Information transmission method and apparatus, and communication device, communication system and storage medium

Abstract

Provided in the embodiments of the present disclosure are an information transmission method and apparatus, and a communication device, a communication system and a storage medium. The method comprises: a terminal sending first information, which is used for determining a target model which is used for compressing and transmitting channel state information (CSI), wherein the model comprises at least one of a first model and a second model, the first model being located in the terminal and being used for compressing CSI, the second model being located in a network-device end and being used for decompressing the compressed CSI, and the first model corresponding to the second model.

Description

Information transmission method and device, communication equipment, communication system and storage medium Technical Field

[0001] The present disclosure relates to the field of communication technologies, and in particular to information transmission methods and devices, communication equipment, communication systems, and storage media. Background Art

[0002] In a mobile communication system, a network device sends a downlink reference signal to a terminal. The terminal receives the downlink reference signal, measures the downlink reference signal, and reports the measured channel state information (CSI) to the network device. CSI can be compressed to reduce CSI feedback overhead.

[0003] Summary of the Invention

[0004] As the functionality of terminals increases, their energy consumption increases, resulting in weak battery life.

[0005] Embodiments of the present disclosure provide an information transmission method and apparatus, a communication device, and a storage medium.

[0006] According to a first aspect of an embodiment of the present disclosure, an information transmission method is provided, which is performed by a terminal. The method includes:

[0007] The terminal sends first information, where the first information is used to determine a target model for compressing and transmitting channel state information CSI, where the model includes at least one of a first model and a second model;

[0008] The first model is located at the terminal and is used to compress the CSI, and the second model is located at the network device and is used to decompress the compressed CSI;

[0009] The first model corresponds to the second model.

[0010] According to a second aspect of an embodiment of the present disclosure, an information transmission method is provided, wherein the method includes:

[0011] The network device receives first information, where the first information is used to determine a target model for compressing and transmitting channel state information (CSI), where the model includes at least one of a first model and a second model.

[0012] The first model is located at the terminal and is used to compress the CSI, and the second model is located at the network device and is used to decompress the compressed CSI;

[0013] The first model corresponds to the second model.

[0014] According to a third aspect of an embodiment of the present disclosure, an information transmission method is provided, which is performed by a communication system. The method includes:

[0015] The terminal sends first information to the network device, where the first information is used to determine a target model for compressing and transmitting channel state information CSI, where the model includes at least one of a first model and a second model;

[0016] The first model is located at the terminal and is used to compress the CSI, and the second model is located at the network device and is used to decompress the compressed CSI;

[0017] The first model corresponds to the second model.

[0018] According to a fourth aspect of an embodiment of the present disclosure, an embodiment of the present disclosure provides a terminal, wherein the terminal includes:

[0019] a transceiver module configured to send first information, where the first information is used to determine a target model for compressing and transmitting channel state information (CSI), the model including at least one of a first model and a second model;

[0020] The first model is located at the terminal and is used to compress the CSI, and the second model is located at the network device and is used to decompress the compressed CSI;

[0021] The first model corresponds to the second model.

[0022] According to a fifth aspect of an embodiment of the present disclosure, an embodiment of the present disclosure provides a network device, wherein the network device includes:

[0023] a transceiver module configured to receive first information, where the first information is used to determine a target model for compressing and transmitting channel state information (CSI), the model including at least one of a first model and a second model;

[0024] The first model is located at the terminal and is used to compress the CSI, and the second model is located at the network device and is used to decompress the compressed CSI;

[0025] The first model corresponds to the second model.

[0026] According to a sixth aspect of the embodiments of the present disclosure, the embodiments of the present disclosure provide a communication system, wherein the communication system includes: a terminal and a network device; wherein,

[0027] The terminal is configured to implement the information transmission method according to the first aspect;

[0028] The network device is configured to implement the information transmission method described in the second aspect.

[0029] According to a seventh aspect of an embodiment of the present disclosure, an embodiment of the present disclosure provides a communication device, wherein the communication device includes:

[0030] one or more processors;

[0031] The processor is used to call instructions to enable the communication device to execute the information transmission method described in the first aspect or the second aspect.

[0032] According to the eighth aspect of the embodiment of the present disclosure, the embodiment of the present disclosure proposes a storage medium, wherein the storage medium stores instructions, and when the instructions are executed on a communication device, the communication device executes the information transmission method described in the first aspect or the second aspect.

[0033] By determining the target model through the first information, the terminal and the network device can reach a consensus on the target model, thereby increasing the probability that the terminal and the network device can obtain mutually related models.

[0034] It should be understood that the foregoing general description and the following detailed description are merely exemplary and explanatory and are not restrictive of the embodiments of the present disclosure. BRIEF DESCRIPTION OF THE DRAWINGS

[0035] The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the present invention and, together with the description, serve to explain the principles of the embodiments of the present invention.

[0036] FIG1a is a schematic diagram showing an architecture of a communication system according to an exemplary embodiment;

[0037] FIG1b is a schematic diagram showing model compression and decompression according to an exemplary embodiment;

[0038] FIG2a is a schematic flow chart showing an information transmission method according to an exemplary embodiment;

[0039] FIG2 b is a schematic flow chart showing an information transmission method according to an exemplary embodiment;

[0040] FIG2c is a schematic flow chart showing an information transmission method according to an exemplary embodiment;

[0041] FIG2 d is a schematic flow chart showing an information transmission method according to an exemplary embodiment;

[0042] FIG2e is a schematic flow chart showing an information transmission method according to an exemplary embodiment;

[0043] FIG3a is a schematic flow chart showing an information transmission method according to an exemplary embodiment;

[0044] FIG3 b is a schematic flow chart showing an information transmission method according to an exemplary embodiment;

[0045] FIG3c is a schematic flow chart showing an information transmission method according to an exemplary embodiment;

[0046] FIG3 d is a schematic flow chart showing an information transmission method according to an exemplary embodiment;

[0047] FIG3e is a schematic flow chart showing an information transmission method according to an exemplary embodiment;

[0048] FIG3 f is a schematic flow chart showing an information transmission method according to an exemplary embodiment;

[0049] FIG4a is a schematic flow chart showing an information transmission method according to an exemplary embodiment;

[0050] FIG4 b is a schematic flow chart showing an information transmission method according to an exemplary embodiment;

[0051] FIG4c is a schematic flow chart showing an information transmission method according to an exemplary embodiment;

[0052] FIG4 d is a schematic flow chart showing an information transmission method according to an exemplary embodiment;

[0053] FIG4e is a schematic flow chart showing an information transmission method according to an exemplary embodiment;

[0054] FIG5 is a schematic flow chart showing an information transmission method according to an exemplary embodiment;

[0055] FIG6 is a schematic flow chart showing an information transmission method according to an exemplary embodiment;

[0056] FIG7a is a schematic structural diagram of a network device according to an exemplary embodiment;

[0057] FIG7b is a schematic diagram showing a terminal structure according to an exemplary embodiment;

[0058] FIG8a is a schematic structural diagram of a UE according to an exemplary embodiment;

[0059] Fig. 8b is a schematic structural diagram of a communication device according to an exemplary embodiment. DETAILED DESCRIPTION

[0060] Embodiments of the present disclosure provide an information transmission method and apparatus, a communication device, a communication system, and a storage medium.

[0061] In a first aspect, an embodiment of the present disclosure provides an information transmission method, wherein the method includes:

[0062] The terminal sends first information, where the first information is used to determine a target model for compressing and transmitting channel state information CSI, where the model includes at least one of a first model and a second model;

[0063] The first model is located at the terminal and is used to compress the CSI, and the second model is located at the network device and is used to decompress the compressed CSI;

[0064] The first model corresponds to the second model.

[0065] In the above embodiment, the target model is determined by the first information, so that the terminal and the network device reach a consensus in determining the target model, thereby improving system performance.

[0066] In conjunction with some embodiments of the first aspect, in some embodiments, the method further includes:

[0067] According to the second information, N candidate models are determined from the M models, wherein the N candidate models are used to determine the target model, and N is a positive integer, and 1≤N≤M.

[0068] In the above embodiment, the candidate model is determined by the second information, so that the determined candidate model can meet the requirements of the terminal and / or the network side device.

[0069] In conjunction with some embodiments of the first aspect, in some embodiments, the second information includes at least one of the following:

[0070] Indicative information of candidate model parameters;

[0071] Auxiliary information for determining a candidate model, wherein the auxiliary information is used to indicate output information of the second model;

[0072] Indication information of the current status of the terminal.

[0073] In the above embodiment, the candidate model is determined by the second information, so that the determined candidate model can meet the requirements of the terminal and / or the network side device.

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

[0075] Determine the target model from the N candidate models; wherein the first information is used to indicate the target model determined by the terminal.

[0076] In the above embodiment, the terminal determines the target model and indicates the target model to the network device through the first information, so that the terminal and the network device reach a consensus on the target model, thereby improving system performance.

[0077] In conjunction with some embodiments of the first aspect, in some embodiments, the method further includes:

[0078] Sending third information indicating a current state of the terminal, wherein the third information is used by the network device to determine whether to allow the terminal to determine a target model from the N candidate models;

[0079] Receive fourth information sent by the network device, where the fourth information is used to indicate whether the terminal is allowed to determine a target model from the N candidate models.

[0080] In the above embodiment, through the third information and the fourth information, the network device determines whether the target model is determined by the terminal, and the terminal and the network device can reach a consensus on whether the target model is determined by the terminal; reducing the situation where the models determined by the two sides are inconsistent due to uncertainty about whether the target model is determined by the terminal.

[0081] In combination with some embodiments of the first aspect, in some embodiments, the first information is used to indicate the N candidate models, wherein the target model is determined from the N candidate models.

[0082] In the above embodiment, the first information can enable the terminal and the network device to reach a consensus on the selection of candidate models.

[0083] In combination with some embodiments of the first aspect, in some embodiments, the first information is used by the network device to determine the target model from the N candidate models.

[0084] In the above embodiment, the network device determines the target model from the N candidate models based on the first information, so that the terminal and the network device reach a consensus on the target model, thereby increasing the probability that the terminal and the network device obtain mutually related models.

[0085] In conjunction with some embodiments of the first aspect, in some embodiments, the method further includes:

[0086] Receive fifth information, where the fifth information is used to indicate one of the following:

[0087] The target model determined by the network device from the N candidate models;

[0088] The terminal sends CSI in a manner, wherein the fifth information is sent by the network device without determining the target model.

[0089] In the above embodiment, the network device determines the target model and indicates the target model to the network device via the fifth information, so that the terminal and the network device reach consensus on the determined target model. This increases the probability that both the terminal and the network device will obtain mutually correlated models. Furthermore, the method of instructing the terminal to transmit CSI when the target model is not determined improves the compatibility of CSI transmission.

[0090] In combination with some embodiments of the first aspect, in some embodiments, the first information is used by the network device to determine the target model from M models; or

[0091] When the first information is a first value, it indicates that the target model is determined by the network device.

[0092] In combination with some embodiments of the first aspect, in some embodiments, when the first information is a second value, it indicates that the network device is not allowed to determine the target model.

[0093] In the above embodiment, the network device determines the target model from the M models based on the first information, so that the terminal and the network device reach a consensus on the target model, thereby increasing the probability that the terminal and the network device obtain mutually related models.

[0094] The terminal indicates through the first information whether the target model is determined by the network device, and the terminal and the network device can reach a consensus on whether the target model is determined by the terminal, thereby reducing the situation where the models determined by both parties are inconsistent due to uncertainty about whether the target model is determined by the network device.

[0095] In conjunction with some embodiments of the first aspect, in some embodiments, the method further includes:

[0096] Receive sixth information sent by the network device, wherein:

[0097] The first information is used by the network device to determine the target model from M models, and the sixth information is used to indicate the target model; or

[0098] When the first information is the first value, the sixth information is used to indicate the N candidate models determined by the network device from the M models.

[0099] In the above embodiment, the sixth information enables the terminal and the network device to reach consistency in the target model, thereby increasing the probability that the terminal and the network device obtain mutually related models.

[0100] In the above embodiment, the sixth information enables the terminal and the network device to reach a consensus on the candidate model, thereby increasing the probability that the terminal and the network device obtain mutually related models.

[0101] In conjunction with some embodiments of the first aspect, in some embodiments, the method further includes:

[0102] When the first information is the first value, seventh information sent by the network device is received, where the seventh information is used to indicate one of the following:

[0103] The network device determines a target model from the N candidate models;

[0104] The terminal performs a fallback operation, wherein the seventh information is sent when the network device determines that it does not have the candidate model or the network device is not allowed to determine the target model from the N candidate models.

[0105] In the above embodiment, the seventh information enables the terminal and the network device to reach consistency in the target model, thereby increasing the probability that the terminal and the network device obtain mutually related models.

[0106] The seventh information instructs the terminal to fall back when the target model is not determined, thereby reducing the performance loss caused by the terminal being unable to obtain the target model.

