Communication processing method, terminal, network device, system, and medium

Abstract

The present disclosure relates to a communication processing method, a terminal, a network device, a system, and a medium. The method comprises: determining an AI model for an inference stage on the basis of auxiliary information, wherein the auxiliary information is used for indicating the characteristics of the AI model. In the method of the present disclosure, a terminal can obtain, on the basis of the auxiliary information, the characteristics of the AI model suitable for the current application scenario (for example, matching the current CSI-RS period), so that when the application scenario of the model changes, the terminal can select or determine, on the basis of the auxiliary information, an appropriate AI model in a targeted mode for use in the inference stage, to effectively adapt to the current application scenario such as the current CSI-RS period, thereby improving the accuracy of the applied model.

Description

Communication processing method, terminal, network equipment, system and medium Technical Field

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

[0002] Artificial intelligence (AI) or machine learning (ML) models consist of a training phase, an inference phase, and a monitoring phase. During the training phase, the AI ​​or ML model is trained using training data until the model converges. During the inference phase, the AI ​​or ML model can be used to predict or compress information. During the monitoring phase, supervisory metrics are calculated to verify the rationality of the AI ​​or ML model.

[0003] Summary of the Invention

[0004] When the application scenario of the model changes, the model input information involving historical data may not be available or the input information may cause the model output results to be inaccurate.

[0005] Embodiments of the present disclosure provide a communication processing method, a terminal, a network device, a system, and a medium.

[0006] In a first aspect, an embodiment of the present disclosure provides a communication processing method, executed by a terminal, the method comprising:

[0007] An AI model to be used in the inference phase is determined based on the auxiliary information, where the auxiliary information is used to indicate characteristics of the AI ​​model.

[0008] In a second aspect, an embodiment of the present disclosure provides a communication processing method, which is performed by a network device, and the method includes:

[0009] An AI model for the inference phase is determined based on the auxiliary information, where the auxiliary information is used to indicate characteristics of the AI ​​model.

[0010] In a third aspect, an embodiment of the present disclosure provides a terminal, including:

[0011] A processing module is used to determine an AI model for the reasoning stage based on auxiliary information, where the auxiliary information is used to indicate characteristics of the AI ​​model.

[0012] In a fourth aspect, an embodiment of the present disclosure provides a network device, including:

[0013] A processing module is used to determine an AI model for the reasoning stage based on auxiliary information, where the auxiliary information is used to indicate characteristics of the AI ​​model.

[0014] In a fifth aspect, an embodiment of the present disclosure provides a terminal, including:

[0015] one or more processors;

[0016] The terminal is configured to implement the method described in the first aspect.

[0017] In a sixth aspect, an embodiment of the present disclosure provides a network device, including:

[0018] one or more processors;

[0019] The network device is configured to implement the method described in the second aspect.

[0020] In a seventh aspect, an embodiment of the present disclosure provides a communication system, including a terminal and a network device, wherein:

[0021] The terminal is configured to implement the method according to the first aspect;

[0022] The network device is configured to implement the method according to the second aspect.

[0023] In an eighth aspect, an embodiment of the present disclosure provides a storage medium, wherein the storage medium stores instructions, wherein:

[0024] When the instruction is executed on a communication device, the communication device is caused to execute the method according to the first aspect or the second aspect.

[0025] In a ninth aspect, an embodiment of the present disclosure provides a program product, wherein:

[0026] When the program product is executed by a communication device, the communication device is caused to execute the method according to the first aspect or the second aspect.

[0027] In an embodiment of the present disclosure, the terminal can obtain the characteristics of the AI ​​model applicable to the current application scenario (for example, matching the current CSI-RS period) based on the auxiliary information. The terminal can select or determine the appropriate AI model for application in the reasoning stage based on the auxiliary information, effectively apply the current application scenario such as the current CSI-RS period, and thereby improve the accuracy of the application model. BRIEF DESCRIPTION OF THE DRAWINGS

[0028] In order to more clearly illustrate the technical solutions in the embodiments of the present disclosure, the following drawings required for describing the embodiments are introduced. The following drawings are merely some embodiments of the present disclosure and do not impose specific limitations on the protection scope of the present disclosure.

[0029] FIG1 is an exemplary schematic diagram of the architecture of a communication system provided according to an embodiment of the present disclosure;

[0030] 2a to 2b are exemplary interaction diagrams of a method according to an embodiment of the present disclosure;

[0031] FIG2c is a schematic diagram of an architecture for determining an AI model according to an embodiment of the present disclosure;

[0032] 3a to 3d are exemplary flowcharts of a method according to an embodiment of the present disclosure;

[0033] 4a to 4d are exemplary flowcharts of a method according to an embodiment of the present disclosure;

[0034] FIG5a is a schematic structural diagram of a terminal according to an embodiment of the present disclosure;

[0035] FIG5b is a schematic structural diagram of a network device according to an embodiment of the present disclosure;

[0036] FIG6a is a schematic diagram of a communication device according to an embodiment of the present disclosure;

[0037] FIG6 b is a schematic diagram of a communication device according to an embodiment of the present disclosure. DETAILED DESCRIPTION

[0038] Embodiments of the present disclosure provide a communication processing method, a terminal, a network device, a system, and a medium.

[0039] In a first aspect, an embodiment of the present disclosure provides a communication processing method, executed by a terminal, the method comprising:

[0040] An AI model for the inference phase is determined based on the auxiliary information, where the auxiliary information is used to indicate characteristics of the AI ​​model.

[0041] In the above embodiment, the terminal can obtain the characteristics of the AI ​​model applicable to the current application scenario (for example, matching the current CSI-RS period) based on the auxiliary information. The terminal can select or determine the appropriate AI model for application in the reasoning stage based on the auxiliary information, effectively apply the current application scenario such as the current CSI-RS period, and thereby improve the accuracy of the application model.

[0042] In conjunction with the embodiments of the first aspect, in some embodiments, the method further includes:

[0043] Receive the configuration information of the AI ​​model sent by the network device, which includes auxiliary information.

[0044] In the above embodiment, the auxiliary information is sent by the network device through configuration information. The terminal can obtain the characteristics of the applicable AI model based on the configuration information sent by the network device, so as to facilitate the selection of the AI ​​model indicated or configured by the network device for application in the reasoning stage.

[0045] In conjunction with the embodiments of the first aspect, in some embodiments, the method further includes:

[0046] Send capability information to the network device, the capability information including auxiliary information.

[0047] In the above embodiment, the terminal can report auxiliary information to the network device through capability information, so that the network device can know the relevant features of the AI ​​model selected by the terminal for application, so that the network device can perform corresponding operations such as configuration or management.

[0048] In conjunction with the embodiments of the first aspect, in some embodiments, the method further includes:

[0049] Receive request information sent by the network device;

[0050] Send auxiliary information to the network device based on the request information.

[0051] In the above embodiment, after receiving the request information from the network device, the terminal can report the requested auxiliary information to the network device, so that the network device can obtain the required model features based on the auxiliary information to facilitate corresponding operations such as configuration or management.

[0052] In conjunction with the embodiments of the first aspect, in some embodiments, the auxiliary information includes at least one of the following:

[0053] Time-domain compression information during the AI ​​model training phase;

[0054] Time-domain compression information during the AI ​​model inference phase;

[0055] Among them, the AI ​​model is used for channel state information (CSI) compression.

[0056] In the above embodiment, the auxiliary information may include information of the AI ​​model training stage or the inference stage, so that the terminal can determine the corresponding AI model based on the auxiliary information.

[0057] In conjunction with the embodiments of the first aspect, in some embodiments, the time domain compression information includes at least one of the following:

[0058] The compression number is used to indicate the number of historical CSI in the compressed accumulated CSI information;

[0059] Compression duration, which is used to indicate the time range of historical CSI in the compressed accumulated CSI information;

[0060] Among them, the input information of the AI ​​model is determined based on the accumulated CSI information.

