Communication method, terminal, network device, system, storage medium, and program product

Abstract

The present disclosure relates to a communication method, a terminal, a network device, a system, a storage medium, and a program product. The communication method comprises: a terminal determining scalability information of a first model and / or scalability information of a second model, wherein the first model is deployed at the terminal, and the second model is deployed at a network device; the first model is associated with the second model; and the scalability information of the first model is related to dimensions of input and / or output data of the first model, and the scalability information of the second model is related to dimensions of input and / or output data of the second model. The present disclosure can improve the communication efficiency.

Description

Communication methods, terminals, network devices, systems, storage media and software products Technical Field

[0001] This disclosure relates to the field of communication technology, and in particular to communication methods, terminals, network devices, systems, storage media, and program products. Background Technology

[0002] Current research and simulation results show that by adopting artificial intelligence (AI) technology, the feedback overhead of the terminal can be reduced or the feedback accuracy can be improved. Summary of the Invention

[0003] This disclosure provides communication methods, terminals, network devices, systems, storage media, and program products.

[0004] According to a first aspect of the present disclosure, a communication method is proposed, the method comprising: a terminal determining scalability information of a first model and / or a second model, the first model being deployed on the terminal, the second model being deployed on a network device, the first model and the second model being associated, the scalability information of the first model being related to the input and / or output data dimensions of the first model, and the scalability information of the second model being related to the input and / or output data dimensions of the second model.

[0005] According to a second aspect of the present disclosure, a communication method is proposed, the method comprising: a network device determining scalability information of a first model and / or a second model, the first model being deployed on a terminal, the second model being deployed on the network device, the first model and the second model being associated, the scalability information of the first model being related to the input and / or output data dimensions of the first model, and the scalability information of the second model being related to the input and / or output data dimensions of the second model.

[0006] According to a third aspect of the present disclosure, a terminal is provided, comprising: a processing module configured to determine scalability information of a first model and / or a second model, wherein the first model is deployed on the terminal, the second model is deployed on a network device, the first model and the second model are associated, the scalability information of the first model is related to the input and / or output data dimensions of the first model, and the scalability information of the second model is related to the input and / or output data dimensions of the second model.

[0007] According to a fourth aspect of the present disclosure, a network device is provided, comprising: a processing module configured to determine scalability information of a first model and / or a second model, wherein the first model is deployed on a terminal, the second model is deployed on the network device, the first model and the second model are associated, the scalability information of the first model is related to the input and / or output data dimensions of the first model, and the scalability information of the second model is related to the input and / or output data dimensions of the second model.

[0008] According to a fifth aspect 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.

[0009] According to a sixth aspect of the present disclosure, a network device is provided, comprising: one or more processors; wherein the network device is configured to perform the second aspect and any one of the communication methods in the second aspect.

[0010] According to a seventh aspect 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 second aspect and any one of the communication methods in the second aspect.

[0011] According to an eighth aspect of the present disclosure, a storage medium is provided that stores instructions which, when executed on a communication device, cause the communication device to perform a communication method as described in the first aspect and any one thereof, or the second aspect and any one thereof.

[0012] According to a ninth aspect of the present disclosure, a program product is provided, comprising: a computer program, which, when executed by a communication device, causes the communication device to perform a communication method as described in the first aspect and any one of the first aspects or the second aspect and the second aspect.

[0013] This disclosure improves communication efficiency by determining the scalability information of a first model, which is deployed on the terminal side, and sending this scalability information to the network device. This allows the network device to configure appropriate parameters such as the number of antenna ports, frequency domain granularity, and load size for the terminal. Alternatively, the terminal can improve communication efficiency by determining the scalability information of a second model, which allows it to determine appropriate load sizes, etc. Attached Figure Description

[0014] To more clearly illustrate the technical solutions in the embodiments of this disclosure, the accompanying drawings required for the description of the embodiments are introduced below. The following drawings are only some embodiments of this disclosure and do not impose specific limitations on the protection scope of this disclosure.

[0015] Figure 1a is a schematic diagram of a communication system architecture according to an embodiment of the present disclosure.

[0016] Figure 1b is a schematic diagram of CSI compressed feedback and recovery based on a bilateral model.

[0017] Figure 1c is a schematic diagram of CSI compression for reporting multiple future moments.

[0018] Figure 2 is a schematic diagram of a communication method interaction according to an embodiment of the present disclosure.

[0019] Figure 3 is a flowchart illustrating a communication method according to an embodiment of the present disclosure.

[0020] Figure 4 is a flowchart illustrating a communication method according to an embodiment of the present disclosure.

[0021] Figure 5 is a flowchart illustrating a communication method according to an embodiment of the present disclosure.

[0022] Figure 6a is a schematic diagram of the structure of the terminal device proposed in an embodiment of this disclosure.

[0023] Figure 6b is a schematic diagram of the structure of the network device proposed in an embodiment of this disclosure.

[0024] Figure 7a is a schematic diagram of the structure of a communication device proposed in an embodiment of this disclosure.

[0025] Figure 7b is a schematic diagram of the chip structure proposed in an embodiment of this disclosure. Detailed Implementation

[0026] This disclosure provides communication methods, terminals, network devices, systems, storage media, and program products.

[0027] In a first aspect, embodiments of this disclosure propose a communication method, the method comprising: a terminal determining scalability information of a first model and / or a second model, wherein the first model is deployed on the terminal, the second model is deployed on a network device, the first model and the second model are associated, the scalability information of the first model is related to the input and / or output data dimensions of the first model, and the scalability information of the second model is related to the input and / or output data dimensions of the second model.

[0028] In some alternative embodiments of the first aspect, the method further includes: the terminal sending first information to a network device, the first information being used by the network device to determine scalability information of the first model.

[0029] In some alternative embodiments of the first aspect, the first information is used to indicate the scalability information of the first model, or the first information is used to indicate the first model, and the scalability information of the first model is predefined in the protocol.

[0030] In some alternative embodiments of the first aspect, before sending the first information, the method further includes: the terminal receiving second information sent by a network device, the second information being used to instruct the terminal to send the first information.

[0031] In some alternative embodiments of the first aspect, the first information is carried by a message reporting the terminal capability.

[0032] In some alternative embodiments of the first aspect, the method further includes: the terminal receiving third information sent by the network device, the third information being used to configure at least one of the following: number of antenna ports; number of frequency domain units; load size; number of time points; the terminal sending the first model output data to the network device based on the third information.

[0033] In some alternative embodiments of the first aspect, the terminal determines the scalability information of the second model in the following manner: the terminal receives fourth information sent by the network device; the terminal determines the scalability information of the second model based on the fourth information.

[0034] In some alternative embodiments of the first aspect, the fourth information is used to indicate scalability information of the second model; or, the fourth information is used to indicate the second model, and scalability information of the second model is predetermined in the protocol.

[0035] In some alternative embodiments of the first aspect, the scalability information includes a value or set or range of values ​​for each of at least one of the following: the number of supported antenna ports; the number of supported frequency domain units; the supported payload size, wherein the payload is the first model output data sent to the network device; and the supported number of times, wherein the times are the times corresponding to the first model output data.

[0036] In some alternative embodiments of the first aspect, the scalability information includes at least one combination, each combination including at least one of the following values: the number of supported antenna ports; the number of supported frequency domain units; the supported payload size, the payload being the payload for sending the first model output data to the network device; and the supported number of times, the times being the times corresponding to the first model output data.

[0037] In some alternative embodiments of the first aspect, the value of the load size is the actual value corresponding to the load size or the quantization granularity corresponding to the load size.

[0038] In a second aspect, a communication method is provided, the method comprising: a network device determining scalability information of a first model and / or a second model, the first model being deployed on a terminal, the second model being deployed on the network device, the first model and the second model being associated, the scalability information of the first model being related to the input and / or output data dimensions of the first model, and the scalability information of the second model being related to the input and / or output data dimensions of the second model.

[0039] In some alternative embodiments of the second aspect, the network device determines the first model scalability information in the following manner: the network device receives first information sent by the terminal; the network device determines the first model scalability information based on the first information.

[0040] In some alternative embodiments of the second aspect, the first information is used to indicate the scalability information of the first model, or the first information is used to indicate the first model, and the scalability information of the first model is predefined in the protocol.

[0041] In some alternative embodiments of the second aspect, before receiving the first information, the method further includes: the network device sending second information to the terminal, the second information being used to instruct the terminal to send the first information.

[0042] In some alternative embodiments of the second aspect, the first information is carried by a message reporting the terminal capability.

[0043] In some alternative embodiments of the second aspect, the method further includes: the network device sending third information to the terminal, the third information being used to configure at least one of the following: number of antenna ports; number of frequency domain units; load size; number of time points; the third information being used by the terminal to send the first model output data to the network device.

[0044] In some alternative embodiments of the second aspect, the method further includes: the network device sending fourth information to the terminal, the fourth information being used by the terminal to determine scalability information of the second model.

[0045] In some alternative embodiments of the second aspect, the fourth information is used to indicate scalability information of the second model; or, the fourth information is used to indicate the second model, and the scalability information of the second model is predetermined in the protocol.

[0046] In some alternative embodiments of the second aspect, the scalability information includes a value or set or range of values ​​for each of at least one of the following: the number of supported antenna ports; the number of supported frequency domain units; the supported payload size, wherein the payload is the first model output data sent to the network device; and the number of supported time points, wherein the time point is the time point corresponding to the first model output data.

