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

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

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

[0106] In the disclosed embodiments, in NR, especially when the communication frequency band is in frequency range 2, since the high-frequency channel attenuates rapidly, beam-based transmission and reception are required to ensure coverage.

[0107] In some traditional beam management processes, network equipment configures a set of reference signal resources for beam measurement. The terminal measures the reference signal resources in this set and reports the IDs of some of the stronger reference signal resources, along with the corresponding layer 1 reference signal received power (L1-RSRP) and / or layer 1 signal to interference plus noise ratio (L1-SINR), to the network equipment.

[0108] In related art, it is assumed that the reference signal resource set configured by a network device includes X reference signal resources, each of which corresponds to a different transmit beam of the network device. For each reference signal resource, the terminal needs to use all receive beams to measure the reference signal. This results in obtaining the beam measurement qualities corresponding to all receive beams. In some cases, one or more best beam measurement qualities and / or the beam identifier corresponding to the best beam measurement quality can be determined. Therefore, the number of beam pairs that the terminal needs to measure is G*H. Here, G represents the number of transmit beams of the network device, and H represents the number of receive beams of the terminal.

[0109] In some embodiments, an AI model and / or AI function is provided to implement beam prediction, wherein an AI function can be considered as one or more AI models that implement the same function and purpose.

[0110] In some embodiments, the AI ​​model used for beam prediction can be referred to as a beam prediction model. Of course, it can also be referred to as a beam prediction AI model, a prediction AI model, a predicted beam model, etc. This disclosure does not limit the names of such AI models.

[0111] In some implementations, when the beam prediction model uses spatial prediction, the terminal measures the L1-RSRP of set B and inputs the measured value into the beam prediction model. The beam prediction model can predict the L1-RSRP of the best beam and / or beam pair in set A, and / or the identifier of the best beam and / or beam pair in set A.

[0112] The relationship between set B and set A includes the following two types:

[0113] The first relationship is that set B is a subset of set A. For example, if set A contains 32 reference signal resources (each reference signal resource corresponds to a beam direction), then set B contains some of them, for example, set B contains 8 of the 32 reference signal resources.

[0114] The second relationship is that set B is a wide beam and set A is a narrow beam. For example, set A contains 32 reference signal resources (each reference signal resource corresponds to a beam direction, and the 32 reference signal resources cover a 120-degree direction). Set B contains another Y reference signal resources, for example, Y = 8. These Y reference signal resources also cover a 120-degree direction, that is, the beam direction of each reference signal resource in set B covers the beam directions of multiple reference signal resources in set A. It can be understood that the relationship between the 32 / Y reference signal resources in set A and the one reference signal resource in set B is QCL Type D.

[0115] It should be understood that the examples of the first and second relationships described above only describe the transmit beam case. When considering beam pairs consisting of transmit and receive beams, the terminal's receive beams must also be considered. For example, if there are 32 transmit beams and 4 receive beams, then set A consists of 32*4 beam pairs, and set B can consist of 32 beam pairs, 16 beam pairs, and so on.

[0116] In some embodiments, if the performance of the beam prediction model does not need to be monitored, assuming that the AI ​​model has been trained in advance, the network device only needs to periodically send the reference signal on the reference resource of set B (for example, the first period). The terminal then measures the L1-RSRP of the reference signal on the reference signal resource in set B and inputs it into the beam prediction model. This outputs the L1-RSRP corresponding to the reference signal resource of set A or the strongest one or more reference signal resource IDs among the 32 reference signal resources in set A.

[0117] In some embodiments, if it is necessary to monitor the performance of the beam prediction model, the network device is required to periodically send the reference signal on the reference signal resource of set A (for example, the second period). Then the terminal needs to measure the L1-RSRP of the reference signal on the reference signal resource of set B. For the terminal side model, the terminal inputs the measured L1-RSRP of the reference signal on the reference signal resource of set B into the beam prediction model, obtains the predicted beam information, and reports it to the network device; for the network side model, the terminal reports the measured L1-RSRP and / or identifier of the reference signal on the reference signal resource of set B to the network device, and the network device inputs the L1-RSRP and / or identifier of the reference signal on the reference signal resource of set B into the beam prediction model to obtain the predicted beam information. At the same time, the terminal also measures the L1-RSRP of the reference signals on all reference signal resources in set A, and reports the measured L1-RSRP and / or identifier of the reference signals on all reference signal resources in set A, and / or the L1-RSRP and / or identifier of the best L beams / beam pairs as the beam information obtained by the traditional method to the base station.

[0118] In various embodiments of the present disclosure, the terms "terminal-side model" and "AI model deployed on the terminal" can be used interchangeably. The terms "network device-side model" and "AI model deployed on the network device" can be used interchangeably.

[0119] In some implementations, when the beam prediction model uses time-domain prediction, the terminal measures the L1-RSRP at a historical time point, set B, and inputs this into the beam prediction model to predict the L1-RSRP at a future time point, set A. In addition to the two aforementioned relationships between set B and set A, there is another relationship in which set B and set A are identical.

[0120] When beam measurement is performed using methods described in related technologies, the base station also needs to transmit reference signals at future times. The terminal measures the reference signals at future times and reports the measured beam information to the network device. Specifically, the terminal needs to measure and report the beam information for all beams and / or beam pairs in set A to the network device.

[0121] In some related technologies, in order to reduce the number of beam pairs measured by the terminal, an AI model is used for beam prediction. For example, the terminal originally needs to measure a total of G*H beam pairs. When using the AI ​​model for beam prediction, for spatial domain beam prediction, the terminal only needs to measure a part of the G*H beam pairs. For example, measure 1 / 8, 1 / 4 of G*H beam pairs, etc. Then, the beam measurement quality of these beam pairs measured is input into the AI ​​model, and the AI ​​model can output the beam information of G*H beam pairs. For time domain beam prediction, the terminal can measure the beam measurement quality of beam pairs at historical times to predict the beam information of beam pairs at future times.

[0122] Of course, for the input and output of some AI models, it is also possible to not consider the beam quality or beam identification of the beam pair, but only consider the beam quality or beam identification of the downlink transmit beam. For example, an AI model based on a downlink beam, rather than an AI model based on a beam pair, is not limited in this disclosure.

[0123] It's clear that AI models have a specific lifecycle or scope of application. For example, some AI models are suitable for specific environments, such as suburban areas, urban areas, and indoor environments. Another example is that some AI models are suitable for rush hour, while others are suitable for specific time periods, such as during the sparse rush hour of work. Another example is that some AI models may be suitable for specific times and environments, such as on busy roads during the rush hour. Therefore, it's necessary to monitor the performance of AI models in real time. If the performance of an AI model falls short of expectations, it's necessary to promptly update or switch the model.

[0124] In some embodiments, different AI models also have different corresponding performance. For example, when the AI ​​model is used for spatial domain beam prediction, set B is a subset of set A. If the number of beams or beam pairs contained in set B is different, the accuracy of the beam information of set A predicted by the AI ​​model will be different. For another example, when the AI ​​model is used for time domain beam prediction, if the number of historical measurement times input or the number of future times output is different, the accuracy of the beam information output by the AI ​​model will also be different.

[0125] In some embodiments, an AI function corresponds to one or more AI models. If an AI function corresponds to multiple AI models, the network device cannot control the AI ​​models when managing the lifecycle of the AI ​​function. That is, the network device can only manage the AI ​​function on the terminal side, such as configuring, activating, deactivating, or switching the AI ​​function. However, the network cannot control which AI model the terminal side specifically configures, activates, deactivates, or switches the AI ​​function to. In this case, if the AI ​​models corresponding to the AI ​​function on the terminal side have different performance, the network device cannot control the terminal to select the correct AI model.

[0126] FIG2 is a schematic diagram illustrating an interaction of a communication method according to an embodiment of the present disclosure. As shown in FIG2 , the present disclosure embodiment relates to a communication method for use in a communication system 100, the method comprising:

[0127] In step S2101 , the terminal 101 sends the performance of each AI model to the network device 102 .

[0128] In some embodiments, the network device 102 receives the performance of each AI model sent by the terminal 101.

[0129] In some embodiments, terms such as "send", "transmit", "report", "download", "transmit", "bidirectional transmission", "send and / or receive" can be used interchangeably.

[0130] In some embodiments, "obtain", "get", "get", "receive", "transmit", "bidirectional transmission", "send and / or receive" can be interchangeable, and can be interpreted as receiving from other entities, obtaining from protocols, obtaining from higher layers, obtaining by self-processing, autonomous implementation, etc.

[0131] In some embodiments, the names of information, etc. are not limited to the names described in the embodiments, and terms such as "information", "message", "signal", "signaling", "report", "configuration", "indication", "instruction", "command", "channel", and "parameter" can be used interchangeably.

[0132] In some embodiments, the network device may determine the first information based on the performance and performance requirements of each received AI model. The first information is used to instruct the terminal to select an AI model that meets the performance requirements.

[0133] For example, the network device can determine the AI ​​model that meets the performance requirements based on the performance of each received AI model, and send the AI ​​model identifier that identifies the AI ​​model to the terminal to instruct the terminal to select the AI ​​model that meets the performance requirements.

[0134] In some embodiments, the name of the performance of each AI model is not limited. For example, it can be "performance information", "capability information", etc.

[0135] Step S2102 , the network device 102 sends first information to the terminal 101 .

[0136] In some embodiments, the terminal 101 receives first information sent by the network device 102 .

[0137] In some embodiments, the first information is used to instruct the terminal to select an AI model that meets performance requirements.

[0138] In some embodiments, the first information includes at least one of the following:

[0139] AI function identification;

[0140] AI model identification;

[0141] Performance requirements.

