Information transmission method, and apparatus and storage medium

Abstract

Provided in the present disclosure are an information transmission method, and an apparatus and a storage medium. The method comprises: sending first information to a second device, wherein the first information is at least used for identifying a first artificial intelligence (AI) model and / or a second AI model, the first AI model is used for compressing channel state information (CSI), and the second AI model is used for decompressing the compressed CSI. The present disclosure can achieve the aim of identifying the first AI model and / or the second AI model, and using AI technology improves the reliability and availability of CSI transmission, reduces the feedback overhead of a terminal, and improves the feedback precision of the CSI.

Description

Information transmission method and device, and storage medium Technical Field

[0001] The present disclosure relates to the field of communications, and in particular to an information transmission method and device, and a storage medium. Background Art

[0002] Currently, artificial intelligence (AI) technology can be used to reduce terminal feedback overhead or improve feedback accuracy.

[0003] Summary of the Invention

[0004] To improve the availability and reliability of AI technology in the information transmission process, the embodiments of the present disclosure provide an information transmission method and device, and a storage medium.

[0005] According to a first aspect of an embodiment of the present disclosure, there is provided an information transmission method, the method being performed by a first device and including:

[0006] First information is sent to a second device, where the first information is at least used to identify a first artificial intelligence (AI) model and / or a second AI model, where the first AI model is used to compress channel state information (CSI), and the second AI model is used to decompress the compressed CSI.

[0007] According to a second aspect of an embodiment of the present disclosure, there is provided an information transmission method, the method being performed by a second device, including:

[0008] Receive first information sent by a first device, where the first information is used at least to identify a first artificial intelligence (AI) model and / or a second AI model, where the first AI model is used to compress channel state information (CSI), and the second AI model is used to decompress the compressed CSI.

[0009] According to a third aspect of an embodiment of the present disclosure, there is provided a first device, including:

[0010] The transceiver module is configured to send first information to the second device, where the first information is used at least to identify a first artificial intelligence (AI) model and / or a second AI model, where the first AI model is used to compress channel state information (CSI), and the second AI model is used to decompress the compressed CSI.

[0011] According to a fourth aspect of an embodiment of the present disclosure, a second device is provided, including:

[0012] The transceiver module is configured to receive first information sent by a first device, where the first information is used at least to identify a first artificial intelligence (AI) model and / or a second AI model, where the first AI model is used to compress channel state information (CSI), and the second AI model is used to decompress the compressed CSI.

[0013] According to a fifth aspect of an embodiment of the present disclosure, a first device is provided, including:

[0014] one or more processors;

[0015] The processor is used to execute the information transmission method described in any one of the first aspects.

[0016] According to a sixth aspect of an embodiment of the present disclosure, a second device is provided, including:

[0017] one or more processors;

[0018] The processor is used to execute the information transmission method described in any one of the second aspects.

[0019] According to a seventh aspect of an embodiment of the present disclosure, there is provided a communication system, including:

[0020] A first device, wherein the first device is configured to implement the information transmission method according to any one of the first aspects;

[0021] A second device, wherein the second device is configured to implement the information transmission method described in any one of the second aspects.

[0022] According to an eighth aspect of an embodiment of the present disclosure, a storage medium is provided, which stores instructions. When the instructions are executed on a communication device, the communication device executes the information transmission method as described in any one of the first aspect or the second aspect.

[0023] According to a ninth aspect of an embodiment of the present disclosure, a computer program product is provided, comprising a computer program, which, when executed by a processor, is used to implement the information transmission method described in any one of the first aspect or the second aspect.

[0024] In an embodiment of the present disclosure, after a first device has acquired the first AI model and / or the second AI model, it can interact with a second device, thereby allowing the second device to identify the first AI model and / or the second AI model. The first AI model is used to compress channel state information (CSI), and the second AI model is used to decompress the compressed CSI. The present disclosure can achieve the purpose of identifying the first AI model and / or the second AI model, using AI technology to improve the reliability and availability of CSI transmission, reduce terminal feedback overhead, and improve CSI feedback accuracy.

[0025] It is to be understood that the foregoing general description and the following detailed description are exemplary and explanatory only and are not restrictive of the disclosure. BRIEF DESCRIPTION OF THE DRAWINGS

[0026] The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the invention and, together with the description, serve to explain the principles of the invention.

[0027] FIG1A is an exemplary schematic diagram of the architecture of a communication system provided according to an embodiment of the present disclosure.

[0028] FIG1B is an exemplary schematic diagram of a bilateral AI model provided according to an embodiment of the present disclosure.

[0029] FIG2A is an exemplary interaction diagram of an information transmission method provided according to an embodiment of the present disclosure.

[0030] FIG2B is an exemplary interaction diagram of the information transmission method provided according to an embodiment of the present disclosure.

[0031] FIG2C is an exemplary interaction diagram of the information transmission method provided according to an embodiment of the present disclosure.

[0032] FIG2D is an exemplary interaction diagram of the information transmission method provided according to an embodiment of the present disclosure.

[0033] FIG2E is an exemplary interaction diagram of the information transmission method provided according to an embodiment of the present disclosure.

[0034] FIG2F is an exemplary interaction diagram of the information transmission method provided according to an embodiment of the present disclosure.

[0035] FIG3A is an exemplary interaction diagram of an information transmission method provided according to an embodiment of the present disclosure.

[0036] FIG3B is an exemplary interaction diagram of the information transmission method provided according to an embodiment of the present disclosure.

[0037] FIG4A is a schematic diagram of an exemplary interaction of an information transmission method provided according to an embodiment of the present disclosure.

[0038] FIG4B is an exemplary interaction diagram of the information transmission method provided according to an embodiment of the present disclosure.

[0039] FIG4C is an exemplary interaction diagram of the information transmission method provided according to an embodiment of the present disclosure.

[0040] FIG4D is an exemplary interaction diagram of the information transmission method provided according to an embodiment of the present disclosure.

[0041] FIG4E is an exemplary interaction diagram of the information transmission method provided according to an embodiment of the present disclosure.

[0042] FIG4F is an exemplary interaction diagram of the information transmission method provided according to an embodiment of the present disclosure.

[0043] FIG5A is an exemplary block diagram of a first device according to an embodiment of the present disclosure.

[0044] FIG5B is an exemplary block diagram of a second device provided according to an embodiment of the present disclosure.

[0045] FIG6A is a schematic diagram of an exemplary interaction of a communication device according to an embodiment of the present disclosure.

[0046] FIG6B is an exemplary interaction diagram of a chip provided according to an embodiment of the present disclosure. DETAILED DESCRIPTION

[0047] Exemplary embodiments will be described in detail herein, examples of which are illustrated in the accompanying drawings. In the following description, when referring to the drawings, like numbers in different figures represent like or similar elements unless otherwise indicated. The embodiments described in the following exemplary embodiments are not intended to represent all possible embodiments consistent with the present invention. Rather, they are merely examples of apparatus and methods consistent with certain aspects of the present invention, as detailed in the appended claims.

[0048] The embodiments of the present disclosure provide an information transmission method, an information transmission device, and a storage medium.

[0049] In a first aspect, an embodiment of the present disclosure provides an information transmission method, which is performed by a first device and includes:

[0050] First information is sent to a second device, where the first information is at least used to identify a first artificial intelligence (AI) model and / or a second AI model, where the first AI model is used to compress channel state information (CSI), and the second AI model is used to decompress the compressed CSI.

[0051] In the above embodiment, the first device may send first information to the second device. The first information may be used to identify at least a first AI model and / or a second AI model. The first AI model is used to compress channel state information (CSI), and the second AI model is used to decompress the compressed CSI. The present disclosure can achieve the purpose of identifying the first AI model and / or the second AI model, using AI technology to improve the reliability and availability of CSI transmission, reduce terminal feedback overhead, and improve CSI feedback accuracy.

[0052] In conjunction with some embodiments of the first aspect, in some embodiments, the method further includes:

[0053] The second device is a terminal, and receives capability indication information sent by the second device, where the capability indication information is used to indicate AI model capabilities supported by the second device;

[0054] The sending the first information to the second device includes:

[0055] The capability indication information indicates that the second device supports the first AI model and / or the second AI model, and the first information is sent to the second device.

[0056] In the above embodiment, when the second device is a terminal, the first device can receive capability indication information reported by the second device and, upon determining based on the capability indication information that the second device supports the first AI model and / or the second AI model, send the first information to the second device. This achieves the purpose of providing the terminal with the first information based on the terminal's capabilities, and provides high availability.

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

[0058] an AI model identifier supported by the second device;

[0059] The AI ​​model structure supported by the second device.

[0060] In the above embodiment, the capability indication information can be used to indicate at least one of the above items, thereby informing the network device of the terminal's ability to support the AI ​​model, so that the network device determines whether to provide the first information to the terminal, thereby improving the reliability of AI model recognition.

[0061] In conjunction with some embodiments of the first aspect, in some embodiments, the method further includes:

[0062] The second device is a terminal, and second information is sent to the second device. The second information is used by the second device to determine whether it can recognize the first AI model and / or the second AI model, and determine to receive the first information when it can be recognized.

[0063] In the above embodiment, the network device may first send the second information to the terminal. If the terminal determines that it can recognize the first AI model and / or the second AI model based on the second information, it then receives the first information. This avoids wasting signaling resources and improves availability.

[0064] In conjunction with some embodiments of the first aspect, in some embodiments, the second information includes at least one of the following:

[0065] the first AI model;

[0066] the second AI model;

[0067] A training dataset, where the training dataset is a dataset used to train the first AI model and / or the second AI model;

[0068] Configuration parameters, where the configuration parameters correspond to the first AI model and / or the second AI model;

[0069] A model identifier, where the model identifier is used to identify the first AI model and / or the second AI model.

[0070] In the above embodiment, the second information may include but is not limited to at least one of the above items, which is easy to implement and has high usability.

[0071] In conjunction with some embodiments of the first aspect, in some embodiments, the method further includes:

[0072] receiving first indication information sent by the second device, where the first indication information is used to instruct the second device to determine to receive the first information;

[0073] The sending the first information to the second device includes:

[0074] Based on the first indication information, the first information is sent to the second device.

[0075] In the above embodiment, when the terminal determines that it can identify the first AI model and / or the second AI model based on the second information, it can send first indication information to the network device, so that the network device sends the first information to the terminal based on the first indication information. The first information can be transmitted in a targeted manner with high availability.

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

[0077] Sending second indication information to the second device, where the second indication information is used to instruct the second device to send auxiliary information, where the auxiliary information is used to assist the first device in determining whether to send the first information to the second device;

[0078] receiving the auxiliary information sent by the second device based on the second indication information;

[0079] Based on the auxiliary information, it is determined whether to send the first information to the second device.

[0080] In the above embodiment, the first device may determine whether to send the first information to the second device based on the auxiliary information sent by the second device, thereby improving the reliability of recognition of the first AI model and / or the second AI model.

