Communication method, communication system and storage medium

Abstract

The present disclosure provides a communication method, a device, and a storage medium. The method is executed by a first device on which a first model is deployed, and comprises: receiving first information sent by a second device, wherein the first information is used for indicating at least one of time domain information, quantization information, model training information, training network environment information, and model performance monitoring information for training the first model and / or a second model, the first model is used by the first device to perform channel state information (CSI) compression, and the second model is used by the second device to perform CSI recovery.

Description

Communication method, communication system and storage medium TECHNICAL FIELD

[0001] The present disclosure relates to the technical field of communication, and particularly relates to a communication method, a communication system and a storage medium. BACKGROUND

[0002] In mobile communication, deep learning (DL) and artificial intelligence (AI) technologies provide a new way to solve the channel state information (CSI) feedback problem in large-scale MIMO systems, and can reduce the feedback overhead of terminals or improve the feedback accuracy.

[0003] SUMMARY

[0004] The present disclosure provides a communication method, a communication device, a communication system and a storage medium.

[0005] According to a first aspect of embodiments of the present disclosure, a communication method is provided, which is performed by a first device, and the method comprises: receiving first information sent by a second device, the first information being used to indicate at least one of time domain information, quantization information, model training information, training network environment information, and model performance monitoring information for training a first model and / or a second model, the first model being used for the first device to perform channel state information (CSI) compression, and the second model being used for the second device to perform CSI recovery.

[0006] In the above method, the first device can receive additional information sent by the second device, which is used to indicate the model training or model performance monitoring, thereby improving the effectiveness of training or performance monitoring of the model for CSI compression and recovery, ensuring the consistency of the bilateral model trained by the two devices, and improving the application accuracy of the trained model.

[0007] According to a second aspect of embodiments of the present disclosure, a communication method is provided, which is performed by a second device, and the method comprises: sending first information to a first device, the first information being used to indicate at least one of time domain information, quantization information, model training information, training network environment information, and model performance monitoring information for training a first model and / or a second model, the first model being used for the first device to perform channel state information (CSI) compression, and the second model being used for the second device to perform CSI recovery.

[0008] In the method, the second device can send additional information related to model training or model performance monitoring to the first device, thereby improving the effectiveness of training or performance monitoring of the model for CSI compression and recovery, ensuring consistency of the bilateral model trained by the two devices, and improving the application accuracy of the trained model.

[0009] According to a third aspect of the embodiments of the present disclosure, a first device is provided, comprising a transceiver module configured to receive first information sent by a second device, the first information being used to indicate at least one of time domain information, quantization information, model training information, training network environment information, and model performance monitoring information for training a first model and / or a second model, the first model being used for channel state information (CSI) compression performed by the first device, and the second model being used for CSI recovery performed by the second device.

[0010] According to a fourth aspect of the embodiments of the present disclosure, a second device is provided, comprising a transceiver module configured to send first information to a first device, the first information being used to indicate at least one of time domain information, quantization information, model training information, training network environment information, and model performance monitoring information for training a first model and / or a second model, the first model being used for channel state information (CSI) compression performed by the first device, and the second model being used for CSI recovery performed by the second device.

[0011] According to a fifth aspect of the embodiments of the present disclosure, a communication device is provided, comprising one or more processors, wherein the one or more processors are configured to invoke instructions to cause the communication device to perform the method described in any one of the first aspect of the present disclosure, or to perform the method described in any one of the second aspect of the present disclosure.

[0012] According to a sixth aspect of the embodiments of the present disclosure, a communication system is provided, comprising a first device and a second device, wherein the first device is configured to implement the method of the first aspect, and the second device is configured to implement the method of the second aspect.