[0061] In the above embodiment, the auxiliary information can indicate the compression quantity and / or compression duration in the training phase, or indicate the compression quantity and / or compression duration in the reasoning phase, so that the terminal can select a qualified AI model based on the auxiliary information for application in the reasoning phase to improve the accuracy of the model application.

[0062] In conjunction with the embodiments of the first aspect, in some embodiments, the compression quantity or compression duration satisfies one of the following:

[0063] There is at least one candidate value defined by the configuration or protocol;

[0064] There are candidate ranges that are configured or defined by the protocol.

[0065] In the above embodiment, the compression quantity or compression duration in the auxiliary information can be selected as a suitable value based on the configuration of the network device or the protocol definition.

[0066] In combination with the embodiments of the first aspect, in some embodiments, the auxiliary information is condition information (condition) and / or additional condition information (additional condition) of the AI ​​model defined by the protocol.

[0067] In the above embodiment, the characteristics of the AI ​​model can be determined based on the condition information and additional condition information so that the network device can better manage the model.

[0068] In combination with the embodiments of the first aspect, in some embodiments, the AI ​​model is a compression model based on spatial information (Spatial), time domain information (time) and frequency domain information (Frequency) sft.

[0069] In the above embodiment, the AI ​​model is compressed based on SFT, which can effectively improve the compression performance.

[0070] In a second aspect, an embodiment of the present disclosure provides a communication processing method, which is performed by a network device, and the method includes:

[0071] An AI model for the inference phase is determined based on the auxiliary information, where the auxiliary information is used to indicate characteristics of the AI ​​model.

[0072] In conjunction with the embodiments of the second aspect, in some embodiments, the method further includes:

[0073] Send the configuration information of the AI ​​model to the terminal, including auxiliary information.

[0074] In conjunction with the embodiments of the second aspect, in some embodiments, the method further includes:

[0075] The capability information sent by the receiving terminal includes auxiliary information.

[0076] In conjunction with the embodiments of the second aspect, in some embodiments, the method further includes:

[0077] Send request information to the terminal;

[0078] The auxiliary information corresponding to the request information sent by the receiving terminal.

[0079] In conjunction with the embodiments of the second aspect, in some embodiments, the auxiliary information includes at least one of the following:

[0080] Time-domain compression information during the AI ​​model training phase;

[0081] Time-domain compression information during the AI ​​model inference phase;

[0082] Among them, the AI ​​model is used for CSI compression.

[0083] In conjunction with the embodiments of the second aspect, in some embodiments, the time domain compression information includes at least one of the following:

[0084] Compression quantity, which is used to indicate the quantity of historical CSI in the accumulated CSI information to be compressed;

[0085] Compression duration, which is used to indicate the time range of historical CSI in the compressed accumulated CSI information;

[0086] Among them, the input information of the AI ​​model is determined based on the accumulated CSI information.

[0087] In conjunction with the embodiments of the second aspect, in some embodiments, the compression quantity or compression duration satisfies one of the following:

[0088] There is at least one candidate value defined by the configuration or protocol;

[0089] There are candidate ranges that are configured or defined by the protocol.

[0090] In combination with the embodiments of the second aspect, in some embodiments, the auxiliary information is conditional information and / or additional conditional information of the AI ​​model defined by the protocol.

[0091] In combination with the embodiments of the second aspect, in some embodiments, the AI ​​model is a compression model based on spatial domain information, time domain information and frequency domain information sft.

[0092] In a third aspect, an embodiment of the present disclosure provides a terminal, including:

[0093] A processing module is used to determine an AI model for the reasoning stage based on auxiliary information, where the auxiliary information is used to indicate characteristics of the AI ​​model.

[0094] In a fourth aspect, an embodiment of the present disclosure provides a network device, including:

[0095] A processing module is used to determine an AI model for the reasoning stage based on auxiliary information, where the auxiliary information is used to indicate characteristics of the AI ​​model.

[0096] In a fifth aspect, an embodiment of the present disclosure provides a terminal, including:

[0097] one or more processors;

[0098] The terminal is configured to implement the method described in the first aspect.

[0099] In a sixth aspect, an embodiment of the present disclosure provides a network device, including:

[0100] one or more processors;

[0101] The network device is configured to implement the method described in the second aspect.

[0102] In a seventh aspect, an embodiment of the present disclosure provides a communication system, including a terminal and a network device, wherein:

[0103] The terminal is configured to implement the method according to the first aspect;

[0104] The network device is configured to implement the method according to the second aspect.

[0105] In an eighth aspect, an embodiment of the present disclosure provides a storage medium, wherein the storage medium stores instructions, wherein:

[0106] When the instruction is executed on a communication device, the communication device is caused to execute the method according to the first aspect or the second aspect.

[0107] In a ninth aspect, an embodiment of the present disclosure provides a program product, wherein:

[0108] When the program product is executed by a communication device, the communication device is caused to execute the method according to the first aspect or the second aspect.

[0109] In a tenth aspect, an embodiment of the present disclosure proposes a computer program, which, when executed on a computer, enables the computer to execute the method described in the optional implementation of the first and second aspects.

[0110] In an eleventh aspect, an embodiment of the present disclosure provides a chip or a chip system, wherein the chip or chip system includes a processing circuit configured to execute the method described in the optional implementation of the first and second aspects above.

[0111] It is understandable that the above-mentioned terminals, network devices, communication systems, storage media, program products, computer programs, chips, or chip systems are all used to perform the methods proposed in the embodiments of the present disclosure. Therefore, the beneficial effects that can be achieved can refer to the beneficial effects of the corresponding methods and will not be repeated here.

[0112] The embodiments of the present disclosure are not exhaustive and are merely illustrative of some embodiments, and are not intended to be a specific limitation on the scope of protection of the present disclosure. In the absence of contradiction, each step in a certain embodiment can be implemented as an independent embodiment, and the steps can be arbitrarily combined. For example, a solution after removing some steps in a certain embodiment can also be implemented as an independent embodiment, and the order of the steps in a certain embodiment can be arbitrarily exchanged. In addition, the optional implementation methods in a certain embodiment can be arbitrarily combined; in addition, the embodiments can be arbitrarily combined. For example, some or all steps of different embodiments can be arbitrarily combined, and a certain embodiment can be arbitrarily combined with the optional implementation methods of other embodiments.

[0113] In each embodiment of the present disclosure, unless otherwise specified or provided for by logic, the terms and / or descriptions between the embodiments are consistent and can be referenced by each other. The technical features in different embodiments can be combined to form a new embodiment based on their inherent logical relationships.

[0114] The terms used in the embodiments of the present disclosure are only for the purpose of describing specific embodiments and are not intended to limit the present disclosure.

[0115] In the embodiments of the present disclosure, unless otherwise specified, elements expressed in the singular, such as "a", "an", "the", "above", "said", "the", "the", etc., may mean "one and only one", or "one or more", "at least one", etc. For example, when using articles such as "a", "an", "the" in English in translation, the noun following the article may be understood as a singular expression or a plural expression.

[0116] In the embodiments of the present disclosure, “plurality” refers to two or more.

[0117] In some embodiments, the terms "at least one," "one or more," "a plurality of," "multiple," etc. may be used interchangeably.

[0118] In some embodiments, descriptions such as "at least one of A and B," "A and / or B," "A in one case, B in another case," or "in response to one case A, in response to another case B" may include the following technical solutions depending on the situation: in some embodiments, A (A is executed independently of B); in some embodiments, B (B is executed independently of A); in some embodiments, execution is selected from A and B (A and B are selectively executed); and in some embodiments, A and B (both A and B are executed). The above is also applicable when there are more branches such as A, B, and C.

[0119] In some embodiments, "A or B" and other descriptions may include the following technical solutions depending on the situation: in some embodiments, A (A is executed independently of B); in some embodiments, B (B is executed independently of A); in some embodiments, execution is selected from A and B (A and B are selectively executed). The above is also applicable when there are more branches such as A, B, C, etc.