[0047] In some alternative embodiments of the second aspect, the scalability information includes at least one combination, each combination including at least one of the following values: the number of supported antenna ports; the number of supported frequency domain units; the supported payload size, the payload being the payload for sending the first model output data to the network device; and the supported number of times, the times being the times corresponding to the first model output data.

[0048] In some alternative embodiments of the second aspect, the value of the load size is the actual value corresponding to the load size or the quantization granularity corresponding to the load size.

[0049] Thirdly, a terminal is provided, comprising: a processing module, configured to determine scalability information of a first model and / or a second model, wherein the first model is deployed on the terminal, the second model is deployed on a network device, the first model and the second model are associated, the scalability information of the first model is related to the input and / or output data dimensions of the first model, and the scalability information of the second model is related to the input and / or output data dimensions of the second model.

[0050] Fourthly, a network device is provided, comprising: a processing module, configured to determine scalability information of a first model and / or a second model, wherein the first model is deployed on a terminal, the second model is deployed on the network device, the first model and the second model are associated, the scalability information of the first model is related to the input and / or output data dimensions of the first model, and the scalability information of the second model is related to the input and / or output data dimensions of the second model.

[0051] Fifthly, 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.

[0052] A sixth aspect provides a network device, comprising: one or more processors; wherein the network device is configured to perform the second aspect and any one of the communication methods in the second aspect.

[0053] A seventh aspect provides a communication system, 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 second aspect and any one of the communication methods in the second aspect.

[0054] Eighthly, a storage medium is provided that stores instructions, which, when executed on a communication device, cause the communication device to perform a communication method as described in the first aspect and any one thereof, or the second aspect and any one thereof.

[0055] Ninth aspect, a program product is provided, comprising: a computer program, which, when executed by a communication device, causes the communication device to perform a communication method as described in the first aspect and any one of the first aspects or the second aspect and the second aspect.

[0056] In a tenth aspect, embodiments of this disclosure provide a computer program that, when run on a computer, causes the computer to perform the methods described in an optional implementation of the first or second aspect.

[0057] Eleventhly, embodiments of this disclosure provide a chip or chip system. The chip or chip system includes processing circuitry configured to perform the methods described in the optional implementations of the first or second aspect above.

[0058] It is understood that the terminals, access network devices, first network elements, other network elements, core network devices, communication systems, storage media, program products, computer programs, chips, or chip systems involved in the embodiments of this disclosure are all used to execute the methods proposed in the embodiments of this disclosure. Therefore, the beneficial effects that can be achieved can be referred to the beneficial effects in the corresponding methods, and will not be repeated here.

[0059] This disclosure provides communication methods, terminals, network devices, systems, storage media, and program products. In some embodiments, the terms "communication method" and "information processing method" can be used interchangeably, as can the terms "communication device" and "information processing device" and "communication device," and the terms "information processing system" and "communication system."

[0060] This disclosure is not exhaustive, but merely illustrative of some embodiments, and is not intended to limit the scope of protection of this disclosure. Unless otherwise specified, each step in a particular 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 particular embodiment can also be implemented as an independent embodiment, and the order of the steps in a particular embodiment can be arbitrarily interchanged. Furthermore, the optional implementation methods in a particular embodiment can be arbitrarily combined; moreover, the embodiments can be arbitrarily combined, for example, some or all steps of different embodiments can be arbitrarily combined, and a particular embodiment can be arbitrarily combined with the optional implementation methods of other embodiments.

[0061] In each of the disclosed embodiments, unless otherwise specified or in case of logical conflict, the terminology and / or descriptions of the embodiments are consistent and can be referenced by each other. The technical environments of different embodiments can be combined to form new embodiments according to their inherent logical relationships.

[0062] The terminology used in the embodiments of this disclosure is for the purpose of describing particular embodiments only and is not intended to limit the scope of this disclosure.

[0063] In this embodiment of the disclosure, unless otherwise stated, elements expressed in the singular form, such as "a," "an," "the," "the," "the," "the," "the," "the," "this," etc., can mean "one and only one," or "one or more," "at least one," etc. For example, when using articles such as "a," "an," "the," etc. in translation, the noun following the article can be understood as either a singular expression or a plural expression.

[0064] In the embodiments disclosed herein, "multiple" refers to two or more.

[0065] In some embodiments, the terms “at least one of”, “one or more”, “a plurality of”, “multiple”, etc., may be used interchangeably.

[0066] In some embodiments, the notation "at least one of A and B", "A and / or B", "A in one case, B in another", "in response to one case A, in response to another case B", etc., may include the following technical solutions depending on the situation: in some embodiments, A (execute A regardless of B); in some embodiments, B (execute B regardless of A); in some embodiments, execution is selected from A and B (A and B are selectively executed); in some embodiments, A and B (both A and B are executed). The same applies when there are more branches such as A, B, C, etc.

[0067] In some embodiments, the notation "A or B" may include the following technical solutions, depending on the situation: in some embodiments, A (execution of A regardless of B); in some embodiments, B (execution of B regardless of A); in some embodiments, execution is selected from A and B (A and B are selectively executed). The same applies when there are more branches such as A, B, C, etc.

[0068] The prefixes "first," "second," etc., used in the embodiments of this disclosure are merely for distinguishing different descriptive objects and do not impose restrictions on the position, order, priority, quantity, or content of the descriptive objects. The description of the descriptive objects is found in the claims or the context of the embodiments, and the use of prefixes should not constitute unnecessary restrictions. For example, if the descriptive object is a "field," the ordinal numbers preceding "field" in "first field" and "second field" do not restrict the position or order of the "fields." "First" and "second" do not restrict whether the "fields" they modify are in the same message, nor do they restrict the order of "first field" and "second field." Similarly, if the descriptive object is a "level," the ordinal numbers preceding "level" in "first level" and "second level" do not restrict the priority between "levels." Furthermore, the number of descriptive objects is not limited by ordinal numbers and can be one or more. For example, in "first device," the number of "devices" can be one or more. Furthermore, the objects modified by different prefixes can be the same or different. For example, if the object being described is "device", then "first device" and "second device" can be the same device or different devices, and their types can be the same or different. Similarly, if the object being described is "information", then "first information" and "second information" can be the same information or different information, and their content can be the same or different.

[0069] In some embodiments, “including A,” “containing A,” “for indicating A,” and “carrying A” can be interpreted as directly carrying A or indirectly indicating A.

[0070] In some embodiments, the terms “in response to…”, “in response to determining…”, “in the case of…”, “when…”, “if…”, “if…”, etc., can be used interchangeably.

[0071] In some embodiments, the terms “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 lower than,” and “above” can be used interchangeably, as can the terms “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”.

[0072] In some embodiments, the apparatus and device may be interpreted as physical or virtual, and their names are not limited to the names recorded in the embodiments. In some cases, they may also be understood as "equipment", "device", "circuit", "network element", "node", "function", "unit", "section", "system", "network", "chip", "chip system", "entity", "body", etc.

[0073] In some embodiments, "network" can be interpreted as devices included in the network, such as access network devices, core network devices, etc.

[0074] 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," or "fixed station." In some embodiments, it may also be understood as "node," "access point," "transmission point (TP)," "reception point (RP)," "transmission / reception point (TRP)," "panel," "antenna panel," "antenna array," "cell," "macro cell," "small cell," "femto cell," "pico cell," "sector," "cell group," "serving cell," "carrier," "component carrier," or "bandwidth part (BWP)."

[0075] 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.

[0076] In some embodiments, the acquisition of data, information, etc., may comply with the laws and regulations of the country where the location is situated.

[0077] In some embodiments, data, information, etc., may be obtained with the user's consent.

[0078] Furthermore, each element, each row, or each column in the table of this disclosure can be implemented as an independent embodiment, and any combination of any element, any row, or any column can also be implemented as an independent embodiment.

[0079] Figure 1a is a schematic diagram of a communication system architecture according to an embodiment of the present disclosure.

[0080] As shown in Figure 1a, the communication system 100 includes a terminal 101 and a network device 102.

[0081] In some embodiments, terminal 101 includes, but is not limited to, at least one of the following: mobile phone, wearable device, Internet of Things device, car with communication function, smart car, tablet computer, computer with wireless transceiver function, virtual reality (VR) terminal device, augmented reality (AR) terminal device, wireless terminal device in industrial control, wireless terminal device in self-driving, wireless terminal device in remote medical surgery, wireless terminal device in smart grid, wireless terminal device in transportation safety, wireless terminal device in smart city, and wireless terminal device in smart home.

[0082] In some embodiments, network device 102 may include at least one of access network device and core network device.

[0083] In some embodiments, the access network device is, for example, a node or device that connects a terminal to a wireless network. The access network device may include, but is not limited to, at least one of the following in a 5G communication system: evolved Node B (eNB), next-generation eNB (ng-eNB), next-generation Node B (gNB), node B (NB), home node B (HNB), home evolved node B (HeNB), radio backhaul device, radio network controller (RNC), base station controller (BSC), base transceiver station (BTS), base band unit (BBU), mobile switching center, base station in a 6G communication system, open RAN, cloud RAN, base station in other communication systems, and access node in a Wi-Fi system.

[0084] In some embodiments, the technical solutions of this disclosure can be applied to the Open RAN architecture. In this case, the interfaces between or within access network devices involved in the embodiments of this disclosure can be transformed into internal interfaces of Open RAN. The processes and information interactions between these internal interfaces can be implemented by software or programs.

[0085] In some embodiments, the access network device may be composed of a central unit (CU) and a distributed unit (DU). The CU may also be called a control unit. The CU-DU structure can separate the protocol layer of the access network device. Some of the protocol layer functions are centrally controlled by the CU, while the remaining part or all of the protocol layer functions are distributed in the DU and centrally controlled by the CU. However, this is not the only possibility.