[0081] In conjunction with some embodiments of the first aspect, in some embodiments, the method further includes:

[0082] receiving auxiliary information and / or third indication information sent by the second device, where the auxiliary information is used to assist the first device in determining whether to send the first information to the second device, and the third indication information is used to instruct the first device to send the first information to the second device;

[0083] Based on the auxiliary information and / or the third indication information, determine whether to send the first information to the second device.

[0084] In the above embodiment, the second device can actively initiate a model recognition process to achieve the purpose of identifying the first AI model and / or the second AI model. The use of AI technology improves the reliability and availability of CSI transmission, reduces the feedback overhead of the terminal, and improves the feedback accuracy of CSI.

[0085] In conjunction with some embodiments of the first aspect, in some embodiments, the auxiliary information includes at least one of the following:

[0086] Channel scenario information;

[0087] mobility information of the second device;

[0088] software parameter information of the second device;

[0089] Hardware parameter information of the second device.

[0090] In the above embodiment, the auxiliary information may include but is not limited to at least one of the above items, which assists the first device in determining whether to send the first information to the second device, thereby improving the reliability of the transmission of the first information.

[0091] In conjunction with some embodiments of the first aspect, in some embodiments, the first information includes at least one of the following:

[0092] a model identifier, where the model identifier is used to identify the first AI model and / or the second AI model;

[0093] the first AI model;

[0094] the second AI model;

[0095] A training data set, where the training data set is a data set used to train the first AI model and / or the second AI model.

[0096] In the above embodiments, the first information may include, but is not limited to, at least one of the above items. This allows the second device to identify the first AI model and / or the second AI model based on the first information, thereby achieving AI model identification. Furthermore, the use of AI technology improves the reliability and availability of CSI transmission, reduces terminal feedback overhead, and improves the accuracy of CSI feedback.

[0097] In conjunction with some embodiments of the first aspect, in some embodiments, the model identification includes at least one of the following:

[0098] First AI model identification;

[0099] Second AI model identification;

[0100] The updated first AI model identifier;

[0101] Updated second AI model identifier;

[0102] a pairing identifier, where the pairing identifier is used to identify a pairing between the first AI model and the second AI model;

[0103] a training session identifier, the training session identifier being associated with the first AI model and / or the second AI model;

[0104] A training data set identifier, where the training data set identifier is associated with the first AI model and / or the second AI model.

[0105] In the above embodiments, the AI ​​model in the present disclosure can be identified by at least one of the above items, which is simple to implement and has high usability.

[0106] In a second aspect, an embodiment of the present disclosure provides an information transmission method, which is performed by a second device and includes:

[0107] Receive first information sent by a first device, where the first information is used at least to identify a first artificial intelligence (AI) model and / or a second AI model, where the first AI model is used to compress channel state information (CSI), and the second AI model is used to decompress the compressed CSI.

[0108] In the above embodiment, the first AI model and / or the second AI model can be identified based on the first information, and the use of AI technology improves the reliability and availability of CSI transmission, reduces the feedback overhead of the terminal, and improves the feedback accuracy of CSI.

[0109] In conjunction with some embodiments of the second aspect, in some embodiments, the method further includes:

[0110] The second device is a terminal, which sends capability indication information to the first device, where the capability indication information is used to indicate the AI ​​model capabilities supported by the second device.

[0111] In conjunction with some embodiments of the second aspect, in some embodiments, the capability indication information includes at least one of the following:

[0112] Model identifiers supported by the second device;

[0113] A model structure supported by the second device.

[0114] In conjunction with some embodiments of the second aspect, in some embodiments, the method further includes:

[0115] The second device is a terminal, which receives second information sent by the first device. The second information is used by the second device to determine whether it can recognize the first AI model and / or the second AI model, and determine to receive the first information when it can be recognized.

[0116] In conjunction with some embodiments of the second aspect, in some embodiments, the second information includes at least one of the following:

[0117] the first AI model;

[0118] the second AI model;

[0119] A training dataset, where the training dataset is a dataset used to train the first AI model and / or the second AI model;

[0120] Configuration parameters, where the configuration parameters correspond to the first AI model and / or the second AI model;

[0121] A model identifier, where the model identifier is used to identify the first AI model and / or the second AI model.

[0122] In conjunction with some embodiments of the second aspect, in some embodiments, the method further includes any one of the following:

[0123] The second information includes the training data set, and determines that the first AI model and / or the second AI model can be identified;

[0124] supporting the first AI model and / or the second AI model included in the second information, and determining that the first AI model and / or the second AI model can be recognized;

[0125] The first AI model and / or the second AI model included in the second information is not supported, and it is determined that the first AI model and / or the second AI model cannot be identified.

[0126] In conjunction with some embodiments of the second aspect, in some embodiments, the method further includes:

[0127] Determine that the first AI model and / or the second AI model can be recognized, and send first indication information to the first device, where the first indication information is used to instruct the second device to determine to receive the first information.

[0128] In conjunction with some embodiments of the second aspect, in some embodiments, the method further includes:

[0129] receiving second indication information sent by the first device, where the second indication information is used to instruct the second device to send auxiliary information, where the auxiliary information is used to assist the first device in determining whether to send the first information to the second device;

[0130] Based on the second indication information, the auxiliary information is sent to the first device.

[0131] In conjunction with some embodiments of the second aspect, in some embodiments, the method further includes:

[0132] Auxiliary information and / or third indication information are sent to the first device, where the auxiliary information is used to assist the first device in determining whether to send the first information to the second device, and the third indication information is used to instruct the first device to send the first information to the second device.

[0133] In conjunction with some embodiments of the second aspect, in some embodiments, the auxiliary information includes at least one of the following:

[0134] Channel scenario information;

[0135] mobility information of the second device;

[0136] software parameter information of the second device;

[0137] Hardware parameter information of the second device.

[0138] In conjunction with some embodiments of the second aspect, in some embodiments, the first information includes at least one of the following:

[0139] a model identifier, where the model identifier is used to identify the first AI model and / or the second AI model;

[0140] the first AI model;

[0141] the second AI model;

[0142] A training data set, where the training data set is a data set used to train the first AI model and / or the second AI model.

[0143] In conjunction with some embodiments of the second aspect, in some embodiments, the model identifier includes at least one of the following:

[0144] First AI model identification;

[0145] Second AI model identification;

[0146] The updated first AI model identifier;

[0147] Updated second AI model identifier;

[0148] a pairing identifier, where the pairing identifier is used to identify a pairing between the first AI model and the second AI model;

[0149] a training session identifier, the training session identifier being associated with the first AI model and / or the second AI model;

[0150] A training data set identifier, where the training data set identifier is associated with the first AI model and / or the second AI model.

[0151] In a third aspect, an embodiment of the present disclosure provides a first device, including:

[0152] The transceiver module is configured to send first information to the second device, where the first information is used at least to identify a first artificial intelligence (AI) model and / or a second AI model, where the first AI model is used to compress channel state information (CSI), and the second AI model is used to decompress the compressed CSI.

[0153] In a fourth aspect, an embodiment of the present disclosure provides a second device, including:

[0154] The transceiver module is configured to receive first information sent by a first device, where the first information is used at least to identify a first artificial intelligence (AI) model and / or a second AI model, where the first AI model is used to compress channel state information (CSI), and the second AI model is used to decompress the compressed CSI.

[0155] In a fifth aspect, an embodiment of the present disclosure provides a first device, including:

[0156] one or more processors;

[0157] The processor is used to execute the information transmission method described in any one of the first aspects.

[0158] In a sixth aspect, an embodiment of the present disclosure provides a second device, including:

[0159] one or more processors;

[0160] The processor is used to execute the information transmission method described in any one of the second aspects.

[0161] In a seventh aspect, an embodiment of the present disclosure provides a communication system, including:

[0162] A first device, wherein the first device is configured to implement the information transmission method according to any one of the first aspects;

[0163] A second device, wherein the second device is configured to implement the information transmission method described in any one of the second aspects.

[0164] In an eighth aspect, an embodiment of the present disclosure proposes a storage medium storing instructions. When the instructions are executed on a communication device, the communication device executes the information transmission method as described in any one of the first aspect or the second aspect.

[0165] In a ninth aspect, an embodiment of the present disclosure proposes a computer program product, comprising a computer program, which, when executed by a processor, is used to implement the information transmission method described in any one of the first aspect or the second aspect.

[0166] It is understandable that the first device, the second device, the communication system, the storage medium, and the computer program are all used to execute the method proposed in the embodiment of the present disclosure. Therefore, the beneficial effects that can be achieved can refer to the beneficial effects of the corresponding method and will not be repeated here.

[0167] The present disclosure provides an information transmission method, apparatus, and storage medium. In some embodiments, the terms "information transmission method," "information processing method," and "communication method" are interchangeable; the terms "information transmission apparatus," "information processing apparatus," and "communication apparatus" are interchangeable; and the terms "information processing system," "communication system," and "communication system" are interchangeable.

[0168] 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.

[0169] 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.

[0170] 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.

[0171] In the embodiments of the present disclosure, unless otherwise specified, elements expressed in the singular, such as "a", "an", "the", "above", "the", "the", etc., may mean "one and only one", or "one or more", "at least one", etc. For example, when articles such as "a", "an", "the" in English are used in translation, the noun following the article may be understood as a singular expression or a plural expression.

[0172] In the embodiments of the present disclosure, “plurality” refers to two or more.

[0173] In some embodiments, the terms "at least one," "one or more," "a plurality of," "multiple," etc. may be used interchangeably.

[0174] In some embodiments, descriptions such as "at least one of A and B," "A and / or B," "A in one case, B in another case," or "in response to one case A, in response to another case B" may include the following technical solutions depending on the situation: in some embodiments, A (A is executed independently of B); in some embodiments, B (B is executed independently of A); in some embodiments, execution is selected from A and B (A and B are selectively executed); and in some embodiments, A and B (both A and B are executed). The above is also applicable when there are more branches such as A, B, and C.

[0175] 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.

[0176] 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.

[0177] 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.

[0178] In some embodiments, devices and equipment can be interpreted as physical or virtual, and their names are not limited to the names recorded in the embodiments. In some cases, they can also be understood as "equipment", "device", "circuit", "network element", "node", "function", "unit", "section", "system", "network", "entity", "subject", etc.

[0179] In some embodiments, obtaining data, information, etc. may comply with the laws and regulations of the country where the data is obtained.

[0180] In some embodiments, data, information, etc. may be obtained with the user's consent.

[0181] 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.

[0182] FIG1A is a schematic diagram showing the architecture of a communication system according to an embodiment of the present disclosure.

[0183] As shown in FIG1A , a communication system 100 includes a first device (terminal) 101 and a second device 102 .

[0184] In some embodiments, the first device 101 may be a device that has obtained a first AI model and / or a second AI model, wherein the first AI model is used to compress channel state information (CSI), and the second AI model is used to decompress the compressed CSI.

[0185] In one example, the first device 101 may be a network device or a terminal.

[0186] In some embodiments, the second device 102 may be a peer device of the first device 101 , and the second device 102 has not yet obtained the first AI model and / or the second AI model.