[0120] The prefixes such as "first" and "second" in the embodiments of the present disclosure are only used to distinguish different description objects and do not constitute any restriction on the position, order, priority, quantity or content of the description objects. For the statement of the description object, please refer to the description in the context of the claims or embodiments, and no unnecessary restriction should be constituted due to the use of prefixes. For example, if the description object is a "field", the ordinal number before the "field" in the "first field" and the "second field" does not limit the position or order between the "fields". "First" and "second" do not limit whether the "fields" they modify are in the same message, nor do they limit the order of the "first field" and the "second field". For another example, if the description object is a "level", the ordinal number before the "level" in the "first level" and the "second level" does not limit the priority between the "levels". For another example, the number of description objects is not limited by the ordinal number and can be one or more. Taking "first device" as an example, the number of "devices" can be one or more. In addition, the objects modified by different prefixes can be the same or different. For example, if the description object is "device", then the "first device" and the "second device" can be the same device or different devices, and their types can be the same or different; for another example, if the description object is "information", then the "first information" and the "second information" can be the same information or different information, and their contents can be the same or different.

[0121] In some embodiments, “including A,” “comprising A,” “used to indicate A,” and “carrying A” can be interpreted as directly carrying A or indirectly indicating A.

[0122] In some embodiments, terms such as "in response to...", "in response to determining...", "in the case of...", "at the time of...", "when...", "if...", "if...", etc. can be used interchangeably.

[0123] In some embodiments, terms such as "greater than", "greater than or equal to", "not less than", "more than", "more than or equal to", "not less than", "higher than", "higher than or equal to", "not less than", and "above" can be replaced with each other, and terms such as "less than", "less than or equal to", "not greater than", "less than", "less than or equal to", "not more than", "lower than", "lower than or equal to", "not higher than", and "below" can be replaced with each other.

[0124] In some embodiments, devices and equipment can be interpreted as physical or virtual, and their names are not limited to the names recorded in the embodiments. In some cases, they can also be understood as "equipment", "device", "circuit", "network element", "node", "function", "unit", "section", "system", "network", "chip", "chip system", "entity", "subject", etc.

[0125] In some embodiments, "network" can be interpreted as devices included in the network, such as access network equipment, core network equipment, etc.

[0126] In some embodiments, "access network device (AN device)" may also be referred to as "radio access network device (RAN device)", "base station (BS)", "radio base station", "fixed station", and in some embodiments may also be understood as "node", "access point", "transmission point (TP)", "reception point (RP)", "transmission and / or reception point (TRP)" "panel", "antenna panel", "antenna array", "cell", "macro cell", "small cell", "femto cell", "pico cell", "sector", "cell group", "serving cell", "carrier", "component carrier", "bandwidth part (BWP)", etc.

[0127] 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.

[0128] In some embodiments, obtaining data, information, etc. may comply with the laws and regulations of the country where the data is obtained.

[0129] In some embodiments, data, information, etc. may be obtained with the user's consent.

[0130] In addition, each element, each row, or each column in the table of the embodiment of the present disclosure can be implemented as an independent embodiment, and the combination of any elements, any rows, and any columns can also be implemented as an independent embodiment.

[0131] FIG1 is a schematic diagram showing the architecture of a communication system according to an embodiment of the present disclosure.

[0132] As shown in FIG. 1 , a communication system 100 includes a terminal 101 and a network device 102 .

[0133] In some embodiments, the terminal 101 includes, for example, a mobile phone, a wearable device, an Internet of Things device, a car with communication function, a smart car, a tablet computer, a computer with wireless transceiver function, a virtual reality (VR) terminal device, an augmented reality (AR) terminal device, a wireless terminal device in industrial control, a wireless terminal device in self-driving, a wireless terminal device in remote medical surgery, a wireless terminal device in a smart grid, a wireless terminal device in transportation safety, a wireless terminal device in a smart city, and at least one of a wireless terminal device in a smart home, but is not limited thereto.

[0134] In some embodiments, the network device 102 may include at least one of an access network device and a core network device.

[0135] In some embodiments, the access network device is, for example, a node or device that accesses a terminal to a wireless network. The access network device may include an evolved NodeB (eNB), a next generation evolved NodeB (ng-eNB), a next generation NodeB (gNB), a node B (NB), a home node B (HNB), a home evolved nodeB (HeNB), a wireless backhaul device, a radio network controller (RNC), a base station controller (BSC), a base transceiver station (BTS), a base band unit (BBU), a mobile switching center, a base station in a 6G communication system, an open base station (Open RAN), a cloud base station (Cloud RAN), a base station in other communication systems, and at least one of an access node in a wireless fidelity (WiFi) system, but is not limited thereto.

[0136] In some embodiments, the technical solution of the present disclosure can be applied to the Open RAN architecture. In this case, the interfaces between or within the access network devices involved in the embodiments of the present disclosure can be transformed into internal interfaces of the Open RAN, and the processes and information interactions between these internal interfaces can be implemented through software or programs.

[0137] In some embodiments, the access network device can be composed of a centralized unit (CU) and a distributed unit (DU), where the CU can also be called a control unit. The CU-DU structure can be used to split the protocol layer of the access network device, with the functions of some protocol layers centrally controlled by the CU, and the functions of the remaining part or all of the protocol layers distributed in the DU, which is centrally controlled by the CU, but is not limited to this.

[0138] In some embodiments, the core network device can be a device including one or more network elements, or it can be multiple devices or device groups, each including all or part of one or more network elements. The network element can be virtual or physical. The core network includes, for example, at least one of the Evolved Packet Core (EPC), the 5G Core Network (5GCN), and the Next Generation Core (NGC). Alternatively, the core network device refers to a network element with a specific function, such as the Access Management Function (AMF), the Service Management Function (SMF), etc.

[0139] It can be understood that the communication system described in the embodiment of the present disclosure is for the purpose of more clearly illustrating the technical solution of the embodiment of the present disclosure, and does not constitute a limitation on the technical solution provided by the embodiment of the present disclosure. Ordinary technicians in this field can know that with the evolution of the system architecture and the emergence of new business scenarios, the technical solution provided by the embodiment of the present disclosure is also applicable to similar technical problems.

[0140] The following embodiments of the present disclosure may be applied to the communication system 100 shown in FIG. 1 , or a part of the main body thereof, but are not limited thereto.

[0141] The entities shown in Figure 1 are examples. The communication system may include all or part of the entities in Figure 1, and may also include other entities outside of Figure 1. The number and form of each entity are arbitrary. The connection relationship between the entities is an example. The entities may be connected or disconnected. The connection may be in any manner, which may be direct or indirect, and may be wired or wireless.

[0142] The embodiments of the present disclosure can be applied to Long Term Evolution (LTE), LTE-Advanced (LTE-A), LTE-Beyond (LTE-B), SUPER 3G, IMT-Advanced, 4th generation mobile communication system (4G), 5th generation mobile communication system (5G), 5G new radio (NR), future radio access (FRA), new radio access technology (RAT), new radio (NR), new radio access (NX), future generation radio access (FX), Global System for Mobile communications (GSM (registered trademark)), CDMA2000, Ultra Mobile Broadband (UMB), IEEE 802.11 (Wi-Fi (registered trademark)), IEEE 802.16 (WiMAX (registered trademark)), IEEE 802.20, Ultra-WideBand (UWB), Bluetooth (registered trademark), Public Land Mobile Network (PLMN) networks, Device-to-Device (D2D) systems, Machine-to-Machine (M2M) systems, Internet of Things (IoT) systems, Vehicle-to-Everything (V2X), systems utilizing other communication processing methods, and next-generation systems based on and extending these. Furthermore, multiple systems may be combined (for example, a combination of LTE or LTE-A with 5G).

[0143] When predicting CSI based on an AI model, time domain compression information can be introduced into the AI ​​model, for example, an SFT model. In an AI model for CSI compression (such as an AI CSI model), the input information needs to include cumulative CSI information. Cumulative CSI information includes historical CSI information (or historical data) learned by the AI ​​model in a specific scenario and can be calculated from multiple historical CSIs. For example, during the training phase of the AI ​​model, a large amount of accumulated CSI information can be used to train the AI ​​model, wherein each historical CSI in the accumulated CSI information can be obtained by measuring the CSI reference signal (CSI Resource Signal, CSI-RS) by the terminal at a set time or a time unit before the current time, so that the accumulated CSI information is associated with the period of the CSI-RS. When the application scenario of the model changes, for example, when the CSI-RS period configured by the network device 102 changes, the historical data learned before the application scenario change, such as the accumulated CSI information associated with a certain CSI-RS period, may become unavailable, that is, the input of the model is unavailable. Therefore, it can be seen that it is necessary to optimize the method for predicting CSI based on the AI ​​model.