[0107] In conjunction with some embodiments of the first aspect, in some embodiments, the first information instructs the network device to determine a model parameter adopted by the target model from M models, where the model parameter includes at least one of the following:

[0108] a channel characteristic vector determined by the terminal;

[0109] A compressed CSI obtained by compressing the feature vector by the M models;

[0110] The M models respectively correspond to model identifiers.

[0111] In the above embodiment, the target model is determined based on the first information, so that the determined target model meets the requirements of the terminal and / or network device.

[0112] In a second aspect, an embodiment of the present disclosure provides an information transmission method, wherein the method includes:

[0113] The network device receives first information, where the first information is used to determine a target model for compressing and transmitting channel state information (CSI), where the model includes at least one of a first model and a second model.

[0114] The first model is located at the terminal and is used to compress the CSI, and the second model is located at the network device and is used to decompress the compressed CSI;

[0115] The first model corresponds to the second model.

[0116] In the above embodiment, the target model is determined by the first information, so that the terminal and the network device reach a consensus on the target model, thereby increasing the probability that the terminal and the network device obtain mutually related models.

[0117] In conjunction with some embodiments of the second aspect, in some embodiments, the method further includes:

[0118] Send second information, wherein the second information is used by the terminal to determine N candidate models from M models, wherein the N candidate models are used to determine the target model, and N is a positive integer, and 1≤N≤M.

[0119] In conjunction with some embodiments of the second aspect, in some embodiments, the second information includes at least one of the following:

[0120] Indicative information of candidate model parameters;

[0121] Auxiliary information used to determine the candidate model, where the auxiliary information is used to indicate output information of the second model.

[0122] In combination with some embodiments of the second aspect, in some embodiments, the N candidate models are used by the terminal to determine the target model; wherein the first information is used to indicate the target model determined by the terminal.

[0123] In conjunction with some embodiments of the second aspect, in some embodiments, the method further includes:

[0124] receiving third information indicating a current state of the terminal, wherein the third information is used by the network device to determine whether to allow the terminal to determine a target model from the N candidate models;

[0125] Send fourth information, where the fourth information is used to indicate whether the terminal is allowed to determine a target model from the N candidate models.

[0126] In combination with some embodiments of the second aspect, in some embodiments, the first information is used to indicate the N candidate models, wherein the target model is determined from the N candidate models.

[0127] In conjunction with some embodiments of the second aspect, in some embodiments, the method further includes:

[0128] The target model is determined from the N candidate models.

[0129] In conjunction with some embodiments of the second aspect, in some embodiments, the method further includes:

[0130] Send fifth information, where the fifth information is used to indicate one of the following:

[0131] The target model determined by the network device from the N candidate models;

[0132] The terminal sends CSI in a manner, wherein the fifth information is sent by the network device without determining the target model.

[0133] In conjunction with some embodiments of the second aspect, in some embodiments, the first information is used by the network device to determine the target model from M models; or

[0134] When the first information is a first value, it indicates that the target model is determined by the network device.

[0135] In combination with some embodiments of the second aspect, in some embodiments, when the first information is a second value, it indicates that the network device is not allowed to determine the target model.

[0136] In conjunction with some embodiments of the second aspect, in some embodiments, the method further includes:

[0137] Sending a sixth message, wherein,

[0138] The first information is used by the network device to determine the target model from M models, and the sixth information is used to indicate the target model; or

[0139] When the first information is the first value, the sixth information is used to indicate the N candidate models determined by the network device from the M models.

[0140] In conjunction with some embodiments of the second aspect, in some embodiments, the method further includes:

[0141] When the first information is the first value, seventh information is sent, where the seventh information is used to indicate one of the following:

[0142] The target model determined by the network device from the N candidate models;

[0143] The terminal performs a fallback operation, wherein the seventh information is sent when the network device determines that it does not have the candidate model or the network device is not allowed to determine the target model from the N candidate models.

[0144] In conjunction with some embodiments of the second aspect, in some embodiments, the first information instructs the network device to determine a model parameter adopted by the target model from M models, where the model parameter includes at least one of the following:

[0145] a channel characteristic vector determined by the terminal;

[0146] A compressed CSI obtained by compressing the feature vector by the M models;

[0147] The M models respectively correspond to model identifiers.

[0148] In a third aspect, an embodiment of the present disclosure provides an information transmission method, which is performed by a communication system, wherein the method includes:

[0149] The terminal sends first information to the network device, where the first information is used to determine a target model for compressing and transmitting channel state information CSI, where the model includes at least one of a first model and a second model;

[0150] The first model is located at the terminal and is used to compress the CSI, and the second model is located at the network device and is used to decompress the compressed CSI;

[0151] The first model corresponds to the second model.

[0152] In a fourth aspect, an embodiment of the present disclosure provides a terminal, wherein the terminal includes:

[0153] a transceiver module configured to send first information, where the first information is used to determine a target model for compressing and transmitting channel state information (CSI), the model including at least one of a first model and a second model;

[0154] The first model is located at the terminal and is used to compress the CSI, and the second model is located at the network device and is used to decompress the compressed CSI;

[0155] The first model corresponds to the second model.

[0156] In a fifth aspect, an embodiment of the present disclosure provides a network device, wherein the network device includes:

[0157] a transceiver module configured to receive first information, where the first information is used to determine a target model for compressing and transmitting channel state information (CSI), the model including at least one of a first model and a second model;

[0158] The first model is located at the terminal and is used to compress the CSI, and the second model is located at the network device and is used to decompress the compressed CSI;

[0159] The first model corresponds to the second model.

[0160] In a sixth aspect, an embodiment of the present disclosure provides a communication system, wherein the communication system includes: a terminal and a network device; wherein,

[0161] The terminal is configured to implement the information transmission method according to the first aspect;

[0162] The network device is configured to implement the information transmission method described in the second aspect.

[0163] In a seventh aspect, an embodiment of the present disclosure provides a communication device, wherein the communication device includes:

[0164] one or more processors;

[0165] The processor is used to call instructions to enable the communication device to execute the information transmission method described in the first aspect or the second aspect.

[0166] In an eighth aspect, an embodiment of the present disclosure proposes a storage medium, wherein the storage medium stores instructions, and when the instructions are executed on a communication device, the communication device executes the information transmission method described in the first aspect or the second aspect.

[0167] 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.

[0168] The present disclosure provides an information transmission method and apparatus, a communication device, a communication system, and a storage medium. In some embodiments, the terms "information transmission method" and "information processing method" are interchangeable; the terms "information transmission apparatus" and "information processing apparatus" are interchangeable; and the terms "communication system" and "information processing system" are interchangeable.

[0169] 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.

[0170] 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.

[0171] 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.

[0172] 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.

[0173] In the embodiments of the present disclosure, “plurality” refers to two or more.

[0174] In some embodiments, the terms "at least one," "one or more," "a plurality of," "multiple," etc. may be used interchangeably.

[0175] In some embodiments, descriptions such as "at least one of A and B," "A and / or B," "in one case A, in another case B," or "in one case A, in 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 same applies when there are more branches such as A, B, and C.

[0176] 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.

[0177] 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.

[0178] 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.

[0179] In some embodiments, terms such as "time / frequency" and "time / frequency domain" refer to the time domain and / or the frequency domain.

[0180] 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.

[0181] 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.

[0182] In some embodiments, devices, etc. can be interpreted as physical or virtual, and their names are not limited to the names recorded in the embodiments. Terms such as "device", "equipment", "device", "circuit", "network element", "node", "function", "unit", "section", "system", "network", "chip", "chip system", "entity", and "subject" can be used interchangeably.

[0183] In some embodiments, "network" can be interpreted as devices included in the network (eg, access network equipment, core network equipment, etc.).

[0184] In some embodiments, the terms "access network device (AN device)", "radio access network device (RAN device)", "base station (BS)", "radio base station" "fixed station", "node", "access point", "transmission point (TP)", "reception point (RP)", "transmission / reception point (TRP)", "panel", "antenna panel", "antenna array", "cell", "macro cell", "small cell", "femto cell", "pico cell", "sector", "cell group", "serving cell", "carrier", "component carrier", "bandwidth part (BWP)" and the like may be used interchangeably.

[0185] In some embodiments, the terms "terminal", "terminal device", "user equipment (UE)", "user terminal", "mobile station (MS)", "mobile terminal (MT)", subscriber station, mobile unit, subscriber unit, wireless unit, remote unit, mobile device, wireless device, wireless communication device, remote device, mobile subscriber station, access terminal, mobile terminal, wireless terminal, remote terminal, handset, user agent, mobile client, client, etc. can be used interchangeably.

[0186] In some embodiments, the access network device, the core network device, or the network device can be replaced by a terminal. For example, the various embodiments of the present disclosure can also be applied to a structure in which the communication between the access network device, the core network device, or the network device and the terminal is replaced by communication between multiple terminals (for example, device-to-device (D2D), vehicle-to-everything (V2X), etc.). In this case, it is also possible to set the structure in which the terminal has all or part of the functions of the access network device. In addition, terms such as "uplink" and "downlink" can also be replaced by terms corresponding to communication between terminals (for example, "side"). For example, uplink channels, downlink channels, etc. can be replaced by side channels, and uplinks, downlinks, etc. can be replaced by side links.

[0187] In some embodiments, the terminal may be replaced by an access network device, a core network device, or a network device. In this case, the access network device, the core network device, or the network device may have a structure that has all or part of the functions of the terminal.

[0188] In some embodiments, obtaining data, information, etc. may comply with the laws and regulations of the country where the data is obtained.

[0189] In some embodiments, data, information, etc. may be obtained with the user's consent.

[0190] 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.

[0191] FIG1a is a schematic diagram showing the architecture of a communication system according to an embodiment of the present disclosure.

[0192] As shown in FIG. 1 a , a communication system 100 includes a terminal 101 and a network device 102 .

[0193] In some embodiments, the network device 102 may include at least one of the following: a core network device; an access network device.

[0194] In some embodiments, the core network device may be a single device including an access and mobility management function (AMF), a user plane function (UPF), a policy control function (PCF), a session management function (SMF), etc., or may be multiple devices or a group of devices including all or part of the AMF, SMF, UPF, PCF, etc. The network element may be virtual or physical. The core network may include, for example, at least one of an evolved packet core (EPC), a 5G core network (5GCN), and a next generation core (NGC).

[0195] In some embodiments, the access network device may be, for example, a node or device that accesses a terminal to a wireless network. The access network device may include an evolved NodeB (eNB), a next generation evolved NodeB (ng-eNB), a next generation NodeB (gNB), a node B (NB), a home node B (HNB), a home evolved nodeB (HeNB), a wireless backhaul device, a radio network controller (RNC), a base station controller (BSC), a base transceiver station (BTS), a base band unit (BBU), a mobile switching center, a base station in a 6G communication system, an open base station (Open RAN), a cloud base station (Cloud RAN), a base station in other communication systems, and at least one of an access node in a Wi-Fi system, but is not limited thereto.

[0196] 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.

[0197] 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.

[0198] 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.

[0199] 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.

[0200] The following embodiments of the present disclosure may be applied to the communication system 100 shown in FIG1a, or a portion thereof, but are not limited thereto. The entities shown in FIG1a are illustrative only. The communication system may include all or part of the entities shown in FIG1a, or may include other entities other than those shown in FIG1a. The number and form of the entities may be arbitrary. The connection relationship between the entities is illustrative only. The entities may be connected or disconnected, and the connection may be in any manner, including direct or indirect, wired or wireless.

[0201] The embodiments of the present disclosure can be applied to Long Term Evolution (LTE), LTE-Advanced (LTE-A), LTE-Beyond (LTE-B), SUPER 3G, IMT-Advanced, 4th generation mobile communication system (4G), 5th generation mobile communication system (5G), 5G new radio (NR), future radio access (FRA), new radio access technology (RAT), new radio (NR), new radio access (NX), future generation radio access (FX), Global System for Mobile communications (GSM (registered trademark)), CDMA2000, Ultra Mobile Broadband (UMB), IEEE 802.11 (Wi-Fi (registered trademark)), IEEE 802.16 (WiMAX (registered trademark)), IEEE 802.20, Ultra-WideBand (UWB), Bluetooth (registered trademark), Public Land Mobile Network (PLMN) networks, Device-to-Device (D2D) systems, Machine-to-Machine (M2M) systems, Internet of Things (IoT) systems, Vehicle-to-Everything (V2X), systems utilizing other communication methods, and next-generation systems based on and extending these methods. Furthermore, multiple systems may be combined (for example, a combination of LTE or LTE-A with 5G).

[0202] CSI compression feedback and recovery can be implemented based on the terminal-side CSI generation model and the network-side CSI recovery model, respectively. The terminal-side CSI generation model and the network-side CSI recovery model can be bilateral artificial intelligence (AI) / machine learning (ML) models. Figure 1b is a schematic diagram of implementing CSI compression feedback and recovery using a bilateral AI / ML model. The UE compresses the downlink channel information H through the CSI generation model and quantizes it into a binary bit stream, which is then sent to the network-side device (e.g., gNB). The network-side device recovers H', which is approximately the original downlink information, through the CSI recovery model.

[0203] In some embodiments, the UE or gNB may select an AI model based on the following performance criteria or methods:

[0204] Option 1: Intermediate KPI such as the square of cosine similarity.