[0142] In some embodiments, the first information may include an AI function identifier. The AI ​​function identified by the AI ​​function identifier is an AI function managed by the network device. Management may include configuration, activation, deactivation, switching, and fallback to a non-AI mode.

[0143] In some embodiments, an AI function corresponds to one or more AI models. When an AI function corresponds to one AI model, the first information includes an AI function identifier, and the AI ​​model corresponding to the AI ​​function identified by the AI ​​function identifier can be managed. When an AI function corresponds to multiple AI models, the first information includes the AI ​​function identifier, and an AI model can be selected for management from the multiple AI models corresponding to the AI ​​function identified by the AI ​​function identifier.

[0144] In some embodiments, the first information may include an AI model identifier.

[0145] In some embodiments, the terminal may send the performance of each AI model to the network device. The first information includes an AI model identifier, and the AI ​​model identified by the AI ​​model identifier may be managed according to the AI ​​model identifier.

[0146] In some embodiments, the first information may include performance requirements.

[0147] In some embodiments, different AI models have different performances, and the first information includes performance requirements. An AI model that meets the performance requirements can be selected based on the performance requirements. For example, if the performance requirement included in the first information is that the prediction accuracy of beam prediction is greater than A, the terminal manages AI models with prediction accuracy greater than A.

[0148] In some embodiments, the first information includes an AI function identifier and performance requirements.

[0149] For example, if the lifecycle management is based on an AI function, the first information may include an AI function identifier and performance requirements. The terminal may select the AI ​​function identified by the AI ​​function identifier based on the AI ​​function identifier, and select an AI model that meets the performance requirements for management based on the performance requirements.

[0150] In some embodiments, the first information includes an AI model identifier and performance requirements.

[0151] For example, if the lifecycle management is based on an AI model, the first information may include an AI model identifier and performance requirements. The AI ​​model identifier may be one or more. If there are multiple AI model identifiers, an AI model that meets the performance requirements may be selected for management based on the performance requirements.

[0152] In some embodiments, the performance requirements include different types of performance requirements.

[0153] This disclosure uses the use of AI functions or AI models for beam prediction as an example to illustrate performance requirements. However, AI functions or AI models are not limited to beam prediction. For example, they can also be used for CSI compression, CSI prediction, positioning, etc. This disclosure does not list all of these.

[0154] Among them, different types of performance requirements can also be called performance requirements of different dimensions. The performance requirements include at least one of the following types: beam or beam pair prediction accuracy; beam or beam pair prediction accuracy with an L1-RSRP difference within a first threshold, the L1-RSRP difference is the difference between the measured L1-RSRP of the best predicted beam or beam pair and the measured L1-RSRP of the best beam or beam pair; L1-RSRP difference, the L1-RSRP difference is the difference between the measured L1-RSRP of the best predicted beam or beam pair and the measured L1-RSRP of the best beam or beam pair, wherein the L1-RSRP difference includes at least one of the following: the average value of the L1-RSRP difference, the cumulative distribution function of the L1-RSRP difference, the proportion of the L1-RSRP difference less than or equal to the second threshold, and the proportion of the L1-RSRP difference greater than the third threshold, wherein the L1-RSRP difference is the measured L1-RSRP of the best predicted beam or beam pair. The method comprises the following steps: determining a difference between the measured L1-RSRP and the measured L1-RSRP of the best predicted beam or beam pair; a predicted L1-RSRP difference, wherein the predicted L1-RSRP difference is the difference between the predicted L1-RSRP of the best predicted beam or beam pair and the measured L1-RSRP of the best predicted beam or beam pair, wherein the predicted L1-RSRP difference includes at least one of the following: an average value of the predicted L1-RSRP differences, a cumulative distribution function of the predicted L1-RSRP differences, a proportion of the predicted L1-RSRP differences less than or equal to a fourth threshold, and a proportion of the predicted L1-RSRP differences greater than a fifth threshold, wherein the predicted L1-RSRP difference is the difference between the predicted L1-RSRP of the best predicted beam or beam pair and the measured L1-RSRP of the best predicted beam or beam pair; terminal throughput; reference signal overhead; uplink control information overhead; and predicted delay.

[0155] In some embodiments, terms such as "uplink", "uplink", "physical uplink" can be interchangeable with each other, and terms such as "downlink", "downlink", "physical downlink" can be interchangeable with each other, and terms such as "side", "sidelink", "side communication", "sidelink communication", "direct connection", "direct link", "direct communication", "direct link communication" can be interchangeable with each other.

[0156] In some embodiments, the terms "downlink control information (DCI)", "downlink (DL) assignment", "DL DCI", "uplink (UL) grant", "UL DCI" and the like may be used interchangeably.

[0157] In some embodiments, the performance requirements include: beam or beam pair prediction accuracy.

[0158] For example, when using an AI model for beam prediction, if the predicted best K1 beams include the measured best beam, the prediction is accurate. Alternatively, if the predicted best beam is among the measured best K2 beams, the prediction is accurate. If the AI ​​model performs M beam predictions and N of them are correct, the prediction accuracy is N / M. K1 and K2 are positive integers, such as 1, 2, 3, 4, 5, and so on.

[0159] In some embodiments, the downlink transmit beam ID may be equivalent to a reference signal resource ID, such as a synchronization signal block (SSB) ID, a sounding reference signal (SRS) ID, or a channel state information reference signal (CSI-RS) ID. The downlink receive beam ID may be the receive beam ID of the terminal. The beam pair ID may be the ID corresponding to the combination of a downlink transmit beam and a downlink receive beam.

[0160] In some embodiments, terms such as "synchronization signal (SS)", "synchronization signal block (SSB)", "reference signal (RS)", "pilot", and "pilot signal" can be used interchangeably.

[0161] In some embodiments, the best beam may be the beam with the strongest L1-RSRP or L1-SINR.

[0162] In some embodiments, the performance requirement includes: beam or beam pair prediction accuracy with an L1-RSRP difference within a first threshold. The L1-RSRP difference is the difference between the measured L1-RSRP of the best predicted beam or beam pair and the measured L1-RSRP of the best beam or beam pair.

[0163] For example, when using an AI model for beam prediction, if the difference between the measured L1-RSRP of the predicted best beam and the measured L1-RSRP of the measured best beam is less than a first threshold, the prediction is accurate. Then, if the AI ​​model is used to predict beams P times, and the differences between the measured L1-RSRP of the predicted best beam and the measured L1-RSRP of the measured best beam are less than the first threshold Q times, the prediction accuracy for beams or beam pairs with L1-RSRP differences within the first threshold is Q / P. The "optimal predicted beam" represents the optimal beam predicted by the AI ​​model. The "measured L1-RSRP" represents the L1-RSRP measured for the beam. That is, the "measured L1-RSRP" of the predicted best beam represents the optimal beam predicted by the AI ​​model and measured for that optimal beam. The "measured best beam" represents the optimal beam obtained through actual measurement. For example, the actual measurement may be to measure the L1-RSRP or L1-SINR of multiple beams respectively, and the beam with the largest L1-RSRP or L1-SINR is the best beam. Measuring the L1-RSRP of the best beam means obtaining the best beam through actual measurement, and measuring the L1-RSRP of the best beam.

[0164] In some embodiments, the first threshold may be, for example, 1 dB, and the prediction accuracy of a beam or beam pair with an L1-RSRP difference within the first threshold may be the prediction accuracy of a beam or beam pair with an L1-RSRP difference within 1 dB. The L1-RSRP difference is the difference between the measured L1-RSRP of the best predicted beam or beam pair and the measured L1-RSRP of the best beam or beam pair.

[0165] In some embodiments, the performance requirement includes: L1-RSRP difference. The L1-RSRP difference is the difference between the measured L1-RSRP of the best predicted beam or beam pair and the measured L1-RSRP of the best beam or beam pair before measurement.

[0166] In some embodiments, the L1-RSRP difference can be the average value of the L1-RSRP difference. For example, the AI ​​model is used to perform one or more predictions to obtain A best predicted beams, and these A best predicted beams are measured respectively to obtain the measured L1-RSRP of the A best predicted beams. The difference between the predicted L1-RSRP of the A best predicted beams and the measured L1-RSRP of the measured best beam is calculated respectively, and the average value is taken, which is the average value of the L1-RSRP difference, that is, the L1-RSRP difference. Among them, the A best beams can be the A best beams obtained by using the AI ​​model for one prediction, or the A best beams obtained by using the AI ​​model for multiple predictions.

[0167] In some embodiments, the L1-RSRP difference may be a cumulative distribution function of L1-RSRP differences. For example, the value of the cumulative distribution function of L1-RSRP differences at a fixed percentage point is the L1-RSRP difference.

[0168] In some embodiments, the L1-RSRP difference may be a value of a cumulative distribution function at 5%, for example, YdB.

[0169] In some embodiments, the L1-RSRP difference may be a ratio of L1-RSRP differences less than or equal to a second threshold. For example, if model AI is used to perform A predictions, and B of the predictions have L1-RSRP differences less than or equal to the second threshold, then the L1-RSRP difference is B / A.

[0170] In some embodiments, the L1-RSRP difference may be a ratio of L1-RSRP differences greater than a third threshold. For example, if the AI ​​model is used to perform C predictions, and D of the L1-RSRP differences are greater than the third threshold, then the L1-RSRP difference is D / C.

[0171] The term "greater than the third threshold" may also mean "greater than or equal to the third threshold," which is not limited in this disclosure. The first, second, and third thresholds in this disclosure may be set based on actual circumstances, and may be the same or different.

[0172] In some embodiments, the performance requirement includes: a predicted L1-RSRP difference, where the predicted L1-RSRP difference is a difference between the predicted L1-RSRP of the best predicted beam or beam pair and the measured L1-RSRP of the best predicted beam or beam pair.