[0144] Figure 2a is an interactive diagram of a communication processing method according to an embodiment of the present disclosure. As shown in Figure 2a, the present disclosure embodiment relates to a communication processing method, the method comprising:

[0145] Step S2101 , the terminal 101 sends auxiliary information to the network device 102 .

[0146] In some embodiments, auxiliary information is used to indicate characteristics of the AI ​​model.

[0147] Optionally, the AI ​​model is a compression model based on SFT, and the auxiliary information is used to indicate the characteristics of the AI ​​model of the current application scenario. For example, the AI ​​model is a compression model suitable for the current application scenario, such as the current CSI-RS period.

[0148] Optionally, corresponding AI models can be deployed on terminal 101 and network device 102, respectively. For example, the encoding portion of the AI ​​model can be deployed on terminal 101, while the decoding portion of the AI ​​model can be deployed on network device 102. Both models will generate corresponding historical data. In the embodiments of this disclosure, the selection or management of the AI ​​model on terminal 101 is used as an example for explanation. The selection or management of the AI ​​model on network device 102 can refer to the description of the embodiments of this disclosure.

[0149] Optionally, the AI ​​model can be used in areas such as CSI compression, CSI time-domain prediction, beam prediction, and combined CSI time-domain prediction and compression. The disclosed embodiments use the AI ​​model for CSI compression as an example, but the methods described in the disclosed embodiments are applicable to other AI models, such as other AI models that use historical information. For example, historical information refers to historical CSI information, which can include historical feature vector information, historical channel feature information, historical channel matrix information, or historical beam RSRP information.

[0150] Optionally, the AI ​​model is a compression model based on SFT. For example, the input information of the AI ​​model includes the measured CSI corresponding to the current moment and the accumulated CSI information before the current moment. The measured CSI corresponding to the current moment can be obtained by the terminal 101 measuring the CSI-RS at the current moment; the accumulated CSI information includes multiple historical CSIs before the current moment, and each historical CSI can be obtained by measuring the CSI-RS at a moment or a time domain unit before the current moment. Therefore, the accumulated CSI information can also be called historical information or historical CSI information. Based on the input information, the AI ​​model can output compressed CSI.

[0151] Optionally, the characteristics of the AI ​​model may identify or specify the corresponding AI model, and may include relevant information of multiple AI models.

[0152] For example, the characteristics of an AI model may include: the identification (ID) of the AI ​​model or information used to determine the AI ​​model ID, the functional identification of the AI ​​model or information used to determine the function of the AI ​​model, the input information of the AI ​​model or information related to the input information, the output information of the AI ​​model or information related to the output information, etc.

[0153] Optionally, the characteristics of the AI ​​model are represented by condition information and / or additional condition information. For example, the auxiliary information is the condition information or additional condition information of the AI ​​model defined by the protocol.

[0154] The condition information is used to indicate information associated with the capability of the terminal 101 (associated with UE capability). The additional condition information is used to indicate information not associated with the capability of the terminal 101 (not associated with UE capability).

[0155] Optionally, in combination with the architecture shown in Figure 2c, for the standard-defined aspects (specified aspects) and non-standard-defined aspects (aspects not specified) of the AI ​​model, the characteristics of the model can be determined through condition information and additional condition information, and then the AI ​​model associated with the network configuration (associated with configuration) or the condition associated with the terminal capability and additional condition information (condition associated with UE capability and additional condition) can be determined.

[0156] In some embodiments, the terminal 101 may send auxiliary information to the network device 102 via first signaling.

[0157] Optionally, the auxiliary information may include auxiliary information for assisting the network side in performing AI operations.

[0158] In a first possible example, the terminal 101 sends capability information (UE capability report or UE capability information) to the network device 102 , where the capability information includes auxiliary information.

[0159] In this example, the auxiliary information may be reported together with other terminal capabilities to save signaling resources.

[0160] In this example, the auxiliary information may be model features related to terminal capabilities, that is, conditional information.

[0161] In a second possible example, the terminal 101 sends the auxiliary information according to the request information. For example, the network device 102 sends a request information (request) to the terminal 101, and the terminal 101 sends the auxiliary information to the network device 102 according to the request information.

[0162] In this example, the request information is used to request model information or features of the AI ​​model.

[0163] In this example, the network device 102 may configure or instruct the terminal 101 on the time-frequency resources corresponding to the sending of the auxiliary information through request information or configuration information sent separately.

[0164] In this example, after receiving the request information, the terminal 101 reports the auxiliary information corresponding to the request information on the time-frequency resources allocated by the network device 102 .

[0165] In some embodiments, the auxiliary information may indicate the characteristics of the AI ​​model through different contents.

[0166] In some embodiments, the auxiliary information includes at least one of the following:

[0167] Time-domain compression information during the AI ​​model training phase;

[0168] Time-domain compression information during the AI ​​model inference phase;

[0169] Among them, the AI ​​model is used for channel state information CSI compression.

[0170] Optionally, the time domain compression information in the training phase is the time domain compression information used when training the AI ​​model, and a corresponding AI model can be determined or located through this information.

[0171] Optionally, the time domain compression information in the inference stage, that is, the time domain compression information of the AI ​​model that can be used for inference when the AI ​​model is actually applied, can be used to determine or locate a corresponding AI model.

[0172] Optionally, terminals 101 with different capabilities may support multiple AI models. For example, terminals 101 with higher capabilities may support multiple types of AI models, and may support AI models with different functions or identifiers under a certain type.

[0173] For example, the AI ​​model type may include SFT-based compression or SF-based compression; the AI ​​model functions may include CSI compression, CSI time-domain prediction, and a combination of CSI time-domain prediction and compression. Alternatively, the AI ​​model can be further differentiated, such as an AI model associated with a specific CSI-RS period. By reporting auxiliary information, the terminal 101 can help the network device 102 obtain information about the selected SFT-based AI model, facilitating the network device 102 to perform corresponding operations based on the AI ​​model, such as performing corresponding configurations.

[0174] In some embodiments, the time domain compression information includes at least one of the following:

[0175] Compression quantity, which is used to indicate the quantity of historical CSI in the accumulated CSI information to be compressed;

[0176] Compression duration, which is used to indicate the time range of historical CSI in the compressed accumulated CSI information;

[0177] Among them, the input information of the AI ​​model is determined based on the accumulated CSI information.

[0178] Optionally, the time-domain compression information corresponding to different SFT-based AI models may be different, such as different compression amounts and / or different compression durations. Thus, the corresponding AI model can be located based on the compression amount and / or compression duration.

[0179] Optionally, the network device 102 can configure or indicate the period of CSI-RS corresponding to the compression amount and / or compression duration, so that the terminal 101 determines the compressed historical CSI based on the period of CSI-RS and the compression amount and / or compression duration.

[0180] For example, if auxiliary information is reported by terminal 101 to network device 102, network device 102 can configure or indicate the corresponding CSI-RS period based on the compression quantity and / or compression duration. For example, if the compression duration reported by terminal 101 is 100ms and the CSI-RS period configured by network device 102 is 20ms, terminal 101 can obtain five historical CSIs for compression within 100ms. This process improves the flexibility of network device 102 in configuring the period.

[0181] For another example, as described in step S2201 of the following embodiment, the auxiliary information is sent by the network device 102 to the terminal 101, then the network device 102 can also send the CSI-RS period corresponding to the compression number and / or compression duration, so that the terminal 101 obtains the historical CSI suitable for the current application scenario for compression according to the configuration and instructions of the network device 102.