[0086] In some embodiments, a core network device may be a single device comprising one or more network elements, or it may be multiple devices or a group of devices, each comprising all or part of the aforementioned one or more network elements. Network elements 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), or a Next Generation Core (NGC).

[0087] It is understood that the communication system described in this disclosure is for the purpose of more clearly illustrating the technical solutions of this disclosure, and does not constitute a limitation on the technical solutions proposed in this disclosure. As those skilled in the art will know, with the evolution of system architecture and the emergence of new business scenarios, the technical solutions proposed in this disclosure are also applicable to similar technical problems.

[0088] The following embodiments of this disclosure can be applied to the communication system 100 shown in FIG1a, or to some of the main bodies, but are not limited thereto. The main bodies shown in FIG1a are illustrative. The communication system may include all or some of the main bodies in FIG1a, or it may include other main bodies outside of FIG1a. The number and form of each main body are arbitrary. Each main body may be physical or virtual. The connection relationship between the main bodies is illustrative. The main bodies may not be connected or may be connected. The connection may be in any way, such as direct connection or indirect connection, wired connection or wireless connection.

[0089] The embodiments disclosed herein 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), 6th generation mobile communication system (6G), 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), CDMA2000, Ultra Mobile Broadband (UMB), IEEE 802.11 (Wi-Fi), IEEE 802.16 (WiMAX), and IEEE 802.20, Ultra-Wideband (UWB), Bluetooth (a 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, systems utilizing other communication methods, and next-generation systems built upon them, etc. Furthermore, multiple systems can be combined (e.g., a combination of LTE or LTE-A with 5G).

[0090] In some embodiments, a bilateral AI / machine learning (ML) model based on a terminal-side Channel State Information (CSI) generation partial model and a network-side CSI recovery partial model is used to implement CSI compression feedback and recovery, respectively. Figure 1b is a schematic diagram of CSI compression feedback and recovery based on a bilateral model. As shown in Figure 1b, the UE side compresses the downlink channel information H using the CSI generation partial model (defined as an encoder) and sends it to the gNB after quantization into a binary bit stream. The gNB side recovers H', which is approximately the same as the original downlink information, using the CSI recovery partial model (defined as a decoder).

[0091] In some embodiments, the correlation of time-domain channels is utilized to improve CSI compression performance. First, the CSI for one or more future time points is predicted based on estimated historical channel information. Then, a bilateral AI model is used to compress and report the predicted CSI for one or more time points. For example, the UE first estimates channel information for multiple historical time points based on multiple received Channel State Information-Reference Signals (CSI-RS). These multiple received CSI-RS are transmitted by the gNB via CSI-R bursts, and each CSI-RS burst is defined within an observation window, as shown in Figure 1c. A CSI-RS burst can be understood as the transmission of continuous CSI-RS signals. Figure 1c is a schematic diagram of CSI compression reporting for multiple future time points. Based on the channel information measured within the observation window, the UE predicts the CSI for one or more future time points using an AI / ML or non-AI / ML algorithm, and defines the CSI for one or more future time points within a prediction window, as shown by the dashed arrow in Figure 1c. The UE then compresses the predicted CSI for one or more time points using the encoder model in the bilateral model before reporting it. In Figure 1c, the CSI for each time point within the prediction window is reported at time n. The gNB recovers the CSI corresponding to multiple time points using the decoder model based on the received compressed CSI.

[0092] In some embodiments, the input information of the UE-side encoder model can be CSI at one or more time points. For a CSI at one time point, the input data dimension of the encoder model is related to the number of antenna ports configured in the gNB, as well as the transmission data bandwidth and frequency domain granularity, while the output data dimension of the encoder model is related to the CSI feedback load. Similarly, the input and output data dimensions of the decoder model also depend on the CSI feedback load, the number of antenna ports configured in the gNB, as well as the transmission data bandwidth and frequency domain granularity. If a corresponding model is trained for each input / output dimension of the model, the number of trained models will increase significantly, correspondingly increasing the UE or gNB's storage overhead and management complexity. To solve this problem, it is necessary to train scalable encoder / decoder models, that is, to train only a few scalable models for different encoder / decoder input / output data dimensions.

[0093] In some embodiments, scalability model training research was conducted for different numbers of ports, different subband sizes, and different CSI feedback load sizes. The scalability-supporting model was trained by introducing adaptive layers into the model or by padding or truncating the input / output dimensions of the model with zeros.

[0094] However, network devices, unaware of the scalability supported by the terminal-side encoder model, cannot configure appropriate parameters such as the number of antenna ports, frequency domain granularity, and CSI feedback load size for the terminal. Similarly, terminals, unaware of the scalability supported by the network device-side decoder model, cannot select the corresponding CSI feedback load based on its scalability.

[0095] It is understood that the CSI feedback in this disclosure is only an exemplary case. The input and output data of the encoder and decoder models can also be other types of data besides CSI, such as beam measurement or prediction results, radio resource management measurement or prediction results, etc. This disclosure only uses CSI as an example, but is not limited to this.

[0096] Therefore, this disclosure provides a communication method in which a terminal determines the scalability information of a first model to send this scalability information to a network device. The first model is deployed on the terminal side. The terminal sends the scalability information to the network device, which then configures appropriate parameters such as the number of antenna ports, frequency domain granularity, and load size for the terminal, thereby improving communication efficiency. And / or, the terminal determines the scalability information of a second model to determine appropriate load size, etc., thereby improving communication efficiency.

[0097] Figure 2 is a schematic diagram of a communication method interaction according to an embodiment of the present disclosure. As shown in Figure 2, this embodiment of the present disclosure relates to a communication method for a communication system 100, the method including:

[0098] In step S2101, terminal 101 determines the scalability information of the first model.

[0099] In some embodiments, a first model is deployed on a terminal, and the scalability information of the first model is related to the dimensions of its input and / or output data. The first model is associated with a second model, which is deployed on a network device. For ease of description, this disclosure refers to the model deployed on the terminal as the first model and the model deployed on the network device as the second model; the first model and the second model can be referred to as a two-sided model. The models (the first model and / or the second model) can be AI models or ML models, and this disclosure is not limited thereto.

[0100] Understandably, network devices can send configuration information to terminals, enabling the terminals to perform operations such as model inference based on this configuration information. Configuration information can include information used to measure and obtain model input data; this type of configuration information affects the model's input data dimensions. Configuration information can also include information indicating the required model output data type and how the model's output data should be reported; this type of configuration information affects the model's output data dimensions. When the values, sets of values, or ranges of values ​​in the configuration information differ, the terminal should use models with different input and / or output data dimensions to perform inference and other operations. However, if a corresponding model is trained for each data dimension, the number of trained models becomes too large, correspondingly increasing the overhead of storing models and the complexity of managing models for both the terminal and network devices. Therefore, scalable models can be trained so that a single model can support multiple data dimensions and be applicable to multiple values, sets of values, or ranges of values ​​in the configuration information. These multiple values, sets of values, or ranges of values ​​in the configuration information can be referred to as the model's scalability information. The terminal determines the scalability information of the first model so as to report the scalability information of the first model to the network device so that the network device can send configuration information in a targeted manner. For ease of description, the configuration information sent by the network device to the terminal based on the scalability information of the first model is referred to as the third information. For details, please refer to the embodiment of step S2105 below.

[0101] In some embodiments, the scalability information of the first model includes a value or set of values ​​or range of values ​​for each of at least one of the following: the number of supported antenna ports; the number of supported frequency domain units; the supported payload size, wherein the payload is the first model output data sent to the network device; and the supported number of times, wherein the times are the times corresponding to the first model output data.

[0102] Optionally, scalability information may include the values, sets of values, or ranges of antenna ports supported by the first model. For example, scalability information may be multiple antenna port numbers supported by the first model, or a set of one or more antenna port numbers supported by the first model, or a range of one or more antenna port numbers supported by the first model. It is understood that a set of values ​​is a collection of discrete values, while a range of values ​​is a continuous range. For example, if the number of antenna ports can be used to measure CSI, and the model can be used to compress CSI, then the number of antenna ports affects the input data dimension of the model. As another example, the number of antenna ports can be used to measure CSI at historical moments. Inputting the historical CSI into the model to predict the CSI at future moments further affects the input data dimension of the model. By determining the number of antenna ports supported by the first model, the input data dimension supported by the first model can be determined. The terminal can send the antenna port number to the network device so that the network device can more accurately configure the number of antenna ports to suit the input data dimension supported by the terminal's first model, thereby improving communication efficiency and model performance.

[0103] Optionally, the scalability information may include the value, set of values, or range of the number of frequency domain units supported by the first model. Here, a frequency domain unit can be a sub-band, a resource block (RB), etc., but is not limited to these. For example, the scalability information may include multiple numbers of frequency domain units supported by the first model, or a set of one or more numbers of frequency domain units supported by the first model, or a range of one or more numbers of frequency domain units supported by the first model. It is understood that a set of values ​​is a collection of discrete values, while a range of values ​​is a range of continuous values. For example, the number of frequency domain units can be used to measure CSI, and the model can be used to compress CSI; therefore, the number of frequency domain units affects the input data dimension of the model. As another example, the number of frequency domain units can be used to measure CSI at historical times. Inputting the CSI at historical times into the model can predict the CSI at future times. The number of frequency domain units affects the input data dimension of the model; by determining the number of frequency domain units supported by the first model, the input data dimension supported by the first model can be determined. The terminal can send the number of frequency domain units to the network device so that the network device can configure the number of frequency domain units more accurately to suit the input data dimensions supported by the terminal's first model, thereby improving communication efficiency and model performance.