[0173] The predicted L1-RSRP represents the predicted L1-RSRP of a beam using the AI ​​model. That is, the predicted L1-RSRP of the best predicted beam or beam pair represents the best predicted beam predicted by the AI ​​model, and the L1-RSRP of that best predicted beam also predicted by the AI ​​model.

[0174] In some embodiments, the predicted L1-RSRP difference may be an average of the differences in the predicted L1-RSRP.

[0175] In some embodiments, the predicted L1-RSRP difference may be a cumulative distribution function of the differences in the predicted L1-RSRP.

[0176] In some embodiments, the predicted L1-RSRP difference may be a ratio of the predicted L1-RSRP difference being less than or equal to a fourth threshold.

[0177] In some embodiments, the predicted L1-RSRP difference may be a ratio of the predicted L1-RSRP difference being greater than a fifth threshold.

[0178] The difference in predicted L1-RSRP is the difference between the predicted L1-RSRP of the best predicted beam or beam pair and the measured L1-RSRP of the best predicted beam or beam pair.

[0179] In the present disclosure, the best predicted beam, the predicted best beam, and the predicted best beam have the same meaning and can be used interchangeably.

[0180] In some embodiments, the performance requirements include terminal throughput. For example, the optimal beam or beam pair can be predicted and the SINR of the optimal beam or beam pair can be measured. The capacity of each beam or beam pair can be calculated based on the Shannon capacity. The difference between the capacities of the two beams or beam pairs can be used as the average UE throughput difference.

[0181] In some embodiments, the terminal throughput may be an average throughput or a throughput at a fixed percentage of a cumulative distribution function, for example, the fixed percentage may be 5% or 95%.

[0182] In some embodiments, the performance requirements include reference signal overhead, which refers to the amount of reference signal resources required by the AI ​​model.

[0183] Among them, the size of set B input to the AI ​​model and the number of historical measurement times during time domain beam prediction have an impact on the reference signal overhead.

[0184] In some embodiments, the performance requirements include: uplink control information overhead. If the AI ​​model is an AI model deployed on the network device side, the terminal needs to send the measurement results based on set B to the network device. The uplink control information overhead is the signaling overhead of sending the measurement results of set B.

[0185] In some embodiments, performance requirements include predicted latency. For example, the unit of predicted latency can be milliseconds (ms). This means that if multiple beam information measured at time A is input into the AI ​​model, and the AI ​​model predicts the optimal beam at time B, the predicted latency is the difference between time A and time B. For example, the smaller the predicted latency, the better the performance of the AI ​​model.

[0186] In some embodiments, the first information includes the environment of the AI ​​model.

[0187] In some embodiments, the environment may include an environment (condition) or an additional environment (additional condition), and the environment may represent an environment or condition to which the AI ​​model is applicable, or represent a feature of the AI ​​model.

[0188] For example, the AI ​​model environment is used for beam prediction, CSI compression, CSI prediction, positioning, etc. This disclosure does not provide a complete list of examples. For another example, the AI ​​model is used for spatial beam prediction or time beam prediction.

[0189] The present disclosure takes the use of an AI model for spatial beam prediction as an example. The environment of the AI ​​model also includes at least one of the following: the number of beams or beam pairs in the first beam set, the measurement value of the first beam set is used as the input of the AI ​​model; the beam pattern of the beams or beam pairs in the first beam set; the number of beams or beam pairs in the second beam set, wherein the output of the AI ​​model is used to obtain beam information in the second beam set; the beam pattern of the beams or beam pairs in the second beam set; the relationship between the first beam set and the second beam set; the content of the AI ​​model input; the content of the AI ​​model output; AI model performance monitoring information; auxiliary information; applicable deployment scenarios; applicable network equipment beam codebook; applicable terminal beam codebook; applicable terminal distribution information; the number of measurement instances input by the AI ​​model; the number of prediction instances output by the AI ​​model; and the moving speed of the applicable terminal.

[0190] In some embodiments, the terms "codebook," "codeword," and "precoding matrix" may be used interchangeably. For example, a codebook may be a collection of one or more codewords / precoding matrices.

[0191] In some embodiments, the environment of the AI ​​model includes: the number of beams or beam pairs in the first beam set. The measurement values ​​of the first beam set are used as input to the AI ​​model. That is, the number of beams or beam pairs in the first beam set represents the number of measurement values ​​input to the AI ​​model. Different numbers of measurement values ​​input to the AI ​​model result in different performance of the AI ​​model. It can be understood that when the terminal sends the number of beams or beam pairs in the first beam set to the network device, it can facilitate the network device to determine whether the AI ​​model meets the performance requirements based on the number of beams or beam pairs in the first beam set to which the AI ​​model is applicable, thereby instructing the terminal to activate or deactivate the AI ​​model. The measurement values ​​of the first beam set are obtained by measuring the beams or beam pairs in the first beam set. Measuring the beams or beam pairs refers to measuring the L1-RSRP and / or L1-SINR of reference signal resources, such as SSB, CSI-RS, SRS, etc.

[0192] In some embodiments, the first set of beams may be set B.

[0193] In some embodiments, the environment of the AI ​​function or the environment of the AI ​​model includes: a beam pattern of beams or beam pairs in the first beam set.

[0194] In some embodiments, the beam pattern may indicate the direction in which the reference signal is transmitted and the direction in which the reference signal is not transmitted.

[0195] In some embodiments, the context of the AI ​​function or the context of the AI ​​model includes: the number of beams or beam pairs in the second beam set. The output of the AI ​​model is used to obtain beam information in the second beam set.

[0196] For example, the beams or beam pairs in the first beam set can be measured, and the measured values ​​can be input into the AI ​​model to obtain beam information for the beams or beam pairs in the second beam set. The number of beams or beam pairs in the first beam set and the second beam set, as well as the beam pattern, can both be context for the AI ​​function or AI model.

[0197] In some embodiments, the second set of beams may be set A.

[0198] In some embodiments, the environment of the AI ​​function or the environment of the AI ​​model includes: a relationship between a first wave number set and a second beam number set.

[0199] For example, the relationship between the first wave number set and the second beam set may be that the first beam set is a subset of the second beam set. Alternatively, the first beam set is a wide beam and the second beam set is a narrow beam. This disclosure does not list all of these, but is not limited to them.

[0200] In some embodiments, the environment of the AI ​​function or the environment of the AI ​​model includes: the content of the AI ​​model input.

[0201] For example, the input of the AI ​​model is the L1-RSRP and / or identifier corresponding to the beam or beam pair in the first beam set. That is, the input of the AI ​​model can be the L1-RSRP corresponding to the beam or beam pair in the first beam set, or the identifier corresponding to the beam or beam pair in the first beam set, or the L1-RSRP and identifier corresponding to the beam or beam pair in the first beam set.

[0202] In some embodiments, the environment of the AI ​​function or the environment of the AI ​​model includes: the content output by the AI ​​model.

[0203] For example, the output of the AI ​​model is the L1-RSRP and / or identifier of the beam or beam pair in the second beam set.

[0204] In some embodiments, the environment of the AI ​​function or the environment of the AI ​​model includes: AI function or AI model performance monitoring information.

[0205] For example, AI function or AI model performance monitoring information includes terminal monitoring of AI function or AI model performance, network equipment monitoring of AI function or AI model performance, terminal and network equipment jointly monitoring the performance of AI function or AI model performance, and performance indicators during AI function or AI model performance monitoring. Among them, the performance indicators during AI model monitoring include the different types of performance mentioned above. When a certain type of performance of an AI function or AI model is poor, it is considered that the AI ​​function or AI model needs to be deactivated or updated.

[0206] In some embodiments, the environment of the AI ​​function or the environment of the AI ​​model includes: auxiliary information.

[0207] In some embodiments, the environment of the AI ​​function or the environment of the AI ​​model includes: applicable deployment scenarios. For example, the deployment scenario can be an urban macro cell, an urban micro cell, or an indoor location. The deployment scenario can also include different inter-cell distances (ISDs), such as an ISD of 500m or 200m.

[0208] In some embodiments, the environment of the AI ​​function or the environment of the AI ​​model includes: a beam codebook of an applicable network device.

[0209] For example, the beam codebook of the applicable network device is a beam codebook used by the applicable network device for transmission.

[0210] In some embodiments, the context of the AI ​​function or the context of the AI ​​model includes: a beam codebook of an applicable terminal.

[0211] For example, the beam codebook of the applicable terminal is the beam codebook used by the applicable terminal for transmission.

[0212] In some embodiments, the environment of the AI ​​function or the environment of the AI ​​model includes: distribution information of applicable terminals.

[0213] In some embodiments, the terminal distribution information may include the ratio of users distributed indoors and outdoors.

[0214] In some embodiments, the context of the AI ​​function or the context of the AI ​​model includes: the number of measurement instances input to the AI ​​model.

[0215] For example, if the AI ​​model is used for time-domain beamforming prediction, the input of the AI ​​model may be multiple measurement instances (time instances), i.e., measurement results at multiple times. The environment of the AI ​​model may include the number of measurement instances input. The number of measurement instances input to the AI ​​model may affect the performance of the AI ​​model.

[0216] In some embodiments, the context of the AI ​​function or the context of the AI ​​model includes: the number of prediction instances output by the AI ​​model.

[0217] For example, if the AI ​​model is used for time-domain beamforming prediction, the output of the AI ​​model may be multiple prediction instances. The environment of the AI ​​model may include the number of prediction instances output. The difference in the number of prediction instances output by the AI ​​model may affect the performance of the AI ​​model.