[0205] For Option 1, the UE can report the target input CSI (i.e., input-CSI-NW), or the NW can send the target output CSI (i.e., output-CSI-UE) to achieve the calculation of the intermediate KPI on the NW side or the UE side respectively.

[0206] Option 2: Final KPI, such as throughput, Block Error Rate (BLER), assumed BLER, or non-acknowledgement (NACK) / acknowledgement (ACK).

[0207] Option 3: Use traditional CSI feedback reporting as a reference for model selection.

[0208] Traditional CSI feedback reporting includes CSI measurement and reporting based on Type I or Type II codebooks. The codebook type or codebook parameters are configured by the NW to the UE.

[0209] Option 4: The input or output data distribution of the AI / ML network model, such as data drift changes between training data and observation data.

[0210] Assume that the UE has deployed M ≥ 1 CSI generation partial models and the gNB has deployed M ≥ 1 CSI recovery partial models. Alternatively, M CSI generation partial model and CSI recovery partial model pairs are deployed on the UE or gNB. To achieve optimal system performance, it is necessary to ensure that the CSI generation partial model used on the UE and the CSI recovery partial model used on the gNB match, that is, ensure that they are compatible.

[0211] In different scenarios and configurations, when M or more partial models are deployed on the UE or NW side, or when a partial model and a CSI recovery partial model are paired, how to select a partial model that matches or is compatible with the model used by the other end on the UE or gNB side remains an unresolved issue. Furthermore, as partial models are implemented on the UE side, hardware limitations such as UE battery life can limit the number of available models. This also raises the question of how to notify the gNB to select a matching or compatible model from the available models to match the terminal's state.

[0212] FIG2a is an interactive diagram illustrating an information transmission method according to an embodiment of the present disclosure. As shown in FIG2a, the present disclosure embodiment relates to an information transmission method for a communication system 100, the method comprising:

[0213] Step S2101: The terminal determines a candidate model.

[0214] In some embodiments, the terminal determines N candidate models from M models based on the second information.

[0215] Optionally, N is a positive integer, and 1≤N≤M.

[0216] In some embodiments, the M models may be all available models for the configuration.

[0217] In some embodiments, the terminal and / or network device selects a target model from candidate models, and the target model is used to perform CSI compression and CSI decompression.

[0218] In some embodiments, the terminal may determine N candidate models from M models after accessing the network.

[0219] In some embodiments, the second information may be sent by the network device to the terminal.

[0220] In some embodiments, the second information may be pre-stored in the terminal.

[0221] In some embodiments, the second information may be determined by the terminal.

[0222] In some embodiments, the model may include at least one of the following: an AI model; an ML model.

[0223] In some embodiments, the model includes at least one of a first model and a second model, wherein the first model is located at the terminal and is used to compress the CSI, and the second model is located at the network device end and is used to decompress the compressed CSI.

[0224] In some embodiments, the first model has a binding relationship with the second model.

[0225] Optionally, the model identifier of the first model and the model identifier of the second model may be the same.

[0226] Optionally, the model identifier of the first model and the model identifier of the second model may have a binding association.

[0227] In some embodiments, determining a candidate model by the terminal may include at least one of the following: determining a first model by the terminal; determining a second model by the terminal; or determining the first model and the second model by the terminal. Determining the first model by the terminal is equivalent to simultaneously determining the second model. Determining the second model by the terminal is equivalent to simultaneously determining the first model.

[0228] In some embodiments, the second information may be used to indicate conditions that the candidate model needs to meet.

[0229] In some embodiments, the second information includes at least one of the following:

[0230] Indicative information of candidate model parameters;

[0231] Auxiliary information used to determine candidate models;

[0232] An indication of the current status of the terminal.

[0233] In some embodiments, the auxiliary information may be pre-stored in the terminal, or may be sent to the terminal by a network device.

[0234] In some embodiments, the auxiliary information is used to indicate at least one of the following:

[0235] Input information of candidate models required;

[0236] Output information of candidate models required;

[0237] Data service type;

[0238] Data business scenarios;

[0239] The terminal's capability information is used to determine the candidate models that the terminal can adopt.

[0240] Exemplarily, the terminal may determine N candidate models that meet the current data service scenario from the M models. For example, the terminal may determine N candidate models that meet the outdoor scenario from the M models.

[0241] In some embodiments, the network device may also determine N candidate models from the M models. The specific implementation is similar to that of the terminal side and will not be repeated here.

[0242] Step S2102: The terminal determines the target model.

[0243] In some embodiments, the target model is a model determined by the terminal for performing CSI compression and CSI decompression.

[0244] In some embodiments, the terminal may determine a target model from N candidate models based on a selection rule.

[0245] Determining a target model from N candidate models based on a selection rule includes at least one of the following:

[0246] Determine a target model from N candidate models based on the priority of the candidate models;

[0247] Determining a target model from the N candidate models based on a degree of matching between the candidate models and the second information;

[0248] Based on the performance of the candidate models, a target model is determined from N candidate models;

[0249] Based on the outputs of the candidate models, a target model is determined from N candidate models.

[0250] Step S2103: The terminal sends the first information.

[0251] In some embodiments, the terminal sends first information to the network device.

[0252] In some embodiments, the first information is used to indicate a target model.

[0253] In some embodiments, the first information is used to indicate a model identifier of the target model.

[0254] In some embodiments, the first information is used to indicate a position of the target model in the M models.

[0255] In some embodiments, the terminal bits indicate 1 target model from M models.

[0256] For example, M=16, that is, there are 16 models, and the terminal passes bits indicate the 0th to 15th selected target models.

[0257] In some embodiments, the first information is used to indicate a position of the target model among the N candidate models.

[0258] In some embodiments, the terminal bits indicate the target model from N candidate models.

[0259] In some embodiments, the first information is used to indicate N candidate models.

[0260] In some embodiments, the target model is determined from N candidate models.

[0261] In some embodiments, the first information indicating the target model and the first information indicating the N candidate models may be the same information or different information.

[0262] In some embodiments, the first information may indicate N candidate models in a bitmap or other manner.

[0263] Optionally, the first information may be a bitmap of M bits, used to indicate N candidate models selected from M models.

[0264] In some embodiments, the terminal bits indicate the selected N candidate models, where bits are used to determine the value of N, bits are used to indicate the N models selected from M.

[0265] In some embodiments, the term "information" can be interchangeable with terms such as "message", "signal", "signaling", "report", "configuration", "indication", "instruction", "command", "channel", "parameter", "field", and "data".

[0266] In some embodiments, the term "send" can be interchanged with terms such as "transmit", "report", and "transmit".

[0267] The information transmission method involved in the embodiments of the present disclosure may include at least one of steps S2101 to S2103. For example, step S2101 may be implemented as an independent embodiment, step S2102 may be implemented as an independent embodiment, step S2103 may be implemented as an independent embodiment, and step S2102 combined with step S2103 may be implemented as an independent embodiment, but the present invention is not limited thereto.

[0268] FIG2b is an interactive diagram illustrating an information transmission method according to an embodiment of the present disclosure. As shown in FIG2b , the present disclosure embodiment relates to an information transmission method for use in a communication system 100, the method comprising:

[0269] Step S2201: The terminal determines a candidate model.

[0270] In some embodiments, the terminal determines N candidate models from M models based on the second information.

[0271] Optionally, N is a positive integer, and 1≤N≤M.

[0272] In some embodiments, the M models may be candidate models previously selected by the terminal.

[0273] Optionally, the M models may be candidate models selected by the terminal after accessing the network.

[0274] In some embodiments, the M models may be candidate models determined by the terminal in step 2101 in FIG. 2 a based on the second information.

[0275] Combining the embodiment of FIG. 2a with the embodiment of FIG. 2b , the M models in the embodiment of FIG. 2b may be the N candidate models determined in the embodiment of FIG. 2a .

[0276] In the embodiment of FIG2b, N candidate models are determined from M models, which can be determined from the N candidate models in the embodiment of FIG2a, where K is a positive integer and 1≤K≤N.

[0277] The following embodiment of FIG. 2 b is described by taking the example of a terminal determining K candidate models from N candidate models.

[0278] In some embodiments, when the terminal determines, based on the second information, that the currently adopted model is not applicable, it determines K candidate models from N candidate models.

[0279] In some embodiments, the model (including candidate models and target models) may include at least one of the following: an AI model; an ML model.

[0280] In some embodiments, the model includes at least one of a first model and a second model, wherein the first model is located at the terminal and is used to compress the CSI, and the second model is located at the network device end and is used to decompress the compressed CSI.

[0281] In some embodiments, the first model has a binding relationship with the second model.

[0282] Optionally, the model identifier of the first model and the model identifier of the second model may be the same.

[0283] Optionally, the model identifier of the first model and the model identifier of the second model may have a binding association.

[0284] In some embodiments, determining a candidate model by the terminal may include at least one of the following: determining a first model by the terminal; determining a second model by the terminal; or determining the first model and the second model by the terminal. Determining the first model by the terminal is equivalent to simultaneously determining the second model. Determining the second model by the terminal is equivalent to simultaneously determining the first model.

[0285] In some embodiments, the second information may be determined by the terminal.

[0286] In some embodiments, the second information may be used to indicate conditions that the candidate model needs to meet.

[0287] In some embodiments, the second information includes at least one of the following:

[0288] Indication information indicating the current business type;

[0289] Indication information indicating the current status of the terminal.

[0290] Exemplarily, the information indicating the current status of the terminal may be used to indicate at least one of the following:

[0291] The processing capacity of the terminal;

[0292] The battery status of the terminal;

[0293] The load condition of the terminal;

[0294] The hardware capabilities of the terminal.

[0295] In some embodiments, the terminal may determine K candidate models from N candidate models.

[0296] In some embodiments, K candidate models may satisfy the current state of the terminal.

[0297] For example, the terminal may determine K candidate models of the terminal's current state (eg, battery state) from N candidate models selected when accessing the network.

[0298] Step S2202: The terminal sends the third information.

[0299] In some embodiments, the terminal sends third information indicating the current state of the terminal to the network device.

[0300] In some embodiments, the third information is used by the network device to determine whether to allow the terminal to determine the target model from K candidate models.

[0301] In some embodiments, the current state of the terminal may include: the current model is unavailable.

[0302] Optionally, the network device may deactivate the current model if it is unavailable.

[0303] Step S2203: The network device sends the fourth information.

[0304] In some embodiments, fourth information sent by the network device is received, where the fourth information is used to indicate whether the terminal is allowed to determine a target model from the K candidate models.

[0305] In some embodiments, if the fourth information indicates that the terminal is not allowed to determine the target model from the K candidate models, the terminal no longer determines a new target model.

[0306] Optionally, the fourth information may instruct the terminal to perform a fall back operation. If the fourth information indicates that the terminal is not allowed to determine the target model from the N candidate models, the terminal no longer determines a new target model.

[0307] Step S2204: The terminal determines the target model.

[0308] In some embodiments, the terminal may determine a target model from K candidate models based on a selection rule.

[0309] Determining a target model from K candidate models based on a selection rule includes at least one of the following:

[0310] Determine the target model from K candidate models based on the priority of the candidate models;

[0311] Determine a target model from the K candidate models based on a degree of match between the candidate models and the second information;

[0312] Based on the performance of the candidate models, the target model is determined from the K candidate models;

[0313] Based on the output of the candidate models, the target model is determined from the K candidate models.

[0314] Step S2205: The terminal sends the first information.

[0315] In some embodiments, the terminal sends first information to the network device.

[0316] In some embodiments, the first information is used to indicate a target model.

[0317] In some embodiments, the first information is used to indicate a model identifier of the target model.

[0318] In some embodiments, the first information is used to indicate a position of the target model in the N models.

[0319] Optionally, the UE can bits or a bitmap of size N bits indicates the K models available as candidates, where bits are used to determine the value of K, It is used to indicate which K models are selected from N, and then the UE passes Indicates the target model selected from K models, or the UE directly indicates the ID of the selected model to the NW.

[0320] In some embodiments, model management can include management based on model ID and management based on function ID. The aforementioned method of indicating the selected model by model ID can also indicate the selected model by function ID. That is, the model ID can be replaced by the function ID.

[0321] In some embodiments, the model identifier includes at least one of the following: a model ID and a function ID. In some embodiments, the term "information" can be interchangeably used with terms such as "message," "signal," "signaling," "report," "configuration," "indication," "instruction," "command," "channel," "parameter," "field," and "data."

[0322] In some embodiments, the term "send" can be interchanged with terms such as "transmit", "report", and "transmit".

[0323] The information transmission method involved in the embodiments of the present disclosure may include at least one of steps S2201 to S2205. For example, step S2201 may be implemented as an independent embodiment, step S2202 may be implemented as an independent embodiment, step S2203 may be implemented as an independent embodiment, step S2204 may be implemented as an independent embodiment, step S2205 may be implemented as an independent embodiment, steps S2201 to 2205 may be implemented in combination as independent embodiments, and step S2201 may be implemented in combination with steps 2204 and 2205 as independent embodiments, but the present invention is not limited thereto.