[0104] Optionally, scalability information may include the load size supported by the first model, where the load is the first model output data sent to the network device. For example, scalability information may include multiple load sizes supported by the first model, or a set of one or more load sizes supported by the first model, or a range of one or more load sizes supported by the first model. It is understood that a set of values ​​is a collection of discrete values, while a range of values ​​is a continuous range of values. For example, if the model's input data is CSI and the output data is compressed CSI, the load size can be used to indicate how much compressed CSI is reported. As another example, if the model's input data is historical CSI and the model's output data is future CSI, the load size can be used to indicate how much future CSI is reported. The load size affects the dimension of the model's output data; by determining the load size supported by the first model, the dimension of the output data supported by the first model can be determined. The terminal can send the load size to the network device so that the network device can more accurately configure the load size to suit the dimension of the output data supported by the terminal's first model, improving communication efficiency and model performance.

[0105] Optionally, scalability information may include the number of time points supported by the first model, where each time point corresponds to the output data of the first model. For example, scalability information may include multiple time point counts supported by the first model, a set of one or more time point counts supported by the first model, or a range of one or more time point counts supported by the first model. It is understood that a set of values ​​is a collection of discrete numerical values, while a range of values ​​is a continuous numerical range. For example, if the model's input data is CSI and its output data is compressed CSI, the load size can be used to indicate how many compressed CSI values ​​are reported, and the number of time points can be used to indicate how many time points of CSI are compressed. As another example, if the model's input data is historical CSI values ​​and its output data is future CSI values, the number of time points can be used to indicate that the predicted CSI values ​​are for several future time points. The number of time points affects the dimension of the model's output data; by determining the number of time points supported by the first model, the dimension of the output data supported by the first model can be determined. The terminal can send the number of time points to the network device so that the network device can more accurately configure the number of time points to suit the output data dimension supported by the terminal's first model, thereby improving communication efficiency and model performance.

[0106] It is understood that the above optional examples can be implemented in any combination; that is, the scalability information may include multiple of the above-mentioned items. For example, the scalability information may include one or more sets of values ​​for the number of antenna ports and one or more ranges of values ​​for the number of frequency domain elements. As another example, the scalability information may include multiple values ​​for the number of frequency domain elements and one or more sets of values ​​for the load size. This disclosure does not provide a complete list, but is not limited thereto.

[0107] In some embodiments, the scalability information includes at least one combination, each combination including at least one of the following values: the number of supported antenna ports; the number of supported frequency domain elements; the supported payload size, where the payload is the payload for sending the first model output data to the network device; and the supported number of times, where the times are the times corresponding to the first model output data. For example, the scalability message may include two combinations: combination 1 includes the number of supported antenna ports A1 and the number of supported frequency domain elements B1; combination 2 includes the number of supported antenna ports A2 and the number of supported frequency domain elements B2. The scalability information of the first model may include the number of supported antenna ports A1 and A2, and the number of supported frequency domain elements B1 and B2.

[0108] In some embodiments, the payload size is either the actual value corresponding to the payload size or the quantization granularity corresponding to the payload size. Each real number output by the first model can be quantized using 1 bit, 2 bits, or 4 bits. 1, 2, or 4 represent the quantization granularity, while the real number output by the first model is the actual value.

[0109] In step S2102, network device 102 sends second information to terminal 101.

[0110] In some embodiments, terminal 101 receives second information sent by network device 102.

[0111] In some embodiments, the second information is used to instruct the terminal to send the first information, which is used by the network device to determine the scalability information of the first model.

[0112] It is understood that step S2102 is optional. That is, if the terminal can actively report the first information, then step S2102 can be omitted. Alternatively, the terminal can report the first information in response to a request from the network device, in which case step S2102 can be executed.

[0113] In some embodiments, the second information may be carried in a signaling message requesting the terminal to report its capabilities, or in a newly designed signaling message requesting the first information. For example, the second information may be carried in Radio Resource Control (RRC), Medium Access Control Control Element (MAC CE), or Downlink Control Information (DCI).

[0114] In some embodiments, the names of the first information and the second information are not limited. For example, the first information may also be called instruction information, reporting information, response information, etc. The second information may also be called request information, etc.

[0115] In step S2103, terminal 101 sends first information to network device 102.

[0116] In some embodiments, network device 102 receives first information sent by terminal 101.

[0117] In some embodiments, the first information is used by the network device to determine scalability information for the first model.

[0118] In some embodiments, network device 102 determines scalability information of a first model. For example, network device 102 determines scalability information of the first model based on first information.

[0119] In some embodiments, the first information can be used to indicate scalability information of the first model. That is, the first information enables the network device to determine the scalability information of the first model by indicating the scalability information of the first model. This can be understood as an explicit indication.

[0120] Optionally, the first information may indicate scalability information.

[0121] For example, the value or set or range of values ​​for each of at least the following can be indicated: the number of supported antenna ports; the number of supported frequency domain units; the supported payload size, which is the first model output data sent to the network device; and the supported number of times, which is the time corresponding to the first model output data.

[0122] For example, at least one combination can be indicated, each combination including at least one of the following values: the number of supported antenna ports; the number of supported frequency domain units; the supported payload size, the payload being the payload for sending the first model output data to the network device; and the supported number of times, the times being the times corresponding to the first model output data.

[0123] Optionally, the first information may indicate the index (or number or identifier) ​​corresponding to the scalability information.

[0124] For example, multiple sets of values ​​or multiple ranges of values ​​can be predefined for each type of scalability information. Each predefined set of values ​​or range of values ​​corresponds to an index (or number or identifier), and the first information can indicate that at least one set of values ​​or at least one range of values ​​is supported by indicating the index (or number or identifier).

[0125] For example, a set of values ​​can be predefined for each type of extensibility information, and each value in the predefined set corresponds to an index (or number or identifier). The first piece of information can indicate the supported values ​​by indicating the index (or number or identifier).

[0126] In some embodiments, for the supported payload size, the first information can indicate either the actual numerical value or the quantization granularity. For example, each real number output by the first model can be quantized using 1 bit, 2 bits, or 4 bits. 1, 2, or 4 represent the quantization granularity, while the real number output by the first model represents the actual numerical value.

[0127] In some embodiments, the first information may be used to indicate a first model, and the protocol predefines scalability information of the first model. That is, the first information indicates the first model so that the network device can determine the scalability information of the first model from the protocol. This approach can be understood as an implicit indication method.

[0128] For example, one or more model structures or models can be standardized, each standardized model structure / model corresponding to scalability information. Network devices can implicitly determine the scalability information supported by the terminal from the protocol based on the first model indicated by the first information. For example, the scalability information corresponding to the first model can be determined based on its model structure. In this case, each model structure corresponds to one type of scalability information, and different models with the same model structure can correspond to the same scalability information. The model structure includes, but is not limited to, deep neural networks (DNNs), convolutional neural networks (CNNs), residual networks (ResNets), and transformers. As another example, the scalability information corresponding to the first model can be determined based on its identifier. In this case, different models can correspond to different scalability information.

[0129] For example, the number of antenna ports can be configured to 2, 4, 8, 12, 16, 24, and 32. Taking sub-bands as an example, the number of sub-bands in the frequency domain can be expressed as follows: Where W represents the configured bandwidth size in RBs, and S represents the number of RBs contained in the subband. The CSI feedback load size can be predefined, indicated by the UE, or determined by NW configuration.

[0130] Assume the UE-side encoder model supports configurations with 16 and 32 antenna ports, 8 and 13 subbands, CSI feedback load sizes of 60 and 120 bits, and CSI compression of 1 and 4 future time points. To indicate these supported parameters by the UE-side encoder model, a set of supported parameters can be defined, such as the set of antenna port numbers P∈{16,32}, the set of subband numbers N∈{8,13}, the CSI feedback load size L∈{60,120}, and the number of CSI compression times T∈{1,4}. The UE indicates these supported parameter combinations in its capability reporting.

[0131] These parameters can also be defined with ranges. For example, P∈[2,64], N∈{8,13}, L∈[30,240], and T∈[1,8], where [a,b] represents any integer value between a and b, including a and b themselves. In this case, the UE can simply indicate the minimum and maximum values ​​of each parameter in its capability reporting. Optionally,

[0132] All supported parameter combinations are given through predefined definitions. Taking P and N as an example, P∈{2,4,8,12,16,24,32} and N∈{6,10,13,16,30} are predefined. There are 42 possible combinations, so the UE can... The bits indicate one combination. If three combinations are supported, the total indication is 18 bits. Alternatively, assuming the encoder supports two values ​​in P and two values ​​in N, the UE can... and These indicate the number of supported antenna ports and sub-bands, respectively.

[0133] If the protocol predefines one or more standardized encoder models / structures, the parameter values ​​supported by different standardized models may be the same or different, or some parameter values ​​may be the same. For example, standardized model structure 1 supports P∈{16,32}, N∈{13,16}, L∈{60,120}, and T∈{1,4}, while standardized model structure 2 supports P∈{4,12}, N∈{6,12}, L∈{160,240}, and T∈{3,6}. The UE can indicate the supported standardized models / structures through capability reporting, such as supporting model structure 1. The NW can determine the scalability parameters P∈{16,32}, N∈{13,16}, L∈{60,120}, and T∈{1,4} supported by the UE based on the supported model / structure result information indicated by the UE.

[0134] It is understood that the examples given in this disclosure with specific numerical values ​​are for the purpose of explanation and illustration, and this disclosure is not limited thereto.