[0218] In some embodiments, the environment of the AI ​​function or the environment of the AI ​​model includes: the moving speed of the applicable terminal.

[0219] For example, the applicable terminal movement speed indicates the terminal movement speed to which the AI ​​model can be applied. For example, the AI ​​model is applicable to terminals with a movement speed of A. The movement speed can be a speed magnitude or a speed range.

[0220] In some embodiments, the performance requirements include different types of performance requirements. The AI ​​model is used for spatial beam prediction, and each type of performance requirement corresponds to a performance requirement value.

[0221] The performance requirement value indicates a numerical value corresponding to the performance requirement.

[0222] For example, the performance requirement may be a type of performance requirement. For example, if the performance requirement includes beam or beam pair prediction accuracy, the performance requirement value may be one or more of accuracy A, accuracy B, and accuracy C.

[0223] For another example, the performance requirements include multiple types of performance requirements, such as beam or beam prediction accuracy, L1-RSRP difference, and predicted delay. The performance requirement values ​​may be accuracy A, difference B, and delay C.

[0224] For example, performance requirements include multiple types of performance requirements, such as beam or beam pair prediction accuracy, L1-RSRP variability, and predicted L1-RSRP variability. Each type corresponds to a performance requirement value. For example, beam or beam pair prediction accuracy corresponds to a performance requirement value, L1-RSRP variability corresponds to a performance requirement value, and predicted L1-RSRP variability corresponds to a performance requirement value.

[0225] In some embodiments, the performance requirements include different types of performance requirements. The AI ​​model is used for time-domain beam prediction, and each type of performance requirement corresponds to multiple performance requirement values. The multiple performance requirement values ​​include a performance requirement value corresponding to each prediction instance.

[0226] For example, performance requirements may include multiple types of performance requirements, such as beam or beam pair prediction accuracy, L1-RSRP variability, and predicted L1-RSRP variability. Each type corresponds to multiple performance requirement values. For example, beam or beam pair prediction accuracy may include the beam or beam pair prediction accuracy for each prediction instance. A prediction instance includes a prediction time instance.

[0227] In some embodiments, the first information may be carried by any of the following:

[0228] Unlimited Resource Control RRC;

[0229] Media Access Control Element MAC CE;

[0230] Downlink control information DCI.

[0231] In some embodiments, the terminal may manage the AI ​​model based on the first information.

[0232] In some embodiments, the name of the first information is not limited and may be, for example, "indication information", "performance information", etc.

[0233] In step S2103, the terminal 101 manages the AI ​​model based on the first information.

[0234] In some embodiments, the terminal 101 may manage the AI ​​model based on the received first information, where management may include coordination, activation, deactivation, switching, and the like.

[0235] In some embodiments, the first information includes an AI function identifier. The terminal can manage the AI ​​function identified by the AI ​​function identifier based on the AI ​​function identifier. One AI function corresponds to one or more AI models. When one function corresponds to one AI model, the terminal can manage the AI ​​model corresponding to the AI ​​function identified by the AI ​​function identifier based on the AI ​​function identifier. When one function corresponds to multiple AI models, the terminal can select an AI model to manage from the multiple AI models corresponding to the AI ​​function identified by the AI ​​function identifier based on the AI ​​function identifier.

[0236] In some embodiments, the first information includes an AI model identifier. The terminal may manage the AI ​​model identified by the AI ​​model identifier based on the AI ​​model identifier.

[0237] In some embodiments, the first information includes a performance requirement. Based on the performance requirement, the terminal may select an AI model that meets the performance requirement from various AI models for management.

[0238] In some embodiments, the first information includes an AI function identifier and a performance requirement. The terminal may determine the AI ​​function identified by the AI ​​function identifier based on the AI ​​function identifier, and determine at least one AI model corresponding to the AI ​​function to manage based on the performance requirement. For example, an AI model that meets the performance requirement may be determined for management.

[0239] In some embodiments, the first information includes an AI model identifier and a performance requirement. The terminal may select an AI model that meets the performance requirement based on the AI ​​model identifier and the performance requirement.

[0240] For example, if there are multiple AI model identifiers, the terminal can select an AI model to manage from the AI ​​models identified by the multiple AI model identifiers based on performance requirements. For example, an AI model that meets the performance requirements can be selected for management.

[0241] In some embodiments, the first information includes an environment of the AI ​​model. The terminal can select an AI model that meets performance requirements for management based on the environment of the AI ​​model.

[0242] For example, the environment of the AI ​​model includes the number B of beams or beam pairs in the first beam set, and the terminal can select the AI ​​model with the number B of beams or beam pairs in the first beam set for management.

[0243] The communication method involved in the embodiment of the present disclosure may include at least one of steps S2101 to S2103. For example, step S2101 may be implemented as an independent embodiment. Steps 2101 and 2102 may be implemented as separate embodiments.

[0244] In some embodiments, step S2101 and step S2103 are optional and can be omitted or replaced in different embodiments.

[0245] In some embodiments, reference may be made to other optional implementations described before or after the description corresponding to FIG. 2 .

[0246] FIG3a is a flow chart of a communication method according to an embodiment of the present disclosure. As shown in FIG3a, the present disclosure embodiment relates to a communication method, which is executed by terminal 101 and includes:

[0247] Step S3101, sending the performance of each AI model.

[0248] The optional implementation of step S3101 can refer to the optional implementation of step S2101 in Figure 2 and other related parts in the embodiment involved in Figure 2, which will not be repeated here.

[0249] In some embodiments, the terminal 101 sends the performance of each AI model to the network device 102, but is not limited to this. The performance of each AI model can also be sent to other entities.

[0250] Step S3102, obtaining first information.

[0251] The optional implementation of step S3102 can refer to the optional implementation of step S2102 in Figure 2 and other related parts in the embodiment involved in Figure 2, which will not be repeated here.

[0252] In some embodiments, the terminal 101 receives the first information sent by the network device 102, but is not limited thereto and may also receive the first information sent by other entities.

[0253] In some embodiments, terminal 101 obtains first information specified by a protocol.

[0254] In some embodiments, terminal 101 obtains the first information from upper layer(s).

[0255] In some embodiments, the terminal 101 performs processing to obtain the first information.

[0256] In some embodiments, step S3102 is omitted, and the terminal 101 autonomously implements the function indicated by the first information, or the above function is default or by default.

[0257] Step S3103: manage the AI ​​model based on the first information.

[0258] The optional implementation of step S3103 can refer to the optional implementation of step S2103 in Figure 2 and other related parts in the embodiment involved in Figure 2, which will not be repeated here.

[0259] In some embodiments, the AI ​​model is managed based on the first information.

[0260] The communication method involved in the embodiment of the present disclosure may include at least one of steps S3101 to S3103. For example, step S3102 may be implemented as an independent embodiment.

[0261] In some embodiments, step S3101 and step S3103 are optional and can be omitted or replaced in different embodiments.

[0262] In some embodiments, reference may be made to other optional implementations described before or after the description corresponding to FIG. 3 a .

[0263] FIG3b is a flow chart of a communication method according to an embodiment of the present disclosure. As shown in FIG3b, the embodiment of the present disclosure relates to a communication method, which is executed by terminal 101 and includes:

[0264] Step S3201, obtain first information.

[0265] Optional implementations of step S3201 may refer to step S2102 in FIG. 2 , optional implementations of step S3102 in FIG. 3 a , and other related parts in the embodiments involved in FIG. 2 and FIG. 3 a , which will not be described in detail here.

[0266] In some embodiments, the terminal 101 receives the first information sent by the network device 102, but is not limited thereto and may also receive the first information sent by other entities.

[0267] In some embodiments, terminal 101 obtains first information specified by a protocol.

[0268] In some embodiments, terminal 101 obtains the first information from upper layer(s).

[0269] In some embodiments, the terminal 101 performs processing to obtain the first information.

[0270] In some embodiments, step S3201 is omitted, and the terminal 101 autonomously implements the function indicated by the first information, or the above function is default or by default.

[0271] Step S3202: Manage the AI ​​model based on the first information.

[0272] The optional implementation of step S3202 can refer to the optional implementation of step S2103 in Figure 2, step S3103 in Figure 3a, and other related parts in the embodiments involved in Figures 2 and 3, which will not be repeated here.

[0273] In some embodiments, the AI ​​model is managed based on the first information.

[0274] The communication method involved in the embodiment of the present disclosure may include at least one of steps S3201 to S3202. For example, step S3201 may be implemented as an independent embodiment.

[0275] FIG3c is a flow chart of a communication method according to an embodiment of the present disclosure. As shown in FIG3c, the embodiment of the present disclosure relates to a communication method, which is executed by terminal 101 and includes:

[0276] Step S3301, obtain first information.

[0277] The optional implementation of step S3301 can refer to the optional implementation of step S2102 in Figure 2, step S3202 in Figure 3a, and other related parts in the embodiments involved in Figures 2 and 3a, which will not be repeated here.

[0278] In some embodiments, the terminal 101 receives the first information sent by the network device 102, but is not limited thereto and may also receive the first information sent by other entities.

[0279] In some embodiments, terminal 101 obtains first information specified by a protocol.

[0280] In some embodiments, terminal 101 obtains the first information from upper layer(s).

[0281] In some embodiments, the terminal 101 performs processing to obtain the first information.

[0282] In some embodiments, step S3301 is omitted, and the terminal 101 autonomously implements the function indicated by the first information, or the above function is default or by default.

[0283] In some embodiments, the first information includes at least one of the following: AI function identification; AI model identification; performance requirements.

[0284] In some embodiments, the first information includes an AI function identifier and performance requirements; the AI ​​function identified by the AI ​​function identifier is an AI function configured, activated, or deactivated by the network device.