[0324] FIG2c is an interactive diagram illustrating an information transmission method according to an embodiment of the present disclosure. As shown in FIG2c, the present disclosure embodiment relates to an information transmission method for use in a communication system 100, the method comprising:

[0325] Step S2301: The terminal sends the first information.

[0326] In some embodiments, the terminal sends first information to the network device.

[0327] In some embodiments, the first information is used by the network device to determine the target model from M models.

[0328] In some embodiments, the M models may be all available models for the configuration.

[0329] In some embodiments, the model (including candidate models and target models) may include at least one of the following: an AI model; an ML model.

[0330] In some embodiments, the model includes at least one of a first model and a second model, wherein the first model is located at the terminal and is used to compress the CSI, and the second model is located at the network device end and is used to decompress the compressed CSI.

[0331] In some embodiments, the first model has a binding relationship with the second model.

[0332] Optionally, the model identifier of the first model and the model identifier of the second model may be the same.

[0333] Optionally, the model identifier of the first model and the model identifier of the second model may have a binding association.

[0334] In some embodiments, determining a candidate model by the terminal may include at least one of the following: determining a first model by the terminal; determining a second model by the terminal; or determining the first model and the second model by the terminal. Determining the first model by the terminal is equivalent to simultaneously determining the second model. Determining the second model by the terminal is equivalent to simultaneously determining the first model.

[0335] In some embodiments, the first information instructs the network device to determine model parameters used by the target model from M models, wherein the model parameters include at least one of the following:

[0336] a channel characteristic vector determined by the terminal;

[0337] A compressed CSI obtained by compressing the feature vector by M models;

[0338] The M models respectively correspond to model identifiers.

[0339] In some embodiments, the terminal may determine a channel eigenvector based on a downlink pilot.

[0340] In some embodiments, the terminal may use M first models of the terminal to compress the feature vector and determine the compressed CSI.

[0341] In some embodiments, the network device may send an instruction to the terminal to instruct the network device to determine the target model, and the terminal sends the first information to the network device based on the instruction.

[0342] In some embodiments, the compressed CSI corresponding to each of the M models may be identified and distinguished using the model identifier of the model.

[0343] In some embodiments, the compressed CSI may be sent using a predefined rule, and the network device determines a model corresponding to the compressed CSI based on the rule.

[0344] In some embodiments, the content included in the first information may be sent through a single signaling.

[0345] In some embodiments, the content included in the first information may be sent through multiple signalings.

[0346] Optionally, one first information corresponds to one model.

[0347] Optionally, one signaling may send one first information corresponding to one or more models. Step S2302: The network device determines the target model.

[0348] In some embodiments, the network device determines a target model from the M models based on the first information.

[0349] In some embodiments, the network device determines performance parameters of the M models for the channel feature vector according to the first information, and determines a target model based on the performance parameters.

[0350] In some embodiments, the network device may determine an intermediate KPI of the model based on the compressed CSI. Here, the intermediate KPI may include the square of the cosine similarity, etc. The intermediate KPI may be used by the network device to select a target model.

[0351] In some embodiments, the network device may determine the model with the best intermediate KPI as the target model.

[0352] Step S2303: The network device sends the sixth information.

[0353] In some embodiments, after determining the target model from the M models, the network device may send sixth information to the terminal to indicate the target model selected by the network device.

[0354] In some embodiments, the term "information" can be interchangeable with terms such as "message", "signal", "signaling", "report", "configuration", "indication", "instruction", "command", "channel", "parameter", "field", and "data".

[0355] In some embodiments, the term "send" can be interchanged with terms such as "transmit", "report", and "transmit".

[0356] The information transmission method involved in the embodiments of the present disclosure may include at least one of steps S2301 to S2303. For example, step S2301 may be implemented as an independent embodiment, step S2302 may be implemented as an independent embodiment, and step S2303 may be implemented as an independent embodiment. Steps S2301 to 2303 may be implemented in combination as independent embodiments, but the present invention is not limited thereto.

[0357] FIG2d is an interactive diagram illustrating an information transmission method according to an embodiment of the present disclosure. As shown in FIG2d , the present disclosure embodiment relates to an information transmission method for use in a communication system 100, the method comprising:

[0358] Step S2401: The network device determines a candidate model.

[0359] In some embodiments, the network device selects N candidate models from the M models.

[0360] In some embodiments, the network device determines N candidate models from M models based on the second information.

[0361] Optionally, N is a positive integer, and 1≤N≤M.

[0362] In some embodiments, the M models may be all available models for the configuration.

[0363] In some embodiments, the terminal and / or network device selects a target model from candidate models, and the target model is used to perform CSI compression and CSI decompression.

[0364] In some embodiments, the second information may be sent by the terminal to the network device.

[0365] In some embodiments, the second information may be pre-stored in the network device.

[0366] In some embodiments, the second information may be determined by the network device.

[0367] In some embodiments, the model may include at least one of the following: an AI model; an ML model.

[0368] In some embodiments, the model includes at least one of a first model and a second model, wherein the first model is located at the terminal and is used to compress the CSI, and the second model is located at the network device end and is used to decompress the compressed CSI.

[0369] In some embodiments, the first model has a binding relationship with the second model.

[0370] Optionally, the model identifier of the first model and the model identifier of the second model may be the same.

[0371] Optionally, the model identifier of the first model and the model identifier of the second model may have a binding association.

[0372] In some embodiments, the network device determining the candidate model may include at least one of the following: the network device determining a first model; the network device determining a second model; the network device determining the first model and the second model. The network device determining the first model is equivalent to simultaneously determining the second model. The network device determining the second model is equivalent to simultaneously determining the first model.

[0373] In some embodiments, the second information may be used to indicate conditions that the candidate model needs to meet.

[0374] In some embodiments, the second information includes at least one of the following:

[0375] Indicative information of candidate model parameters;

[0376] Auxiliary information used to determine candidate models;

[0377] An indication of the current status of the terminal.

[0378] In some embodiments, the auxiliary information may be pre-stored in the network device.

[0379] In some embodiments, the auxiliary information is used to indicate at least one of the following:

[0380] Input information of candidate models required;

[0381] Output information of candidate models required;

[0382] Data service type;

[0383] Data business scenarios;

[0384] The terminal's capability information is used to determine the candidate models that the terminal can adopt.

[0385] Exemplarily, the network device may determine N candidate models that meet the current data service scenario from the M models. For example, the network device may determine N candidate models that meet the outdoor scenario from the M models.

[0386] Step S2402: The network device sends sixth information.

[0387] In some embodiments, the sixth information is used to indicate the N candidate models determined by the network device from the M models.

[0388] In some embodiments, the sixth information may be a bitmap of M bits. The M-bit bitmap may be used to indicate N candidate models among the M models. N is an integer greater than or equal to 1 and less than or equal to M.

[0389] In some embodiments, the sixth information may be bits indicate N candidate models where bits are used to determine the value of N, bits are used to indicate the N candidate models selected from M.

[0390] Step S2403: The terminal sends the first information.

[0391] In some embodiments, the first information is used to indicate whether the network device is allowed to determine the target model.

[0392] In some embodiments, when the first information is a first value, it indicates that the target model is determined by the network device.

[0393] In some embodiments, when the first information is the second value, it indicates that the network device is not allowed to determine the target model.

[0394] In some embodiments, the terminal determines whether N candidate models are available, and if at least one of the N candidate models is available, sends a first information indicating that the network device is not allowed to determine the target model if none of the N candidate models are available.

[0395] Step S2404: The network device determines the target model.

[0396] In some embodiments, the network device determines a target model from N candidate models.

[0397] In some embodiments, when the network device determines that the terminal allows the network device to determine the target model, the target model is determined from N candidate models.

[0398] In some embodiments, the network device may determine a target model from N candidate models based on performance parameters of the candidate models, etc.

[0399] For example, the network device may determine a target model from N candidate models based on intermediate KPIs of the candidate models.

[0400] Step S2405: The network device sends the seventh information.

[0401] In some embodiments, the seventh information is used to instruct the network device to determine the target model from N candidate models.

[0402] In some embodiments, the seventh information may indicate a model identification of the target model.

[0403] In some embodiments, the seventh information is bits indicate that the target model is determined from N candidate models.

[0404] In some embodiments, the term "information" can be interchangeable with terms such as "message", "signal", "signaling", "report", "configuration", "indication", "instruction", "command", "channel", "parameter", "field", and "data".

[0405] In some embodiments, the term "send" can be interchanged with terms such as "transmit", "report", and "transmit".

[0406] The information transmission method involved in the embodiments of the present disclosure may include at least one of steps S2401 to S2405. For example, step S2401 can be implemented as an independent embodiment, step S2402 can be implemented as an independent embodiment, step S2403 can be implemented as an independent embodiment, step S2404 can be implemented as an independent embodiment, step S2405 can be implemented as an independent embodiment, steps S2401 to 2405 can be implemented in combination as an independent embodiment, step S2401, step S2404, and step 2405 can be implemented in combination as an independent embodiment, and steps S2401, step S2402, step S2404, and step 2405 can be implemented in combination as an independent embodiment, but the present invention is not limited thereto.

[0407] FIG2e is an interactive diagram illustrating an information transmission method according to an embodiment of the present disclosure. As shown in FIG2e , the present disclosure embodiment relates to an information transmission method for use in a communication system 100, the method comprising:

[0408] Step S2501: The terminal determines a candidate model.

[0409] In some embodiments, the terminal determines N candidate models from M models based on the second information.

[0410] Optionally, N is a positive integer, and 1≤N≤M.

[0411] In some embodiments, the M models may be all available models for the configuration.

[0412] In some embodiments, the terminal and / or network device selects a target model from candidate models, and the target model is used to perform CSI compression and CSI decompression.

[0413] In some embodiments, the terminal may determine N candidate models from M models after accessing the network.

[0414] In some embodiments, the terminal may further determine K candidate models from the N candidate models.

[0415] Optionally, the N candidate models are determined from the M models when the terminal accesses the network, and the K candidate models are determined from the N candidate models according to the current state of the terminal after the terminal runs for a stage.

[0416] This embodiment is described using N candidate models as an example. The processing method for K candidate models is similar to that for N candidate models, and will not be repeated here.

[0417] In some embodiments, the second information may be sent by the network device to the terminal.

[0418] In some embodiments, the second information may be pre-stored in the terminal.

[0419] In some embodiments, the second information may be determined by the terminal.

[0420] In some embodiments, the model may include at least one of the following: an AI model; an ML model.

[0421] In some embodiments, the model includes at least one of a first model and a second model, wherein the first model is located at the terminal and is used to compress the CSI, and the second model is located at the network device end and is used to decompress the compressed CSI.

[0422] In some embodiments, the first model has a binding relationship with the second model.

[0423] Optionally, the model identifier of the first model and the model identifier of the second model may be the same.

[0424] Optionally, the model identifier of the first model and the model identifier of the second model may have a binding association.

[0425] In some embodiments, determining a candidate model by the terminal may include at least one of the following: determining a first model by the terminal; determining a second model by the terminal; or determining the first model and the second model by the terminal. Determining the first model by the terminal is equivalent to simultaneously determining the second model. Determining the second model by the terminal is equivalent to simultaneously determining the first model.

[0426] In some embodiments, the second information may be used to indicate conditions that the candidate model needs to meet.

[0427] In some embodiments, the second information includes at least one of the following:

[0428] Indicative information of candidate model parameters;

[0429] Auxiliary information used to determine candidate models;

[0430] An indication of the current status of the terminal.

[0431] In some embodiments, the auxiliary information may be pre-stored in the terminal, or may be sent to the terminal by a network device.

[0432] In some embodiments, the auxiliary information is used to indicate at least one of the following:

[0433] Input information of candidate models required;

[0434] Output information of candidate models required;

[0435] Data service type;

[0436] Data business scenarios;

[0437] The terminal's capability information is used to determine the candidate models that the terminal can adopt.

[0438] Exemplarily, the terminal may determine N candidate models that meet the current data service scenario from the M models. For example, the terminal may determine N candidate models that meet the outdoor scenario from the M models.

[0439] In some embodiments, the network device may also determine N candidate models from the M models. The specific implementation is similar to that of the terminal side and will not be repeated here.

[0440] Step S2502: The terminal sends the first information.

[0441] In some embodiments, the terminal sends first information to the network device.

[0442] In some embodiments, the first information is used to indicate N candidate models.

[0443] In some embodiments, the target model is determined from N candidate models.

[0444] In some embodiments, the first information is used to indicate N candidate models for the network device to determine the target model.

[0445] In some embodiments, the N candidate models may be the N candidate models determined in the embodiment of Figure 2a, or the K candidate models determined in the embodiment of Figure 2b. This embodiment takes N candidate models as an example.

[0446] In some embodiments, the first information indicating the target model and the first information indicating the N candidate models may be the same information or different information.

[0447] In some embodiments, the first information may indicate N candidate models in a bitmap or other manner.

[0448] Optionally, the first information may be a bitmap of M bits, used to indicate N candidate models selected from M models.