[0187] In one example, when the first device 101 is a network device, the second device 102 may be a terminal.

[0188] In one example, when the first device 101 is a terminal, the second device 102 may be a network device.

[0189] In some embodiments, the above-mentioned terminals include, for example, mobile phones, wearable devices, Internet of Things devices, cars with communication functions, smart cars, tablet computers, computers with wireless transceiver functions, virtual reality (VR) terminal devices, augmented reality (AR) terminal devices, wireless terminal devices in industrial control, wireless terminal devices in self-driving, wireless terminal devices in remote medical surgery, wireless terminal devices in smart grids, wireless terminal devices in transportation safety, wireless terminal devices in smart cities, and at least one of wireless terminal devices in smart homes, but are not limited thereto.

[0190] In some embodiments, the network device may include an access network device, such as 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.

[0191] 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.

[0192] 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.

[0193] In some embodiments, the aforementioned network devices may include core network devices, which may be a single device, multiple devices, or a group of devices. Network elements may be virtual or physical. The core network may include, for example, at least one of an Evolved Packet Core (EPC), a 5G Core Network (5GCN), and a Next Generation Core (NGC).

[0194] In some embodiments, the aforementioned network devices may include access network devices and core network devices.

[0195] In some embodiments, the terminal can access the core network device through the access network device.

[0196] It can be understood that the communication system described in the embodiment of the present disclosure is for the purpose of more clearly illustrating the technical solution of the embodiment of the present disclosure, and does not constitute a limitation on the technical solution proposed in the embodiment of the present disclosure. Ordinary technicians in this field can know that with the evolution of the system architecture and the emergence of new business scenarios, the technical solution proposed in the embodiment of the present disclosure is also applicable to similar technical problems.

[0197] 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, and the entities may be physical or virtual. The connection relationships between the entities are illustrative only. The entities may be connected or disconnected, and the connection may be in any manner, including direct or indirect, wired or wireless.

[0198] 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, systems utilizing other communication methods, and next-generation systems based on these. Furthermore, a combination of multiple systems (for example, a combination of LTE or LTE-A with 5G) may also be used.

[0199] Currently, CSI compression feedback and CSI recovery can be achieved on the terminal side and network device side respectively through bilateral AI / machine learning (ML) models.

[0200] For example, Figure 1B shows a schematic diagram of CSI compression feedback and recovery based on a bilateral AI / ML model. The terminal compresses the downlink channel information H using the CSI generation model, quantizes it into a binary bit stream, and sends it to the network device. The network device then recovers H', which is approximately the original downlink information, using the CSI recovery model.

[0201] In some embodiments, a CSI generation model can be represented as an encoder, and a CSI recovery model can be represented as a decoder. The training methods of the encoder and decoder models are shown in Table 1.

[0202] Table 1. Encoder and Decoder training methods

[0203] For methods 3 and 4 in Table 1, a training session identifier (ID) is introduced to represent the trained Encoder / Decoder model. For methods 5 and 6, a dataset identifier (dataset ID) is introduced to represent the trained Encoder / Decoder model.

[0204] Since the bilateral model needs to be deployed on the terminal side and the network device side respectively, when multiple encoder and decoder models are deployed, it is also necessary to ensure that the encoder and decoder are matched in pairs, otherwise the model inference performance will deteriorate.

[0205] In some embodiments, a corresponding model may be identified before model inference. The model identification method includes any of the following:

[0206] Type A: realizes model recognition of network devices and terminals in an offline manner.

[0207] During the offline identification of the model, the corresponding model may be assigned a corresponding model ID.

[0208] Type B implements model recognition through air interface signaling. Specifically, it can be divided into the following two types:

[0209] Type B1: The terminal actively initiates model recognition, and the network device can assist in completing the remaining steps of model recognition.

[0210] During model identification, the corresponding model can be assigned a corresponding Model ID.

[0211] Type B2: The network device actively initiates model recognition, and the terminal can assist in completing the remaining steps of model recognition.

[0212] During model identification, the corresponding model can be assigned a corresponding Model ID.

[0213] The present disclosure provides the following information transmission method, device, and storage medium to achieve the purpose of identifying a first AI model and / or a second AI model. The use of AI technology improves the reliability and availability of CSI transmission, reduces terminal feedback overhead, and improves CSI feedback accuracy.

[0214] The following describes the information transmission method provided by the present disclosure, taking the first device 101 as a network device and the second device 102 as a terminal as an example. It should also be noted that in the embodiments of the present disclosure, CSI is used as an example to describe the identification of the corresponding AI model. Other information that can be processed or identified using AI technology should also fall within the protection scheme of the present disclosure.

[0215] FIG2A is an interactive diagram of 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, which includes:

[0216] Step S2101 : The second device 102 sends capability indication information to the first device 101 .

[0217] In some embodiments, the first device 101 is a device that has acquired a first AI model and / or a second AI model. The first AI model is used to compress channel state information (CSI), and the first AI model may also be referred to as an encoder. The second AI model is used to decompress the compressed CSI, and the second AI model may also be referred to as a decoder.

[0218] In the embodiment of the present disclosure, the first device 101 is a network device.

[0219] In some embodiments, the second device 102 is a device that has not acquired the first AI model and / or the second AI model. In the embodiment of the present disclosure, the second device 102 may be a terminal.

[0220] In some embodiments, the capability indication information is used to indicate the AI ​​model capabilities supported by the second device 102.

[0221] In one example, the capability indication information may include, but is not limited to, at least one of the following:

[0222] An AI model identifier supported by the second device 102;

[0223] The AI ​​model structure supported by the second device 102.

[0224] Among them, the AI ​​model identifier may include but is not limited to at least one of the following: a first AI model identifier; a second AI model identifier; an updated first AI model identifier; an updated second AI model identifier; a pairing identifier, the pairing identifier is used to identify the pairing between a first AI model and a second AI model; a training session identifier, the training session identifier is associated with the first AI model and / or the second AI model; a training data set identifier, the training data set identifier is associated with the first AI model and / or the second AI model.

[0225] Among them, the pairing identifier (pair ID) can identify a group of AI models, which includes a first AI model (Encoder) and a second AI model (Decoder).

[0226] It is understandable that the pairing identifier can be updated based on the update of the AI ​​model.

[0227] For example, when the first AI model is updated, the pairing identifier may be used to identify the updated first AI model and the second AI model.

[0228] For example, when the second AI model is updated, the pairing identifier may be used to identify the updated first AI model and the updated second AI model.

[0229] For example, when the first AI model and the second AI model are updated, the pairing identifier may be used to identify the first AI model and the updated second AI model.

[0230] When a training session identifier is associated with a first AI model, it can identify a session for training the first AI model. When a training session identifier is associated with a second AI model, it can identify a session for training the second AI model. When a training session identifier is associated with a first AI model and a second AI model, it can identify a session for collaborative training of the first and second AI models.

[0231] When the training dataset identifier is associated with a first AI model, it may identify a dataset for training the first AI model, i.e., the first AI model is trained based on this dataset. When the training dataset identifier is associated with a second AI model, it may identify a dataset for training the second AI model, i.e., the second AI model is trained based on this dataset. When the training dataset identifier is associated with a first AI model and a second AI model, it may identify a dataset for collaborative training of the first and second AI models, i.e., both the first and second AI models are trained based on this dataset.

[0232] All of the above identifiers can be used as model identifiers to identify the first AI model and / or the second AI model. This disclosure does not limit the selection of model identifiers.

[0233] The AI ​​model structure may include, but is not limited to, at least one of the following: each network layer included in the AI ​​model; and the network parameters corresponding to each network layer. The AI ​​model may include at least one of the following: an input layer, a convolutional layer, a pooling layer, a fully connected layer, and an output layer.

[0234] This disclosure does not limit the AI ​​model structure supported by the second device 102.

[0235] In some embodiments, the name of the capability indication information is not limited and can be interchangeable with indication information, capability information, terminal capability information, etc.

[0236] In some embodiments, the first device 101 receives the capability indication information.

[0237] Step S2102 : The first device 101 sends first information to the second device 102 .

[0238] In some embodiments, when the first device 101 determines, based on the capability indication information, that the second device 102 is capable of supporting the first AI model and / or the second AI model, the first device 101 sends the first information to the second device 102. Otherwise, the first device 101 may not send the first information to the second device 102.

[0239] In some embodiments, the first information may be used to identify the first AI model and / or the second AI model.

[0240] Among them, identifying the first AI model and / or the second AI model may include but is not limited to at least one of the following: identifying the first AI model used on the terminal side; identifying the second AI model used on the network device side.

[0241] Accordingly, the first device 101 and the second device 102 can determine the matching relationship between the first AI model and the second AI model offline. That is, after the terminal compresses the CSI using a first AI model, the network device decompresses it using a second AI model that matches or corresponds to the first AI model. For example, first AI model #1 corresponds to second AI model #3, first AI model #2 corresponds to second AI model #1, first AI model #3 corresponds to second AI model #2, and so on.

[0242] In some embodiments, the first information may be used to identify the first AI model and / or the second AI model, and to determine a matching relationship between the first AI model and the second AI model.

[0243] In some embodiments, the name of the first information is not limited and can be interchangeable with identification information, indication information, etc.

[0244] In some embodiments, the first information may include but is not limited to at least one of the following: a model identifier, wherein the model identifier is used to identify the first AI model and / or the second AI model; the first AI model; the second AI model; a training data set, wherein the training data set is a data set used to train the first AI model and / or the second AI model.

[0245] In one example, the content of the model identification has been introduced in the aforementioned embodiment and will not be repeated here.

[0246] In some embodiments, the second device 102 receives the first information.

[0247] In some embodiments, the second device 102 identifies the first AI model and / or the second AI model based on the first information. The specific identification process includes at least one of the following:

[0248] The first information includes a model identifier, and the second device 102 can identify the corresponding AI model based on the model identifier;

[0249] The first information includes the first AI model and / or the second AI model, and the second device 102 can directly identify the first AI model and / or the second AI model;

[0250] The first information includes a training data set, and the second device 102 can perform training based on the training data set to obtain a corresponding AI model.

[0251] In some embodiments, the names of information, etc. are not limited to the names described in the embodiments, and terms such as "information", "message", "signal", "signaling", "report", "configuration", "indication", "instruction", "command", "channel", "parameter", "domain", "field", "symbol", "symbol", "codeword", "codebook", "codeword", "codepoint", "bit", "data", "program", and "chip" can be used interchangeably.

[0252] In some embodiments, terms such as "send", "transmit", "report", "download", "transmit", "bidirectional transmission", "send and / or receive" can be used interchangeably.

[0253] In some embodiments, "obtain", "get", "get", "receive", "transmit", "bidirectional transmission", "send and / or receive" can be interchangeable, and can be interpreted as receiving from other entities, obtaining from protocols, obtaining from higher layers, obtaining by self-processing, autonomous implementation, etc.