[0285] In some embodiments, the first information includes an AI model identifier, and the method further includes: the terminal sends the performance of each AI model to the network device.

[0286] In some embodiments, in response to lifecycle management based on an AI model, the first information includes an AI model identifier and performance requirements.

[0287] In some embodiments, the number of AI model identifiers is one or more.

[0288] In some embodiments, the performance requirements include different types of performance requirements, and the performance requirements include at least one of the following: the AI ​​function is used for spatial beam prediction, and each type of different performance requirements corresponds to a performance requirement value; the AI ​​function is used for time domain beam prediction, and each type of different performance requirements corresponds to one or more performance requirement values, and the multiple performance requirement values ​​include a performance requirement value corresponding to each prediction instance.

[0289] In some embodiments, the performance requirements include at least one of the following types: beam or beam pair prediction accuracy; beam or beam pair prediction accuracy with an L1-RSRP difference within a first threshold, the L1-RSRP difference being the difference between the measured L1-RSRP of the best predicted beam or beam pair and the measured L1-RSRP of the best beam or beam pair; L1-RSRP difference, the L1-RSRP difference being the difference between the measured L1-RSRP of the best predicted beam or beam pair and the measured L1-RSRP of the best beam or beam pair, wherein the difference includes at least one of the following: the average value of the L1-RSRP difference, the cumulative distribution function of the L1-RSRP difference, the proportion of the L1-RSRP difference less than or equal to the second threshold, and the proportion of the L1-RSRP difference greater than a third threshold, wherein the L1-RSRP difference is the difference between the measured L1-RSRP of the best predicted beam or beam pair and the measured L1-RSRP of the best beam or beam pair. The difference between the measured L1-RSRP and the measured L1-RSRP of the best beam or beam pair; the predicted L1-RSRP difference, the predicted L1-RSRP difference being the difference between the predicted L1-RSRP of the best predicted beam or beam pair and the measured L1-RSRP of the best predicted beam or beam pair, wherein the predicted L1-RSRP difference comprises at least one of the following: an average value of the predicted L1-RSRP differences, a cumulative distribution function of the predicted L1-RSRP differences, a proportion of the predicted L1-RSRP differences being less than or equal to a second threshold, and a proportion of the L1-RSRP differences being greater than a third threshold, wherein the predicted L1-RSRP difference is the difference between the predicted L1-RSRP of the best predicted beam or beam pair and the measured L1-RSRP of the best predicted beam or beam pair; terminal throughput; reference signal overhead; uplink control information overhead; predicted delay.

[0290] In some embodiments, the first information includes the environment of the AI ​​function or the environment of the AI ​​model, and the environment includes at least one of the following: the number of beams or beam pairs in the first beam set, and the measurement value of the first beam set is used as the input of the AI ​​model; the beam pattern of the beams or beam pairs in the first beam set; the number of beams or beam pairs in the second beam set, wherein the output of the AI ​​model is used to obtain the beam information in the second beam set; the beam pattern of the beams or beam pairs in the second beam set; the relationship between the first beam set and the second beam set; the content of the AI ​​model input; the content of the AI ​​model output; AI function or model performance monitoring information; auxiliary information; applicable deployment scenarios; applicable network equipment beam codebook; applicable terminal beam codebook; applicable terminal distribution information; the number of measurement instances input to the AI ​​model; the number of prediction instances output by the AI ​​model; and the moving speed of the applicable terminal.

[0291] In some embodiments, the first information is carried by any one of the following: a resource control (RRC); a media access control (MAC) control element; or downlink control information (DCI).

[0292] FIG4a is a flow chart of a communication method according to an embodiment of the present disclosure. As shown in FIG4a, the embodiment of the present disclosure relates to a communication method, and the method includes:

[0293] Step S4101, obtain the performance of each AI model.

[0294] The optional implementation of step S4101 can refer to the optional implementation of step S2101 in Figure 2 and other related parts in the embodiment involved in Figure 2, which will not be repeated here.

[0295] In some embodiments, the network device 102 receives the performance of each AI model sent by the terminal 101, but is not limited to this. The network device 102 can also receive the performance of each AI model sent by other entities.

[0296] In some embodiments, the network device 102 obtains the performance of each AI model specified by the protocol.

[0297] In some embodiments, the network device 102 obtains the performance of each AI model from the upper layer(s).

[0298] In some embodiments, the network device 102 performs processing to obtain the performance of each AI model.

[0299] In some embodiments, step S4101 is omitted, and the network device 102 autonomously implements the functions indicated by the performance of each AI model, or the above functions are default or by default.

[0300] Step S4102, sending the first information.

[0301] The optional implementation of step S4102 can refer to the optional implementation of step S2102 in Figure 2 and other related parts in the embodiment involved in Figure 2, which will not be repeated here.

[0302] In some embodiments, the network device 102 sends the first information to the terminal 101, but is not limited thereto and may also send the first information to other entities.

[0303] The communication method involved in the embodiment of the present disclosure may include at least one of steps S4101 to S4102. For example, step S4102 may be implemented as an independent embodiment.

[0304] FIG4b is a flow chart of a communication method according to an embodiment of the present disclosure. As shown in FIG4b, the embodiment of the present disclosure relates to a communication method, and the method includes:

[0305] Step S4201, sending the first information.

[0306] The optional implementation of step S4201 can refer to the optional implementation of step S2102 in Figure 2 and other related parts in the embodiment involved in Figure 2, which will not be repeated here.

[0307] In some embodiments, the network device 102 sends the first information to the terminal 101, but is not limited thereto and may also send the first information to other entities.

[0308] FIG5 is a flow chart of a communication method according to an embodiment of the present disclosure. As shown in FIG5 , the embodiment of the present disclosure relates to a communication method, and the method includes:

[0309] Step S5101: The network device 102 sends first information to the terminal 101.

[0310] Optional implementations of step S5101 can be found in S2102 of FIG. 2 , step S3102 of FIG. 3 a , and other related parts in the embodiments involved in FIG. 2 and FIG. 3 a , which will not be described in detail here.

[0311] In some embodiments, the above method may include the method of the above embodiments related to the communication system 100, the terminal 101, the network device 102, etc., which will not be repeated here.

[0312] Step S5102: Terminal 101 receives first information.

[0313] The optional implementation of step S5102 can refer to S2102 in Figure 2, the optional implementation of step S4102 in Figure 4a, and other related parts in the embodiments involved in Figures 2 and 4a, which will not be repeated here.

[0314] In some embodiments, the above method may include the method of the above embodiments related to the communication system 100, the terminal 101, the network device 102, etc., which will not be repeated here.

[0315] The present disclosure also provides a communication method as follows:

[0316] In some embodiments, a terminal receives first information, where the first information is used to configure, activate, or indicate an AI function or an AI model, and the first information includes at least one of the following:

[0317] 1) AI functional identity (functionality ID).

[0318] In some embodiments, each AI functionality corresponds to a functionality ID, such as whether the functionality is used for beam prediction, CSI compression, CSI prediction, or positioning.

[0319] More specifically, if it is used for beam prediction, is it spatial domain beam prediction or time domain beam prediction?

[0320] Furthermore, in the case of spatial beam prediction, the number and / or pattern of beams (pairs) contained in set B used for model input; the number and / or pattern of beams (pairs) contained in set A corresponding to the model output; the relationship between set B and set A; the model input is L1-RSRP and / or beam ID, and the model output is L1-RSRP and / or beam ID; what auxiliary information is available, what deployment is applicable, the beam codebook applicable to the base station (gNB), and the beam codebook applicable to the terminal (UE); applicable UE distribution information; and applicable UE mobility speed.

[0321] In some embodiments, a beam refers to a beam, and a beam measurement refers to measuring the L1-RSRP and / or L1-SINR of reference signals including SSB, CSI-RS, and SRS; a beam indication refers to an indication of a transmission configuration indication (TCI) state, where the TCI state includes at least one quasi co-location (QCL) type, including QCL types A, B, C, and D, where type D is reception parameter information, commonly known as a beam. Types A, B, and C include at least one of parameters related to Doppler shift, Doppler spread, average delay, and delay spread. For an uplink beam, it refers to spatial relation information, a spatial filter parameter, or an uplink TCI state.

[0322] 2) AI model identification (model ID).

[0323] In some embodiments, each model corresponds to a model ID

[0324] 3) Performance requirements.

[0325] In some embodiments, the performance in the performance requirement may include at least one of the following values ​​(all taking the beam prediction model as an example):

[0326] 1) Beam prediction accuracy: beams (pairs) with a beam prediction accuracy of top 1 / K.

[0327] In some embodiments, a correct prediction means that the predicted strongest beam (pair) ID includes the measured strongest beam (pair) ID, or the predicted strongest beam (pair) ID is included in the N strongest measured beam (pair) IDs. The downlink transmit beam ID can be equivalent to a reference signal resource ID, such as an SSB ID, a CSI-RS ID, or an SRS ID. The downlink receive beam ID is the terminal's Rx beam ID. The beam pair ID is the ID corresponding to the combination of the downlink transmit beam and the downlink receive beam.

[0328] In some embodiments, the strongest means that the L1-RSRP or L1-SINR is the strongest.

[0329] In some embodiments, this indicator may be the accuracy of the beam information output based on multiple derivations of the model, for example, it may be a ratio.

[0330] 2) Beam prediction accuracy within 1 dB: The accuracy of the predicted best beam (pair) when the measured L1-RSRP is within 1 dB of the measured L1-RSRP of the best beam.

[0331] In some embodiments, this indicator may be the accuracy of the beam information output based on multiple derivations of the model, for example, a ratio.