[0449] In some embodiments, the terminal bits indicate the selected N candidate models, where bits are used to determine the value of N, bits are used to indicate the N models selected from M.

[0450] Step S2503: The network device determines the target model.

[0451] In some embodiments, the network device may determine a target model from N candidate models based on a selection rule.

[0452] Determining a target model from N candidate models based on a selection rule includes at least one of the following:

[0453] Determine a target model from N candidate models based on the priority of the candidate models;

[0454] Determining a target model from the N candidate models based on a degree of matching between the candidate models and the second information;

[0455] Based on the performance of the candidate models, a target model is determined from N candidate models;

[0456] Based on the outputs of the candidate models, a target model is determined from N candidate models.

[0457] Step S2504: The network device sends the fifth information.

[0458] In some embodiments, the network device sends fifth information to the terminal.

[0459] In some embodiments, the fifth information is used to indicate a target model.

[0460] In some embodiments, the fifth information is used to indicate a model identifier of the target model.

[0461] In some embodiments, the fifth information is used to indicate the position of the target model among the N candidate models.

[0462] In some embodiments, the terminal bits indicate the target model from N candidate models.

[0463] In some embodiments, if the network device fails to determine the target model, the fifth information indicates a manner in which the terminal transmits the CSI.

[0464] In some embodiments, the fifth information indicates a manner in which the terminal sends the CSI, which is different from a manner in which the CSI is compressed by a model.

[0465] In some embodiments, the fifth information indicates that the terminal may send CSI in a traditional non-AI CSI feedback manner.

[0466] In some embodiments, the terminal compresses the CSI based on the target model indicated by the fifth information.

[0467] In some embodiments, the terminal sends CSI based on the CSI sending method indicated by the fifth information.

[0468] In some embodiments, the term "information" can be interchangeable with terms such as "message", "signal", "signaling", "report", "configuration", "indication", "instruction", "command", "channel", "parameter", "field", and "data".

[0469] In some embodiments, the term "send" can be interchanged with terms such as "transmit", "report", and "transmit".

[0470] The information transmission method involved in the embodiments of the present disclosure may include at least one of steps S2501 to S2505. For example, step S2501 may be implemented as an independent embodiment, step S2502 may be implemented as an independent embodiment, step S2503 may be implemented as an independent embodiment, step S2504 may be implemented as an independent embodiment, and step S2505 may be implemented as an independent embodiment. Steps S2501 to 2505 may be implemented in combination as independent embodiments, step S2501 may be combined with step 2504, and step 2505 may be implemented as independent embodiments, but the present invention is not limited thereto.

[0471] FIG3a is a flow chart of an information transmission method according to an embodiment of the present disclosure. As shown in FIG3a, the present disclosure embodiment relates to an information transmission method, which is executed by terminal 101 and includes:

[0472] Step S3101: Determine candidate models.

[0473] In some embodiments, the optional implementation of step S3101 can refer to the optional implementation of step S2101 in Figure 2a and other related parts of the embodiment involved in Figure 2a, which will not be repeated here.

[0474] Step S3102: Determine the target model.

[0475] In some embodiments, the optional implementation of step S3102 can refer to the optional implementation of step S2102 in Figure 2a and other related parts of the embodiment involved in Figure 2a, which will not be repeated here.

[0476] Step S3103: Send the first information.

[0477] In some embodiments, the optional implementation of step S3103 can refer to the optional implementation of step S2103 in Figure 2a and other related parts of the embodiment involved in Figure 2a, which will not be repeated here.

[0478] The information transmission method involved in the embodiments of the present disclosure may include at least one of steps S3101 to S3103. For example, step S3101 may be implemented as an independent embodiment, step S3102 may be implemented as an independent embodiment, and step S3103 may be implemented as an independent embodiment, but is not limited thereto.

[0479] FIG3b is a flow chart of an information transmission method according to an embodiment of the present disclosure. As shown in FIG3b, the present disclosure embodiment relates to an information transmission method, which is executed by terminal 101 and includes:

[0480] Step S3201: Determine candidate models.

[0481] In some embodiments, the optional implementation of step S3201 can refer to the optional implementation of step S2201 in Figure 2b and other related parts of the embodiment involved in Figure 2b, which will not be repeated here.

[0482] Step S3202: Send the third information.

[0483] In some embodiments, the optional implementation of step S3202 can refer to the optional implementation of step S2202 in Figure 2b and other related parts of the embodiment involved in Figure 2b, which will not be repeated here.

[0484] Step S3203: Obtain the fourth information.

[0485] In some embodiments, the optional implementation of step S3202 can refer to the optional implementation of step S2202 in Figure 2b and other related parts of the embodiment involved in Figure 2b, which will not be repeated here.

[0486] In some embodiments, the terminal 101 receives the first information sent by the network device 102, but is not limited thereto and may also receive the first information sent by other entities.

[0487] In some embodiments, terminal 101 obtains first information specified by a protocol.

[0488] In some embodiments, terminal 101 obtains the first information from upper layer(s).

[0489] In some embodiments, the terminal 101 performs processing to obtain the first information.

[0490] In some embodiments, step S3203 is omitted, and the terminal 101 autonomously implements the function indicated by the first information, or the above function is default or by default.

[0491] Step S3204: Determine the target model.

[0492] In some embodiments, the optional implementation of step S3204 can refer to the optional implementation of step S2204 in Figure 2b and other related parts of the embodiment involved in Figure 2b, which will not be repeated here.

[0493] Step S3205: Send the first information.

[0494] In some embodiments, the optional implementation of step S3205 can refer to the optional implementation of step S2205 in Figure 2b and other related parts of the embodiment involved in Figure 2b, which will not be repeated here.

[0495] The information transmission method involved in the embodiments of the present disclosure may include at least one of steps S3201 to S3205. For example, step S3201 may be implemented as an independent embodiment, step S3202 may be implemented as an independent embodiment, step S3203 may be implemented as an independent embodiment, step S3204 may be implemented as an independent embodiment, step S3205 may be implemented as an independent embodiment, steps S3201 to 3205 may be implemented in combination as independent embodiments, step S3201 may be combined with step 3204, and step 3205 may be implemented as independent embodiments, but the present invention is not limited thereto.

[0496] FIG3c is a flow chart of an information transmission method according to an embodiment of the present disclosure. As shown in FIG3c, the present disclosure embodiment relates to an information transmission method, which is executed by terminal 101 and includes:

[0497] Step S3301: Send the first message.

[0498] In some embodiments, the optional implementation of step S3301 can refer to the optional implementation of step S2301 in Figure 2c and other related parts of the embodiment involved in Figure 2c, which will not be repeated here.

[0499] Step S3302: Obtain sixth information.

[0500] In some embodiments, the optional implementation of step S3302 can refer to the optional implementation of step S2303 in Figure 2c and other related parts of the embodiment involved in Figure 2c, which will not be repeated here.

[0501] In some embodiments, the terminal 101 receives the sixth information sent by the network device 102, but is not limited thereto and may also receive the first information sent by other entities.

[0502] In some embodiments, terminal 101 obtains sixth information specified by the protocol.

[0503] In some embodiments, the terminal 101 obtains the sixth information from an upper layer(s). In some embodiments, the terminal 101 performs processing to obtain the sixth information.

[0504] In some embodiments, step S3302 is omitted, and the terminal 101 autonomously implements the function indicated by the sixth information, or the above function is default or by default.

[0505] The information transmission method involved in the embodiment of the present disclosure may include at least one of step S3301 to step S3302. For example, step S3301 may be implemented as an independent embodiment, and step S3302 may be implemented as an independent embodiment, but is not limited thereto.

[0506] FIG3 d is a flow chart of an information transmission method according to an embodiment of the present disclosure. As shown in FIG3 d , the present disclosure embodiment relates to an information transmission method, which is executed by terminal 101 and includes:

[0507] Step S3401: Obtain sixth information.

[0508] In some embodiments, the optional implementation of step S3401 can refer to the optional implementation of step S2402 in Figure 2d and other related parts of the embodiment involved in Figure 2d, which will not be repeated here.

[0509] In some embodiments, the terminal 101 receives the sixth information sent by the network device 102, but is not limited thereto and may also receive the sixth information sent by other entities.

[0510] In some embodiments, terminal 101 obtains sixth information specified by the protocol.

[0511] In some embodiments, terminal 101 obtains the sixth information from upper layer(s).

[0512] In some embodiments, the terminal 101 performs processing to obtain the sixth information.

[0513] In some embodiments, step S3401 is omitted, and the terminal 101 autonomously implements the function indicated by the sixth information, or the above function is default or by default.

[0514] Step S3402: Send the first message.

[0515] In some embodiments, the optional implementation of step S3402 can refer to the optional implementation of step S2403 in Figure 2d and other related parts of the embodiment involved in Figure 2d, which will not be repeated here.

[0516] Step S3403: Obtain the seventh information.

[0517] In some embodiments, the optional implementation of step S3403 can refer to the optional implementation of step S2405 in Figure 2d and other related parts of the embodiment involved in Figure 2d, which will not be repeated here.

[0518] In some embodiments, the terminal 101 receives the seventh information sent by the network device 102, but is not limited thereto and may also receive the seventh information sent by other entities.

[0519] In some embodiments, terminal 101 obtains seventh information specified by the protocol.

[0520] In some embodiments, the terminal 101 obtains the seventh information from an upper layer(s).

[0521] In some embodiments, the terminal 101 performs processing to obtain the seventh information.

[0522] In some embodiments, step S3403 is omitted, and the terminal 101 autonomously implements the function indicated by the seventh information, or the above function is default or by default.

[0523] The information transmission method involved in the embodiments of the present disclosure may include at least one of steps S3401 to S3403. For example, step S3401 may be implemented as an independent embodiment, step S3402 may be implemented as an independent embodiment, step S3403 may be implemented as an independent embodiment, and step S3401 may be implemented in combination with step S3403 as an independent embodiment, but the present invention is not limited thereto.

[0524] FIG3e is a flow chart of an information transmission method according to an embodiment of the present disclosure. As shown in FIG3e , the present disclosure embodiment relates to an information transmission method, which is executed by terminal 101 and includes:

[0525] Step S3501: Determine candidate models.

[0526] In some embodiments, the optional implementation of step S3501 can refer to the optional implementation of step S2501 in Figure 2e and other related parts of the embodiment involved in Figure 2e, which will not be repeated here.

[0527] Step S3502: Send the first information.

[0528] In some embodiments, the optional implementation of step S3502 can refer to the optional implementation of step S2502 in Figure 2e and other related parts of the embodiment involved in Figure 2e, which will not be repeated here.

[0529] Step S3503: Obtain the fifth information.

[0530] In some embodiments, the optional implementation of step S3503 can refer to the optional implementation of step S2504 in Figure 2e and other related parts of the embodiment involved in Figure 2e, which will not be repeated here.

[0531] In some embodiments, the terminal 101 receives the fifth information sent by the network device 102, but is not limited thereto and may also receive the fifth information sent by other entities.

[0532] In some embodiments, terminal 101 obtains fifth information specified by the protocol.

[0533] In some embodiments, terminal 101 obtains the fifth information from upper layer(s).

[0534] In some embodiments, the terminal 101 performs processing to obtain the fifth information.

[0535] In some embodiments, step S3503 is omitted, and the terminal 101 autonomously implements the function indicated by the fifth information, or the above function is default or by default.

[0536] The information transmission method involved in the embodiments of the present disclosure may include at least one of steps S3501 to S3503. For example, step S3501 may be implemented as an independent embodiment, step S3502 may be implemented as an independent embodiment, step S3503 may be implemented as an independent embodiment, and steps S3501 to 3503 may be implemented in combination as independent embodiments, but the present invention is not limited thereto.

[0537] FIG3f is a flow chart of an information transmission method according to an embodiment of the present disclosure. As shown in FIG3f , the present disclosure embodiment relates to an information transmission method, which is executed by terminal 101 and includes:

[0538] Step S3601: Send the first message.

[0539] In some embodiments, the first information is used to determine a target model for compressing and transmitting channel state information CSI, and the model includes at least one of a first model and a second model.

[0540] In some embodiments, the first model is located at the terminal and is used to compress the CSI, and the second model is located at the network device and is used to decompress the compressed CSI.

[0541] In some embodiments, the first model corresponds to the second model.

[0542] In some embodiments, the method further comprises:

[0543] According to the second information, N candidate models are determined from the M models, wherein the N candidate models are used to determine the target model, and N is a positive integer, and 1≤N≤M.

[0544] In some embodiments, the second information includes at least one of the following:

[0545] Indicative information of candidate model parameters;

[0546] Auxiliary information for determining a candidate model, wherein the auxiliary information is used to indicate output information of the second model;

[0547] Indication information of the current status of the terminal.

[0548] In some embodiments, the method further comprises:

[0549] Determine the target model from the N candidate models; wherein the first information is used to indicate the target model determined by the terminal.

[0550] In some embodiments, the method further comprises:

[0551] Sending third information indicating a current state of the terminal, wherein the third information is used by the network device to determine whether to allow the terminal to determine a target model from the N candidate models;

[0552] Receive fourth information sent by the network device, where the fourth information is used to indicate whether the terminal is allowed to determine a target model from the N candidate models.