[0135] In some embodiments, the first information may be carried by a message reporting the terminal's capabilities.

[0136] In step S2104, network device 102 determines the scalability information of the first model.

[0137] In some embodiments, network device 102 determines scalability information of a first model based on first information.

[0138] In some embodiments, network device 102 may determine scalability information of the first model from the first information.

[0139] In some embodiments, network device 102 may determine scalability information of a first model from a protocol based on first information.

[0140] In step S2105, network device 102 sends third information to terminal 101.

[0141] In some embodiments, the third information is used to configure at least one of the following: number of antenna ports; number of frequency domain elements; load size; number of time points.

[0142] In some embodiments, the network device determines the scalability information of the first model based on the first information, and may configure at least one of the following for the first model: number of antenna ports; number of frequency domain units; load size; number of time intervals. This allows the terminal to perform operations such as inference using the first model, improving the accuracy and efficiency of the first model.

[0143] It is understood that the content of the third information configuration is similar to that included in the scalability information of the first model, and its meaning can be referred to the above embodiments, which will not be repeated here. For example, if the scalability information of the first model includes the value, set of values, or range of values ​​for the number of antenna ports, the network device can configure the number of antenna ports for the terminal through the third information. For example, a suitable number of antenna ports can be selected from the scalability information of the first model (i.e., the value, set of values, or range of values ​​for the number of antenna ports) and configured for the terminal. The third information may not be completely consistent with the scalability information of the first model. For example, if the scalability information of the first model includes the number of antenna ports and the number of frequency domain units, the network device can configure the number of antenna ports and the number of frequency domain units for the terminal, or it can only configure the number of antenna ports. As for the number of frequency domain units, it can be determined in other ways, such as reusing the one used last time, etc., which is not limited here.

[0144] In some embodiments, the terminal may perform operations such as inference using the first model based on third information, and send the output data of the first model to the network device.

[0145] In some embodiments, the name of the third information is not limited, and it may be, for example, configuration information.

[0146] In step S2106, network device 102 determines the scalability information of the second model.

[0147] In some embodiments, the scalability information of the second model includes a value or set of values ​​or range of values ​​for each of at least one of the following: the number of supported antenna ports; the number of supported frequency domain units; the supported payload size, wherein the payload is the first model output data sent to the network device; and the supported number of times, wherein the times are the times corresponding to the first model output data.

[0148] In some embodiments, the scalability information of the second model includes at least one combination, each combination including at least one of the following values: the number of supported antenna ports; the number of supported frequency domains; the supported payload size, where the payload is the payload for sending the output data of the first model to the network device; and the supported number of times, where the times are the times corresponding to the output data of the first model.

[0149] It is understood that the scalability information of the second model is similar to that of the first model, and can be referred to the above embodiments, which will not be repeated here. The terminal can determine how to report the output data of the first model to the network device based on the scalability information of the second model. For example, the first model can be used to compress CSI, and the second model can be used to decompress CSI. That is, the input data of the first model is CSI, and the output data of the first model is the compressed CSI. The terminal sends the compressed CSI to the network device. The input data of the second model is the compressed CSI, and the output data of the second model is the decompressed CSI. In other words, the compressed CSI affects the dimension of the input data of the second model. Therefore, when the terminal reports the compressed CSI to the network device, it must also consider the scalability information of the second model. That is, the terminal can determine how to report the output data of the first model to the network device based on the scalability information of the second model to improve the efficiency of the communication system.

[0150] In step S2107, network device 102 sends fourth information to terminal 101.

[0151] In some embodiments, terminal 101 receives fourth information sent by network device 102.

[0152] In some embodiments, the fourth information is used to determine the scalability information of the second model.

[0153] In some embodiments, terminal 101 determines the scalability information of the second model. For example, terminal 101 may determine the scalability information of the second model based on fourth information.

[0154] In some embodiments, the fourth information is used to indicate the scalability information of the second model. The terminal can determine the scalability information of the second model from the fourth information.

[0155] In some embodiments, the fourth information is used to indicate the second model, and the protocol predefines scalability information for the second model. The terminal can determine the scalability information of the second model from the protocol based on the fourth information.

[0156] For example, the network device can explicitly indicate the range of load values ​​supported by the second model via RRC signaling, such as L ∈ [30, 240] bits or L ∈ [15, 120] real numbers. Assume each real number is quantized using 2 bits. Similarly, other parameters such as the number of antenna ports can also be explicitly indicated to the terminal.

[0157] It is understood that the way the terminal determines the scalability information of the second model based on the fourth information is similar to the way the network device determines the scalability information of the first model based on the first information. The above embodiments can be referred to, and this disclosure will not repeat them.

[0158] In step S2108, terminal 101 determines the scalability information of the second model.

[0159] In some embodiments, terminal 101 determines second model scalability information based on fourth information.

[0160] In some embodiments, the terminal may determine the scalability information of the second model from the fourth information.

[0161] In some embodiments, the terminal may determine the scalability information of the second model from the protocol based on the fourth information.

[0162] In some embodiments, the terminal may perform the derivation of the first model and the reporting of the output data of the first model based on the third information and the scalability information of the second model.

[0163] The communication method involved in the embodiments of this disclosure may include at least one of steps S2101 to S2108. For example, steps S2101 and S2108 may be implemented as independent embodiments, but are not limited thereto.

[0164] In some embodiments, steps S2102-S2107 are optional, and one or more of them may be omitted or substituted in different embodiments.

[0165] In some embodiments, other optional implementations described before or after the specification corresponding to FIG2 may be referred to.

[0166] Figure 3 is a flowchart illustrating a communication method according to an embodiment of the present disclosure. As shown in Figure 3, this embodiment of the present disclosure relates to a communication method executed by terminal 101, the method including:

[0167] Step S3101: Determine the scalability information of the first model.

[0168] The optional implementation of step S3101 can be found in the optional implementation of step S2101 in Figure 2, as well as other related parts in the embodiments involved in Figure 2, which will not be repeated here.

[0169] Step S3102: Obtain the second information.

[0170] The optional implementation of step S3102 can be found in the optional implementation of step S2102 in Figure 2, as well as other related parts in the embodiments involved in Figure 2, which will not be repeated here.

[0171] In some embodiments, terminal 101 receives second information sent by network device 102, but is not limited thereto; it may also receive second information sent by other entities.

[0172] In some embodiments, terminal 101 obtains second information as defined by the protocol.

[0173] In some embodiments, terminal 101 obtains second information from upper layer(s).

[0174] In some embodiments, the terminal 101 performs processing to obtain the second information.

[0175] In some embodiments, step S3102 is omitted, and the terminal 101 autonomously implements the function indicated by the second information, or the above function is defaulted or set to default.

[0176] Step S3103: Send the first message.

[0177] The optional implementation of step S3103 can be found in the optional implementation of step S2103 in Figure 2, as well as other related parts in the embodiments involved in Figure 2, which will not be repeated here.

[0178] In some embodiments, terminal 101 sends first information to network device 102, but is not limited thereto; it may also send first information to other entities.

[0179] Step S3104: Obtain third information.

[0180] The optional implementation of step S3104 can be found in the optional implementation of step S2105 in Figure 2, as well as other related parts in the embodiments involved in Figure 2, which will not be repeated here.

[0181] In some embodiments, terminal 101 receives third information sent by network device 102, but is not limited thereto; it may also receive third information sent by other entities.

[0182] In some embodiments, terminal 101 obtains third information as defined by the protocol.

[0183] In some embodiments, terminal 101 obtains third information from upper layer(s).

[0184] In some embodiments, terminal 101 processes the information to obtain third information.

[0185] In some embodiments, step S3102 is omitted, and the terminal 101 autonomously implements the function indicated by the third information, or the above function is defaulted or set to default.

[0186] Step S3105: Obtain the fourth information.

[0187] The optional implementation of step S3105 can be found in the optional implementation of step S2107 in Figure 2, as well as other related parts in the embodiments involved in Figure 2, which will not be repeated here.

[0188] In some embodiments, terminal 101 receives fourth information sent by network device 102, but is not limited thereto; it may also receive fourth information sent by other entities.

[0189] In some embodiments, terminal 101 obtains fourth information as defined by the protocol.

[0190] In some embodiments, terminal 101 obtains fourth information from upper layer(s).

[0191] In some embodiments, the terminal 101 processes the information to obtain the fourth information.

[0192] In some embodiments, step S3102 is omitted, and the terminal 101 autonomously implements the function indicated by the fourth information, or the above function is defaulted or set to default.

[0193] Step S3106: Determine the scalability information of the second model.

[0194] The optional implementation of step S3106 can be found in the optional implementation of step S2108 in Figure 2, as well as other related parts in the embodiments involved in Figure 2, which will not be repeated here.

[0195] The communication method involved in the embodiments of this disclosure may include at least one of steps S3101 to S3106. For example, steps S3101 and S3106 may be implemented as independent embodiments, but are not limited thereto.

[0196] In some embodiments, steps S3102-S3105 are optional, and one or more of them may be omitted or substituted in different embodiments.

[0197] In some embodiments, other optional implementations may be described before or after the specification corresponding to FIG3.

[0198] Figure 4 is a flowchart illustrating a communication method according to an embodiment of the present disclosure. As shown in Figure 4, this embodiment of the present disclosure relates to a communication method executed by a network device 102, the method comprising:

[0199] Step S4101: Send the second message.

[0200] The optional implementation of step S4101 can be found in the optional implementation of step S2102 in Figure 2, as well as other related parts in the embodiments involved in Figure 2, which will not be repeated here.