[0013] According to a seventh aspect of the embodiments of the present disclosure, a storage medium is provided, the storage medium storing instructions, when the instructions are executed on a communication device, causing the communication device to perform the method of any one of the first aspect or the second aspect. BRIEF DESCRIPTION OF DRAWINGS

[0014] The above and / or additional aspects and advantages of the present disclosure will become apparent and more readily appreciated from the following description of the embodiments, taken in conjunction with the accompanying drawings, in which:

[0015] FIG. 1a is a schematic diagram of an application scenario of the embodiments of the present disclosure;

[0016] FIG. 1b is a schematic diagram of time-space-frequency CSI compression related to the present disclosure;

[0017] FIG. 1c is a schematic diagram of CSI compression corresponding to multiple future time points reported once according to the present disclosure;

[0018] FIG. 1d is a schematic diagram of the architecture of some communication systems according to an embodiment of the present disclosure;

[0019] FIG. 2 is a schematic diagram of the interaction of a communication method according to an embodiment of the present disclosure;

[0020] FIGS. 3a-3b are schematic diagrams of the flow of some communication methods according to embodiments of the present disclosure;

[0021] FIGS. 4a-4b are schematic diagrams of the flow of some other communication methods according to embodiments of the present disclosure;

[0022] FIG. 5 is a schematic diagram of the flow of some other communication methods according to embodiments of the present disclosure;

[0023] FIG. 6a is a schematic diagram of the structure of a first device according to an embodiment of the present disclosure;

[0024] FIG. 6b is a schematic diagram of the structure of a second device according to an embodiment of the present disclosure;

[0025] FIG. 7a is a schematic diagram of the structure of a communication device according to an embodiment of the present disclosure;

[0026] FIG. 7b is a schematic diagram of the structure of a chip according to an embodiment of the present disclosure. DETAILED DESCRIPTION

[0027] Embodiments of the present disclosure provide a communication method, a communication device, a communication system, and a storage medium.

[0028] In a first aspect, embodiments of the present disclosure provide a communication method performed by a first device, the method comprising: receiving first information sent by a second device, the first information being used to indicate at least one of time domain information, quantization information, model training information, training network environment information, and model performance monitoring information for training a first model and / or a second model, the first model being used for the first device to perform channel state information (CSI) compression, and the second model being used for the second device to perform CSI recovery.

[0029] In some embodiments of the first aspect, the time domain information comprises at least one of: first indication information used to indicate time information of input information of the first model; second indication information used to indicate time information of output information of the first model; third indication information used to indicate time information of input information of the second model; and fourth indication information used to indicate time information of output information of the second model.

[0030] In some embodiments of the first aspect, in some embodiments, the time information comprises at least one of: fifth indication information indicating N historical measurement time instants, N≥1; sixth indication information indicating M predicted future time instants, M≥1; seventh indication information indicating a time interval between two historical measurement time instants; eighth indication information indicating a time interval between two future time instants; ninth indication information indicating a starting time instant of the future time instants.

[0031] In some embodiments of the first aspect, in some embodiments, the quantization information comprises at least one of: tenth indication information indicating a quantization manner adopted by the first model during training; eleventh indication information indicating a dequantization manner adopted by the second model during training.

[0032] In some embodiments of the first aspect, in some embodiments, the model training information comprises at least one of: twelfth indication information indicating a model training type of the first model and / or the second model, the model training type comprising at least one of a first training type Type 1, a second training type Type 2, and a third training type Type 3; thirteenth indication information indicating dataset distribution information of the first model and / or the second model trained by the second device; fourteenth indication information indicating a dataset size of the first model and / or the second model trained by the second device; fifteenth indication information indicating a size of each sample in the dataset of the first model and / or the second model trained by the second device; sixteenth indication information indicating a format of input information of the first model; seventeenth indication information indicating a format of output information of the first model; eighteenth indication information indicating a type of input information of the first model; nineteenth indication information indicating a type of output information of the first model; twentieth indication information indicating a format of input information of the second model; twenty-first indication information indicating a format of output information of the second model; twenty-second indication information indicating a type of input information of the second model; twenty-third indication information indicating a type of output information of the second model; twenty-fourth indication information indicating whether the first model and / or the second model is trained as a scalable model, the scalable model having a same model structure under different configuration conditions.

[0033] In some embodiments of the first aspect, in some embodiments, the training network environment information comprises at least one of: twenty-fifth indication information indicating identification information associated with network information; twenty-sixth indication information indicating cell identification information of a plurality of cells having same network information.

[0034] In some embodiments of the first aspect, in some embodiments, the network information comprises at least one of: location information of a network cell; identification information of a network analog beam; urban macro station model UMA; rural macro station model RMA; micro station model UMI; physical downtilt angle.