[0553] In some embodiments, the first information is used to indicate the N candidate models, wherein the target model is determined from the N candidate models.

[0554] In some embodiments, the first information is used by the network device to determine the target model from the N candidate models.

[0555] In some embodiments, the method further comprises:

[0556] Receive fifth information, where the fifth information is used to indicate one of the following:

[0557] The target model determined by the network device from the N candidate models;

[0558] The terminal sends CSI in a manner, wherein the fifth information is sent by the network device without determining the target model.

[0559] In some embodiments, the first information is used by the network device to determine the target model from M models; or

[0560] When the first information is a first value, it indicates that the target model is determined by the network device.

[0561] In some embodiments, when the first information is a second value, it indicates that the network device is not allowed to determine the target model.

[0562] In some embodiments, the method further comprises:

[0563] Receive sixth information sent by the network device, wherein:

[0564] The first information is used by the network device to determine the target model from M models, and the sixth information is used to indicate the target model; or

[0565] When the first information is the first value, the sixth information is used to indicate the N candidate models determined by the network device from the M models.

[0566] In some embodiments, the method further comprises:

[0567] When the first information is the first value, seventh information sent by the network device is received, where the seventh information is used to indicate one of the following:

[0568] The network device determines a target model from the N candidate models;

[0569] The terminal performs a fallback operation, wherein the seventh information is sent when the network device determines that it does not have the candidate model or the network device is not allowed to determine the target model from the N candidate models.

[0570] In some embodiments, the first information instructs the network device to determine model parameters used by the target model from M models, wherein the model parameters include at least one of the following:

[0571] a channel characteristic vector determined by the terminal;

[0572] A compressed CSI obtained by compressing the feature vector by the M models;

[0573] The M models respectively correspond to model identifiers.

[0574] FIG4a is a flow chart of an information transmission method according to an embodiment of the present disclosure. As shown in FIG4a, the present disclosure embodiment relates to an information transmission method, which is executed by the network device 102. The method includes:

[0575] Step S4101: Obtain first information.

[0576] In some embodiments, the optional implementation of step S4101 can refer to the optional implementation of step S2103 in Figure 2a and other related parts in the embodiment involved in Figure 2a, which will not be repeated here.

[0577] In some embodiments, the network device 102 receives the first information sent by the terminal 101, but is not limited thereto and may also receive the first information sent by other entities.

[0578] In some embodiments, the network device 102 obtains first information specified by the protocol.

[0579] In some embodiments, the network device 102 obtains the first information from an upper layer(s).

[0580] In some embodiments, the network device 102 performs processing to obtain the first information.

[0581] In some embodiments, step S4101 is omitted, and the network device 102 autonomously implements the function indicated by the first information, or the above function is default or by default.

[0582] FIG4b is a flow chart of an information transmission method according to an embodiment of the present disclosure. As shown in FIG4b, the present disclosure embodiment relates to an information transmission method, which is executed by the network device 102, and the method includes:

[0583] Step S4201: Obtain third information.

[0584] In some embodiments, the optional implementation of step S4201 can refer to the optional implementation of step S2202 in Figure 2b and other related parts of the embodiment involved in Figure 2b, which will not be repeated here.

[0585] In some embodiments, the network device 102 receives the third information sent by the terminal 101, but is not limited thereto and may also receive the third information sent by other entities.

[0586] In some embodiments, the network device 102 obtains third information specified by the protocol.

[0587] In some embodiments, the network device 102 obtains the third information from upper layer(s).

[0588] In some embodiments, the network device 102 performs processing to obtain the third information.

[0589] In some embodiments, step S4201 is omitted, and the network device 102 autonomously implements the function indicated by the third information, or the above function is default or by default.

[0590] Step S4202: Send the fourth message.

[0591] In some embodiments, the optional implementation of step S4202 can refer to the optional implementation of step S2203 in Figure 2b and other related parts of the embodiment involved in Figure 2b, which will not be repeated here.

[0592] Step S4203: Obtain first information.

[0593] In some embodiments, the optional implementation of step S4203 can refer to the optional implementation of step S2205 in Figure 2b and other related parts of the embodiment involved in Figure 2b, which will not be repeated here.

[0594] In some embodiments, the network device 102 receives the first information sent by the terminal 101, but is not limited thereto and may also receive the first information sent by other entities.

[0595] In some embodiments, the network device 102 obtains first information specified by the protocol.

[0596] In some embodiments, the network device 102 obtains the first information from an upper layer(s).

[0597] In some embodiments, the network device 102 performs processing to obtain the first information.

[0598] In some embodiments, step S4203 is omitted, and the network device 102 autonomously implements the function indicated by the first information, or the above function is default or by default.

[0599] The information transmission method involved in the embodiments of the present disclosure may include at least one of steps S4201 to S4203. For example, step S4201 may be implemented as an independent embodiment, step S4202 may be implemented as an independent embodiment, step S4203 may be implemented as an independent embodiment, and steps 4201 to 4203 may be implemented in combination as independent embodiments, but the present invention is not limited thereto.

[0600] FIG4c is a flow chart of an information transmission method according to an embodiment of the present disclosure. As shown in FIG4c, the present disclosure embodiment relates to an information transmission method, which is executed by the network device 102 and includes:

[0601] Step S4301: Obtain first information.

[0602] In some embodiments, the optional implementation of step S4301 can refer to the optional implementation of step S2301 in Figure 2c and other related parts of the embodiment involved in Figure 2c, which will not be repeated here.

[0603] In some embodiments, the network device 102 receives the first information sent by the terminal 101, but is not limited thereto and may also receive the first information sent by other entities.

[0604] In some embodiments, the network device 102 obtains first information specified by the protocol.

[0605] In some embodiments, the network device 102 obtains the first information from an upper layer(s). In some embodiments, the network device 102 performs processing to obtain the first information.

[0606] In some embodiments, step S4301 is omitted, and the network device 102 autonomously implements the function indicated by the first information, or the above function is default or by default.

[0607] Step S4302: Determine the target model.

[0608] In some embodiments, the optional implementation of step S4302 can refer to the optional implementation of step S2302 in Figure 2c and other related parts of the embodiment involved in Figure 2c, which will not be repeated here.

[0609] Step S4303: Send the sixth message.

[0610] In some embodiments, the optional implementation of step S43032 can refer to the optional implementation of step S2303 in Figure 2c and other related parts of the embodiment involved in Figure 2c, which will not be repeated here.

[0611] The information transmission method involved in the embodiments of the present disclosure may include at least one of steps S4301 to S4303. For example, step S4301 may be implemented as an independent embodiment, step S4302 may be implemented as an independent embodiment, and step S4303 may be implemented as an independent embodiment, but is not limited thereto.

[0612] FIG4 d is a flow chart of an information transmission method according to an embodiment of the present disclosure. As shown in FIG4 d , the present disclosure embodiment relates to an information transmission method, which is executed by the network device 102 and includes:

[0613] Step S4401: Determine candidate models.

[0614] In some embodiments, the optional implementation of step S4401 can refer to the optional implementation of step S2401 in Figure 2d and other related parts of the embodiment involved in Figure 2d, which will not be repeated here.

[0615] Step S4402: Send the sixth message.

[0616] In some embodiments, the optional implementation of step S4402 can refer to the optional implementation of step S2402 in Figure 2d and other related parts of the embodiment involved in Figure 2d, which will not be repeated here.

[0617] Step S4403: Obtain first information.

[0618] In some embodiments, the optional implementation of step S4403 can refer to the optional implementation of step S2403 in Figure 2d and other related parts of the embodiment involved in Figure 2d, which will not be repeated here.

[0619] In some embodiments, the network device 102 receives the first information sent by the terminal 101, but is not limited thereto and may also receive the first information sent by other entities.

[0620] In some embodiments, the network device 102 obtains first information specified by the protocol.

[0621] In some embodiments, the network device 102 obtains the first information from an upper layer(s).

[0622] In some embodiments, the network device 102 performs processing to obtain the first information.

[0623] In some embodiments, step S4403 is omitted, and the network device 102 autonomously implements the function indicated by the first information, or the above function is default or by default.

[0624] Step S4404: Determine the target model.

[0625] In some embodiments, the optional implementation of step S4404 can refer to the optional implementation of step S2404 in Figure 2d and other related parts of the embodiment involved in Figure 2d, which will not be repeated here.

[0626] Step S4405: Send the seventh message.

[0627] In some embodiments, the optional implementation of step S4405 can refer to the optional implementation of step S2405 in Figure 2d and other related parts of the embodiment involved in Figure 2d, which will not be repeated here.

[0628] The information transmission method involved in the embodiments of the present disclosure may include at least one of steps S4401 to S4405. For example, step S4401 can be implemented as an independent embodiment, step S4402 can be implemented as an independent embodiment, step S4403 can be implemented as an independent embodiment, step S4404 can be implemented as an independent embodiment, step S4405 can be implemented as an independent embodiment, step S4401 combined with step 4405 can be implemented as an independent embodiment, step S4401 combined with step 4405 can be implemented as an independent embodiment, and steps S4401, step S4402, step S4404, and step 4405 can be implemented in combination as independent embodiments, but the present invention is not limited thereto.

[0629] FIG4e is a flow chart of an information transmission method according to an embodiment of the present disclosure. As shown in FIG4e , the present disclosure embodiment relates to an information transmission method, which is executed by the network device 102 and includes:

[0630] Step S4501: Obtain first information.

[0631] In some embodiments, the optional implementation of step S4501 can refer to the optional implementation of step S2502 in Figure 2e and other related parts of the embodiment involved in Figure 2e, which will not be repeated here.

[0632] In some embodiments, the network device 102 receives the first information sent by the terminal 101, but is not limited thereto and may also receive the first information sent by other entities.

[0633] In some embodiments, the network device 102 obtains first information specified by the protocol.

[0634] In some embodiments, the network device 102 obtains the first information from an upper layer(s).

[0635] In some embodiments, the network device 102 performs processing to obtain the first information.

[0636] In some embodiments, step S4501 is omitted, and the network device 102 autonomously implements the function indicated by the first information, or the above function is default or by default.

[0637] Step S4502: Determine the target model.

[0638] In some embodiments, the optional implementation of step S4502 can refer to the optional implementation of step S2503 in Figure 2e and other related parts of the embodiment involved in Figure 2e, which will not be repeated here.

[0639] Step S4503: Send the fifth message.

[0640] In some embodiments, the optional implementation of step S4503 can refer to the optional implementation of step S2504 in Figure 2e and other related parts of the embodiment involved in Figure 2e, which will not be repeated here.

[0641] The information transmission method involved in the embodiments of the present disclosure may include at least one of steps S4501 to S4503. For example, step S4501 may be implemented as an independent embodiment, step S4502 may be implemented as an independent embodiment, step S4503 may be implemented as an independent embodiment, and steps S4501 to 4503 may be implemented in combination as independent embodiments, but the present invention is not limited thereto.

[0642] FIG5 is a flow chart of an information transmission method according to an embodiment of the present disclosure. As shown in FIG5 , the present disclosure embodiment relates to an information transmission method, which is executed by the network device 102 and includes:

[0643] Step S5101: Receive first information.

[0644] In some embodiments, the first information is used to determine a target model for compressing and transmitting channel state information CSI, and the model includes at least one of a first model and a second model.

[0645] In some embodiments, the first model is located at the terminal and is used to compress the CSI, and the second model is located at the network device and is used to decompress the compressed CSI.

[0646] In some embodiments, the first model corresponds to the second model.

[0647] In some embodiments, the method further comprises:

[0648] Send second information, wherein the second information is used by the terminal to determine N candidate models from M models, wherein the N candidate models are used to determine the target model, and N is a positive integer, and 1≤N≤M.

[0649] In some embodiments, the second information includes at least one of the following:

[0650] Indicative information of candidate model parameters;

[0651] Auxiliary information used to determine the candidate model, where the auxiliary information is used to indicate output information of the second model.

[0652] In some embodiments, the N candidate models are used by the terminal to determine the target model; wherein the first information is used to indicate the target model determined by the terminal.

[0653] In some embodiments, the method further comprises:

[0654] receiving third information indicating a current state of the terminal, wherein the third information is used by the network device to determine whether to allow the terminal to determine a target model from the N candidate models;

[0655] Send fourth information, where the fourth information is used to indicate whether the terminal is allowed to determine a target model from the N candidate models.

[0656] In some embodiments, the first information is used to indicate the N candidate models, wherein the target model is determined from the N candidate models.

[0657] In some embodiments, the method further comprises:

[0658] The target model is determined from the N candidate models.

[0659] In some embodiments, the method further comprises:

[0660] Send fifth information, where the fifth information is used to indicate one of the following:

[0661] The target model determined by the network device from the N candidate models;

[0662] The terminal sends CSI in a manner, wherein the fifth information is sent by the network device without determining the target model.

[0663] In some embodiments, the first information is used by the network device to determine the target model from M models; or

[0664] When the first information is a first value, it indicates that the target model is determined by the network device.