[0254] In some embodiments, terms such as "certain", "preset", "preset", "setting", "indicated", "a certain", "any", and "first" can be interchangeable. "Specific A", "preset A", "preset A", "setting A", "indicated A", "a certain A", "any A", and "first A" can be interpreted as A pre-specified in a protocol, etc., or as A obtained through setting, configuration, or indication, etc., or as specific A, a certain A, any A, or first A, etc., but not limited to this.

[0255] In some embodiments, the information transmission method involved in the embodiments of the present disclosure may include at least one of steps S2101 and S2102. For example, step S2101 may be implemented as an independent embodiment, step S2102 may be implemented as an independent embodiment, and steps S2101+S2102 may be implemented as independent embodiments, but are not limited thereto.

[0256] In some embodiments, step S2101 is optional, and one or more of these steps may be omitted or replaced in different embodiments. For example, if the first device 101 obtains capability indication information from other execution entities or does not consider terminal capabilities, step S2101 may not be performed.

[0257] In some embodiments, step S2102 is optional, and one or more of these steps may be omitted or replaced in different embodiments. For example, if the first device 101 determines, based on the terminal's capabilities, that the terminal does not have the ability to compress the CSI using the AI ​​model, step S2102 may not be performed.

[0258] In some embodiments, steps S2101 to S2102 are optional, and one or more of these steps may be omitted or replaced in different embodiments.

[0259] In the above embodiment, when the second device is a terminal, the capability indication information can be reported to allow the first network device, such as a network device, to send the first information so that the second device can identify the first AI model and / or the second AI model, thereby achieving the purpose of identifying the first AI model and / or the second AI model. The use of AI technology improves the reliability and availability of CSI transmission, reduces the feedback overhead of the terminal, and improves the feedback accuracy of CSI.

[0260] FIG2B is an interactive diagram of 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, which includes:

[0261] Step S2201: The first device 101 sends second information to the second device 102.

[0262] In some embodiments, the first device 101 is a device that has acquired a first AI model and / or a second AI model. The first AI model is used to compress channel state information (CSI), and the first AI model may also be referred to as an encoder. The second AI model is used to decompress the compressed CSI, and the second AI model may also be referred to as a decoder.

[0263] In the embodiment of the present disclosure, the first device 101 is a network device.

[0264] In some embodiments, the second device 102 is a device that has not acquired the first AI model and / or the second AI model. In the embodiment of the present disclosure, the second device 102 may be a terminal.

[0265] In some embodiments, the second information may be used by the second device 102 to determine whether the first AI model and / or the second AI model can be recognized, and to determine to receive the first information if the first AI model and / or the second AI model can be recognized.

[0266] In some embodiments, the second information includes but is not limited to at least one of the following: the first AI model; the second AI model; a training data set; configuration parameters; and a model identifier.

[0267] The training data set is a data set used to train the first AI model and / or the second AI model.

[0268] Among them, the configuration parameters may refer to parameters corresponding to the first AI model and / or the second AI model configured by the network device to the terminal, including but not limited to at least one of the following: antenna port; subband size.

[0269] The model identification has been described in the foregoing embodiments and will not be repeated here.

[0270] In step S2202 , the second device 102 determines whether it can recognize the first AI model and / or the second AI model.

[0271] In some embodiments, the second information includes the training dataset, and it is determined that the first AI model and / or the second AI model can be recognized. Accordingly, the second device 102 can perform model training based on the training dataset to obtain the first AI model and / or the second AI model, thereby realizing recognition of the first AI model and / or the second AI model. In this case, subsequent steps S2203 and S2204 may not be performed.

[0272] In some embodiments, the second device 102 supports the first AI model and / or the second AI model included in the second information, and the second device 102 may determine that it can recognize the first AI model and / or the second AI model.

[0273] In some embodiments, the second device 102 does not support the first AI model and / or the second AI model included in the second information, and the second device 102 may determine that the first AI model and / or the second AI model cannot be recognized.

[0274] In some embodiments, when the second device 102 is able to recognize the first AI model and / or the second AI model, it may be determined that the first information needs to be received, and steps S2203 to S2204 may be continued.

[0275] If the second device 102 determines that the first AI model and / or the second AI model cannot be recognized, it may determine that there is no need to receive the first information.

[0276] Step S2203 : The second device 102 sends first indication information to the first device 101 .

[0277] In some embodiments, the first indication information is used to instruct the second device 102 to determine to receive the first information.

[0278] In some embodiments, the first device 101 receives the first indication information.

[0279] Step S2204 : The first device 101 sends first information to the second device 102 .

[0280] In some embodiments, the first device 101 may send the first information to the second device 102 based on the first indication information. The specific content of the first information has been introduced in the above embodiment and will not be repeated here.

[0281] Accordingly, the process of the second device 102 identifying the first AI model and / or the second AI model based on the first information can refer to the corresponding process in step S2102, which is not repeated here.

[0282] In some embodiments, the information transmission method involved in the embodiments of the present disclosure may include at least one of steps S2201 to S2204. For example, step S2201 can be implemented as an independent embodiment, step S2202 can be implemented as an independent embodiment, steps S2201+S2202 can be implemented as an independent embodiment, steps S2203+S2204 can be implemented as an independent embodiment, and steps S2201 to S2204 can be implemented as independent embodiments, but are not limited thereto.

[0283] In some embodiments, step S2201 is optional, and one or more of these steps may be omitted or replaced in different embodiments. For example, when the second device 102 obtains the second information from other execution entities, step S2201 may not be performed.

[0284] In some embodiments, step S2202 is optional, and one or more of these steps may be omitted or replaced in different embodiments. For example, if the second device 102 has already recognized the first AI model and / or the second AI model, step S2202 may not be performed.

[0285] In some embodiments, steps S2203 to S2204 are optional, and one or more of these steps may be omitted or replaced in different embodiments. For example, if the second device 102 has successfully identified the first AI model and / or the second AI model based on the second information, steps S2203 to S2204 may not be performed.

[0286] In some embodiments, steps S2201 to S2204 are optional, and one or more of these steps may be omitted or replaced in different embodiments.

[0287] In the above embodiment, the first device can send second information to the second device. If the second device determines that it can identify the first AI model and / or the second AI model based on the second information, the first device then sends the first information to the second device, thereby also achieving the purpose of identifying the first AI model and / or the second AI model. The use of AI technology improves the reliability and availability of CSI transmission, reduces the feedback overhead of the terminal, and improves the feedback accuracy of CSI.

[0288] FIG2C is an interactive diagram of 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, which includes:

[0289] Step S2301 : The second device 102 sends capability indication information to the first device 101 .

[0290] In the embodiment of the present disclosure, the first device 101 is a network device, and the second device 102 may be a terminal.

[0291] The implementation of step S2301 is similar to that of step S2101 and will not be repeated here.

[0292] Step S2302: The first device 101 sends second indication information to the second device 102.

[0293] In some embodiments, the second indication information is used to instruct the second device 102 to send auxiliary information, and the auxiliary information is used to assist the first device 101 in determining whether to send the first information to the second device.

[0294] In some embodiments, the auxiliary information may include, but is not limited to, at least one of the following: mobility information of the second device 102 ; software parameter information of the second device 102 ; and hardware parameter information of the second device 102 .

[0295] In some embodiments, the second device 102 receives the second indication information.

[0296] Step S2303 : The second device 102 sends the auxiliary information to the first device 101 .

[0297] In some embodiments, the second device 102 sends auxiliary information to the first device 101 based on the second indication information.

[0298] In some embodiments, the first device 101 receives the auxiliary information.

[0299] Step S2304 : The first device 101 determines whether to send the first information to the second device 102 .

[0300] In some embodiments, the first device 101 determines whether to send the first information to the second device 102 based on capability indication information and / or auxiliary information.

[0301] In some embodiments, the first device 101 determines, based on the capability indication information, that the second device 102 is capable of supporting the first AI model and / or the second AI model, and determines to send the first information to the second device 102. Otherwise, it determines not to send the first information to the second device 102, and may fall back to the legacy mode for CSI processing and transmission. The legacy mode refers to a mode in which no AI model is used to compress and recover the CSI.

[0302] In some embodiments, the first device 101 determines that it has the ability to support the first AI model and / or the second AI model based on auxiliary information, such as the software and hardware parameters of the second device 102 (i.e., the terminal), and determines to send the first information to the second device 102.

[0303] In some embodiments, the first device 101 determines, based on auxiliary information, such as a mobility parameter of the second device 102 (i.e., a terminal), that the second device 102 is about to leave the coverage of the first device 102, and determines not to send the first information to the second device 102. The serving base station of the second device 102 may subsequently send the first information.

[0304] In some embodiments, the first device 101 determines that the second device 102 is within the coverage of the first device 102 based on auxiliary information, such as the mobility parameter of the second device 102 (ie, the terminal), and determines to send the first information to the second device 102.

[0305] In some embodiments, the first device 101 determines, based on the capability indication information and the auxiliary information, that the second device 102 is capable of supporting the first AI model and / or the second AI model, and determines to send the first information to the second device 102. Otherwise, the first information is not sent to the second device 102.

[0306] In some embodiments, the first device 101 determines, based on the capability indication information and the auxiliary information, that the second device 102 is capable of supporting the first AI model and / or the second AI model and is within the coverage range of the first device 101, and determines to send the first information to the second device 102. Otherwise, the first information is not sent to the second device 102.

[0307] The above description is merely exemplary, and any solution in which the first device 101 determines whether to send the first information to the second device 102 based on the capability indication information and / or auxiliary information should fall within the scope of protection of this disclosure.

[0308] Step S2305 : The first device 101 sends first information to the second device 102 .

[0309] The implementation of step S2305 is similar to that of step S2102 and will not be repeated here.

[0310] In some embodiments, the information transmission method involved in the embodiments of the present disclosure may include at least one of steps S2301 to S2305. For example, step S2301 can be implemented as an independent embodiment, step S2302 can be implemented as an independent embodiment, steps S2301+S2302 can be implemented as an independent embodiment, step S2303 can be implemented as an independent embodiment, steps S2301+S2302+S2303 can be implemented as an independent embodiment, step S2204 can be implemented as an independent embodiment, step S2205 can be implemented as an independent embodiment, steps S2304+S2305 can be implemented as an independent embodiment, and steps S2301 to S2305 can be implemented as independent embodiments, but are not limited thereto.

[0311] In some embodiments, step S2301 is optional, and one or more of these steps may be omitted or replaced in different embodiments. For example, if the first device 101 obtains capability indication information from other execution entities or does not consider terminal capabilities, step S2301 may not be performed.

[0312] In some embodiments, step S2302 is optional, and one or more of these steps may be omitted or replaced in different embodiments. For example, if the first device 101 does not consider the auxiliary information or the second device 102 automatically reports the auxiliary information, step S2302 may not be performed.

[0313] In some embodiments, step S2303 is optional, and one or more of these steps may be omitted or replaced in different embodiments. For example, if the first device 101 obtains auxiliary information from another execution entity, or if the first device 101 determines the auxiliary information itself, step S2303 may not be performed.