[0182] Optionally, the CSI-RS period corresponding to the compression quantity and / or compression duration configured or indicated by the network device 102 is applicable to the current application scenario or the current time range. Alternatively, when the application scenario of the AI ​​model changes, the network device 102 needs to configure or indicate the CSI-RS period corresponding to the compression quantity and / or compression duration. Optionally, the CSI-RS period corresponding to the compression quantity and / or compression duration is different from the CSI-RS period before the application scenario changes.

[0183] In the first example, the auxiliary information includes the number of compressions during the AI ​​model training phase. The compression number represents the length of time-domain compression during the training phase. If the number of compressions is N, it indicates that during the AI ​​model training phase, the accumulated CSI information includes N historical CSI values; these N historical CSI values ​​are compressed, or the input information for the AI ​​model training phase is determined based on these N historical CSI values.

[0184] In the second example, the auxiliary information includes the compressed duration of the AI ​​model training phase. The compressed duration represents the time domain compression length of the training phase. If the compressed duration is X milliseconds (ms), it means that during the AI ​​model training phase, the accumulated CSI information includes historical CSI within Xms; the CSI within this historical Xms is compressed, or the input information for the AI ​​model training phase is determined based on the CSI value within this historical Xms.

[0185] In a third example, the auxiliary information includes the compression count for the AI ​​model's inference phase. The compression count represents the time-domain compression length that the AI ​​model can apply to inference, or the time-domain compression length that the AI ​​model recommends for inference. If the compression count is N, it indicates that N historical CSI values ​​are compressed, or that the input information for the AI ​​model's inference phase is determined based on these N historical CSI values.

[0186] In a fourth example, the auxiliary information includes the compressed duration of the AI ​​model's inference phase. The compressed duration represents the time-domain compression length that the AI ​​model can apply to inference, or the time-domain compression length recommended by the AI ​​model for inference. If the compressed duration is Xms, this indicates that the CSI values ​​within the past Xms are compressed, or that the input information for the AI ​​model's inference phase is determined based on the CSI values ​​within the past Xms.

[0187] Optionally, the compression quantity or compression duration satisfies one of the following:

[0188] There is at least one candidate value defined by the configuration or protocol;

[0189] There are candidate ranges that are configured or defined by the protocol.

[0190] Optionally, the compression amount or compression duration is configured or defined with a candidate value.

[0191] Optionally, the compression quantity or compression duration is configured or defined with multiple candidate values. For example, the compression quantity satisfies {5, 10, 20}, that is, the compression quantity supports 5, 10, or 20.

[0192] Optionally, the compression amount or compression duration is configured or defined with a candidate range. For example, the compression amount or compression duration satisfies {infinite}, where infinite indicates that the AI ​​model supports time domain compression lengths of any length. For another example, the compression amount or compression duration satisfies [5, 100], indicating that the AI ​​model supports time domain compression lengths of any value from 5 to 100.

[0193] In some embodiments, network device 102 receives the assistance information.

[0194] Step S2102: Determine the AI ​​model used for the reasoning stage based on the auxiliary information.

[0195] Optionally, the terminal 101 may select an AI model to be applied from multiple models on the terminal 101 side, and report it to the network device 102 through auxiliary information so that the network device 102 knows the AI ​​model selected by the terminal 101.

[0196] Optionally, the network device 102 instructs the terminal 101 to select an AI model to be applied from multiple models on the terminal 101 side through auxiliary information.

[0197] Optionally, the network device 102 may select an AI model to be applied from a plurality of models on the network device 102 side, and inform the terminal 101 of the AI ​​model selected by the network device 102 through auxiliary information.

[0198] Optionally, in combination with the description of the foregoing embodiments, the AI ​​model may be of multiple types or used to implement different functions, and the terminal 101 or the network device 102 may select an AI model of a type or a function corresponding to the auxiliary information.

[0199] Optionally, the AI ​​model used in the inference phase includes the AI ​​model used in the inference phase and the AI ​​model refined for use in the inference phase. It is understood that the AI ​​model used in the inference phase can be understood as an AI model that is actually applied, i.e., the AI ​​model is actually applied to obtain the desired output result.

[0200] In some embodiments, when the terminal 101 supports an AI model, the auxiliary information reported by it can help the network device 102 determine the characteristics or information of the AI ​​model used or to be used by the terminal 101.

[0201] In some embodiments, when the terminal 101 supports multiple AI models, the auxiliary information reported by it can help the network device 102 determine the AI ​​model used or to be used by the terminal 101.

[0202] In some embodiments, terminal 101 and network device 102 can determine the same AI model based on auxiliary information. Thus, terminal 101 and network device 102 have a consistent understanding of the AI ​​model used in the current application scenario, facilitating communication between the two using the AI ​​model. For example, network device 102 can determine relevant information about the AI ​​model used or to be used by terminal 101 based on auxiliary information, facilitating network device 102 and terminal 101 to determine the same model, and network device 102 can better perform AI operations based on this auxiliary information.

[0203] Optionally, the AI ​​operation performed by the network device 102 may include managing the AI ​​model, including, for example, performing corresponding configuration according to the characteristics of the AI ​​model, selecting an appropriate AI model to activate, selecting an appropriate AI model to deactivate, selecting an appropriate AI model to update, etc.

[0204] In some embodiments, the names of information, etc. are not limited to the names described in the embodiments, and terms such as "information", "message", "signal", "signaling", "report", "configuration", "indication", "instruction", "command", "channel", "parameter", "domain", and "field" can be used interchangeably.

[0205] In some embodiments, "obtain", "get", "get", "receive", "transmit", "bidirectional transmission", "send and / or receive" can be interchangeable, and can be interpreted as receiving from other entities, obtaining from protocols, obtaining from higher layers, obtaining by self-processing, autonomous implementation, etc.

[0206] In some embodiments, terms such as "send", "transmit", "report", "download", "transmit", "bidirectional transmission", "send and / or receive" can be used interchangeably.

[0207] In some embodiments, the terms "radio", "wireless", "radio access network (RAN)", "access network (AN)", "RAN-based" and the like may be used interchangeably.

[0208] In some embodiments, terms such as "moment", "time point", "time", and "time position" can be replaced with each other, and terms such as "duration", "period", "time window", "window", and "time" can be replaced with each other.

[0209] In some embodiments, the terms "component carrier (CC)", "cell", "frequency carrier", "carrier frequency" and the like can be used interchangeably.

[0210] In some embodiments, terms such as "certain", "preset", "preset", "setting", "indicated", "a certain", "any", and "first" can be interchangeable. "Specific A", "preset A", "preset A", "setting A", "indicated A", "a certain A", "any A", and "first A" can be interpreted as A pre-specified in a protocol, etc., or as A obtained through setting, configuration, or indication, etc., or as specific A, a certain A, any A, or first A, etc., but not limited to this.

[0211] In some embodiments, the determination or judgment can be performed by a value represented by 1 bit (0 or 1), or by a true or false value (Boolean value) represented by true or false, or by comparison of numerical values ​​(for example, comparison with a predetermined value), but is not limited thereto.

[0212] In some embodiments, "not expecting to receive" can be interpreted as not receiving on time domain resources and / or frequency domain resources, or as not performing subsequent processing on the data after receiving it; "not expecting to send" can be interpreted as not sending, or as sending but not expecting the recipient to respond to the content sent.

[0213] The method involved in the embodiment of the present disclosure may include at least one of steps S2101 to S2102; for example, the method includes step S2102.

[0214] In some embodiments, reference may be made to other optional implementations described before or after the description corresponding to FIG. 2 a .

[0215] FIG2b is an interactive diagram of a communication processing method according to an embodiment of the present disclosure. As shown in FIG2b, an embodiment of the present disclosure relates to a communication processing method, the method comprising:

[0216] Step S2201 : The network device 102 sends auxiliary information to the terminal 101 .

[0217] In some embodiments, the content of the auxiliary information or the optional implementation of the auxiliary information, as well as the relevant description of the AI ​​model, can be found in the relevant implementation of step S2102 and will not be repeated here.