[0332] 3) L1-RSRP Difference: The difference between the measured L1-RSRP of the predicted best beam (pair) and the measured L1-RSRP of the best beam, for example, the average value is X dB, or the value at the 5% percentile of the cumulative distribution function is Y dB.

[0333] In some embodiments, it may also be a ratio of the L1-RSRP difference being lower than a threshold value, or a ratio of the L1-RSRP difference being higher than a threshold value.

[0334] 4) Predicted L1-RSRP difference: The difference between the measured L1-RSRP of the predicted best beam (pair) and the predicted L1-RSRP of the best beam of the predicted best beam (pair), e.g., the mean is X dB, or the 5% percentile of the cumulative distribution function is Y dB.

[0335] In some embodiments, it may also be a ratio of the Predicted L1-RSRP difference being lower than a threshold value, or a ratio of the Predicted L1-RSRP difference being higher than a threshold value.

[0336] 5) Average UE throughput, or the UE throughput at the 5% point of the cumulative distribution function.

[0337] In some embodiments, based on the predicted strongest beam (pair) and the measured strongest beam (pair), the SINRs corresponding to the two beams (pairs) are obtained, and the capacity is calculated based on the Shannon capacity, and the difference in capacity is the indicator.

[0338] 6) Reference signal overhead.

[0339] That is, how much reference signal resources the AI ​​model requires. The main influencing factors include the size of set B corresponding to the model input and the number of historical measurement times during time domain prediction.

[0340] 7) Uplink control information overhead.

[0341] In some embodiments, if it is a network deployment (NW-side) model, the measurement results of set B need to be reported to the network, that is, the signaling overhead of this reporting.

[0342] 8) Predicted latency. Milliseconds (ms)

[0343] In some embodiments, for functionality based model management of AI functionality, performance requirements are indicated during AI functionality configuration / activation.

[0344] 1) Can indicate a performance requirement.

[0345] In some embodiments, since there may be multiple models on the terminal side to implement the functionality, and after the network side gives this performance requirement, the terminal cannot select a model at random and needs to select a model that meets the requirement.

[0346] 2) Time domain beam prediction

[0347] In some embodiments, if the model is required to predict multiple time instances, the performance requirements of multiple time instances can be indicated independently, that is, each time instance corresponds to one or a set of performance requirements.

[0348] In some embodiments, for model based model management, if the terminal has reported the performance of each model, the model ID can be directly indicated without additional requirement.

[0349] 1) If the terminal has not reported the performance of each model, it can indicate one or more model IDs and the performance requirement. That is, it instructs the terminal to activate one of the models that meets the requirement among multiple model IDs.

[0350] 2) Time domain beam prediction is the same as above. That is, if the model predicts beam information for multiple time instances, the performance requirements corresponding to each time instance need to be given independently.

[0351] In some embodiments, the first information may be carried via RRC, MAC CE and / or DCI.

[0352] The embodiments of the present disclosure further provide an apparatus for implementing any of the above methods. For example, an apparatus is provided, comprising units or modules for implementing each step performed by a terminal in any of the above methods. For another example, another apparatus is provided, comprising units or modules for implementing each step performed by a network device (e.g., an access network device, a core network function node, a core network device, etc.) in any of the above methods.

[0353] It should be understood that the division of the various units or modules in the above device is merely a division of logical functions. In actual implementation, they may be fully or partially integrated into a physical entity, or they may be physically separated. In addition, the units or modules in the device may be implemented in the form of a processor calling software: for example, the device includes a processor, the processor is connected to a memory, and the memory stores instructions. The processor calls the instructions stored in the memory to implement any of the above methods or implement the functions of the various units or modules of the above device, wherein the processor is, for example, a general-purpose processor, such as a central processing unit (CPU) or a microprocessor, and the memory is a memory within the device or a memory outside the device. Alternatively, the units or modules in the device can be implemented in the form of hardware circuits, and the functions of some or all of the units or modules can be realized by designing the hardware circuits. The above-mentioned hardware circuits can be understood as one or more processors; for example, in one implementation, the above-mentioned hardware circuit is an application-specific integrated circuit (ASIC), which realizes the functions of some or all of the above units or modules by designing the logical relationship of the components in the circuit; for example, in another implementation, the above-mentioned hardware circuit can be realized by a programmable logic device (PLD). Taking a field programmable gate array (FPGA) as an example, it can include a large number of logic gate circuits, and the connection relationship between the logic gate circuits is configured by configuring the configuration file, thereby realizing the functions of some or all of the above units or modules. All units or modules of the above devices can be realized in the form of software called by the processor, or in the form of hardware circuits, or in part by the form of software called by the processor, and the rest by hardware circuits.

[0354] In the embodiments of the present disclosure, the processor is a circuit with signal processing capabilities. In one implementation, the processor can be a circuit with instruction reading and execution capabilities, such as a central processing unit (CPU), a microprocessor, a graphics processing unit (GPU) (which can be understood as a microprocessor), or a digital signal processor (DSP). In another implementation, the processor can implement certain functions through the logical relationship of the hardware circuit. The logical relationship of the above-mentioned hardware circuit is fixed or reconfigurable. For example, the processor is a hardware circuit implemented by an application-specific integrated circuit (ASIC) or a programmable logic device (PLD), such as an FPGA. In a reconfigurable hardware circuit, the process of the processor loading a configuration document and implementing the hardware circuit configuration can be understood as the process of the processor loading instructions to implement the functions of some or all of the above units or modules. In addition, it can also be a hardware circuit designed for artificial intelligence, which can be understood as an ASIC, such as a neural network processing unit (NPU), a tensor processing unit (TPU), a deep learning processing unit (DPU), etc.

[0355] Figure 6a is a structural diagram of the terminal proposed in an embodiment of the present disclosure. As shown in Figure 6a, the terminal 6100 may include: a transceiver module 6101. In some embodiments, the above-mentioned transceiver module receives the first information sent by the network device, and the first information is used to instruct the terminal to select an artificial intelligence AI model that meets the performance requirements. Optionally, the above-mentioned transceiver module is used to execute the communication steps S2101 or S2103 such as sending and / or receiving performed by the terminal 101 in any of the above methods, which are not repeated here. In some embodiments, 6100 may include a processing module 6102. The above-mentioned processing module 6102 is used to manage the AI ​​model based on the first information.

[0356] In some embodiments, the first information includes at least one of the following: AI function identification; AI model identification; performance requirements.

[0357] In some embodiments, the first information includes an AI function identifier and performance requirements; the AI ​​function identified by the AI ​​function identifier is an AI function configured, activated, or deactivated by the network device.

[0358] In some embodiments, the first information includes an AI model identifier, and the transceiver module 6101 is further used for: the terminal sends the performance of each AI model to the network device.

[0359] In some embodiments, in response to lifecycle management based on an AI model, the first information includes an AI model identifier and performance requirements.

[0360] In some embodiments, the number of AI model identifiers is one or more.

[0361] In some embodiments, the performance requirements include different types of performance requirements, and the performance requirements include at least one of the following: the AI ​​function is used for spatial beam prediction, and each type of different performance requirements corresponds to a performance requirement value; the AI ​​function is used for time domain beam prediction, and each type of different performance requirements corresponds to one or more performance requirement values, and the multiple performance requirement values ​​include a performance requirement value corresponding to each prediction instance.

[0362] In some embodiments, the performance requirements include at least one of the following types: beam or beam pair prediction accuracy; beam or beam pair prediction accuracy with an L1-RSRP difference within a first threshold, the L1-RSRP difference being the difference between the measured L1-RSRP of the best predicted beam or beam pair and the measured L1-RSRP of the best beam or beam pair; L1-RSRP difference, the L1-RSRP difference being the difference between the measured L1-RSRP of the best predicted beam or beam pair and the measured L1-RSRP of the best beam or beam pair, wherein the difference includes at least one of the following: the average value of the L1-RSRP difference, the cumulative distribution function of the L1-RSRP difference, the proportion of the L1-RSRP difference less than or equal to the second threshold, and the proportion of the L1-RSRP difference greater than a third threshold, wherein the L1-RSRP difference is the difference between the measured L1-RSRP of the best predicted beam or beam pair and the measured L1-RSRP of the best beam or beam pair. The difference between the measured L1-RSRP and the measured L1-RSRP of the best beam or beam pair; the predicted L1-RSRP difference, the predicted L1-RSRP difference being the difference between the predicted L1-RSRP of the best predicted beam or beam pair and the measured L1-RSRP of the best predicted beam or beam pair, wherein the predicted L1-RSRP difference comprises at least one of the following: an average value of the predicted L1-RSRP differences, a cumulative distribution function of the predicted L1-RSRP differences, a proportion of the predicted L1-RSRP differences being less than or equal to a second threshold, and a proportion of the L1-RSRP differences being greater than a third threshold, wherein the predicted L1-RSRP difference is the difference between the predicted L1-RSRP of the best predicted beam or beam pair and the measured L1-RSRP of the best predicted beam or beam pair; terminal throughput; reference signal overhead; uplink control information overhead; predicted delay.

[0363] In some embodiments, the first information includes the environment of the AI ​​function or the environment of the AI ​​model, and the environment includes at least one of the following: the number of beams or beam pairs in the first beam set, and the measurement value of the first beam set is used as the input of the AI ​​model; the beam pattern of the beams or beam pairs in the first beam set; the number of beams or beam pairs in the second beam set, wherein the output of the AI ​​model is used to obtain the beam information in the second beam set; the beam pattern of the beams or beam pairs in the second beam set; the relationship between the first beam set and the second beam set; the content of the AI ​​model input; the content of the AI ​​model output; AI function or model performance monitoring information; auxiliary information; applicable deployment scenarios; applicable network equipment beam codebook; applicable terminal beam codebook; applicable terminal distribution information; the number of measurement instances input to the AI ​​model; the number of prediction instances output by the AI ​​model; and the moving speed of the applicable terminal.