[0314] In some embodiments, step S2304 is optional, and one or more of these steps may be omitted or replaced in different embodiments. For example, when the first device 101 is required to provide the first information to the second device 102 by default, step S2304 may not be performed.

[0315] In some embodiments, step S2305 is optional, and one or more of these steps may be omitted or replaced in different embodiments. For example, when the second device 102 obtains the first information from other execution entities, step S2305 may not be performed.

[0316] In some embodiments, steps S2301 to S2305 are optional, and one or more of these steps may be omitted or replaced in different embodiments.

[0317] In the above embodiment, the second device can report auxiliary information to the first device to assist the first device in determining whether to send the first information to the second device, thereby achieving the purpose of identifying the first AI model and / or the second AI model. The use of AI technology improves the reliability and availability of CSI transmission, reduces the feedback overhead of the terminal, and improves the feedback accuracy of CSI.

[0318] FIG2D is an interactive diagram of 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, which includes:

[0319] Step S2401: The second device 102 sends auxiliary information and / or third indication information to the first device 101.

[0320] In the embodiment of the present disclosure, the first device 101 is a network device, and the second device 102 may be a terminal.

[0321] In some embodiments, the assistance information is used to assist the first device in determining whether to send the first information to the second device.

[0322] In an example, the auxiliary information may include, but is not limited to, at least one of the following: mobility information of the second device 102 ; software parameter information of the second device 102 ; and hardware parameter information of the second device 102 .

[0323] In some embodiments, the third indication information may be used to instruct the first device 101 to send the first information to the second device 102 .

[0324] In step S2402 , the first device 101 determines whether to send first information to the second device 102 .

[0325] In some embodiments, the first device 101 determines, based on the software and hardware parameters included in the auxiliary information, that the second device 102 supports the first AI model and / or the second AI model, and determines to send the first information to the second device 102. Otherwise, it is determined not to send the first information to the second device 102, and the CSI processing and transmission can be returned to the legacy mode. The legacy mode refers to a mode that does not use any AI model to compress and recover the CSI.

[0326] In some embodiments, the first device 101 determines to send the first information to the second device 102 based on the auxiliary information indicating that the second device 102 is within the coverage of the first device 102. Otherwise, it determines not to send the first information to the second device 102.

[0327] In some embodiments, the first device 101 determines to send the first information to the second device 102 based on the third indication information.

[0328] In some embodiments, the first device 101 determines to send the first information to the second device 102 based on the third indication information and auxiliary information, such as software and hardware parameters. Otherwise, it is determined not to send the first information to the second device 102. Alternatively, if the second device 102 is within the coverage of the first device 102 based on the third indication information and auxiliary information, such as mobility parameters, it is determined to send the first information to the second device 102. Otherwise, it is determined not to send the first information to the second device 102.

[0329] The above description is merely an exemplary description, and all solutions in which the first device 101 determines whether to send the first information to the second device 102 should fall within the scope of protection of the present disclosure.

[0330] Step S2403 : The first device 101 sends first information to the second device 102 .

[0331] The implementation of step S2403 is similar to that of step S2102 and will not be repeated here.

[0332] In some embodiments, the information transmission method involved in the embodiments of the present disclosure may include at least one of steps S2401 to S2403. For example, step S2401 can be implemented as an independent embodiment, step S2402 can be implemented as an independent embodiment, steps S2401+S2402 can be implemented as an independent embodiment, step S2403 can be implemented as an independent embodiment, and steps S2401 to S2403 can be implemented as independent embodiments, but are not limited thereto.

[0333] In some embodiments, step S2401 is optional, and one or more of these steps may be omitted or replaced in different embodiments. For example, when the first device 101 determines whether to send the first information to the second device 102 based on other information (such as capability indication information), step S2301 may not be performed.

[0334] In some embodiments, step S2402 is optional, and one or more of these steps may be omitted or replaced in different embodiments. For example, when the first device 101 needs to send the first information to the second device 102 by default, step S2402 may not be performed.

[0335] In some embodiments, step S2403 is optional, and one or more of these steps may be omitted or replaced in different embodiments. For example, when the second device 102 obtains the first information from other execution entities, step S2403 may not be performed.

[0336] In some embodiments, steps S2401 to S2403 are optional, and one or more of these steps may be omitted or replaced in different embodiments.

[0337] In the above embodiment, the second device can actively initiate the AI ​​model recognition process, thereby achieving the purpose of identifying the first AI model and / or the second AI model. The use of AI technology improves the reliability and availability of CSI transmission, reduces the feedback overhead of the terminal, and improves the feedback accuracy of CSI.

[0338] The following takes the first device 101 as a terminal and the second device 102 as a network device as an example to introduce the information transmission method provided by the present disclosure.

[0339] FIG2E is an interactive diagram of 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, which includes:

[0340] Step S2501: The second device 102 sends auxiliary information and / or third indication information to the first device 101.

[0341] In the embodiment of the present disclosure, the first device 101 is a terminal, and the second device 102 may be a network device. That is, the terminal side has acquired the first AI model and / or the second AI model.

[0342] In some embodiments, the auxiliary information may include but is not limited to channel scenario information, wherein the channel scenario information may be used to identify the current channel scenario.

[0343] Exemplarily, the channel scenario may include but is not limited to any of the following: an urban microcell (UMi) scenario; an urban macrocell (UMa) scenario; an indoor hotspot scenario, etc.

[0344] In some embodiments, the third indication information may be used to instruct the first device 101 to send the first information to the second device 102 .

[0345] In step S2502 , the first device 101 determines whether to send first information to the second device 102 .

[0346] In some embodiments, the first device 101 (ie, the terminal) may determine the current channel scenario based on the auxiliary information, and determine whether to send the first information to the second device 102 in the current channel scenario based on a predefined method.

[0347] Exemplarily, it may be agreed upon by a protocol, for example, in a UMa scenario, the first information needs to be sent to the second device 102 .

[0348] In some embodiments, the first device 101 (ie, the terminal) may determine to send the first information to the second device 102 based on the third indication information.

[0349] In some embodiments, the first device 101 (ie, the terminal) may jointly determine whether to send the first information to the second device 102 based on the third indication information and the auxiliary information.

[0350] Exemplarily, the third indication information instructs the first device 101 to send the first information to the second device 102 , the channel scenario indicated by the auxiliary information is Uma, and the first device 101 determines to send the first information to the second device 102 .

[0351] Exemplarily, the third indication information indicates that the first device 101 sends the first information to the second device 102 , the channel scenario indicated by the auxiliary information is an indoor scenario, and the first device 101 determines not to send the first information to the second device 102 .

[0352] The above description is merely an exemplary description, and the present disclosure does not limit the scheme in which the first device 101 determines whether to send the first information to the second device 102 .

[0353] Step S2503 : The first device 101 sends first information to the second device 102 .

[0354] The implementation of step S2503 is similar to that of step S2102 and will not be repeated here.

[0355] In some embodiments, the information transmission method involved in the embodiments of the present disclosure may include at least one of steps S2501 to S2503. For example, step S2501 can be implemented as an independent embodiment, step S2502 can be implemented as an independent embodiment, steps S2501+S2502 can be implemented as an independent embodiment, step S2503 can be implemented as an independent embodiment, and steps S2501 to S2503 can be implemented as independent embodiments, but are not limited thereto.

[0356] In some embodiments, step S2501 is optional, and one or more of these steps may be omitted or replaced in different embodiments. For example, when the first device 101 determines whether to send the first information to the second device 102 based on other information, step S2501 may not be performed.

[0357] In some embodiments, step S2502 is optional, and one or more of these steps may be omitted or replaced in different embodiments. For example, when the first device 101 needs to send the first information to the second device 102 by default, step S2502 may not be performed.

[0358] In some embodiments, step S2503 is optional, and one or more of these steps may be omitted or replaced in different embodiments. For example, when the second device 102 obtains the first information from other execution entities, step S2503 may not be performed.

[0359] In some embodiments, steps S2501 to S2503 are optional, and one or more of these steps may be omitted or replaced in different embodiments.

[0360] In the above embodiment, the second device can actively initiate the AI ​​model recognition process, thereby achieving the purpose of identifying the first AI model and / or the second AI model. The use of AI technology improves the reliability and availability of CSI transmission, reduces the feedback overhead of the terminal, and improves the feedback accuracy of CSI.

[0361] FIG2F is an interactive diagram of an information transmission method according to an embodiment of the present disclosure. As shown in FIG2F , the present disclosure embodiment relates to an information transmission method, which includes:

[0362] Step S2601: The first device 101 sends second indication information to the second device 102.

[0363] In some embodiments, the first device 101 is a terminal, and the second device 102 is a network device. That is, the terminal side has acquired the first AI model and / or the second AI model.

[0364] In some embodiments, the second indication information is used to instruct the second device 102 to send auxiliary information, and the auxiliary information is used to assist the first device 101 in determining whether to send the first information to the second device 102.

[0365] In some embodiments, the auxiliary information may include but is not limited to channel scenario information.

[0366] In some embodiments, since the first device 101 has acquired the first AI model and / or the second AI model, the second indication information may also include at least one of the following: the first AI model; the second AI model; the updated first AI model; the updated second AI model; the training data set; and the model identifier.

[0367] Exemplarily, the first device 101 may directly provide the first AI model and / or the second AI model to the second device 102 through the second indication information.

[0368] Exemplarily, the first device 101 updates the first AI model and / or the second AI model. The first device 101 may directly send the updated first AI model and / or the updated second AI model to the second device 102 through the second indication information.

[0369] Exemplarily, the first device 101 may provide the training data set to the second device 102 through the second indication information, so that the second device 102 can identify the first AI model and / or the second AI model based on the training data set.

[0370] Exemplarily, the first device 101 may provide the model identifier to the second device 102 through the second indication information, so that the second device 102 can identify the first AI model and / or the second AI model based on the model identifier.

[0371] The above description is merely exemplary, and the second indication information may also be used only to instruct the second device 102 to send auxiliary information.

[0372] Step S2602 : The second device 102 sends the auxiliary information to the first device 101 .

[0373] In some embodiments, the second device 102 sends auxiliary information to the first device 101 based on the second indication information.

[0374] In some embodiments, the first device 101 receives the auxiliary information.

[0375] Step S2603 : The first device 101 determines whether to send the first information to the second device 102 .

[0376] In some embodiments, the first device 101 may determine, based on the auxiliary information, whether to send the first information to the second device 102. The determination method is similar to that in the above step S2502 and will not be repeated here.

[0377] Step S2604 : The first device 101 sends first information to the second device 102 .

[0378] The implementation of step S2604 is similar to that of step S2102 and will not be repeated here.

[0379] In some embodiments, the information transmission method involved in the embodiments of the present disclosure may include at least one of steps S2601 to S2604. For example, step S2601 can be implemented as an independent embodiment, step S2602 can be implemented as an independent embodiment, steps S2601+S2602 can be implemented as an independent embodiment, step S2603 can be implemented as an independent embodiment, step S2604 can be implemented as an independent embodiment, steps S2603+S2604 can be implemented as an independent embodiment, and steps S2601 to S2604 can be implemented as independent embodiments, but are not limited thereto.