[0218] In some embodiments, the network device 102 may send the auxiliary information to the terminal 101 via a second signaling.

[0219] Optionally, the auxiliary information may include auxiliary information for assisting the terminal side in performing AI operations.

[0220] Optionally, the network device 102 sends configuration information of the AI ​​model to the terminal 101, where the configuration information includes auxiliary information.

[0221] Optionally, the configuration information of the AI ​​model can be used to configure various parameters or information of the AI ​​model, and auxiliary information is sent synchronously in the configuration information, which is conducive to saving signaling resources.

[0222] Optionally, the configuration information may be sent via Radio Resource Control (RRC) signaling.

[0223] In some embodiments, terminal 101 receives the assistance information.

[0224] Step S2202: Determine the AI ​​model used for the reasoning stage based on the auxiliary information.

[0225] In some embodiments, optional implementations of step S2202 can refer to the relevant implementations of step S2102 and will not be repeated here.

[0226] In some embodiments, the auxiliary information sent by the network device 102 can be used to assist the terminal 101 in performing AI operations.

[0227] For example, the terminal 101 can support one or more AI models. After receiving the auxiliary information sent by the network device 102, the terminal 101 can select an AI model with features corresponding to the symbol auxiliary information, and perform inference based on the selected AI model to obtain an output result.

[0228] The method involved in the embodiment of the present disclosure may include at least one of steps S2201 to S2202; for example, the method includes step S2202.

[0229] In some embodiments, reference may be made to other optional implementations described before or after the description corresponding to FIG. 2 b .

[0230] FIG3a is a flow chart of a communication processing method according to an embodiment of the present disclosure. As shown in FIG3a, the present disclosure embodiment relates to a communication processing method, which is executed by terminal 101 and includes:

[0231] Step S3101: Send capability information.

[0232] Optionally, the capability information includes auxiliary information.

[0233] Optionally, the implementation of step S3101 can refer to the relevant implementation of step S2101 and will not be repeated here.

[0234] Step S3102: Determine the AI ​​model used for the reasoning stage based on the auxiliary information.

[0235] Optionally, the implementation of step S3102 may refer to the relevant implementation of step S2102 and will not be repeated here.

[0236] In some embodiments, reference may be made to other optional implementations described before or after the description corresponding to FIG. 3 a .

[0237] FIG3b is a flow chart of a communication processing method according to an embodiment of the present disclosure. As shown in FIG3b, the present disclosure embodiment relates to a communication processing method, which is executed by terminal 101 and includes:

[0238] Step S3201, receiving request information.

[0239] Optionally, the implementation of step S3201 can refer to the relevant implementation of step S2101 and will not be repeated here.

[0240] Step S3202: Send auxiliary information.

[0241] Optionally, the implementation of step S3202 may refer to the relevant implementation of step S2101 and will not be repeated here.

[0242] Step S3203: Determine the AI ​​model used for the reasoning stage based on the auxiliary information.

[0243] Optionally, the implementation of step S3203 may refer to the relevant implementation of step S2102 and will not be repeated here.

[0244] In some embodiments, reference may be made to other optional implementations described before or after the description corresponding to FIG. 3 b .

[0245] FIG3c is a flow chart of a communication processing method according to an embodiment of the present disclosure. As shown in FIG3c, the present disclosure embodiment relates to a communication processing method, which is executed by terminal 101 and includes:

[0246] Step S3301, receiving auxiliary information.

[0247] Optionally, the implementation of step S3301 can refer to the relevant implementation of step S2201 and will not be repeated here.

[0248] Step S3302: Determine the AI ​​model used for the reasoning stage based on the auxiliary information.

[0249] Optionally, the implementation of step S3302 may refer to the relevant implementation of step S2202 and will not be repeated here.

[0250] In some embodiments, reference may be made to other optional implementations described before or after the description corresponding to FIG. 3c.

[0251] FIG3 d is a flow chart of a communication processing method according to an embodiment of the present disclosure. As shown in FIG3 d , the present disclosure embodiment relates to a communication processing method, which is executed by terminal 101 and includes:

[0252] Step S3401: Determine the AI ​​model used for the reasoning stage based on the auxiliary information.

[0253] Optionally, the implementation of step S3401 may refer to the relevant implementation of steps S2101 to S2102 or S2101 to S2202, which will not be repeated here.

[0254] In some embodiments, reference may be made to other optional implementations described before or after the description corresponding to FIG. 3 d .

[0255] FIG4a is a flow chart of a communication processing method according to an embodiment of the present disclosure. As shown in FIG4a, the present disclosure embodiment relates to a communication processing method, which is executed by the network device 102 and includes:

[0256] Step S4101: receiving capability information.

[0257] Optionally, the implementation of step S4101 can refer to the relevant implementation of step S2101 and will not be repeated here.

[0258] Step S4102: Determine the AI ​​model used for the reasoning stage based on the auxiliary information.

[0259] Optionally, the implementation of step S4102 can refer to the relevant implementation of step S2102, which will not be repeated here.

[0260] In some embodiments, reference may be made to other optional implementations described before or after the description corresponding to FIG. 4 a .

[0261] FIG4b is a flow chart of a communication processing method according to an embodiment of the present disclosure. As shown in FIG4b, the present disclosure embodiment relates to a communication processing method, which is executed by the network device 102 and includes:

[0262] Step S4201, sending request information.

[0263] Optionally, the implementation of step S4201 can refer to the relevant implementation of step S2101 and will not be repeated here.

[0264] Step S4202, receiving auxiliary information.

[0265] Optionally, the implementation of step S4202 can refer to the relevant implementation of step S2101 and will not be repeated here.

[0266] Step S4203: Determine the AI ​​model used for the reasoning stage based on the auxiliary information.

[0267] Optionally, the implementation of step S4203 may refer to the relevant implementation of step S2102 and will not be repeated here.

[0268] In some embodiments, reference may be made to other optional implementations described before or after the description corresponding to FIG. 4 b .

[0269] FIG4c is a flow chart of a communication processing method according to an embodiment of the present disclosure. As shown in FIG4c, the present disclosure embodiment relates to a communication processing method, which is executed by the network device 102 and includes:

[0270] Step S4301: Send auxiliary information.

[0271] Optionally, the implementation of step S4301 can refer to the relevant implementation of step S2201 and will not be repeated here.

[0272] Step S4302: Determine the AI ​​model used for the reasoning stage based on the auxiliary information.

[0273] Optionally, the implementation of step S4302 may refer to the relevant implementation of step S2202 and will not be repeated here.

[0274] In some embodiments, reference may be made to other optional implementations described before or after the description corresponding to FIG. 4c.

[0275] FIG4d is a flow chart of a communication processing method according to an embodiment of the present disclosure. As shown in FIG4d, the embodiment of the present disclosure relates to a communication processing method, which is executed by the network device 102 and includes:

[0276] Step S4401: Determine the AI ​​model used for the reasoning stage based on the auxiliary information.

[0277] Optionally, the implementation of step S4401 may refer to the relevant implementation of steps S2101 to S2102 or S2101 to S2202, which will not be repeated here.

[0278] In some embodiments, reference may be made to other optional implementations described before or after the description corresponding to FIG. 4 d .

[0279] In the methods of the embodiments of the present disclosure, different model characteristics are provided for different types of models, that is, different conditions and additional conditions are provided. Unlike the SF model, the SFT model introduces time domain compression information, so more information is required to determine the model, or in other words, more information is needed to help the network or UE understand the model. To facilitate understanding of the embodiments of the present disclosure, some examples are listed below:

[0280] Example 1:

[0281] This example provides a method for assisting a network or terminal to perform AI operations, including a first signaling exchanged between the terminal and the network, where the first signaling includes auxiliary information for assisting the network side or the terminal side to perform AI operations.

[0282] Optionally, the first signaling may correspond to the capability information or configuration information of the aforementioned embodiment.

[0283] Optionally, the auxiliary information may be the condition of the model or additional condition information, which is used to describe the characteristics of the SFT model.