[0035] In some embodiments of the first aspect, in some embodiments, the model performance monitoring information comprises at least one of: twenty-seventh indication information indicating T time instants at which performance measurement is performed, T ≥ 1; twenty-eighth indication information indicating at least one of M future time instants at which performance monitoring is performed; twenty-ninth indication information indicating X performance indicators, X ≥ 1; thirtieth indication information indicating output information of the second model; thirty-first indication information indicating whether the first device performs performance monitoring using the output information of the second model sent by the second device; thirty-second indication information indicating performance criteria.

[0036] In some embodiments of the first aspect, in some embodiments, the first information is triggered by a first message, the first message comprising at least one of: radio resource control RRC signaling, medium access control-control element MAC-CE, downlink control information DCI.

[0037] In the above method, the first device can receive the additional information sent by the second device for indicating the model training or model performance monitoring, thereby improving the effectiveness of the training or performance monitoring of the model of CSI compression and recovery, ensuring the consistency of the bilateral model trained by the two devices, and improving the application accuracy of the trained model.

[0038] According to a second aspect of embodiments of the present disclosure, a communication method is provided, the method being performed by a second device, and the method comprising: sending, to a first device, first information for indicating at least one of time domain information, quantization information, model training information, training network environment information, model performance monitoring information of training a first model and / or a second model, the first model being used for the first device to perform channel state information CSI compression, and the second model being used for the second device to perform CSI recovery.

[0039] In some embodiments of the second aspect, in some embodiments, the time domain information comprises at least one of: first indication information indicating time information of input information of the first model; second indication information indicating time information of output information of the first model; third indication information indicating time information of input information of the second model; fourth indication information indicating time information of output information of the second model.

[0040] In some embodiments of the second aspect, in some embodiments, the time information comprises at least one of: fifth indication information indicating N historical measurement time instants, N≥1; sixth indication information indicating M predicted future time instants, M≥1; seventh indication information indicating a time interval between two historical measurement time instants; eighth indication information indicating a time interval between two future time instants; ninth indication information indicating a starting time instant of the future time instants.

[0041] In some embodiments of the second aspect, in some embodiments, the quantization information comprises at least one of: tenth indication information indicating a quantization manner adopted by the first model during training; eleventh indication information indicating a dequantization manner adopted by the second model during training.

[0042] In some embodiments of the second aspect, in some embodiments, the model training information comprises at least one of: twelfth indication information indicating a model training type of the first model and / or the second model, the model training type comprising at least one of a first training type Type 1, a second training type Type 2, and a third training type Type 3; thirteenth indication information indicating dataset distribution information of the first model and / or the second model trained by the second device; fourteenth indication information indicating a dataset size of the first model and / or the second model trained by the second device; fifteenth indication information indicating a size of each sample in the dataset of the first model and / or the second model trained by the second device; sixteenth indication information indicating a format of input information of the first model; seventeenth indication information indicating a format of output information of the first model; eighteenth indication information indicating a type of input information of the first model; nineteenth indication information indicating a type of output information of the first model; twentieth indication information indicating a format of input information of the second model; twenty-first indication information indicating a format of output information of the second model; twenty-second indication information indicating a type of input information of the second model; twenty-third indication information indicating a type of output information of the second model; twenty-fourth indication information indicating whether the first model and / or the second model is trained as a scalable model, the scalable model having a same model structure under different configuration conditions.

[0043] In some embodiments of the second aspect, in some embodiments, the training network environment information comprises at least one of: twenty-fifth indication information indicating identification information associated with network information; twenty-sixth indication information indicating cell identification information of a plurality of cells having same network information.

[0044] In some embodiments of the second aspect, in some embodiments, the network information comprises at least one of: location information of a network cell; identification information of a network analog beam; urban macro station model UMA; rural macro station model RMA; micro station model UMI; physical downtilt angle.

[0045] In some embodiments of the second aspect, in some embodiments, the model performance monitoring information comprises at least one of: twenty-seventh indication information indicating T time instants at which performance measurement is performed, T≥1; twenty-eighth indication information indicating at least one of M future time instants at which performance monitoring is performed; twenty-ninth indication information indicating X performance indicators, X≥1; thirtieth indication information indicating output information of the second model; thirty-first indication information indicating whether the first device performs performance monitoring using the output information of the second model sent by the second device; thirty-second indication information indicating performance criteria.