[0364] In some embodiments, the first information is carried by any one of the following: a resource control (RRC); a media access control (MAC) control element; or downlink control information (DCI).

[0365] Figure 6b is a schematic diagram of the structure of a network device proposed in an embodiment of the present disclosure. As shown in Figure 6b, network device 6200 may include: a transceiver module 6201. The transceiver module 6201 is used to send first information to the terminal, and the first information is used to instruct the terminal to select an artificial intelligence (AI) model that meets performance requirements. Optionally, the transceiver module is used to perform the communication steps S2101 or S2103 such as sending and / or receiving performed by terminal 101 in any of the above methods, and will not be repeated here.

[0366] In some embodiments, the first information includes at least one of the following: AI function identification; AI model identification; performance requirements.

[0367] In some embodiments, the first information includes an AI function identifier and performance requirements; the AI ​​function identified by the AI ​​function identifier is an AI function configured, activated, or deactivated by the network device.

[0368] In some embodiments, the first information includes an AI model identifier, and the transceiver module 6201 is also used for the network device to receive the performance of each AI model sent by the terminal.

[0369] In some embodiments, in response to lifecycle management based on an AI model, the first information includes an AI model identifier and performance requirements.

[0370] In some embodiments, the number of AI model identifiers is one or more.

[0371] In some embodiments, the performance requirements include different types of performance requirements, and the performance requirements include at least one of the following: the AI ​​function is used for spatial beam prediction, and each type of different performance requirements corresponds to a performance requirement value; the AI ​​function is used for time domain beam prediction, and each type of different performance requirements corresponds to one or more performance requirement values, and the multiple performance requirement values ​​include a performance requirement value corresponding to each prediction instance.

[0372] In some embodiments, the performance requirements include at least one of the following types: beam or beam pair prediction accuracy; beam or beam pair prediction accuracy with an L1-RSRP difference within a first threshold, the L1-RSRP difference being the difference between the measured L1-RSRP of the best predicted beam or beam pair and the measured L1-RSRP of the best beam or beam pair; L1-RSRP difference, the L1-RSRP difference being the difference between the measured L1-RSRP of the best predicted beam or beam pair and the measured L1-RSRP of the best beam or beam pair, wherein the difference includes at least one of the following: the average value of the L1-RSRP difference, the cumulative distribution function of the L1-RSRP difference, the proportion of the L1-RSRP difference less than or equal to the second threshold, and the proportion of the L1-RSRP difference greater than a third threshold, wherein the L1-RSRP difference is the difference between the measured L1-RSRP of the best predicted beam or beam pair and the measured L1-RSRP of the best beam or beam pair. The difference between the measured L1-RSRP and the measured L1-RSRP of the best beam or beam pair; the predicted L1-RSRP difference, the predicted L1-RSRP difference being the difference between the predicted L1-RSRP of the best predicted beam or beam pair and the measured L1-RSRP of the best predicted beam or beam pair, wherein the predicted L1-RSRP difference comprises at least one of the following: an average value of the predicted L1-RSRP differences, a cumulative distribution function of the predicted L1-RSRP differences, a proportion of the predicted L1-RSRP differences being less than or equal to a second threshold, and a proportion of the L1-RSRP differences being greater than a third threshold, wherein the predicted L1-RSRP difference is the difference between the predicted L1-RSRP of the best predicted beam or beam pair and the measured L1-RSRP of the best predicted beam or beam pair; terminal throughput; reference signal overhead; uplink control information overhead; predicted delay.

[0373] In some embodiments, the first information includes the environment of the AI ​​function or the environment of the AI ​​model, and the environment includes at least one of the following: the number of beams or beam pairs in the first beam set, and the measurement value of the first beam set is used as the input of the AI ​​model; the beam pattern of the beams or beam pairs in the first beam set; the number of beams or beam pairs in the second beam set, wherein the output of the AI ​​model is used to obtain the beam information in the second beam set; the beam pattern of the beams or beam pairs in the second beam set; the relationship between the first beam set and the second beam set; the content of the AI ​​model input; the content of the AI ​​model output; AI function or model performance monitoring information; auxiliary information; applicable deployment scenarios; applicable network equipment beam codebook; applicable terminal beam codebook; applicable terminal distribution information; the number of measurement instances input to the AI ​​model; the number of prediction instances output by the AI ​​model; and the moving speed of the applicable terminal.

[0374] In some embodiments, the first information is carried by any one of the following: a resource control (RRC); a media access control (MAC) control element; or downlink control information (DCI).

[0375] In some embodiments, the transceiver module may include a transmitting module and / or a receiving module, and the transmitting module and the receiving module may be separate or integrated. Optionally, the transceiver module may be interchangeable with the transceiver.

[0376] In some embodiments, the processing module can be a single module or can include multiple submodules. Optionally, the multiple submodules respectively execute all or part of the steps required to be executed by the processing module. Optionally, the processing module can be interchangeable with the processor.

[0377] Figure 7a is a schematic diagram of the structure of a communication device 7100 proposed in an embodiment of the present disclosure. Communication device 7100 can be a network device, a terminal, a chip, a chip system, or a processor that supports a network device in implementing any of the above methods, or a chip, a chip system, or a processor that supports a terminal in implementing any of the above methods. Optionally, the network device can be an access network device, a core network device, or the like. Optionally, the terminal can be a user equipment, or the like. Communication device 7100 can be used to implement the methods described in the above method embodiments. For details, please refer to the description of the above method embodiments.

[0378] As shown in Figure 7a, communication device 7100 includes one or more processors 7101. Processor 7101 can be a general-purpose processor or a dedicated processor, for example, a baseband processor or a central processing unit. The baseband processor can be used to process communication protocols and communication data, while the central processing unit can be used to control the communication device, execute programs, and process program data. Communication device 7100 is used to perform any of the above methods. Optionally, the communication device can be a base station, a baseband chip, a terminal device, a terminal device chip, a DU or CU, etc.

[0379] In some embodiments, the communication device 7100 further includes one or more memories 7102 for storing instructions. Optionally, all or part of the memories 7102 may be located outside the communication device 7100.

[0380] In some embodiments, the communication device 7100 further includes one or more transceivers 7103. When the communication device 7100 includes one or more transceivers 7103, the transceiver 7103 performs the communication step S2101 such as sending and / or receiving in the above method, and the processor 7101 performs other steps.

[0381] In some embodiments, a transceiver may include a receiver and / or a transmitter. The receiver and transmitter may be separate or integrated. Optionally, the terms transceiver, transceiver unit, transceiver, and transceiver circuit may be used interchangeably; the terms transmitter, transmitting unit, transmitter, and transmitting circuit may be used interchangeably; and the terms receiver, receiving unit, receiver, and receiving circuit may be used interchangeably.

[0382] In some embodiments, the communication device 7100 may include one or more interface circuits 7104. Optionally, the interface circuit 7104 is connected to the memory 7102. The interface circuit 7104 may be configured to receive signals from the memory 7102 or other devices, and may be configured to send signals to the memory 7102 or other devices. For example, the interface circuit 7104 may read instructions stored in the memory 7102 and send the instructions to the processor 7101.

[0383] The communication device 7100 described in the above embodiment may be a network device or a terminal, but the scope of the communication device 7100 described in the present disclosure is not limited thereto, and the structure of the communication device 7100 may not be limited by FIG. 7a. The communication device may be an independent device or may be part of a larger device. For example, the communication device may be: 1) an independent integrated circuit IC, or a chip, or a chip system or subsystem; (2) a collection of one or more ICs, optionally, the above IC collection may also include a storage component for storing data or programs; (3) an ASIC, such as a modem; (4) a module that can be embedded in other devices; (5) a receiver, a terminal device, an intelligent terminal device, a cellular phone, a wireless device, a handheld device, a mobile unit, an in-vehicle device, a network device, a cloud device, an artificial intelligence device, etc.; (6) others, etc.

[0384] FIG7 b is a schematic diagram of the structure of a chip 7200 according to an embodiment of the present disclosure. If the communication device 7100 can be a chip or a chip system, reference can be made to the schematic diagram of the structure of the chip 7200 shown in FIG7 b , but the present disclosure is not limited thereto.

[0385] The chip 7200 includes one or more processors 7201 , and the chip 7200 is configured to execute any of the above methods.

[0386] In some embodiments, the chip 7200 further includes one or more interface circuits 7202. Optionally, the interface circuit 7202 is connected to the memory 7203. The interface circuit 7202 can be used to receive signals from the memory 7203 or other devices, and can be used to send signals to the memory 7203 or other devices. For example, the interface circuit 7202 can read instructions stored in the memory 7203 and send the instructions to the processor 7201.

[0387] In some embodiments, the interface circuit 7202 executes the communication step S2101 of sending and / or receiving in the above method, and the processor 7201 executes other steps.

[0388] In some embodiments, terms such as interface circuit, interface, transceiver pin, and transceiver may be used interchangeably.

[0389] In some embodiments, the chip 7200 further includes one or more memories 7203 for storing instructions. Alternatively, all or part of the memories 7203 may be located outside the chip 7200.

[0390] The present disclosure also proposes a storage medium having instructions stored thereon. When the instructions are executed on the communication device 7100, the communication device 7100 executes any of the above methods. Optionally, the storage medium is an electronic storage medium. Optionally, the storage medium is a computer-readable storage medium, but is not limited thereto and may also be a storage medium readable by other devices. Optionally, the storage medium may be a non-transitory storage medium, but is not limited thereto and may also be a temporary storage medium.