[0665] In some embodiments, when the first information is a second value, it indicates that the network device is not allowed to determine the target model.

[0666] In some embodiments, the method further comprises:

[0667] Sending a sixth message, wherein,

[0668] The first information is used by the network device to determine the target model from M models, and the sixth information is used to indicate the target model; or

[0669] When the first information is the first value, the sixth information is used to indicate the N candidate models determined by the network device from the M models.

[0670] In some embodiments, the method further comprises:

[0671] When the first information is the first value, seventh information is sent, where the seventh information is used to indicate one of the following:

[0672] The target model determined by the network device from the N candidate models;

[0673] The terminal performs a fallback operation, wherein the seventh information is sent when the network device determines that it does not have the candidate model or the network device is not allowed to determine the target model from the N candidate models.

[0674] In some embodiments, the first information instructs the network device to determine model parameters used by the target model from M models, wherein the model parameters include at least one of the following:

[0675] a channel characteristic vector determined by the terminal;

[0676] A compressed CSI obtained by compressing the feature vector by the M models;

[0677] The M models respectively correspond to model identifiers.

[0678] FIG6 is an interactive diagram illustrating an information transmission method according to an embodiment of the present disclosure. As shown in FIG6 , the present disclosure embodiment relates to an information transmission method for a communication system 100, and the method includes one of the following steps:

[0679] Step S6101: The terminal sends first information to the network device.

[0680] In some embodiments, the first information is used to determine a target model for compressing and transmitting channel state information CSI, the model comprising at least one of a first model and a second model;

[0681] The first model is located at the terminal and is used to compress the CSI, and the second model is located at the network device and is used to decompress the compressed CSI;

[0682] The first model corresponds to the second model.

[0683] Optional implementations of step S6101 may refer to step S2103 of FIG. 2a , step S2205 of FIG. 2b , step S2301 of FIG. 2c , step S2403 of FIG. 2d , step S2502 of FIG. 2e , step S3103 of FIG. 3a , step S3205 of FIG. 3b , step S3301 of FIG. 3c , step S3401 of FIG. 3d , step S3502 of FIG. 3e , step S3601 of FIG. 3f , step S4101 of FIG. 4a , Step S4203 of Figure 4b, step S4301 of Figure 4c, step S4403 of Figure 4d, step S4501 of Figure 4e, step S5101 of Figure 5, step S6101 of Figure 6, and other related parts in the embodiments involved in Figures 2a, 2b, 2c, 2d, 2e, 3a, 3b, 3c, 3d, 3e, 3f, 4a, 4b, 4c, 4d, 4e, 5, and 6 will not be repeated here.

[0684] In some embodiments, the above method may include the methods of the above-mentioned communication system side, terminal side, network device side, etc. embodiments, which will not be repeated here.

[0685] The following provides some specific examples in combination with any of the above embodiments:

[0686] Assume that M>1 models that can be used for CSI compression are deployed on the UE or network. The UE indicates the supported AI models for CSI compression through capability reporting. The AI ​​models described below can be partial models on the UE (e.g., terminal) side or the NW (e.g., network equipment) side, or a pair of partial models on the UE side and the NW side. The following is an implementation method for selecting a model:

[0687] Implementation method 1: UE side selection model.

[0688] Solution 1: (After the UE initially accesses the network, it makes the first selection based on M models):

[0689] Step 1: The UE side determines 1≤N≤M models from M models based on the parameter information or other auxiliary information configured by the network. For example, the N models under the scenario are determined based on the scenario information configured by the network. The method for determining N models is as follows:

[0690] Method 1: Based on NW configuration parameters or auxiliary information, both the UE and the NW can determine N models, such as determining that there are only these N models in a certain outdoor scene.

[0691] Method 2: UE reports Or a bitmap of size M indicates N models supported or available to the UE.

[0692] Step 2: UE selects one model from N models and sends the selected model indication information to NW, or UE directly sends the ID of the selected model to NW. The overhead of indicating the selected model is or Optionally, the NW sends output information of the NW part model in the N models to the UE.

[0693] Solution 2: (After the UE runs the model for a period of time, due to hardware limitations such as UE power, the highly complex model no longer supports all N models, where N is the N models determined in step 1 of Solution 1.)

[0694] Alt1-1: UE actively sends signaling to NW to notify the number of available models K and the indication information of selecting one model from K models. Alternatively, UE determines to select one model from K models based on the information output by one or N NW part models received. UE can select one model from K models by Or a bitmap of size N indicates the K models available as candidates, where Used to determine the value of K, It is used to indicate which K models are selected from N, and then the UE passes Indicates one model selected from K models, or the UE directly indicates the ID of the selected model to the NW.

[0695] Optionally, the UE sends a signaling to the NW to indicate that the currently used model is no longer available, so that the NW deactivates the current model and performs a fallback operation, or the NW re-instructs the UE to select a model.

[0696] Alt1-2: The UE sends the status information of the UE to the NW, enabling the NW to determine whether to allow model selection and send indication information for model selection to the UE. Then, the UE determines whether to select another model from the K models according to the indication information sent by the NW. If the UE is allowed to select another model, the UE selects one of the K models based on the Alt1-1 method. If the received signaling indicates that the UE performs a fallback operation, the UE does not need to perform model selection anymore.

[0697] Embodiment 2: The NW side selects the model.

[0698] Embodiment 2-1: Perform model selection in a single step.

[0699] The NW directly selects one model from the M models according to the first information sent by the received UE. The first information sent by the UE can be the feature vector of the channel information determined by the UE side according to the downlink pilot, the CSI and model ID related information obtained by compressing the feature vector using M partial models on the UE side respectively. The first information sent by the UE is sent by the UE to the NW after receiving the signaling for NW side to select the model. Each content included in the sent first information can be sent by one signaling or by multiple signals. When sent by one signaling, the compressed information corresponding to each model is distinguished by the model ID, or the compressed information of each model is sent respectively according to a predefined rule.

[0700] Embodiment 2-2: Select the model in two steps.

[0701] Step 1: The NW sends indication information of N candidate models to the UE through the first signaling. The NW can indicate through a bitmap of size M or indication.

[0702] Step 2: The NW receives the model selection indication information sent by the UE to determine whether to select the model. If the UE allows the NW to select the model, the NW selects one model from N < M models according to the information sent by the received UE. If the UE does not allow the NW to select the model, such as there is no available model under the current configuration, the NW does not perform model selection.

[0703] Step 3: The NW sends the second signaling to the UE to indicate the model selected by the NW, or indicate that the UE performs a fallback operation. The second signaling can include the model ID information selected by the NW, or the model selected by the indicated NW.

[0704] Embodiment 3: The NW and the UE side jointly select the model.

[0705] Step 1: The UE receives network configuration parameter information or other auxiliary information and an instruction to select a model. Based on the received network configuration parameter information or other auxiliary information, the UE determines 1≤N(K)≤M(N) available models from M(N) models. For example, the UE determines the N(K) models for a given scenario based on the network configuration scenario information, or determines the K available models based on the UE's operating state. The UE indicates the determined N or K models to the NW using the method in Alt 1.

[0706] Step 2: NW receives the instruction information of UE selecting N or K models, and receives the instruction information sent by UE to select one model from N or K models. NW sends the selected model information or the instruction information of the selected model result to UE. The instruction information is similar to step 3 in Alt2-2, that is, or Indicate the selected model or send the selected model ID to the UE, or indicate that the NW has not selected a model that meets the requirements, and instruct the UE to perform other operations, such as using traditional non-AI CSI feedback.

[0707] Step 3: The UE determines the model selected by the NW or the feedback mode of the UE according to the received NW selected model indication information.

[0708] In the above embodiment, model management includes management based on model ID and management based on function ID. The above method of indicating the selected model by model ID can also indicate the selected model by function ID. That is, the model ID can be replaced by the function ID.

[0709] Example 1 (implementation method 1):

[0710] M = 6 CSI generation and CSI recovery models are deployed on the UE and gNB, respectively. After the UE and gNB perform model identification or function identification, the gNB configures the UE with a cell identifier to indicate that the UE is currently in an outdoor scenario. Based on the model identification results, the UE and gNB can determine N = 2 CSI generation and CSI recovery models in this scenario. In other words, the UE and gNB determine the number of candidate models, N = 2, in the first step.

[0711] The gNB sends a signaling to the UE to instruct the UE to select one model from N=2 models, or the UE directly selects the model based on the channel measured by the downlink pilot signal. Optionally, when the UE selects a model again, the gNB sends the information output by the two CSI recovery models to the UE for the UE to select the model. The UE selects the model through The UE indicates the selected model, or the UE sends the ID of the selected model to the gNB. Finally, the gNB sends signaling to the UE to indicate whether the UE is allowed to use the selected model. If the UE is not allowed to use the selected model, the UE can use traditional non-AI methods to implement CSI feedback, or the UE can continue to use the original CSI generation model.

[0712] After the UE has been running for a period of time using the selected model, due to UE power limitations, the number of models allowed by the UE is reduced to K, or the runnable model is no longer available. The UE actively sends a request signaling to the gNB, indicating that the original running model is no longer available, or that the number of available models is only K = 1. The UE can directly select a model and send the indication information of the selected model to the gNB. Or the UE will determine whether to select a model after receiving the indication signaling sent by the gNB. The UE indicates the number of available models through a size of N = 2 bits, and then through Indicates the selection of a model from K models. Since K = 1, no additional bit is required for the indication. The gNB can determine the model selected by the UE based on the received N = 2 bits.

[0713] In particular, when the UE detects that no model is available, that is, K = 0, the UE reports the value of K to the gNB, which then sends a signaling instruction to the UE to determine whether to use non-AI CSI feedback.

[0714] Example 2 (Implementation Method 2):

[0715] Assume that the parameters of M and N are the same as those in Example 1. The gNB sends a model selection indication message to the UE, instructing the UE to send the compressed information of M or N CSI generation models and the feature vector information of the channel information of each subband determined based on the downlink pilot signal, such as CSI-RS, to the gNB. The gNB then selects one model from the M or N models based on the received information. The gNB indicates the selected model information to the UE directly through the model ID or function ID, or the gNB indicates the selected model information to the UE through the model ID or function ID. and Indicates the selected model.

[0716] If the value of N cannot be determined by the parameters configured by the gNB, but is indicated by the gNB, the gNB shall use a parameter of size M = 6 bits or Indicates the selected N models, where and Respectively, gNB selects N models and selects N models from M models. Then, Indicates which model is selected, or the gNB directly indicates the selected model ID or function ID to the UE. In particular, if the gNB fails to select a model that meets the performance requirements, the gNB sends an indication message to the UE to instruct the UE to perform traditional non-AI CSI feedback.

[0717] Example 3 (Implementation Method 3):

[0718] As in Example 1, after receiving the model selection indication information sent by the gNB, the UE first selects N models from the M models, or selects K available models from the N models. The UE sends the indication information of the selected N or K models to the gNB.

[0719] The gNB selects an optimal model from the N or K models based on the model indication information received from the UE and the input and output information of the N or K models sent by the UE. The input information of the N or K models can be the same or different. The UE selects a method of periodic, semi-continuous, aperiodic reporting or event triggering to report the input and output information of these models to the gNB one or more times. The gNB then reports the selected model information to the gNB through or Instruct the UE, or directly send the selected model ID or function ID information to the UE.

[0720] The UE determines the CSI generation model adopted by the UE based on the indication information sent by the gNB, or determines whether to use the traditional non-AI method to feedback CSI.

[0721] 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.

[0722] 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.

[0723] In the embodiment of the present disclosure, the processor is a circuit with signal processing capability. In one implementation, the processor can be a circuit with instruction reading and execution capability, 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, and the logical relationship of the above hardware circuit is fixed or reconfigurable, such as a hardware circuit implemented by a processor as 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.

[0724] Figure 7a is a schematic diagram of the structure of a terminal proposed in an embodiment of the present disclosure. As shown in Figure 7a, terminal 7100 may include at least one of a transceiver module 7101 and a processing module 7102. In some embodiments, the transmitting module 7101 is used to send first information, which is used to determine a target model for compressing and transmitting channel state information (CSI), wherein the model includes at least one of a first model and a second model; wherein the first model is located at the terminal and is used to compress the CSI, and the second model is located at the network device end and is used to decompress the compressed CSI; and the first model corresponds to the second model. Optionally, the transceiver module is used to execute at least one of the communication steps such as sending and / or receiving performed by the terminal 101 in any of the above methods (for example, step S2103, step S2201, step S2202, step S2203, step S2205, step S2301, step S2303, step S2402, step S2403, step S2405, step S2502, step S2504, but not limited to these), which are not described in detail here. Optionally, the processing module is used to execute at least one of the other steps (for example, step S2101, step S2102, step S2201, step S2204, step S2501, but not limited to these) performed by the terminal 101 in any of the above methods, which are not described in detail here.