[0046] In some embodiments of the second aspect, in some embodiments, the first information is triggered by a first message, the first message comprising at least one of: radio resource control RRC signaling, medium access control-control element MAC-CE, downlink control information DCI.

[0047] In the above method, the second device can send additional information related to model training or model performance monitoring to the first device, thereby improving the effectiveness of training or performance monitoring of the model for CSI compression and recovery, ensuring the consistency of the bilateral model trained by the two devices, and improving the application accuracy of the trained model.

[0048] According to a third aspect of embodiments of the present disclosure, a first device is provided, comprising a transceiver module configured to receive first information sent by a second device, the first information being used to indicate at least one of time domain information, quantization information, model training information, training network environment information, and model performance monitoring information for training a first model and / or a second model, the first model being used for the first device to perform channel state information CSI compression, and the second model being used for the second device to perform CSI recovery.

[0049] According to a fourth aspect of embodiments of the present disclosure, a second device is provided, comprising a transceiver module configured to send first information to a first device, the first information being used to indicate at least one of time domain information, quantization information, model training information, training network environment information, and model performance monitoring information for training a first model and / or a second model, the first model being used for the first device to perform channel state information CSI compression, and the second model being used for the second device to perform CSI recovery.

[0050] According to a fifth aspect of the embodiments of the present disclosure, a communication device is provided, including: one or more processors; wherein the one or more processors are configured to invoke instructions to cause the communication device to perform the method described in any one of the first aspect of the present disclosure, or to perform the method described in any one of the second aspect of the present disclosure.

[0051] According to a sixth aspect of the embodiments of the present disclosure, a communication system is provided, including a first device and a second device, wherein the first device is configured to implement the method of the first aspect, and the second device is configured to implement the method of the second aspect.

[0052] According to a seventh aspect of the embodiments of the present disclosure, a storage medium is provided, which stores instructions, when the instructions are run on a communication device, causing the communication device to perform the method of any one of the first aspect or the second aspect.

[0053] It can be understood that the first device, the second device, the communication device, the communication system, and the storage medium are all used to perform the method provided by the embodiments of the present disclosure. Therefore, the beneficial effects that can be achieved are referred to the beneficial effects in the corresponding method, which will not be described here.

[0054] The embodiments of the present disclosure provide a communication method, a communication device, a communication system, and a storage medium. In some embodiments, the communication method and the information processing method, the communication method, and the like can be replaced with each other, the terminal, the network device, the communication device, and the like can be replaced with each other, and the information processing system, the communication system, and the like can be replaced with each other.

[0055] The embodiments of the present disclosure are not exhaustive, but only illustrate some embodiments, and are not specific limitations on the protection scope of the present disclosure. In the case of no contradiction, each step in an embodiment can be implemented as an independent embodiment, and the steps can be combined arbitrarily, for example, the scheme after removing some steps in an embodiment can also be implemented as an independent embodiment, and the order of the steps in an embodiment can be exchanged arbitrarily, in addition, the optional implementation manners in an embodiment can be combined arbitrarily; in addition, the embodiments can be combined arbitrarily, for example, some or all steps of different embodiments can be combined arbitrarily, and an embodiment can be combined with the optional implementation manners of other embodiments.

[0056] In the embodiments of the present disclosure, the terms and / or descriptions of the embodiments are consistent and can be referred to each other if there is no special description and logical conflict, and the technical features in different embodiments can be combined to form new embodiments according to their inherent logical relationship.

[0057] The terms used in the embodiments of the present disclosure are only for the purpose of describing specific embodiments, and not as a limitation on the present disclosure.

[0058] In the embodiments of the present disclosure, an element expressed in singular form, such as "a", "an", "the", "said", "the aforementioned", "the foregoing", "this", and the like, unless otherwise specified, can represent "one and only one", or can represent "one or more", "at least one", and the like. For example, in the case of using an article such as "a", "an", "the" in English, the noun after the article can be understood as a singular expression, or can be understood as a plural expression.

[0059] In the embodiments of the present disclosure, "plurality" refers to two or more.