[0201] In some embodiments, network device 102 sends second information to terminal 101, but is not limited thereto; it may also send second information to other entities.

[0202] Step S4102: Send the first message.

[0203] The optional implementation of step S4102 can be found in the optional implementation of step S2103 in Figure 2, as well as other related parts in the embodiments involved in Figure 2, which will not be repeated here.

[0204] In some embodiments, network device 102 receives first information sent by terminal 101, but is not limited thereto; it may also receive first information sent by other entities.

[0205] In some embodiments, network device 102 obtains first information as defined by a protocol.

[0206] In some embodiments, network device 102 obtains first information from upper layer(s).

[0207] In some embodiments, network device 102 processes information to obtain first information.

[0208] In some embodiments, step S4102 is omitted, and the network device 102 autonomously implements the function indicated by the first information, or the above function is default or default.

[0209] Step S4103: Determine the scalability information of the first model.

[0210] The optional implementation of step S4103 can be found in the optional implementation of step S2104 in Figure 2, as well as other related parts in the embodiments involved in Figure 2, which will not be repeated here.

[0211] In some embodiments, the scalability information of the first model is determined based on first information.

[0212] Step S4104: Send the third message.

[0213] The optional implementation of step S4104 can be found in the optional implementation of step S2105 in Figure 2, as well as other related parts in the embodiments involved in Figure 2, which will not be repeated here.

[0214] In some embodiments, network device 102 sends third information to terminal 101, but is not limited thereto; it may also send third information to other entities.

[0215] Step S4105: Determine the scalability information of the second model.

[0216] The optional implementation of step S4105 can be found in the optional implementation of step S2106 in Figure 2, as well as other related parts in the embodiments involved in Figure 2, which will not be repeated here.

[0217] Step S4106: Send the fourth message.

[0218] The optional implementation of step S4106 can be found in the optional implementation of step S2107 in Figure 2, as well as other related parts in the embodiments involved in Figure 2, which will not be repeated here.

[0219] In some embodiments, network device 102 sends fourth information to terminal 101, but is not limited thereto; it may also send fourth information to other entities.

[0220] The communication method involved in the embodiments of this disclosure may include at least one of steps S4101 to S4106. For example, steps S4103 and S4105 may be implemented as independent embodiments, but are not limited thereto.

[0221] In some embodiments, steps S4101, S2102, S4104, and S4106 are optional, and one or more of them may be omitted or substituted in different embodiments.

[0222] In some embodiments, other optional implementations may be described before or after the specification corresponding to FIG3.

[0223] Figure 5 is a flowchart illustrating a communication method according to an embodiment of the present disclosure. As shown in Figure 5, this disclosure relates to a communication method, which includes:

[0224] In step S5101, terminal 101 determines the scalability information of the first model and / or the second model.

[0225] In some embodiments, the above methods may include the methods of the embodiments related to the communication system 100, terminal 101, and network device 102, which will not be described again here.

[0226] This disclosure provides a method for determining the scalability of the encoder model on the UE side, as follows:

[0227] UE side:

[0228] In some embodiments, the reported UE capability indicates the scalability of the encoder model on the UE side. The UE capability indicates that the encoder model supports at least one or more scalability features, such as different numbers of antenna ports, different frequency domain information configurations (including frequency domain granularity / bandwidth or number of sub-bands), different CSI feedback load sizes, and the number of CSIs compressed at different times.

[0229] In some embodiments, the supported scalability indication methods for antenna ports, frequency domain information configuration, and CSI feedback load are as follows:

[0230] Optionally, the UE may display one or more of the following: a set or range of values ​​for the number of supported antenna ports, a set or range of values ​​for frequency domain information configuration, a set or range of values ​​for CSI feedback load size, and a range of values ​​for the number of times compressed CSI occurs.

[0231] Optionally, for each scalability, multiple value sets or multiple value ranges are predefined. The reported UE capability indicates that at least one value set or at least one value range is supported. If a value set is predefined, the supported values ​​can be indicated by the number of combinations. Alternatively, based on the number of antenna ports, frequency domain information configuration, possible value sets or value ranges for CSI feedback load size, and the number of times or value ranges for compressed CSI, two or more combinations of these can be predefined, and the reported UE capability indicates at least one combination.

[0232] In some embodiments, the UE reports the supported standardized encoder model structure / model, and then determines the scalability of the encoder model on the UE side based on the standardized model structure / model.

[0233] In some embodiments, one or more encoder model structures / models are standardized. Each standardized encoder model structure / model supports at least one or more scalability features among the following: number of antenna ports, frequency domain information configuration, CSI feedback load size, and number of compressed CSI times. Each scalability is associated with at least one set of values ​​or at least one range of values ​​in Option 2 above. The scalability supported by the UE and its corresponding set of values ​​or range of values ​​are implicitly determined based on the standardized encoder model structure / model supported by the UE. The standardized encoder model structure / model supported by the UE is determined by the following method:

[0234] Optionally, the supported encoder model structure / model can be indicated by the reported UE capabilities.

[0235] Optionally, receiving NW signaling triggers the UE to report or the UE to actively report the supported encoder model structure / model.

[0236] In some embodiments, the scalability of the encoder model on the UE side is triggered by receiving NW signaling or actively reported by the UE. The UE-reported information includes that the encoder model supports at least one or more scalability values ​​or ranges for different antenna ports, different frequency domain information configurations (including frequency domain granularity and / or bandwidth), different CSI feedback load sizes, and the number or range of compressed CSI times. The scalability indication methods for supported antenna ports, frequency domain information configurations, CSI feedback loads, and compressed CSI at different times are the same as those in Options 1 and 2 above.

[0237] NW side:

[0238] In some embodiments, the NW determines configuration parameters such as the number of antenna ports, frequency domain information, number of compressed CSI times, or uplink transmission CSI resources based on the scalability indicated by the received UE. Alternatively, the NW sends signaling to instruct the UE to report the supported scalability.

[0239] This disclosure provides a method for determining the scalability of an NW-side decoder model, as follows:

[0240] NW side:

[0241] In some embodiments, the NW configures the UE with a set or range of values ​​for the CSI feedback load size via signaling, indicating the scalability of the CSI feedback load size supported by the decoder model. Optionally, the NW indicates to the UE the number of antenna ports, sub-bands, and CSI compression times supported by the decoder.

[0242] In some embodiments, the NW can also indicate to the UE the scalability of different parameters supported by the NW side, and implicitly indicate that the encoder on the UE side needs to have corresponding scalability.

[0243] In some embodiments, NW indicates the standardized encoder model structure / model used by the UE, and determines the scalability supported by the NW-side decoder model based on the indicated model structure / model.

[0244] In some embodiments, one or more standardized encoder model structures / models are used, each of which supports at least scalability of CSI feedback load size. The standardized encoder and decoder models are jointly trained on the NW side. If the encoder supports scalability of different CSI feedback load sizes, the corresponding decoder model also supports scalability of the corresponding different CSI feedback load sizes.

[0245] In some embodiments, the NW implicitly indicates the scalability of the different CSI feedback load sizes supported by the NW-side decoder model by signaling the quantization granularity of various CSI feedback loads (e.g., quantizing each real number output by the encoder model by 1 bit, 2 bits, or 4 bits).

[0246] UE side:

[0247] In some embodiments, the UE side determines the CSI feedback load size based on the scalability of the CSI load size supported by the NW side.

[0248] Example 1 (UE-side indication of scalability):

[0249] The number of antenna ports can be configured to 2, 4, 8, 12, 16, 24, and 32, and the number of sub-bands can be expressed as follows: Where W represents the configured bandwidth size in RBs, and S represents the number of RBs contained in the subband. The CSI feedback load size can be predefined, indicated by the UE, or determined by NW configuration.

[0250] Assume the UE-side encoder model supports configurations with 16 and 32 antenna ports, 8 and 13 subbands, CSI feedback load sizes of 60 and 120 bits, and CSI compression of 1 and 4 future time points. To indicate these parameters supported by the UE-side encoder model, a set of parameters supported by the UE can be defined, such as the set of antenna port numbers P∈{16,32}, the set of subband numbers N∈{8,13}, the CSI feedback load size L∈{60,120}, and the number of CSI compression times T∈{1,4}. The UE indicates these supported parameter combinations in its capability reporting. Optionally,

[0251] These parameters can also be defined with ranges. For example, P∈[2,64], N∈{8,13}, L∈[30,240], and T∈[1,8], where [a,b] represents any integer value between a and b, including a and b themselves. In this case, the UE can simply indicate the minimum and maximum values ​​of each parameter in its capability reporting. Optionally,

[0252] All supported parameter combinations are given through predefined definitions. Taking P and N as an example, P∈{2,4,8,12,16,24,32} and N∈{6,10,13,16,30} are predefined. There are 42 possible combinations, so the UE can... The bits indicate one combination. If three combinations are supported, the total indication is 18 bits. Alternatively, assuming the encoder supports two values ​​in P and two values ​​in N, the UE can... and These indicate the number of supported antenna ports and sub-bands, respectively.

[0253] The above are the parameter values ​​supported by the reporting indication through UE capabilities. Optionally, the UE reports the supported parameter values ​​based on the indication signaling from the NW side or by the UE actively triggering the reporting. The NW side can indicate the values ​​through one or more of RRC / MAC-CE / DCI signaling, or the UE can report the indication through event triggering.