[0380] In some embodiments, step S2601 is optional, and one or more of these steps may be omitted or replaced in different embodiments. For example, when the second device 102 actively sends auxiliary information to the first device 101, step S2601 may not be performed.

[0381] In some embodiments, step S2602 is optional, and one or more of these steps may be omitted or replaced in different embodiments. For example, when the first device 101 obtains information from other execution entities, step S2602 may not be performed.

[0382] In some embodiments, step S2603 is optional, and one or more of these steps may be omitted or replaced in different embodiments. For example, when the first device 101 needs to send the first information by default, step S2603 may not be performed.

[0383] In some embodiments, step S2604 is optional, and one or more of these steps may be omitted or replaced in different embodiments. For example, when the second device 102 obtains the first information from another execution entity, step S2604 may not be performed.

[0384] In some embodiments, steps S2601 to S2604 are optional, and one or more of these steps may be omitted or replaced in different embodiments.

[0385] In the above embodiment, the first device can actively initiate the AI ​​model recognition process, thereby achieving the purpose of identifying the first AI model and / or the second AI model. The use of AI technology improves the reliability and availability of CSI transmission, reduces the feedback overhead of the terminal, and improves the feedback accuracy of CSI.

[0386] Figure 3A is an interactive diagram of an information transmission method according to an embodiment of the present disclosure. As shown in Figure 3A, the present disclosure embodiment relates to an information transmission method, which can be executed by a first device 101. The first device is a device that has acquired the first AI model and / or the second AI model, and can be a network device or a terminal. The above method includes:

[0387] Step S3101, sending the first information.

[0388] In some embodiments, the first device 101 may send first information to the second device 102 .

[0389] In some embodiments, the first information is used at least to identify the first AI model and / or the second AI model.

[0390] In some embodiments, the second device 102 receives the first information.

[0391] In some embodiments, when the first device 101 is a network device and the second device 102 is a terminal, the first device can obtain capability indication information from the second device and, based on the capability indication information, send the first information to the second device 102. For details, please refer to other related parts of the embodiment involved in FIG2A, which will not be repeated here.

[0392] In some embodiments, when the first device 101 is a network device and the second device 102 is a terminal, the first device may send second information to the second device, and the second device may determine whether it can recognize the first AI model and / or the second AI model based on the second information. If the first AI model and / or the second AI model can be recognized, the second device 102 may send first indication information to the first device 101, and the first device 101 may send the first information to the second device 102 based on the first indication information. For details, please refer to other related parts of the embodiment involved in Figure 2B, and will not be repeated here.

[0393] In some embodiments, when the first device 101 is a network device and the second device 102 is a terminal, the first device 101 may send second indication information to the second device. The second device 102 then sends auxiliary information to the first device 101 based on the second indication information. The first device 101 then determines whether to send the first information to the second device 102. If the decision is to send the first information, the first information is sent to the second device 102. For details, please refer to other related parts of the embodiment involved in FIG. 2C, which will not be repeated here.

[0394] In some embodiments, when the first device 101 is a terminal and the second device 102 is a network device, the first device 101 may receive auxiliary information and / or third indication information sent by the second device 102, thereby determining whether to send the first information to the second device 102. If the decision is to send, the first information is sent to the second device 102. For details, please refer to other related parts of the embodiment involved in FIG2D, which will not be repeated here.

[0395] In some embodiments, when first device 101 is a terminal and second device 102 is a network device, second device 102 directly sends auxiliary information and / or third indication information to first device 101. First device 101 determines whether to send first information to second device 102. If the decision is to send, the first information is sent to second device 102. For details, please refer to other related parts of the embodiment involved in FIG. 2E, which will not be repeated here.

[0396] In the above embodiment, the first device can achieve the purpose of identifying the first AI model and / or the second AI model by sending the first information to the second device. The use of AI technology improves the reliability and availability of transmitted CSI, reduces the feedback overhead of the terminal, and improves the feedback accuracy of CSI.

[0397] FIG3B is an interactive diagram illustrating 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 can be performed by a second device 102, which is a device that has not obtained the first AI model and / or the second AI model, and can be a terminal or a network device. The method includes:

[0398] Step S3201, obtain first information.

[0399] In some embodiments, the second device 102 may obtain the first information from the first device 101 , but is not limited thereto. The second device 102 may also receive the first information sent by other entities.

[0400] In some embodiments, the second device 102 obtains the first information determined according to a predefined rule.

[0401] In some embodiments, the second device 102 performs processing to obtain the first information.

[0402] In some embodiments, step S3201 is omitted, the second device 102 autonomously implements the function indicated by the first information, or the second device 102 obtains the first information from other network nodes, or the above function is default or default.

[0403] In some embodiments, when the first device 101 is a network device and the second device 102 is a terminal, the second device 102 may send capability indication information to the first device 101, and the first device 101 may send the first information to the second device 102 based on the capability indication information. For details, please refer to other related parts of the embodiment involved in FIG2A, which will not be repeated here.

[0404] In some embodiments, when the first device 101 is a network device and the second device 102 is a terminal, the second device 102 can obtain second information from the first device 101, and the second device 102 determines whether it can recognize the first AI model and / or the second AI model based on the second information. If the first AI model and / or the second AI model can be recognized, the second device 102 can send first indication information to the first device 101, and the first device 101 sends the first information to the second device 102 based on the first indication information. For details, please refer to other related parts of the embodiment involved in Figure 2B, and will not be repeated here.

[0405] In some embodiments, when the first device 101 is a network device and the second device 102 is a terminal, the second device can obtain second indication information from the first device 101. The second device 102 sends auxiliary information to the first device 101 based on the second indication information. The first device 101 determines whether to send the first information to the second device 102, and if it is determined to send the first information, sends the first information to the second device 102. For details, please refer to other related parts of the embodiment involved in Figure 2C, which will not be repeated here.

[0406] In some embodiments, when the first device 101 is a terminal and the second device 102 is a network device, the second device 102 may send auxiliary information and / or third indication information to the first device 101, so that the first device 101 determines whether to send the first information to the second device 102. If the first information is determined to be sent, the first information is sent to the second device 102. For details, please refer to other related parts of the embodiment involved in Figure 2D, which will not be repeated here.

[0407] In some embodiments, when first device 101 is a terminal and second device 102 is a network device, second device 102 directly sends auxiliary information and / or third indication information to first device 101. First device 101 determines whether to send first information to second device 102. If the decision is to send, the first information is sent to second device 102. For details, please refer to other related parts of the embodiment involved in FIG. 2E, which will not be repeated here.

[0408] In the above embodiment, the second device can obtain the first information to achieve the purpose of identifying the first AI model and / or the second AI model. The use of AI technology improves the reliability and availability of transmitted CSI, reduces the feedback overhead of the terminal, and improves the feedback accuracy of CSI.

[0409] The above method is further illustrated below with examples.

[0410] For the CSI compression feedback of the bilateral model, if the Encoder / Decoder model is deployed on the terminal side or the network device side, the embodiment of the present disclosure provides a corresponding model identification method and process.

[0411] First, the assignment of model identifiers and the mapping relationship between the Encoder and Decoder models can be determined offline (of course, they can also be determined during the model identification process. If the mapping relationship is determined during the model identification process, this part of the content will be integrated with the model identification process). The details are as follows:

[0412] After completing the relevant model training using the Type 1 / Type 2 / Type 3 methods in Table 1, the terminal or network device will obtain the Encoder / Decoder model (first AI model / second AI model). The model identifier is determined based on a predefined method negotiated privately by the terminal or network device.

[0413] The identification identifier can be: assigning corresponding model IDs to the encoder / decoder model respectively, or assigning a pair identifier (Pair ID) to an encoder and a decoder, or associating the encoder / decoder or a pair of encoder and decoder with a training dataset ID; or associating the encoder / decoder or a pair of encoder and decoder with a training session ID.

[0414] For updated encoder / decoder models, a new model ID can be assigned during model recognition, and the updated model ID can be indicated to the peer end via air interface signaling. Alternatively, the updated pairing ID, or the dataset ID or training session ID associated with the updated encoder / decoder model can be indicated to the peer end.

[0415] For deployed or updated encoder / decoder models, establish a mapping relationship between an encoder model and a decoder model, or between an encoder / decoder and multiple decoders / encoders, using the encoder model ID and decoder model ID, or the pair ID, dataset ID, and training session ID. The pair ID refers to an ID assigned to a paired encoder and decoder.

[0416] The model identification process is as follows:

[0417] In Case 1, the network device has obtained an Encoder / Decoder model based on training types 1 / 2 / 3. That is, the first device 101 is a network device.

[0418] Mode 1 (Type B2): For model identification initiated by the network device side, model identification between the UE and the NW can be completed according to the following methods:

[0419] For example, as shown in Figure 4A, based on the AI ​​model capabilities reported by the terminal, if the network device determines that the terminal can support the encoder and / or decoder to be transmitted, the network device sends the encoder and / or decoder and / or the model ID corresponding to the encoder and decoder to the terminal.

[0420] For example, as shown in FIG4B , the network device instructs the transmission of the information of the encoder / decoder and / or the corresponding model ID to be transmitted to the terminal, including the following steps:

[0421] Step S4201: The network device sends second information to the terminal.

[0422] Among them, the second information may include but is not limited to at least one of the following: the first AI model; the second AI model; the training data set; the configuration parameters; and the model identifier.

[0423] Step S4202: The terminal sends first indication information to the network device.

[0424] In some embodiments, the terminal determines whether the first AI model and / or the second AI model can be recognized based on the second information, and if it can be recognized, sends first indication information to the network device.

[0425] Step S4203: The network device sends first information to the terminal according to the first instruction information.

[0426] The specific content included in the first information has been introduced in the above embodiment and will not be repeated here.

[0427] For example, as shown in FIG4C , the network device instructs the terminal to report additional information (i.e., auxiliary information) and then transmit the first information, including the following steps:

[0428] Step S4301: The network device sends second indication information to the terminal.

[0429] The second indication information is used to instruct the terminal to send auxiliary information, and the auxiliary information is used to assist the network device in determining whether to send the first information to the terminal.

[0430] Step S4302: The terminal reports auxiliary information based on the second indication information.

[0431] In step S4303, the network device determines whether to send the first information to the terminal based on the auxiliary information reported by the terminal. If it is determined to send, the network device sends the first information to the terminal.

[0432] Method 2: (Type B1), for the terminal side to initiate the model recognition method, as shown in Figure 4D, including the following steps:

[0433] Step S4401: The terminal sends auxiliary information and / or third indication information to the network device.

[0434] Step S4402: The network device determines whether to send first information to the terminal according to the received auxiliary information and / or third indication information. If it is determined to send, the network device sends the first information to the terminal.

[0435] It should be noted that the Encoder / Decoder (or first AI model / second AI model) transmitted above can be a model that has been deployed or updated on the network device side.