[0060] In some embodiments, the terms "at least one of", "at least one of", "at least one of", "one or more", "a plurality of", "multiple", and the like can be replaced with each other.

[0061] In the embodiments of the present disclosure, the description manner such as "at least one of A, B, C, and the like", "A and / or B and / or C, and the like" includes any one of A, B, C, and the like existing alone, and also includes any combination of any multiple of A, B, C, and the like, each of which can exist alone; for example, "at least one of A, B, C" includes the cases of A alone, B alone, C alone, A and B in combination, A and C in combination, B and C in combination, A and B and C in combination; for example, A and / or B includes the cases of A alone, B alone, and the combination of A and B.

[0062] In some embodiments, the description manner such as "A in one case, and B in another case", "in response to one case A, in response to another case B", and the like, according to the case, can include the following technical solutions: A is executed regardless of B, that is, A in some embodiments; B is executed regardless of A, that is, B in some embodiments; A and B are selectively executed, that is, A and B are selected from A and B to be executed in some embodiments; A and B are both executed, that is, A and B in some embodiments. When there are more branches such as A, B, C, and the like, it is similar to the above.

[0063] The prefix words of "first", "second" and the like in the embodiments of the present disclosure are merely used to distinguish different description objects, and do not constitute limitation on the position, order, priority, quantity or content of the description objects. The description objects are described in the claims or embodiments, and should not be construed as redundant limitation because of the use of the prefix words. For example, the description object is "field", and the ordinal words before "field" in "first field" and "second field" do not limit the position or order between "fields", and "first" and "second" do not limit whether the "fields" modified thereby are in the same message or not, nor limit the order of "first field" and "second field". For another example, the description object is "level", and the ordinal words before "level" in "first level" and "second level" do not limit the priority between "levels". For another example, the quantity of the description object is not limited by the ordinal words, and can be one or more. For example, "first device", wherein the quantity of "device" can be one or more. In addition, the objects modified by different prefix words can be the same or different, for example, the description object is "device", and "first device" and "second device" can be the same device or different devices, and the types thereof can be the same or different. For another example, the description object is "information", and "first information" and "second information" can be the same information or different information, and the contents thereof can be the same or different.

[0064] In some embodiments, "including A", "containing A", "for indicating A", "carrying A" can be interpreted as directly carrying A, or indirectly indicating A.

[0065] In some embodiments, the terms of "in response to", "in response to determining", "in the case of", "when", "when", "if", "if" and the like can be replaced with each other.

[0066] In some embodiments, the terms of "greater than", "greater than or equal to", "not less than", "more than", "more than or equal to", "not less than", "higher than", "higher than or equal to", "not lower than", "above" and the like can be replaced with each other, and the terms of "less than", "less than or equal to", "not greater than", "less than", "less than or equal to", "not more than", "lower than", "lower than or equal to", "not higher than", "below" and the like can be replaced with each other.

[0067] In some embodiments, an apparatus or the like can be interpreted as an entity, and can also be interpreted as virtual, and the name thereof is not limited to the name described in the embodiments, and the terms "apparatus", "equipment", "device", "circuit", "network element", "node", "function", "unit", "section", "system", "network", "chip", "chip system", "entity", "subject" and the like can be replaced with each other.

[0068] In some embodiments, the terms "access network device (AN device)", "radio access network device (RAN device)", "base station (BS)", "radio base station", "fixed station", "node", "access point", "transmission point (TP)", "reception point (RP)", "transmission / reception point (TRP)", "panel", "antenna panel", "antenna array", "cell", "macro cell", "small cell", "femto cell", "pico cell", "sector", "cell group", "carrier", "component carrier", "bandwidth part (BWP)" and the like can be replaced with each other.

[0069] In some embodiments, the terms "terminal," "terminal device," "user equipment (UE)," "user terminal," "mobile station (MS)," "mobile terminal (MT)," "subscriber station," "mobile unit," "subscriber unit," "wireless unit," "remote unit," "mobile device," "wireless device," "wireless communication device," "remote device," "mobile subscriber station," "access terminal," "mobile terminal," "wireless terminal," "remote terminal," "handset," "user agent," "mobile client," "client," and so on can be replaced with each other.