[0284] Example 2:

[0285] Based on Example 1, the auxiliary information includes at least one of the following information:

[0286] Time domain compression length information used during training;

[0287] In one embodiment: the length is N, indicating that N historical CSI values ​​are compressed;

[0288] In one embodiment, the length is X ms, indicating that the historical CSI values ​​of X ms are compressed.

[0289] The model can be applied to the time-domain compressed length information of the inference, or the time-domain compressed length information of the inference suggested by the model;

[0290] In one embodiment: the length is N, indicating that N historical CSI values ​​are compressed;

[0291] In one embodiment, the length is X ms, indicating that the historical CSI values ​​of X ms are compressed.

[0292] Optionally, the time domain compression length information may be a single value, multiple values, or a range. For example, refer to the following embodiments:

[0293] Example 1: The time domain compression length is {5, 10, 20};

[0294] Example 2: The time domain compression length is {infinite}, where infinite indicates that the value can be any length value;

[0295] Example 3: The time domain compression length is [5,100], which means that the model supports any value of the time domain compression length from 5 to 100.

[0296] Example 3:

[0297] Based on Example 1 or Example 2, the auxiliary information is sent by the terminal to the network.

[0298] In one embodiment, the auxiliary information is reported via UE capability and is included in a UE capability report.

[0299] In one embodiment, the auxiliary information is reported when the base station sends a request for model information, and is reported on the time-frequency resources allocated by the base station.

[0300] Example 4:

[0301] Based on Example 1 or Example 2, the auxiliary information is sent by the network to the terminal.

[0302] In one embodiment, the auxiliary information is sent in the configuration information related to the base station sending model to assist the UE in selecting a UE-side model that meets the characteristics.

[0303] The embodiments of the present disclosure further provide an apparatus for implementing any of the above methods. For example, an apparatus is provided, comprising units or modules for implementing each step performed by a terminal in any of the above methods. For another example, another apparatus is provided, comprising units or modules for implementing each step performed by a network device (e.g., an access network device, a core network function node, a core network device, etc.) in any of the above methods.

[0304] It should be understood that the division of the various units or modules in the above device is merely a division of logical functions. In actual implementation, they may be fully or partially integrated into a physical entity, or they may be physically separated. In addition, the units or modules in the device may be implemented in the form of a processor calling software: for example, the device includes a processor, the processor is connected to a memory, and the memory stores instructions. The processor calls the instructions stored in the memory to implement any of the above methods or implement the functions of the various units or modules of the above device, wherein the processor is, for example, a general-purpose processor, such as a central processing unit (CPU) or a microprocessor, and the memory is a memory within the device or a memory outside the device. Alternatively, the units or modules in the device can be implemented in the form of hardware circuits, and the functions of some or all of the units or modules can be realized by designing the hardware circuits. The above-mentioned hardware circuits can be understood as one or more processors; for example, in one implementation, the above-mentioned hardware circuit is an application-specific integrated circuit (ASIC), which realizes the functions of some or all of the above units or modules by designing the logical relationship of the components in the circuit; for example, in another implementation, the above-mentioned hardware circuit can be realized by a programmable logic device (PLD). Taking a field programmable gate array (FPGA) as an example, it can include a large number of logic gate circuits, and the connection relationship between the logic gate circuits is configured by configuring the configuration file, thereby realizing the functions of some or all of the above units or modules. All units or modules of the above devices can be realized in the form of software called by the processor, or in the form of hardware circuits, or in part by the form of software called by the processor, and the rest by hardware circuits.

[0305] In the embodiments of the present disclosure, the processor is a circuit with signal processing capabilities. In one implementation, the processor can be a circuit with instruction reading and execution capabilities, such as a central processing unit (CPU), a microprocessor, a graphics processing unit (GPU) (which can be understood as a microprocessor), or a digital signal processor (DSP). In another implementation, the processor can implement certain functions through the logical relationship of the hardware circuit. The logical relationship of the above-mentioned hardware circuit is fixed or reconfigurable. For example, the processor is a hardware circuit implemented by an application-specific integrated circuit (ASIC) or a programmable logic device (PLD), such as an FPGA. In a reconfigurable hardware circuit, the process of the processor loading a configuration document and implementing the hardware circuit configuration can be understood as the process of the processor loading instructions to implement the functions of some or all of the above units or modules. In addition, it can also be a hardware circuit designed for artificial intelligence, which can be understood as an ASIC, such as a neural network processing unit (NPU), a tensor processing unit (TPU), a deep learning processing unit (DPU), etc.

[0306] Figure 5a is a schematic diagram of the structure of a terminal proposed in an embodiment of the present disclosure. As shown in Figure 5a, terminal 5100 may include at least one of a transceiver module 5101 and a processing module 5102. In some embodiments, transceiver module 5101 is configured to determine an AI model for inference based on auxiliary information, where the auxiliary information indicates characteristics of the AI ​​model.

[0307] Figure 5b is a schematic diagram of the terminal structure proposed in an embodiment of the present disclosure. As shown in Figure 5b, network device 5200 may include at least one of a transceiver module 5201 and a processing module 5202. In some embodiments, transceiver module 5201 is configured to determine an AI model for inference based on auxiliary information, where the auxiliary information indicates characteristics of the AI ​​model.

[0308] Optionally, the transceiver module 5201 is configured to execute at least one of the communication steps of sending and / or receiving performed by the network device 102 in any of the above methods, which are not described in detail here. Optionally, the processing module 5202 is configured to execute at least one of the other steps performed by the network device 102 in any of the above methods, which are not described in detail here.

[0309] In some embodiments, the transceiver module may include a transmitting module and / or a receiving module, and the transmitting module and the receiving module may be separate or integrated. Optionally, the transceiver module may be interchangeable with the transceiver.

[0310] In some embodiments, the processing module can be a single module or can include multiple submodules. Optionally, the multiple submodules respectively execute all or part of the steps required to be executed by the processing module. Optionally, the processing module can be interchangeable with the processor.

[0311] Figure 6a is a schematic diagram of the structure of a communication device 6100 proposed in an embodiment of the present disclosure. Communication device 6100 can be a network device (e.g., an access network device, a core network device, etc.), a terminal (e.g., a user equipment, etc.), a chip, a chip system, or a processor that supports a network device implementing any of the above methods, or a chip, a chip system, or a processor that supports a terminal implementing any of the above methods. Communication device 6100 can be used to implement the methods described in the above method embodiments. For details, please refer to the description of the above method embodiments.

[0312] As shown in Figure 6a, the communication device 6100 includes one or more processors 6101. The processor 6101 can be a general-purpose processor or a dedicated processor, for example, a baseband processor or a central processing unit. The baseband processor can be used to process the communication protocol and communication data, and the central processing unit can be used to control the communication device (such as a base station, a baseband chip, a terminal device, a terminal device chip, a DU or a CU, etc.), execute programs, and process program data. Optionally, the communication device 6100 is used to perform any of the above methods. Optionally, one or more processors 6101 are used to call instructions to enable the communication device 6100 to perform any of the above methods.

[0313] In some embodiments, the communication device 6100 further includes one or more transceivers 6102. When the communication device 6100 includes one or more transceivers 6102, the transceiver 6102 performs at least one of the communication steps, such as sending and / or receiving, in the above-described method, and the processor 6101 performs at least one of the other steps. In an optional embodiment, the transceiver may include a receiver and / or a transmitter, and the receiver and transmitter may be separate or integrated. Optionally, the terms transceiver, transceiver unit, transceiver, transceiver circuit, interface circuit, and interface may be used interchangeably; the terms transmitter, transmitting unit, transmitter, and transmitting circuit may be used interchangeably; and the terms receiver, receiving unit, receiver, and receiving circuit may be used interchangeably.

[0314] In some embodiments, the communication device 6100 further includes one or more memories 6103 for storing data. Alternatively, all or part of the memories 6103 may be located outside the communication device 6100. In alternative embodiments, the communication device 6100 may include one or more interface circuits 6104. Optionally, the interface circuits 6104 are connected to the memories 6103 and may be configured to receive data from the memories 6103 or other devices, or to send data to the memories 6103 or other devices. For example, the interface circuits 6104 may read data stored in the memories 6103 and send the data to the processor 6101.