[0436] Case 2: The terminal side has obtained the Encoder / Decoder model based on training type Type 1 / 2 / 3. That is, the first device 101 is a terminal.

[0437] Mode 1 (Type B2), for initiating a model identification process on the network device side, as shown in FIG4E , may include the following steps:

[0438] Step S4501: The network device sends auxiliary information and / or third indication information to the terminal.

[0439] In step S4502, the terminal determines whether to send the first information to the network device based on the received auxiliary information and / or the third indication information. If it is possible to send, the terminal sends the first information to the network device.

[0440] Method 2 (Type B1), for example, the model recognition process initiated by the terminal side is shown in Figure 4F:

[0441] Step S4601: The terminal sends second indication information to the network device.

[0442] Step S4602: The network device sends auxiliary information to the terminal according to the received second indication information.

[0443] Step S4603: The terminal determines whether to send the first information to the network device based on the auxiliary information. If it is determined to send, the terminal sends the first information to the network device.

[0444] In the above embodiment, the Encoder / Decoder transferred in Case 1 and Case 2 may be a Model that has been deployed or updated on the network device side or the terminal side.

[0445] Exemplarily, the Model ID described in Case 1 and Case 2 can be the model ID corresponding to the Encoder and Decoder respectively, or a Pair ID assigned to a pair of Encoder and Decoder, or a Dataset ID or training session ID associated with a pair of Encoder and Decoder.

[0446] In Example 1 (Case 1), the network device side can obtain encoder and decoder models for different scenarios or configurations based on training type Type 1. It is assumed that the network device and the terminal have sent the mode IDs of the encoders / decoders supported by the terminal to the terminal through offline negotiation.

[0447] When a terminal accesses the network, it will send the ID of the supported AI model or other auxiliary information, such as scenario information or information about supported configuration capabilities, to the network device through capability reporting. Based on the model ID and / or auxiliary information reported by the terminal, the network device will send the trained encoder / decoder to the terminal. During the subsequent inference process, the terminal will compress the CSI based on the received encoder, quantize the compressed codeword information, and report it to the network device. The network device will then recover the CSI through inference based on the decoder corresponding to the encoder.

[0448] If the network device includes multiple encoders and decoders, the mapping relationship between encoders and decoders can be determined in a predefined manner. For example, the encoder and decoder use the same model ID, as shown in Table 2.

[0449] Table 2, the correspondence between multiple encoders and multiple decoders

[0450] If one encoder corresponds to multiple decoders, the corresponding relationship is predefined, as shown in Table 3.

[0451] Table 3, the correspondence between one encoder and multiple decoders

[0452] Alternatively, define multiple pair IDs, as shown in,4.

[0453] Table 4: Introducing pair ID to indicate the correspondence between an encoder and multiple decoders

[0454] If the network device updates its decoder, the decoder ID on the network device can be updated with a corresponding ID. The updated ID may or may not be indicated to the terminal. If indicated to the terminal, the terminal can update the correspondence between the encoder and decoder.

[0455] Correspondingly, if the terminal side updates the Encoder on the terminal side, the terminal can also indicate the updated Encoder ID to the network device side, so that the network device side updates the correspondence between the Encoder and the Decoder.

[0456] If the method shown in FIG4B is used to realize the recognition of the bilateral AI model, the specific implementation process is as follows.

[0457] In step 1, the network device sends the indication information of the model ID corresponding to the encoder / decoder to be transmitted, such as the indication information of encoder ID1 (ie, the second information), to the terminal.

[0458] Step 2: The terminal determines whether the model can be applied for reasoning based on the received model ID. If the current hardware environment of the terminal can apply the model, the terminal will send a first indication message to notify the network device.

[0459] In step 3, the network device determines whether to transmit the encoder / decoder to the terminal based on the first indication information sent by the terminal. If so, the network device sends the first information to the terminal. The terminal can then perform inference based on the model. The network device determines which decoder to use for inference and CSI recovery based on the mapping relationships in the above tables.

[0460] The above is just an example of the model identification process of Figure 4B in Case 1. Other model processes can also be completed according to the steps of the corresponding solutions, which will not be repeated here.

[0461] In Example 2 (Case 2), assume that the terminal has trained the encoder using Type 3 and then sends the dataset used to train the decoder to the network device. The network device then obtains the decoder based on the dataset trained. Because different datasets may produce different encoders and decoders, the correspondence between the encoder and decoder can be determined by the transmitted dataset.

[0462] Assume that the terminal supports AI model inference for UMA, UMI, and Indoor scenarios, and three encoders and corresponding decoders are deployed in each scenario. The datasets corresponding to the training model in each scenario are defined as dataset ID0, dataset ID1, and dataset ID2, respectively. If model recognition method 2 is used, the terminal and network device sides can implement it through the following steps:

[0463] Step 1: The network device provides configuration information to the terminal indicating the scenarios it supports, such as the current scenario being UMA. Based on this configuration information, the UE sends signaling to the NW side indicating the Dataset IDs corresponding to the three encoders / decoders in this scenario, such as dataset ID2, dataset ID3, and dataset ID4.

[0464] In step 2, the network device determines that the network device side only supports the decoders corresponding to dataset ID2 and dataset ID3 according to the received Dataset ID indication information, and sends a signaling to the terminal indicating that the decoder corresponding to dataset ID4 is not supported.

[0465] In step 3, the terminal determines whether the network device supports the decoders corresponding to dataset IDs 2 and 3 based on the indication sent by the network device. Based on the correspondence between the dataset IDs and the encoders and decoders during model training, the network device and terminal implement the encoder and decoder model identification for dataset IDs 2 and 3 for subsequent CSI compression feedback inference.

[0466] The present disclosure also provides an apparatus for implementing any of the above methods. For example, an apparatus is provided that includes units or modules for implementing each step performed by a terrestrial network device (e.g., an E-UTRAN TN network device) in any of the above methods. For another example, another apparatus is provided that includes units or modules for implementing each step performed by a terminal in any of the above methods.

[0467] 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.

[0468] In the embodiments of the present disclosure, the processor is a circuit with signal processing capabilities. In one implementation, the processor can be a circuit with instruction reading and execution capabilities, such as a central processing unit (CPU), a microprocessor, a graphics processing unit (GPU) (which can be understood as a microprocessor), or a digital signal processor (DSP). In another implementation, the processor can implement certain functions through the logical relationship of the hardware circuit. The logical relationship of the above-mentioned hardware circuit is fixed or reconfigurable. For example, the processor is a hardware circuit implemented by an application-specific integrated circuit (ASIC) or a programmable logic device (PLD), such as an FPGA. In a reconfigurable hardware circuit, the process of the processor loading a configuration document and implementing the hardware circuit configuration can be understood as the process of the processor loading instructions to implement the functions of some or all of the above units or modules. In addition, it can also be a hardware circuit designed for artificial intelligence, which can be understood as an ASIC, such as a neural network processing unit (NPU), a tensor processing unit (TPU), a deep learning processing unit (DPU), etc.

[0469] FIG5A is a schematic diagram of the structure of a first device according to an embodiment of the present disclosure. As shown in FIG5A , the first device 5100 may include a transceiver module 5101 .

[0470] In some embodiments, the transceiver module 5101 is configured to send first information to a second device, where the first information is at least used to identify a first artificial intelligence (AI) model and / or a second AI model, where the first AI model is used to compress channel state information (CSI), and the second AI model is used to decompress the compressed CSI.

[0471] Optionally, the above-mentioned transceiver module 5101 is used to execute at least one of the communication steps such as sending and / or receiving performed by the first device 5100 in any of the above methods (for example, step S2101, step S2102, step S2201, step S2203, step S2204, step S2301, step S2302, step S2303, step S2305, step S2401, step S2403, step S2501, step S2503, step S2601, step S2602, step S2604, but not limited to these), which will not be repeated here.

[0472] FIG5B is a schematic diagram of the structure of a second device according to an embodiment of the present disclosure. As shown in FIG5B , the second device 5200 may include a transceiver module 5201 .

[0473] In some embodiments, the transceiver module 5201 is configured to receive first information sent by a first device, where the first information is used at least to identify a first artificial intelligence AI model and / or a second AI model, where the first AI model is used to compress channel state information CSI, and the second AI model is used to decompress the compressed CSI.

[0474] Optionally, the above-mentioned transceiver module 5201 is used to execute at least one of the communication steps such as sending and / or receiving that can be executed by the second device 5200 in any of the above methods (for example, step S2101, step S2102, step S2201, step S2203, step S2204, step S2301, step S2302, step S2303, step S2305, step S2401, step S2403, step S2501, step S2503, step S2601, step S2602, step S2604, but not limited to these), which will not be repeated here.

[0475] In some embodiments, the transceiver module may include a transmitting module and / or a receiving module, and the transmitting module and the receiving module may be separate or integrated. Optionally, the transceiver module may be interchangeable with the transceiver.

[0476] Figure 6A is a schematic diagram of the structure of a communication device 6100 proposed in an embodiment of the present disclosure. Communication device 6100 can be a network device, or a chip, chip system, or processor that supports a network device in implementing any of the above methods. It can also be a chip, chip system, or processor that supports a terminal in implementing any of the above methods. Communication device 6100 can be used to implement the methods described in the above method embodiments. For details, please refer to the description of the above method embodiments.

[0477] As shown in Figure 6A, the communication device 6100 includes one or more processors 6101. Processor 6101 can be a general-purpose processor or a dedicated processor, for example, a baseband processor or a central processing unit. The baseband processor can be used to process communication protocols and communication data, and the central processing unit can be used to control the communication device (such as a base station, baseband chip, terminal device, terminal device chip, DU or CU, etc.), execute programs, and process program data. The communication device 6100 is used to perform any of the above methods.

[0478] In some embodiments, the communication device 6100 further includes one or more memories 6102 for storing instructions. Optionally, all or part of the memories 6102 may be located outside the communication device 6100.

[0479] In some embodiments, the communication device 6100 further includes one or more transceivers 6103. When the communication device 6100 includes one or more transceivers 6103, the transceiver 6103 performs at least one of the communication steps such as sending and / or receiving in the above method (for example, step S2101, step S2102, step S2201, step S2203, step S2204, step S2301, step S2302, step S2303, step S2305, step S2401, step S2403, step S2501, step S2503, step S2601, step S2602, and step S2604, but not limited thereto), and the processor 6101 performs at least one of the other steps (for example, step S2202, step S2304, step S2402, step S2502, and step S2603, but not limited thereto).

[0480] In some embodiments, a transceiver may include a receiver and / or a transmitter. The receiver and transmitter may be separate or integrated. Optionally, the terms transceiver, transceiver unit, transceiver, and transceiver circuit may be used interchangeably; the terms transmitter, transmitting unit, transmitter, and transmitting circuit may be used interchangeably; and the terms receiver, receiving unit, receiver, and receiving circuit may be used interchangeably.