[0070] In some embodiments, an access network device, a core network device, or a network device can be replaced with a terminal. For example, for a structure in which communication between an access network device, a core network device, or a network device and a terminal is replaced with communication between a plurality of terminals (for example, also referred to as device-to-device (D2D), vehicle-to-everything (V2X), and so on), embodiments of the present disclosure can also be applied. In this case, a structure in which a terminal has all or part of the functions of an access network device can also be provided. Furthermore, the language of "uplink," "downlink," and so on can also be replaced with language corresponding to communication between terminals (for example, "side"). For example, an uplink channel, a downlink channel, and so on can be replaced with a side channel, and an uplink, a downlink, and so on can be replaced with a side link.

[0071] In some embodiments, a terminal can be replaced with an access network device, a core network device, or a network device. In this case, a structure in which an access network device, a core network device, or a network device has all or part of the functions of a terminal can also be provided.

[0072] In some embodiments, the names of information and the like 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", "field", "symbol", "symbol", "codebook", "codeword", "codepoint", "bit", "data", "program", "chip", and the like can be replaced with each other.

[0073] In some embodiments, terms such as "uplink", "uplink", "physical uplink", and the like can be replaced with each other, terms such as "downlink", "downlink", "physical downlink", and the like can be replaced with each other, terms such as "side", "sidelink", "sidelink communication", "sidelink communication", "direct", "direct link", "direct communication", "direct link communication", and the like can be replaced with each other.

[0074] In some embodiments, terms such as "downlink control information (DCI)", "downlink (DL) assignment", "DL DCI", "uplink (UL) grant", "UL DCI", and the like can be replaced with each other.

[0075] In some embodiments, terms such as "physical downlink shared channel (PDSCH)", "DL data", and the like can be replaced with each other, and terms such as "physical uplink shared channel (PUSCH)", "UL data", and the like can be replaced with each other.

[0076] In some embodiments, terms such as "radio", "wireless", "radio access network (RAN)", "access network (AN)", "RAN-based", and the like can be replaced with each other.

[0077] In some embodiments, the terms "synchronization signal (SS)", "synchronization signal block (SSB)", "reference signal (RS)", "pilot", "pilot signal" and the like can be replaced with each other.

[0078] In some embodiments, the terms "moment", "time point", "time", "time position" and the like can be replaced with each other, and the terms "time length", "time period", "time window", "window", "time" and the like can be replaced with each other.

[0079] In some embodiments, the terms "acquire", "obtain", "get", "receive", "transmit", "bidirectional transmission", "send and / or receive" and the like can be replaced with each other, which can be interpreted as receiving from other subjects, obtaining from protocols, obtaining by oneself, autonomously implementing and the like.

[0080] In some embodiments, the terms "send", "transmit", "report", "issue", "transmit", "bidirectional transmission", "send and / or receive" and the like can be replaced with each other.

[0081] In some embodiments, "predetermined" and "preset" can be interpreted as being previously specified in protocols and the like, or can be interpreted as being previously set by devices and the like.

[0082] In some embodiments, determining can be interpreted as judging, deciding, judging, calculating, computing, processing, deriving, investigating, searching, looking up, retrieving, inquiring, ascertaining, receiving, transmitting, inputting, outputting, accessing, resolving, selecting, choosing, establishing, comparing, "assuming", "expecting", "considering", broadcasting, notifying, communicating, forwarding, configuring, reconfiguring, allocating, mapping, assigning, etc., but is not limited thereto.

[0083] In some embodiments, determining or judging can be performed by a value represented by 1 bit (0 or 1), or by a true or false value (Boolean value) represented by true or false, or by comparison of numerical values (for example, comparison with a predetermined value), but is not limited thereto.

[0084] In some embodiments, "network" can be interpreted as devices (for example, access network devices, core network devices, etc.) contained in the network.

[0085] In some embodiments, "not expecting to receive" can be interpreted as not receiving on time domain resources and / or frequency domain resources, or can be interpreted as, after receiving data, etc., not performing subsequent processing on the data, etc.; "not expecting to send" can be interpreted as not sending, or can be interpreted as sending but not expecting the receiving party to respond to the content of the sending.

[0086] In some embodiments, obtaining data, information, etc. can comply with the laws and regulations of the country where the location is located.