[0254] If one or more standardized encoder models / structures are predefined, the parameter values ​​supported by different standardized models may be the same or different, or some parameter values ​​may be the same. For example, standardized model structure 1 supports P∈{16,32}, N∈{13,16}, L∈{60,120}, and T∈{1,4}, while standardized model structure 2 supports P∈{4,12}, N∈{6,12}, L∈{160,240}, and T∈{3,6}. The UE can indicate the supported standardized models / structures through capability reporting, such as supporting model structure 1. The NW can determine the scalability parameters P∈{16,32}, N∈{13,16}, L∈{60,120}, and T∈{1,4} supported by the UE based on the supported model / model result information indicated by the UE.

[0255] Furthermore, NW configures the number of antenna ports, the frequency domain granularity and bandwidth of the sub-bands, the number of CSI compression moments, etc., based on these parameter values.

[0256] Example 2 (Scalability of NW-side decoder model):

[0257] Similar to the encoder model, the decoder model also needs to have corresponding scalability features. Since the encoder and decoder are paired models, the scalability supported by the decoder also requires the encoder to support corresponding scalability, and vice versa.

[0258] On the NW side, the range of values ​​for the CSI feedback control size L supported by the decoder can be explicitly configured via RRC signaling, such as L∈[30,240] bits or L∈[15,120] real numbers. Assume each real number is quantized using 2 bits. Similarly, other parameters such as the number of antenna ports can also be explicitly configured for the UE.

[0259] During collaborative training, the NW indicates the encoder model structure used on the NW side to the UE. This model structure supports the scalability of each parameter. The possible values ​​of these parameters are associated with the corresponding model structure. The UE can determine the scalability of the decoder model based on the indicated model structure.

[0260] If each real number in CSI compression can be quantized using different quantization granularities, such as the NW-side decoder supporting UE quantization of each real number using 1 bit, 2 bits, or 4 bits, this indicates that the decoder model is scalable to the CSI load size. The UE can then select a reasonable quantization granularity or discard part of the compressed CSI based on uplink transmission resources to determine the CSI feedback load size.

[0261] This disclosure also provides an apparatus for implementing any of the above methods. For example, an apparatus is provided that includes units or modules for implementing the steps performed by the terminal in any of the above methods. Alternatively, another apparatus is provided that includes units or modules for implementing the steps performed by a network device (e.g., an access network device, a core network functional node, a core network device, etc.) in any of the above methods.

[0262] It should be understood that the division of units or modules in the above device is only a logical functional division. In actual implementation, they can be fully or partially integrated into a single physical entity, or they can be physically separated. Furthermore, the units or modules in the device can be implemented by a processor calling software: for example, the device includes a processor connected to a memory containing instructions. The processor calls the instructions stored in the memory to implement any of the above methods or to implement the functions of the units or modules in the above device. The processor can be, for example, a general-purpose processor, such as a Central Processing Unit (CPU) or a microprocessor, and the memory can be internal or external to the device. Alternatively, the units or modules in the device can be implemented in the form of hardware circuits. The functionality of some or all of the units or modules can be achieved through the design of these hardware circuits, which can be understood as one or more processors. For example, in one implementation, the hardware circuit is an application-specific integrated circuit (ASIC). The functionality of some or all of the units or modules is achieved through the design of the logical relationships between the components within the circuit. In another implementation, the hardware circuit can be implemented using a programmable logic device (PLD). Taking a field-programmable gate array (FPGA) as an example, it can include a large number of logic gates. The connection relationships between the logic gates are configured through configuration files, thereby achieving the functionality of some or all of the units or modules. All units or modules of the above device can be implemented entirely through processor-called software, entirely through hardware circuits, or partially through processor-called software with the remaining parts implemented through hardware circuits.

[0263] In this embodiment, the processor is a circuit with signal processing capabilities. In one implementation, the processor can be a circuit with instruction read and execute 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 relationships of hardware circuits. The logical relationships of the aforementioned hardware circuits are fixed or reconfigurable. For example, the processor is a hardware circuit implemented using 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 configuring the hardware circuit 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. Furthermore, 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), or a Deep Learning Processing Unit (DPU).

[0264] Figure 6a is a schematic diagram of the terminal structure proposed in an embodiment of this disclosure. As shown in Figure 6a, the terminal 6100 may include at least one of a transceiver module 6101 and a processing module 6102. The processing module 6102 is used to determine the scalability information of a first model and / or a second model. The first model is deployed on the terminal, and the second model is deployed on a network device. The first model and the second model are associated. The scalability information of the first model is related to the input and / or output data dimensions of the first model, and the scalability information of the second model is related to the input and / or output data dimensions of the second model.

[0265] In some embodiments, the transceiver module 6101 is configured to: send first information to the network device, the first information being used by the network device to determine scalability information of the first model.

[0266] In some embodiments, the first information is used to indicate the scalability information of the first model, or the first information is used to indicate the first model, and the scalability information of the first model is predefined in the protocol.

[0267] In some embodiments, before sending the first information, the transceiver module 6101 is further configured to: receive second information sent by the network device, the second information being used to instruct the terminal to send the first information.

[0268] In some embodiments, the first information is carried by a message reporting the terminal's capabilities.

[0269] In some embodiments, the transceiver module 6101 is further configured to: receive third information sent by the network device, the third information being configured to configure at least one of the following: number of antenna ports; number of frequency domain units; load size; number of time intervals; and the terminal sending first model output data to the network device based on the third information.

[0270] In some embodiments, the processing module 6102 determines the scalability information of the second model in the following manner: the terminal receives fourth information sent by the network device; the terminal determines the scalability information of the second model based on the fourth information.

[0271] In some embodiments, the fourth information is used to indicate the scalability information of the second model; or, the fourth information is used to indicate the second model, and the scalability information of the second model is predetermined in the protocol.

[0272] In some embodiments, the scalability information includes a value or set or range of values ​​for each of at least one of the following: the number of supported antenna ports; the number of supported frequency domain units; the supported payload size, wherein the payload is the first model output data sent to the network device; and the supported number of times, wherein the times are the times corresponding to the first model output data.

[0273] In some embodiments, the scalability information includes at least one combination, each combination including at least one of the following values: the number of supported antenna ports; the number of supported frequency domain units; the supported payload size, where the payload is the payload for sending the first model output data to the network device; and the supported number of times, where the time is the time corresponding to the first model output data.

[0274] In some embodiments, the load size is taken as the actual value corresponding to the load size or the quantization granularity corresponding to the load size.

[0275] Figure 6b is a schematic diagram of the network device proposed in an embodiment of this disclosure. As shown in Figure 6b, the network device 6200 may include at least one of a transceiver module 6201 and a processing module 6202. The processing module 6202 is used to determine the scalability information of a first model and / or a second model. The first model is deployed on a terminal, and the second model is deployed on the network device. The first model and the second model are associated. The scalability information of the first model is related to the input and / or output data dimensions of the first model, and the scalability information of the second model is related to the input and / or output data dimensions of the second model.

[0276] In some embodiments, the processing module 6202 determines the first model scalability information in the following manner: the network device receives first information sent by the terminal; the network device determines the scalability information of the first model based on the first information.

[0277] In some embodiments, the first information is used to indicate the scalability information of the first model, or the first information is used to indicate the first model, and the scalability information of the first model is predefined in the protocol.

[0278] In some embodiments, before receiving the first information, the transceiver module 6201 is configured to: send second information to the terminal, the second information being used to instruct the terminal to send the first information.

[0279] In some embodiments, the first information is carried by a message reporting the terminal's capabilities.

[0280] In some embodiments, the transceiver module 6201 is used to: send third information to the terminal, the third information being used to configure at least one of the following: number of antenna ports; number of frequency domain units; load size; number of time intervals; the third information is used by the terminal to send first model output data to the network device.

[0281] In some embodiments, the transceiver module 6201 is configured to: send fourth information to the terminal, the fourth information being used by the terminal to determine the scalability information of the second model.

[0282] In some embodiments, the fourth information is used to indicate the scalability information of the second model; or, the fourth information is used to indicate the second model, and the scalability information of the second model is predetermined in the protocol.

[0283] In some embodiments, the scalability information includes a value or set or range of values ​​for each of at least one of the following: the number of supported antenna ports; the number of supported frequency domain units; the supported payload size, wherein the payload is the first model output data sent to the network device; and the supported number of times, wherein the times are the times corresponding to the first model output data.

[0284] In some embodiments, the scalability information includes at least one combination, each combination including at least one of the following values: the number of supported antenna ports; the number of supported frequency domain units; the supported payload size, where the payload is the payload for sending the first model output data to the network device; and the supported number of times, where the time is the time corresponding to the first model output data.

[0285] In some embodiments, the load size is taken as the actual value corresponding to the load size or the quantization granularity corresponding to the load size.

[0286] Figure 7a is a schematic diagram of a communication device according to an embodiment of this disclosure. The communication device 7100 can be a network device, a terminal device, or a chip, chip system, or processor that supports the implementation of any of the above methods in a network device, or a chip, chip system, or processor that supports the implementation of any of the above methods in a terminal device. Optionally, the network device can be an access network device, a core network device, etc. Optionally, the terminal device can be a user equipment, etc. The communication device 7100 can be used to implement the methods described in the above method embodiments; for details, please refer to the descriptions in the above method embodiments.

[0287] As shown in Figure 7a, the communication device 7100 includes one or more processors 7101. The processor 7101 can be a general-purpose processor or a dedicated processor, such as a baseband processor or a central processing unit (CPU). The baseband processor can be used to process communication protocols and communication data, while the CPU can be used to control the communication device, execute programs, and process program data. The communication device 7100 is used to execute 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 (Distributed Unit), or a CU (Computer Integrated Circuit), etc.