[0725] Figure 7b is a schematic diagram of the structure of a network device proposed in an embodiment of the present disclosure. As shown in Figure 7b, network device 7200 may include: at least one of a transceiver module 7201, a processing module 7202, etc. In some embodiments, the transceiver module 7201 is used to receive first information, and the first information is used to determine a target model for compressing and transmitting channel state information (CSI), wherein the model includes at least one of a first model and a second model; wherein the first model is located at the terminal and is used to compress the CSI, and the second model is located at the network device end and is used to decompress the compressed CSI; and the first model corresponds to the second model. Optionally, the transceiver module is used to execute at least one of the communication steps such as sending and / or receiving performed by the terminal 101 in any of the above methods (for example, step S2103, step S2201, step S2202, step S2203, step S2205, step S2301, step S2303, step S2402, step S2403, step S2405, step S2502, step S2504, but not limited to these), which are not described in detail here. Optionally, the processing module is used to execute at least one of the other steps (for example, step S2302, step S2401, step S2404, step S2503, but not limited to these) performed by the network device 102 in any of the above methods, which are not described in detail here.

[0726] Figure 8a is a schematic diagram of the structure of a communication device 8100 proposed in an embodiment of the present disclosure. Communication device 8100 can be a network device (e.g., an access network device, a core network device, etc.), a terminal (e.g., a user equipment, etc.), a chip, a chip system, or a processor that supports a network device to implement any of the above methods, or a chip, a chip system, or a processor that supports a terminal to implement any of the above methods. Communication device 8100 can be used to implement the methods described in the above method embodiments. For details, please refer to the description of the above method embodiments.

[0727] As shown in Figure 8a, the communication device 8100 includes one or more processors 8101. The processor 8101 can be a general-purpose processor or a dedicated processor, for example, a baseband processor or a central processing unit. The baseband processor can be used to process 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 8100 is used to perform any of the above methods. Optionally, one or more processors 8101 are used to call instructions to enable the communication device 8100 to perform any of the above methods.

[0728] In some embodiments, the communication device 8100 further includes one or more transceivers 8102. When the communication device 8100 includes one or more transceivers 8102, the transceiver 8102 performs at least one of the communication steps such as sending and / or receiving in the above method (for example, step S2103, step S2201, step S2202, step S2203, step S2205, step S2301, step S2303, step S2402, step S2403, step S2405, step S2502, and step S2504, but not limited thereto), and the processor 8101 performs at least one of the other steps (for example, step S2101, step S2102, step S2201, step S2204, step S2501, step S2302, step S2401, step S2404, and step S2503, but not limited thereto). In an optional embodiment, the transceiver may include a receiver and / or a transmitter. The receiver and transmitter may be separate or integrated. Optionally, the terms transceiver, transceiver unit, transceiver, 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.

[0729] In some embodiments, the communication device 8100 further includes one or more memories 8103 for storing data. Alternatively, all or part of the memories 8103 may be located outside the communication device 8100. In alternative embodiments, the communication device 8100 may include one or more interface circuits 8104. Optionally, the interface circuits 8104 are connected to the memory 8102 and may be configured to receive data from the memory 8102 or other devices, or to send data to the memory 8102 or other devices. For example, the interface circuits 8104 may read data stored in the memory 8102 and send the data to the processor 8101.

[0730] The communication device 8100 described in the above embodiment may be a network device or a terminal, but the scope of the communication device 8100 described in the present disclosure is not limited thereto, and the structure of the communication device 8100 may not be limited by FIG. 8a. 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.

[0731] FIG8b is a schematic diagram of the structure of a chip 8200 according to an embodiment of the present disclosure. If the communication device 8100 can be a chip or a chip system, reference can be made to the schematic diagram of the structure of the chip 8200 shown in FIG8b, but the present disclosure is not limited thereto.

[0732] The chip 8200 includes one or more processors 8201. The chip 8200 is configured to execute any of the above methods.

[0733] In some embodiments, chip 8200 further includes one or more interface circuits 8202. Terms such as interface circuit, interface, and transceiver pins may be used interchangeably. In some embodiments, chip 8200 further includes one or more memories 8203 for storing data. Alternatively, all or part of memory 8203 may be located external to chip 8200. Optionally, interface circuit 8202 is connected to memory 8203 and may be used to receive data from memory 8203 or other devices, or may be used to send data to memory 8203 or other devices. For example, interface circuit 8202 may read data stored in memory 8203 and send the data to processor 8201.

[0734] In some embodiments, the interface circuit 8202 performs at least one of the communication steps such as sending and / or receiving in the above method (e.g., step S2103, step S2201, step S2202, step S2203, step S2205, step S2301, step S2303, step S2402, step S2403, step S2405, step S2502, and step S2504, but not limited thereto). The interface circuit 8202 performing the communication steps such as sending and / or receiving in the above method, for example, means that the interface circuit 8202 performs data exchange between the processor 8201, the chip 8200, the memory 8203, or the transceiver device. In some embodiments, the processor 8201 executes at least one of the other steps (for example, step S2101, step S2102, step S2201, step S2204, step S2501, step S2302, step S2401, step S2404, step S2503, but not limited thereto).

[0735] The present disclosure also proposes a storage medium having instructions stored thereon, which, when executed on the communication device 8100, causes the communication device 8100 to execute any of the above methods. Optionally, the storage medium is an electronic storage medium. Optionally, the storage medium is a computer-readable storage medium, but is not limited thereto, and may also be a storage medium readable by other devices. Optionally, the storage medium may be a non-transitory storage medium, but is not limited thereto, and may also be a temporary storage medium.

[0736] The present disclosure also provides a program product, which, when executed by the communication device 8100, enables the communication device 8100 to perform any of the above methods. Optionally, the program product is a computer program product.

[0737] The present disclosure also proposes a computer program, which, when executed on a computer, causes the computer to perform any one of the above methods.

Claims

1. An information transmission method, characterized in that: Methods include: The terminal sends first information, where the first information is used to determine a target model for compressing and transmitting channel state information CSI, where the model includes at least one of a first model and a second model; The first model is located at the terminal and is used to compress the CSI, and the second model is located at the network device end and is used to decompress the compressed CSI; The first model corresponds to the second model.

2. The method according to claim 1, characterized in that The method further comprises: According to the second information, N candidate models are determined from the M models, wherein the N candidate models are used to determine the target model, and N is a positive integer, and 1≤N≤M.

3. The method according to claim 2, characterized in that The second information includes at least one of the following: Indicative information of candidate model parameters; Auxiliary information for determining a candidate model, wherein the auxiliary information is used to indicate output information of the second model; Indicative information of the current status of the terminal.

4. The method according to claim 2, characterized in that: The method further comprises: Determine the target model from the N candidate models; wherein the first information is used to indicate the target model determined by the terminal.

5. The method according to any one of claims 2 to 4, characterized in that: The method further comprises: Sending third information indicating a current state of the terminal, wherein the third information is used by the network device to determine whether to allow the terminal to determine a target model from the N candidate models; Receive fourth information sent by the network device, where the fourth information is used to indicate whether the terminal is allowed to determine a target model from the N candidate models.

6. The method according to claim 2, characterized in that The first information is used to indicate the N candidate models, wherein the target model is determined from the N candidate models.

7. The method according to claim 6, characterized in that The first information is used by the network device to determine the target model from the N candidate models.

8. The method according to claim 7, characterized in that The method further comprises: Receive fifth information, where the fifth information is used to indicate one of the following: The target model determined by the network device from the N candidate models; The terminal sends CSI in a manner, wherein the fifth information is sent by the network device without determining the target model.

9. The method according to claim 1, characterized in that: The first information is used by the network device to determine the target model from M models; or When the first information is a first value, it indicates that the target model is determined by the network device.

10. The method according to claim 9, characterized in that When the first information is a second value, it indicates that the network device is not allowed to determine the target model.

11. The method according to claim 9, characterized in that The method further comprises: receiving sixth information sent by the network device, wherein: The first information is used by the network device to determine the target model from M models, and the sixth information is used to indicate the target model; or When the first information is the first value, the sixth information is used to indicate the N candidate models determined by the network device from the M models.

12. The method according to claim 11, characterized in that The method further comprises: When the first information is the first value, seventh information sent by the network device is received, wherein the seventh information is used to indicate one of the following: The network device determines a target model from the N candidate models; The terminal performs a fallback operation, wherein the seventh information is sent when the network device determines that it does not have the candidate model or the network device is not allowed to determine the target model from the N candidate models.

13. The method according to any one of claims 9 to 12, characterized in that: The first information instructs the network device to determine a model parameter adopted by the target model from the M models, wherein the model parameter includes at least one of the following: A channel feature vector determined by the terminal; The compressed CSI obtained after the M models compress the feature vector; and the model identifiers corresponding to the M models respectively.

14. An information transmission method, characterized in that: The method comprises: The network device receives first information, where the first information is used to determine a target model for compressing and transmitting channel state information CSI, where the model includes at least one of a first model and a second model; The first model is located at the terminal and is used to compress the CSI, and the second model is located at the network device and is used to decompress the compressed CSI; The first model corresponds to the second model.

15. The method according to claim 14, characterized in that The method further comprises: Sending second information, wherein the second information is used by the terminal to determine N candidate models from M models, wherein the N candidate models are used to determine the target model, and N is a positive integer, and 1≤N≤M.

16. The method according to claim 15, characterized in that The second information includes at least one of the following: Indicative information of candidate model parameters; Auxiliary information used to determine the candidate model, where the auxiliary information is used to indicate output information of the second model.

17. The method according to claim 15, characterized in that The N candidate models are used by the terminal to determine the target model; wherein the first information is used to indicate the target model determined by the terminal.

18. The method according to any one of claims 15 to 17, characterized in that The method further comprises: receiving third information indicating a current state of the terminal, wherein the third information is used by the network device to determine whether to allow the terminal to determine a target model from the N candidate models; Send fourth information, where the fourth information is used to indicate whether the terminal is allowed to determine the target model from the N candidate models.

19. The method according to claim 15, characterized in that The first information is used to indicate the N candidate models, wherein the target model is determined from the N candidate models.

20. The method according to claim 19, characterized in that The method further comprises: The target model is determined from the N candidate models.

21. The method according to claim 20, characterized in that The method further comprises: Sending fifth information, wherein the fifth information is used to indicate one of the following: The target model determined by the network device from the N candidate models; The terminal sends CSI in a manner, wherein the fifth information is sent by the network device without determining the target model.

22. The method according to claim 14, characterized in that The first information is used by the network device to determine the target model from M models; or When the first information is a first value, it indicates that the target model is determined by the network device.

23. The method according to claim 22, characterized in that When the first information is a second value, it indicates that the network device is not allowed to determine the target model.

24. The method according to claim 22, characterized in that The method further comprises: Sending a sixth message, wherein The first information is used by the network device to determine the target model from M models, and the sixth information is used to indicate the target model; or When the first information is the first value, the sixth information is used to indicate the N candidate models determined by the network device from the M models.

25. The method according to claim 24, characterized in that The method further comprises: When the first information is the first value, seventh information is sent, where the seventh information is used to indicate one of the following: The target model determined by the network device from the N candidate models; The terminal performs a fallback operation, wherein the seventh information is sent when the network device determines that it does not have the candidate model or the network device is not allowed to determine the target model from the N candidate models.

26. The method according to any one of claims 22 to 25, characterized in that The first information instructs the network device to determine a model parameter adopted by the target model from the M models, wherein the model parameter includes at least one of the following: A channel feature vector determined by the terminal; A compressed CSI obtained by compressing the feature vector by the M models; The M models respectively correspond to model identifiers.

27. An information transmission method, performed by a communication system, characterized in that: The method comprises: The terminal sends first information to the network device, where the first information is used to determine a target model for compressing and transmitting the channel state information CSI, where the model includes at least one of a first model and a second model; The first model is located at the terminal and is used to compress the CSI, and the second model is located at the network device and is used to decompress the compressed CSI; The first model corresponds to the second model.

28. A terminal, characterized in that: The terminal comprises: A transceiver module, configured to send first information, where the first information is used to determine a target model for compressing and transmitting channel state information CSI, where the model includes at least one of a first model and a second model; The first model is located at the terminal and is used to compress the CSI, and the second model is located at the network device end and is used to decompress the compressed CSI; The first model corresponds to the second model.

29. A network device, characterized in that: The network equipment includes: A transceiver module, configured to receive first information, where the first information is used to determine a target model for compressing and transmitting channel state information CSI, where the model includes at least one of a first model and a second model; The first model is located at the terminal and is used to compress the CSI, and the second model is located at the network device and is used to decompress the compressed CSI; The first model corresponds to the second model.

30. A communication system, characterized in that: The communication system includes: a terminal and a network device; wherein, The terminal is configured to implement the information transmission method according to any one of claims 1 to 13; The network device is configured to implement the information transmission method according to any one of claims 14 to 26.

31. A communication device, characterized in that: The communication device comprises: one or more processors; The processor is used to call instructions so that the communication device executes the information transmission method according to any one of claims 1 to 13 and claims 14 to 26.

32. A storage medium, characterized in that: The storage medium stores instructions, and when the instructions are executed on the communication device, the communication device executes the information transmission method according to any one of claims 1 to 13 and claims 14 to 26.

Images