[0087] The current research and simulation results show that by using AI technology, the feedback overhead of the terminal can be reduced or the CSI feedback accuracy can be improved, and in the 3GPP standardization research, a bilateral AI / ML model based on the terminal-side CSI generation part model and the network-side CSI recovery part model is used to realize compressed feedback and recovery of CSI. Figure 1a below shows a schematic diagram of realizing compressed feedback and recovery of CSI based on a bilateral AI / ML model. The UE side compresses the downlink channel information H through a CSI generation part model (defined as an encoder) and sends it to the gNB through quantization as a binary bit stream. The gNB side recovers the approximate H' of the original downlink information through a CSI recovery part model (defined as a decoder).

[0088] The downlink channel H described in Figure 1a only contains spatial-frequency domain channel information. In order to further improve the CSI compression performance, the time domain correlation of the channel can also be used, and the channel information in the time domain can also be included while compressing the spatial-frequency domain. According to whether the encoder and / or decoder use the time domain or the method of using the time domain, it can be divided into several cases.

[0089] Figure 1b shows a schematic diagram of spatial-time-frequency CSI compression. As can be seen from the figure, in addition to the input compressed channel information H, the encoder part model on the UE side (terminal side) also contains historical CSI input information a t . Correspondingly, in addition to the input quantized binary bit stream information, the decoder part model on the NW side (network device side) also contains historical CSI input information b t , and then recovers the approximate H' of the original downlink information at the corresponding time through reasoning. The binary bit stream information refers to the result of quantizing the code word obtained by compressing the input H by the encoder.

[0090] The UE estimates the channel information at multiple historical time points according to the received CSI-RS multiple times, and the gNB can send the CSI-RS multiple times through the CSI-RS burst mode, and define the CSI-RS burst within an observation window (Observation window), as shown in Figure 1c. Then the UE predicts the CSI at one or more future time points according to the measured channel information within the observation window through an AI / ML or non-AI / ML algorithm, and outputs the CSI defined within the prediction window (Prediction window) at one or more future time points. As shown by the dashed arrow in Figure 1c. The UE reports the CSI at one or more time points predicted at one or more time points through an AI model, and in Figure 1c, the CSI at each time point within the prediction window is reported at time n.

[0091] The CSI generation part model and the CSI recovery part model need to be trained by the collected dataset. The types of training the CSI generation part model and the CSI recovery part model include the following three types:

[0092] 1. Training Type 1: The training of the model is completed at one side (such as the terminal side or the network side), and then the trained part model is sent to the other side.

[0093] 2. Training Type 2: The CSI generation part model and the CSI recovery part model are respectively trained by joint training at the terminal side and the network side. Or, after one part model is trained at one of the terminal side or the network side, the other part model of the bilateral model is trained at the other side, wherein the model parameters of the first trained part are not updated.

[0094] 3. Training Type 3: The training of the model is first completed at one side, and then the training of the other part model is completed at the other side by sending the trained data or other auxiliary information. Specifically, the training Type 3 can be divided into:

[0095] 3-1. NW-first training: The network side first trains the CSI generation part model and the CSI recovery part model, and then sends the dataset for training the CSI generation part model and / or other auxiliary information to the terminal side.

[0096] 3-2. UE-first training: The terminal side first trains the CSI generation part model and the CSI recovery part model, and then sends the dataset for training the CSI recovery part model and / or other auxiliary information to the network side.

[0097] In order to reduce or alleviate the complexity of bilateral model training, the following several options for collaborative training between device manufacturers have been proposed:

[0098] Option 1: Standardize the model structure and parameters.

[0099] Option 2: Standardize the dataset.

[0100] Option 3: Standardize the model structure, and the parameters of the model are transmitted between the NW side and the UE side.

[0101] Option 4: Standardize the format of the data, and the data is transmitted between the NW side and the UE side.

[0102] Option 5: Standardize the model format, and the reference model is transmitted between the NW side and the UE side.

[0103] Among them, option 1 can be divided into the following cases:

[0104] Option 1-1: Standardized encoder.

[0105] Option 1-2: Standardized decoder.

[0106] Option 1-3: Standardized encoder and decoder.