[0481] In some embodiments, the communication device 6100 may include one or more interface circuits 6104. Optionally, the interface circuit 6104 is connected to the memory 6102. The interface circuit 6104 may be configured to receive signals from the memory 6102 or other devices, and may be configured to send signals to the memory 6102 or other devices. For example, the interface circuit 6104 may read instructions stored in the memory 6102 and send the instructions to the processor 6101.

[0482] The communication device 6100 described in the above embodiment may be a network device or a terminal, but the scope of the communication device 6100 described in the present disclosure is not limited thereto, and the structure of the communication device 6100 may not be limited to FIG6A. 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 and 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.

[0483] 6B is a schematic diagram of the structure of a chip 6200 according to an embodiment of the present disclosure. If the communication device 6200 can be a chip or a chip system, please refer to the schematic diagram of the structure of the chip 6200 shown in FIG6B , but the present disclosure is not limited thereto.

[0484] The chip 6200 includes one or more processors 6201 , and the chip 6200 is configured to execute any of the above methods.

[0485] In some embodiments, the chip 6200 further includes one or more interface circuits 6202. Optionally, the interface circuit 6202 is connected to the memory 6203. The interface circuit 6202 can be used to receive signals from the memory 6203 or other devices, and can be used to send signals to the memory 6203 or other devices. For example, the interface circuit 6202 can read instructions stored in the memory 6203 and send the instructions to the processor 6201.

[0486] In some embodiments, the interface circuit 6202 executes at least one of the communication steps such as sending and / or receiving in the above method (for example, step S2101, step S2102, step S2201, step S2203, step S2204, step S2301, step S2302, step S2303, step S2305, step S2401, step S2403, step S2501, step S2503, step S2601, step S2602, step S2604, but not limited to these), and the processor 6201 executes at least one of the other steps (for example, step S2202, step S2304, step S2402, step S2502, step S2603, but not limited to these).

[0487] In some embodiments, terms such as interface circuit, interface, transceiver pin, and transceiver may be used interchangeably.

[0488] In some embodiments, the chip 6200 further includes one or more memories 6203 for storing instructions. Alternatively, all or part of the memories 6203 may be located outside the chip 6200.

[0489] The present disclosure also proposes a storage medium having instructions stored thereon. When the instructions are executed on the communication device 6100, the communication device 6100 executes any of the above methods. Optionally, the storage medium is an electronic storage medium. Optionally, the storage medium is a computer-readable storage medium, but is not limited thereto and may also be a storage medium readable by other devices. Optionally, the storage medium may be a non-transitory storage medium, but is not limited thereto and may also be a transient storage medium.

[0490] The present disclosure also provides a program product, which, when executed by the communication device 6100, enables the communication device 6100 to perform any of the above methods. Optionally, the program product is a computer program product.

[0491] 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.

[0492] Other embodiments of the present disclosure will readily occur to those skilled in the art after considering the specification and practicing the invention disclosed herein. This disclosure is intended to cover any variations, uses, or adaptations of the present disclosure that follow the general principles of the present disclosure and include common knowledge or customary techniques in the art not disclosed herein. The description and examples are to be considered as exemplary only, with the true scope and spirit of the present disclosure being indicated by the following claims.

[0493] It should be understood that the present disclosure is not limited to the exact structures that have been described above and shown in the drawings, and that various modifications and changes can be made without departing from the scope thereof. The scope of the present disclosure is limited only by the appended claims.

Claims

1. An information transmission method, characterized in that: The method is performed by a first device and includes: First information is sent to a second device, where the first information is at least used to identify a first artificial intelligence (AI) model and / or a second AI model, where the first AI model is used to compress channel state information (CSI), and the second AI model is used to decompress the compressed CSI.

2. The method according to claim 1, characterized in that The method further comprises: The second device is a terminal, and receives capability indication information sent by the second device, where the capability indication information is used to indicate AI model capabilities supported by the second device; The sending the first information to the second device includes: The capability indication information indicates that the second device supports the first AI model and / or the second AI model, and the first information is sent to the second device.

3. The method according to claim 2, characterized in that The capability indication information includes at least one of the following: an AI model identifier supported by the second device; The AI model structure supported by the second device.

4. The method according to claim 1, wherein The method further comprises: The second device is a terminal, and second information is sent to the second device. The second information is used by the second device to determine whether it can recognize the first AI model and / or the second AI model, and determine to receive the first information when it can be recognized.

5. The method according to claim 4, characterized in that The second information includes at least one of the following: the first AI model; the second AI model; A training dataset, where the training dataset is a dataset used to train the first AI model and / or the second AI model; Configuration parameters, where the configuration parameters correspond to the first AI model and / or the second AI model; A model identifier, where the model identifier is used to identify the first AI model and / or the second AI model.

6. The method according to claim 4 or 5, characterized in that The method further comprises: receiving first indication information sent by the second device, where the first indication information is used to instruct the second device to determine to receive the first information; The sending the first information to the second device includes: Based on the first indication information, the first information is sent to the second device.

7. The method according to any one of claims 1 to 3, characterized in that The method further comprises: Sending second indication information to the second device, where the second indication information is used to instruct the second device to send auxiliary information, where the auxiliary information is used to assist the first device in determining whether to send the first information to the second device; receiving the auxiliary information sent by the second device based on the second indication information; Based on the auxiliary information, it is determined whether to send the first information to the second device.

8. The method according to claim 1, characterized in that The method further comprises: receiving auxiliary information and / or third indication information sent by the second device, where the auxiliary information is used to assist the first device in determining whether to send the first information to the second device, and the third indication information is used to instruct the first device to send the first information to the second device; Based on the auxiliary information and / or the third indication information, determine whether to send the first information to the second device.

9. The method according to claim 7 or 8, characterized in that The auxiliary information includes at least one of the following: Channel scenario information; mobility information of the second device; software parameter information of the second device; Hardware parameter information of the second device.

10. The method according to any one of claims 1 to 9, characterized in that The first information includes at least one of the following: a model identifier, where the model identifier is used to identify the first AI model and / or the second AI model; the first AI model; the second AI model; A training data set, where the training data set is a data set used to train the first AI model and / or the second AI model.

11. The method according to any one of claims 3, 5 or 9, characterized in that: The model identifier includes at least one of the following: First AI model identification; Second AI model identification; The updated first AI model identifier; Updated second AI model identifier; a pairing identifier, where the pairing identifier is used to identify a pairing between the first AI model and the second AI model; a training session identifier, the training session identifier being associated with the first AI model and / or the second AI model; A training data set identifier, where the training data set identifier is associated with the first AI model and / or the second AI model.

12. An information transmission method, characterized in that: The method is performed by a second device and includes: Receive first information sent by a first device, where the first information is used at least to identify a first artificial intelligence (AI) model and / or a second AI model, where the first AI model is used to compress channel state information (CSI), and the second AI model is used to decompress the compressed CSI.

13. The method according to claim 12, characterized in that The method further comprises: The second device is a terminal, which sends capability indication information to the first device, where the capability indication information is used to indicate the AI model capabilities supported by the second device.

14. The method according to claim 13, characterized in that The capability indication information includes at least one of the following: Model identifiers supported by the second device; A model structure supported by the second device.

15. The method according to claim 12, characterized in that The method further comprises: The second device is a terminal, which receives second information sent by the first device. The second information is used by the second device to determine whether it can recognize the first AI model and / or the second AI model, and determine to receive the first information when it can be recognized.

16. The method according to claim 14, characterized in that The second information includes at least one of the following: the first AI model; the second AI model; A training dataset, where the training dataset is a dataset used to train the first AI model and / or the second AI model; Configuration parameters, where the configuration parameters correspond to the first AI model and / or the second AI model; A model identifier, where the model identifier is used to identify the first AI model and / or the second AI model.

17. The method according to claim 16, characterized in that The method further comprises any of the following: The second information includes the training data set, and determines that the first AI model and / or the second AI model can be identified; supporting the first AI model and / or the second AI model included in the second information, and determining that the first AI model and / or the second AI model can be recognized; The first AI model and / or the second AI model included in the second information is not supported, and it is determined that the first AI model and / or the second AI model cannot be identified.

18. The method according to any one of claims 15 to 17, characterized in that: The method further comprises: Determine that the first AI model and / or the second AI model can be recognized, and send first indication information to the first device, where the first indication information is used to instruct the second device to determine to receive the first information.

19. The method according to any one of claims 12 to 14, characterized in that: The method further comprises: receiving second indication information sent by the first device, where the second indication information is used to instruct the second device to send auxiliary information, where the auxiliary information is used to assist the first device in determining whether to send the first information to the second device; Based on the second indication information, the auxiliary information is sent to the first device.

20. The method according to claim 12, wherein The method further comprises: Auxiliary information and / or third indication information are sent to the first device, where the auxiliary information is used to assist the first device in determining whether to send the first information to the second device, and the third indication information is used to instruct the first device to send the first information to the second device.

21. The method according to claim 19 or 20, characterized in that The auxiliary information includes at least one of the following: Channel scenario information; mobility information of the second device; software parameter information of the second device; Hardware parameter information of the second device.

22. The method according to any one of claims 12 to 21, characterized in that The first information includes at least one of the following: a model identifier, where the model identifier is used to identify the first AI model and / or the second AI model; the first AI model; the second AI model; A training data set, where the training data set is a data set used to train the first AI model and / or the second AI model.

23. The method according to any one of claims 14, 16 or 22, characterized in that The model identifier includes at least one of the following: First AI model identification; Second AI model identification; The updated first AI model identifier; Updated second AI model identifier; a pairing identifier, where the pairing identifier is used to identify a pairing between the first AI model and the second AI model; a training session identifier, the training session identifier being associated with the first AI model and / or the second AI model; A training data set identifier, where the training data set identifier is associated with the first AI model and / or the second AI model.

24. A first device, characterized in that: include: The transceiver module is configured to send first information to the second device, where the first information is used at least to identify a first artificial intelligence (AI) model and / or a second AI model, where the first AI model is used to compress channel state information (CSI), and the second AI model is used to decompress the compressed CSI.

25. A second device, characterized in that: include: The transceiver module is configured to receive first information sent by a first device, where the first information is used at least to identify a first artificial intelligence (AI) model and / or a second AI model, where the first AI model is used to compress channel state information (CSI), and the second AI model is used to decompress the compressed CSI.

26. A first device, characterized in that: include: one or more processors; The processor is configured to execute the information transmission method according to any one of claims 1 to 11.

27. A second device, characterized in that: include: one or more processors; The processor is configured to execute the information transmission method according to any one of claims 12 to 23.

28. A communication system, characterized in that: include: A first device, wherein the first device is configured to implement the information transmission method according to any one of claims 1 to 11; The second device is configured to implement the information transmission method according to any one of claims 12 to 23.

29. A storage medium storing instructions, characterized in that: When the instruction is executed on a communication device, the communication device is caused to execute the information transmission method according to any one of claims 1 to 11 or 12 to 23.

30. A computer program product comprising a computer program, characterized in that When the computer program is executed by a processor, it is used to implement the information transmission method according to any one of claims 1 to 11 or 12 to 23.

Images