[0391] The present disclosure also provides a program product, which, when executed by the communication device 7100, enables the communication device 7100 to perform any of the above methods. Optionally, the program product is a computer program product.

[0392] The present disclosure also proposes a computer program, which, when executed on a computer, causes the computer to perform any one of the above methods.

Claims

1. A communication method, characterized in that: The method comprises: The terminal receives first information sent by a network device, where the first information is used to instruct the terminal to select an artificial intelligence AI model that meets performance requirements.

2. The method according to claim 1, characterized in that The first information includes at least one of the following: AI function identification; AI model identification; Performance requirements.

3. The method according to claim 1 or 2, characterized in that: The first information includes AI function identification and performance requirements; The AI ​​function identified by the AI ​​function identifier is the AI ​​function configured, activated or deactivated by the network device.

4. The method according to any one of claims 1 to 2, characterized in that: The first information includes an AI model identifier, and the method further includes: The terminal sends the performance of each AI model to the network device.

5. The method according to claim 2, characterized in that: In response to performing lifecycle management based on an AI model, the first information includes the AI ​​model identifier and the performance requirement.

6. The method according to claim 5, characterized in that The number of the AI ​​model identifiers is one or more.

7. The method according to any one of claims 2 to 6, characterized in that: The performance requirements include different types of performance requirements, and the performance requirements include at least one of the following: The AI ​​function is used for spatial beam prediction, and each type of performance requirements corresponds to a performance requirement value; The AI ​​function is used for time domain beam prediction. Each type of different performance requirements corresponds to one or more performance requirement values, and the multiple performance requirement values ​​include a performance requirement value corresponding to each prediction instance.

8. The method according to any one of claims 1 to 7, characterized in that: The performance requirements include at least one of the following types: Beam or beam pair prediction accuracy; The prediction accuracy of the beam or beam pair for which the L1-RSRP difference is within a first threshold, wherein the L1-RSRP difference is the difference between the measured L1-RSRP of the best predicted beam or beam pair and the measured L1-RSRP of the best beam or beam pair; L1-RSRP difference, the L1-RSRP difference is the difference between the measured L1-RSRP of the best predicted beam or beam pair and the measured L1-RSRP of the best beam or beam pair, wherein the difference includes at least one of the following: an average value of the L1-RSRP difference, a cumulative distribution function of the L1-RSRP difference, a proportion of the L1-RSRP difference less than or equal to a second threshold, and a proportion of the L1-RSRP difference greater than a third threshold, wherein the L1-RSRP difference is the difference between the measured L1-RSRP of the best predicted beam or beam pair and the measured L1-RSRP of the best beam or beam pair; A predicted L1-RSRP difference, wherein the predicted L1-RSRP difference is a difference between a predicted L1-RSRP of a best predicted beam or beam pair and a measured L1-RSRP of the best predicted beam or beam pair, wherein the predicted L1-RSRP difference comprises at least one of the following: an average value of a difference in predicted L1-RSRPs, a cumulative distribution function of a difference in predicted L1-RSRPs, a proportion of predicted L1-RSRP differences less than or equal to a second threshold, and a proportion of L1-RSRP differences greater than a third threshold, wherein the predicted L1-RSRP difference is a difference between a predicted L1-RSRP of a best predicted beam or beam pair and a measured L1-RSRP of the best predicted beam or beam pair; Terminal throughput; Reference signal overhead; Uplink control information overhead; Predict latency.

9. The method according to any one of claims 2 to 8, characterized in that: The first information includes an environment of the AI ​​function or an environment of the AI ​​model, and the environment includes at least one of the following: The number of beams or beam pairs in a first beam set, the measurements of which are used as input to the AI ​​model; beam patterns of beams or beam pairs in the first set of beams; The number of beams or beam pairs in a second beam set, wherein the output of the AI ​​model is used to obtain beam information in the second beam set; a beam pattern of a beam or a beam pair in a second set of beams; A relationship between the first beam set and the second beam set; The content of the AI ​​model input; The content of the AI ​​model output; AI function or model performance monitoring information; Auxiliary information; Applicable deployment scenarios; Beam codebooks for applicable network devices; The beam codebook of the applicable terminal; Applicable terminal distribution information; The number of measurement instances of AI model input; The number of prediction instances output by the AI ​​model; Applicable terminal moving speed.

10. The method according to any one of claims 1 to 9, characterized in that: The first information is carried by any of the following: Unlimited Resource Control RRC; Media access control element MAC CE; Downlink control information DCI.

11. A communication method, characterized in that: The method comprises: The network device sends first information to the terminal, where the first information is used to instruct the terminal to select an artificial intelligence AI model that meets performance requirements.

12. The method according to claim 11, characterized in that The first information includes at least one of the following: AI function identification; AI model identification; Performance requirements.

13. The method according to claim 11 or 12, characterized in that: The first information includes AI function identification and performance requirements; The AI ​​function identified by the AI ​​function identifier is the AI ​​function configured, activated or deactivated by the network device.

14. The method according to any one of claims 11-12, characterized in that: The first information includes an AI model identifier, and the method further includes: The network device receives the performance of each AI model sent by the terminal.

15. The method according to any one of claims 12, characterized in that: In response to performing lifecycle management based on an AI model, the first information includes the AI ​​model identifier and the performance requirement.

16. The method according to claim 15, characterized in that The number of the AI ​​model identifiers is one or more.

17. The method according to any one of claims 12 to 16, characterized in that: The performance requirements include different types of performance requirements, and the performance requirements include at least one of the following: The AI ​​function is used for spatial beam prediction, and each type of performance requirements corresponds to a performance requirement value; The AI ​​function is used for time domain beam prediction, and each type of different types of performance requirements corresponds to one or more performance requirement values, and the multiple performance requirement values ​​include a performance requirement value corresponding to each prediction instance.

18. The method according to any one of claims 11 to 17, characterized in that: The performance requirements include at least one of the following types: Beam or beam pair prediction accuracy; The prediction accuracy of the beam or beam pair for which the L1-RSRP difference is within a first threshold, wherein the L1-RSRP difference is the difference between the measured L1-RSRP of the best predicted beam or beam pair and the measured L1-RSRP of the best beam or beam pair; L1-RSRP difference, the L1-RSRP difference is the difference between the measured L1-RSRP of the best predicted beam or beam pair and the measured L1-RSRP of the best beam or beam pair, wherein the difference includes at least one of the following: an average value of the L1-RSRP difference, a cumulative distribution function of the L1-RSRP difference, a proportion of the L1-RSRP difference less than or equal to a second threshold, and a proportion of the L1-RSRP difference greater than a third threshold, wherein the L1-RSRP difference is the difference between the measured L1-RSRP of the best predicted beam or beam pair and the measured L1-RSRP of the best beam or beam pair; A predicted L1-RSRP difference, wherein the predicted L1-RSRP difference is a difference between a predicted L1-RSRP of a best predicted beam or beam pair and a measured L1-RSRP of the best predicted beam or beam pair, wherein the predicted L1-RSRP difference comprises at least one of the following: an average value of a difference in predicted L1-RSRPs, a cumulative distribution function of a difference in predicted L1-RSRPs, a proportion of predicted L1-RSRP differences less than or equal to a second threshold, and a proportion of L1-RSRP differences greater than a third threshold, wherein the predicted L1-RSRP difference is a difference between a predicted L1-RSRP of a best predicted beam or beam pair and a measured L1-RSRP of the best predicted beam or beam pair; Terminal throughput; Reference signal overhead; Uplink control information overhead; Predict latency.

19. The method according to any one of claims 12 to 18, characterized in that: The first information includes an environment of the AI ​​function or an environment of the AI ​​model, and the environment includes at least one of the following: The number of beams or beam pairs in a first beam set, the measurements of which are used as input to the AI ​​model; beam patterns of beams or beam pairs in the first set of beams; The number of beams or beam pairs in a second beam set, wherein the output of the AI ​​model is used to obtain beam information in the second beam set; a beam pattern of a beam or a beam pair in a second set of beams; A relationship between the first beam set and the second beam set; The content of the AI ​​model input; The content of the AI ​​model output; AI function or model performance monitoring information; auxiliary information; Applicable deployment scenarios; Beam codebooks for applicable network devices; The beam codebook of the applicable terminal; Applicable terminal distribution information; The number of measurement instances of AI model input; The number of prediction instances output by the AI ​​model; Applicable terminal moving speed.

20. The method according to any one of claims 11 to 19, characterized in that: The first information is carried by any of the following: Unlimited Resource Control RRC; Media access control element MAC CE; Downlink control information DCI.

21. A communication method, characterized in that: The method comprises: The network device sends first information to the terminal, where the first information is used to instruct the terminal to select an artificial intelligence AI model that meets the performance requirements; The terminal receives the first information.

22. A terminal, characterized in that: include: The transceiver module is used to receive first information sent by a network device, where the first information is used to instruct the terminal to select an artificial intelligence AI model that meets performance requirements.

23. A network device, characterized in that: include: The transceiver module is used to send first information to the terminal, where the first information is used to instruct the terminal to select an artificial intelligence AI model that meets performance requirements.

24. A terminal, characterized in that: include: one or more processors; The processor is used to execute the communication method according to any one of claims 1 to 10.

25. A network device, characterized in that: include: one or more processors; The processor is used to execute the communication method described in any one of claims 11-20.

26. A communication system, characterized in that: The invention comprises a terminal and a network device, wherein the terminal is configured to implement the communication method according to any one of claims 1 to 10, and the network device is configured to implement the communication method according to any one of claims 11 to 20.

27. A storage medium storing instructions, characterized in that: When the instruction is executed on a communication device, the communication device is caused to execute the communication method according to any one of claims 1-10 or 11-20.

Images