[0288] 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 also be located outside the communication device 7100.

[0289] 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 transceivers 7103 perform communication steps such as sending and / or receiving in the above method, such as step S2102, but are not limited thereto. The processor 7201 performs other steps, such as step S2101, but is not limited thereto.

[0290] In some embodiments, a transceiver may include a receiver and / or a transmitter, which may be separate or integrated. Optionally, the terms transceiver, transceiver unit, transceiver, transceiver circuit, etc., may be used interchangeably; the terms transmitter, transmitting unit, transmitter, transmitting circuit, etc., may be used interchangeably; and the terms receiver, receiving unit, receiver, receiving circuit, etc., may be used interchangeably.

[0291] 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, and the interface circuit 7104 can be used to receive signals from the memory 7102 or other devices, and can be used to send signals to the memory 7102 or other devices. For example, the interface circuit 7104 can read instructions stored in the memory 7102 and send the instructions to the processor 7101.

[0292] The communication device 7100 described in the above embodiments may be a network device or a terminal device, but the scope of the communication device 7100 described in this 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 a standalone device or a part of a larger device. For example, the communication device may be: (1) a standalone integrated circuit IC, or chip, or chip system or subsystem; (2) a collection of one or more ICs, optionally, the IC collection may also include storage components for storing data and programs; (3) an ASIC, such as a modem; (4) a module that can be embedded in other devices; (5) a receiver, terminal device, smart terminal device, cellular phone, wireless device, handheld device, mobile unit, vehicle device, network device, cloud device, artificial intelligence device, etc.; (6) others, etc.

[0293] Figure 7b is a schematic diagram of the chip structure proposed in an embodiment of this disclosure. For cases where the communication device 7100 can be a chip or a chip system, please refer to the schematic diagram of the chip 7200 shown in Figure 7b, but it is not limited thereto.

[0294] Chip 7200 includes one or more processors 7201, which are used to perform any of the above methods.

[0295] In some embodiments, chip 7200 further includes one or more interface circuits 7202. Optionally, the interface circuit 7202 is connected to memory 7203, and the interface circuit 7202 can be used to receive signals from memory 7203 or other devices, and the interface circuit 7202 can be used to send signals to memory 7203 or other devices. For example, the interface circuit 7202 can read instructions stored in memory 7203 and send the instructions to processor 7201.

[0296] In some embodiments, the interface circuit 7202 performs communication steps such as sending and / or receiving in the above method, such as step S2102, but is not limited thereto. The processor 7201 performs other steps, such as step S2101, but is not limited thereto.

[0297] In some embodiments, the terms interface circuit, interface, transceiver pin, transceiver, etc., can be used interchangeably.

[0298] In some embodiments, chip 7200 further includes one or more memories 7203 for storing instructions. Optionally, all or part of the memories 7203 may be located outside of chip 7200.

[0299] This disclosure also proposes a storage medium storing instructions that, when executed on the communication device 7100, cause the communication device 7100 to perform 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 not limited thereto; it may also be a storage medium readable by other devices. Optionally, the storage medium may be a non-transitory storage medium, but not limited thereto; it may also be a temporary storage medium.

[0300] This disclosure also provides a program product that, when executed by the communication device 7100, causes the communication device 7100 to perform any of the above methods. Optionally, the program product is a computer program product.

[0301] This disclosure also proposes a computer program that, when run on a computer, causes the computer to perform any of the above methods.

Claims

1. A communication method, characterized in that, The method includes: The terminal determines the scalability information of a first model and / or a second model, wherein the first model is deployed on the terminal and the second model is deployed on a network device, the first model and the second model are associated, the scalability information of the first model is related to the input and / or output data dimensions of the first model, and the scalability information of the second model is related to the input and / or output data dimensions of the second model.

2. The method according to claim 1, characterized in that, The method further includes: The terminal sends first information to the network device, the first information being used by the network device to determine the scalability information of the first model.

3. The method according to claim 2, characterized in that, The first information is used to indicate the scalability information of the first model, or, The first information is used to indicate the first model, and the protocol predefines the scalability information of the first model.

4. The method according to any one of claims 2-3, characterized in that, Before sending the first information, the method further includes: The terminal receives second information sent by the network device, the second information being used to instruct the terminal to send the first information.

5. The method according to any one of claims 2-4, characterized in that, The first information is carried by a message reporting the terminal's capabilities.

6. The method according to any one of claims 2-5, characterized in that, The method further includes: The terminal receives third information sent by the network device, the third information being used to configure at least one of the following: number of antenna ports; number of frequency domain units; load size; number of time points; Based on the third information, the terminal sends the first model output data to the network device.

7. The method according to any one of claims 1-6, characterized in that, The terminal determines the scalability information of the second model in the following manner: The terminal receives the fourth information sent by the network device; The terminal determines the scalability information of the second model based on the fourth information.

8. The method according to claim 7, characterized in that, The fourth piece of information is used to indicate the scalability information of the second model; or, The fourth information is used to indicate the second model, and the protocol predetermines the scalability information of the second model.

9. The method according to any one of claims 1-8, characterized in that, The scalability information includes a value, set of values, or range of values ​​for each of at least one of the following: Number of supported antenna ports; Number of frequency domain units supported; Supported payload size, where the payload is the first model output data sent to the network device; The number of supported time points, where each time point corresponds to the time point in which the first model outputs data.

10. The method according to any one of claims 1-8, characterized in that, The scalability information includes at least one combination, and each combination includes at least one of the following values: Number of supported antenna ports; Number of frequency domain units supported; Supported load size, wherein the load is the load of sending the first model output data to the network device; The number of supported time points, where each time point corresponds to the time point in which the first model outputs data.

11. The method according to claim 9 or 10, characterized in that, The value of the load size is either the actual value corresponding to the load size or the quantization granularity corresponding to the load size.

12. A communication method, characterized in that, The method includes: The network device determines scalability information for a first model and / or a second model, wherein the first model is deployed on a terminal and the second model is deployed on the network device, the first model and the second model are associated, the scalability information of the first model is related to the input and / or output data dimensions of the first model, and the scalability information of the second model is related to the input and / or output data dimensions of the second model.

13. The method according to claim 12, characterized in that, The network device determines the scalability information of the first model in the following manner: The network device receives the first information sent by the terminal; The network device determines the scalability information of the first model based on the first information.

14. The method according to claim 13, characterized in that, The first information is used to indicate the scalability information of the first model, or, The first information is used to indicate the first model, and the protocol predefines the scalability information of the first model.

15. The method according to any one of claims 13-14, characterized in that, Before receiving the first information, the method further includes: The network device sends a second message to the terminal, the second message being used to instruct the terminal to send the first message.

16. The method according to any one of claims 13-15, characterized in that, The first information is carried by a message reporting the terminal's capabilities.

17. The method according to any one of claims 13-16, characterized in that, The method further includes: The network device sends third information to the terminal, the third information being used to configure at least one of the following: number of antenna ports; number of frequency domain elements; load size; number of time intervals; The third piece of information is used by the terminal to send the first model output data to the network device.

18. The method according to any one of claims 12-17, characterized in that, The method further includes: The network device sends a fourth piece of information to the terminal, the fourth piece of information being used by the terminal to determine the scalability information of the second model.

19. The method according to claim 18, characterized in that, The fourth piece of information is used to indicate the scalability information of the second model; or, The fourth information is used to indicate the second model, and the protocol predetermines the scalability information of the second model.

20. The method according to any one of claims 12-19, characterized in that, The scalability information includes a value, set of values, or range of values ​​for each of at least one of the following: Number of supported antenna ports; Number of frequency domain units supported; Supported payload size, where the payload is the first model output data sent to the network device; The number of supported time points, where each time point corresponds to the time point in which the first model outputs data.

21. The method according to any one of claims 12-19, characterized in that, The scalability information includes at least one combination, and each combination includes at least one of the following values: Number of supported antenna ports; Number of frequency domain units supported; Supported load size, wherein the load is the load of sending the first model output data to the network device; The number of supported time points, where each time point corresponds to the time point in which the first model outputs data.

22. The method according to claim 20 or 21, characterized in that, The value of the load size is either the actual value corresponding to the load size or the quantization granularity corresponding to the load size.

23. A terminal, characterized in that, include: A processing module is used to determine the scalability information of a first model and / or a second model, wherein the first model is deployed on the terminal, the second model is deployed on a network device, the first model and the second model are associated, the scalability information of the first model is related to the input and / or output data dimensions of the first model, and the scalability information of the second model is related to the input and / or output data dimensions of the second model.

24. A network device, characterized in that, include: A processing module is used to determine the scalability information of a first model and / or a second model, wherein the first model is deployed on a terminal, the second model is deployed on the network device, the first model and the second model are associated, the scalability information of the first model is related to the input and / or output data dimensions of the first model, and the scalability information of the second model is related to the input and / or output data dimensions of the second model.

25. 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 1-11.

26. A network device, characterized in that, include: One or more processors; The processor is used to execute the communication method according to any one of claims 12-22.

27. A communication system, characterized in that, include: A terminal and a network device, wherein the terminal is configured to implement the communication method of any one of claims 1-11, and the network device is configured to implement the communication method of any one of claims 12-22.

28. A storage medium, characterized in that, include: The storage medium stores instructions that, when executed on a communication device, cause the communication device to perform the communication method as described in any one of claims 1-11 or 12-22.

29. A program product, characterized in that, include: A computer program, when executed by a communication device, causes the communication device to perform the communication method as described in any one of claims 1-11 or 12-22.

Images