[0315] The communication device 6100 described in the above embodiment may be a network device or a terminal, but the scope of the communication device 6100 described in the present disclosure is not limited thereto, and the structure of the communication device 6100 may not be limited by FIG. 6a. The communication device may be an independent device or may be part of a larger device. For example, the communication device may be: 1) an independent integrated circuit IC, or a chip, or a chip system or subsystem; (2) a collection of one or more ICs, optionally, the above IC collection may also include a storage component for storing data or programs; (3) an ASIC, such as a modem; (4) a module that can be embedded in other devices; (5) a receiver, a terminal device, an intelligent terminal device, a cellular phone, a wireless device, a handheld device, a mobile unit, an in-vehicle device, a network device, a cloud device, an artificial intelligence device, etc.; (6) others, etc.

[0316] FIG6b is a schematic diagram of the structure of a chip 6200 according to an embodiment of the present disclosure. If the communication device 6100 can be a chip or a chip system, reference can be made to the schematic diagram of the structure of the chip 6200 shown in FIG6b , but the present disclosure is not limited thereto.

[0317] The chip 6200 includes one or more processors 6201. The chip 6200 is configured to execute any of the above methods.

[0318] In some embodiments, chip 6200 further includes one or more interface circuits 6202. Terms such as interface circuit, interface, and transceiver pins may be used interchangeably. In some embodiments, chip 6200 further includes one or more memories 6203 for storing data. Alternatively, all or part of memory 6203 may be located external to chip 6200. Optionally, interface circuit 6202 is connected to memory 6203 and may be used to receive data from memory 6203 or other devices, or may be used to send data to memory 6203 or other devices. For example, interface circuit 6202 may read data stored in memory 6203 and send the data to processor 6201.

[0319] In some embodiments, the interface circuit 6202 performs at least one of the communication steps, such as sending and / or receiving, in the above-described method. For example, the interface circuit 6202 performing the communication steps, such as sending and / or receiving, in the above-described method means that the interface circuit 6202 performs data exchange between the processor 6201, the chip 6200, the memory 6203, or the transceiver device. In some embodiments, the processor 6201 performs at least one of the other steps.

[0320] The modules and / or devices described in various embodiments, such as virtual devices, physical devices, and chips, can be arbitrarily combined or separated according to circumstances. Optionally, some or all steps can also be performed collaboratively by multiple modules and / or devices, which is not limited here.

[0321] The present disclosure also proposes a storage medium having instructions stored thereon. When the instructions are executed on the communication device 6100, the communication device 6100 executes any of the above methods. Optionally, the storage medium is an electronic storage medium. Optionally, the storage medium is a computer-readable storage medium, but is not limited thereto and may also be a storage medium readable by other devices. Optionally, the storage medium may be a non-transitory storage medium, but is not limited thereto and may also be a transient storage medium.

[0322] The present disclosure also provides a program product, which, when executed by the communication device 6100, enables the communication device 6100 to perform any of the above methods. Optionally, the program product is a computer program product.

[0323] The present disclosure also proposes a computer program, which, when executed on a computer, causes the computer to perform any one of the above methods. Industrial Applicability

[0324] Based on the auxiliary information, the terminal can obtain the characteristics of the AI ​​model applicable to the current application scenario (for example, matching the current CSI-RS period). Therefore, when the application scenario of the model changes, the terminal can select or determine the appropriate AI model for the reasoning stage based on the auxiliary information, effectively apply the current application scenario such as the current CSI-RS period, and thus improve the accuracy of the application model.

Claims

1. A communication processing method, executed by a terminal, comprising: An artificial intelligence (AI) model to be used in the inference phase is determined based on the auxiliary information, wherein the auxiliary information is used to indicate characteristics of the AI ​​model.

2. The method according to claim 1, wherein The method further comprises: Receive configuration information of the AI ​​model sent by a network device, where the configuration information includes the auxiliary information.

3. The method according to claim 1, wherein The method further comprises: Capability information is sent to the network device, where the capability information includes the auxiliary information.

4. The method according to claim 1, wherein The method further comprises: Receive request information sent by the network device; The auxiliary information is sent to the network device according to the request information.

5. The method according to any one of claims 1 to 4, wherein: The auxiliary information includes at least one of the following: Time-domain compression information during the AI ​​model training phase; Time-domain compression information during the AI ​​model inference phase; The AI ​​model is used for channel state information (CSI) compression.

6. The method according to claim 5, wherein: The time domain compression information includes at least one of the following: A compression quantity, where the compression quantity is used to indicate the quantity of historical CSI in the accumulated CSI information to be compressed; Compression duration, where the compression duration is used to indicate a time range of historical CSI in the compressed accumulated CSI information; The input information of the AI ​​model is determined based on the accumulated CSI information.

7. The method according to claim 6, wherein: The compression quantity or the compression duration satisfies one of the following: There is at least one candidate value defined by the configuration or protocol; There are candidate ranges that are configured or defined by the protocol.

8. The method according to any one of claims 1 to 7, wherein: The auxiliary information is the condition information and / or additional condition information of the AI ​​model defined by the protocol.

9. The method according to any one of claims 1 to 7, wherein: The AI ​​model is a compression model based on spatial domain information, time domain information and frequency domain information SFT.

10. A communication processing method, performed by a network device, the method comprising: An AI model for the inference phase is determined based on the auxiliary information, where the auxiliary information is used to indicate characteristics of the AI ​​model.

11. The method according to claim 10, wherein: The method further comprises: Send configuration information of the AI ​​model to the terminal, where the configuration information includes the auxiliary information.

12. The method of claim 10, wherein: The method further comprises: Capability information sent by a terminal is received, where the capability information includes the auxiliary information.

13. The method of claim 10, wherein: The method further comprises: Send request information to the terminal; The auxiliary information corresponding to the request information is received and sent by the terminal.

14. The method according to any one of claims 10 to 13, wherein: The auxiliary information includes at least one of the following: Time-domain compression information during the AI ​​model training phase; Time-domain compression information during the AI ​​model inference phase; The AI ​​model is used for CSI compression.

15. The method of claim 14, wherein: The time domain compression information includes at least one of the following: A compression quantity, where the compression quantity is used to indicate the quantity of historical CSI in the accumulated CSI information to be compressed; Compression duration, where the compression duration is used to indicate a time range of historical CSI in the compressed accumulated CSI information; The input information of the AI ​​model is determined based on the accumulated CSI information.

16. The method of claim 15, wherein: The compression quantity or the compression duration satisfies one of the following: There is at least one candidate value defined by the configuration or protocol; There are candidate ranges that are configured or defined by the protocol.

17. The method according to any one of claims 10 to 16, wherein: The auxiliary information is the condition information and / or additional condition information of the AI ​​model defined by the protocol.

18. The method according to any one of claims 10 to 16, wherein: The AI ​​model is a compression model based on spatial domain information, time domain information and frequency domain information SFT.

19. A terminal comprising: A processing module is used to determine an AI model for the reasoning stage based on auxiliary information, where the auxiliary information is used to indicate characteristics of the AI ​​model.

20. A network device comprising: A processing module is used to determine an AI model for the reasoning stage based on auxiliary information, where the auxiliary information is used to indicate characteristics of the AI ​​model.

21. A terminal comprising: one or more processors; The terminal is configured to implement the method according to any one of claims 1 to 9.

22. A network device comprising: one or more processors; The network device is configured to implement the method according to any one of claims 10 to 18.

23. A communication system comprising a terminal and a network device, wherein: The terminal is configured to implement the method according to any one of claims 1 to 9; The network device is configured to implement the method according to any one of claims 10 to 18.

24. A storage medium storing instructions, wherein: When the instruction is executed on a communication device, the communication device is caused to perform the method according to any one of claims 1 to 9 or any one of claims 10 to 18.

25. A program product, wherein When the program product is executed by a communication device, the communication device is caused to execute the method according to any one of claims 1 to 9 or any one of claims 10 to 18.

Images