[0107] Option 3 and Option 5 can be further divided into the following cases, depending on the model parameters or model post-UE execution behavior passed to the UE side:

[0108] For Option 3, it can be divided into the following cases:

[0109] Option 3a: The received model parameters are used to retrain the model, redevelop a different model, or test.

[0110] Option 3a-1: Pass the parameters of the encoder.

[0111] Option 3a-2: Pass the parameters of the decoder.

[0112] Option 3a-3: Pass the parameters of the encoder and decoder.

[0113] Option 3b: The received model parameters are directly used for model inference.

[0114] For Option 5, it can be divided into the following cases:

[0115] Option 5a: The received model is trained, a different model is redeveloped, or tested.

[0116] Option 5a-1: Pass the encoder model.

[0117] Option 5a-2: Pass the decoder model.

[0118] Option 5a-3: Pass the encoder and decoder models.

[0119] Option 4 can be further divided into the following cases, depending on the different data content passed:

[0120] For Option 4, the dataset is passed from the NW side to the UE side, where:

[0121] Option 4-1: The dataset is the target CSI (target CSI) and the feedback CSI (CSI feedback)

[0122] Option 4-2: The dataset is the CSI feedback and the reconstructed target CSI (reconstructed target CSI)

[0123] Option 4-3: The dataset is target CSI, CSI feedback and reconstructed target CSI.

[0124] Based on the above trained bilateral model, the NW side also needs to send related additional information to the UE for the training or performance monitoring of the bilateral model, but it is currently uncertain which additional condition information is indicated.

[0125] To solve the above problems, the present disclosure proposes an information indication method and a communication device, a communication system and a storage medium.

[0126] FIG. 1 is a schematic diagram of an architecture of a communication system according to an embodiment of the present disclosure. As shown in FIG. 1, the communication system 100 can include a first device 101 and a second device 102.

[0127] In some embodiments, for example, the first device can be a device performing CSI compression, and the first device can be a device training and / or using a CSI generation partial model. For example, the first device can obtain target CSI (target CSI), and obtain feedback CSI (CSI feedback) through the CSI generation partial model. The first device can be a terminal or a network device.

[0128] In some embodiments, for example, the second device can be a device performing CSI recovery, and the first device can be a device training and / or using a CSI recovery partial model. For example, the second device can obtain the output (feedback CSI) of the first device training the CSI generation partial model, and obtain the reconstructed target CSI (reconstructed target CSI) through the CSI recovery partial model. The second device can be a network device or a terminal.

[0129] In some embodiments, the terminal includes at least one of a mobile phone, a wearable device, an Internet of Things device, a communication-capable automobile, a smart automobile, a Pad, a wireless transceiver-equipped computer, a virtual reality (VR) terminal device, an augmented reality (AR) terminal device, a wireless terminal device in industrial control, a wireless terminal device in self-driving, a wireless terminal device in remote medical surgery, a wireless terminal device in a smart grid, a wireless terminal device in transportation safety, a wireless terminal device in a smart city, a wireless terminal device in a smart home, etc., but is not limited thereto.

[0130] In some embodiments, the network device can include an access network device and / or a core network device. The access network device is, for example, a node or device that accesses a terminal to a wireless network, and can include at least one of an evolved NodeB (eNB) in a 5G communication system, a next generation eNB (ng-eNB), a next generation NodeB (gNB), a node B (NB), a home node B (HNB), a home evolved node B (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 6th generation mobile communication system (6G), an Open RAN, a Cloud RAN, a base station in other communication systems, an access node in a wireless fidelity (WiFi) system, etc., but is not limited thereto.

[0131] In some embodiments, the technical solutions of the present disclosure can be applicable to an Open RAN architecture, at this time, the interfaces between or within the access network devices involved in the embodiments of the present disclosure can become internal interfaces of the Open RAN, and the processes and information interactions between these internal interfaces can be implemented through software or programs.

[0132] In some embodiments, the access network device can be composed of a central unit (CU) and a distributed unit (DU), where the CU can also be referred to as a control unit. The CU-DU structure can split the protocol layers of the access network device, and some of the protocol layers are controlled by the CU, and the rest or all of the protocol layers are distributed in the DU and controlled by the CU. However, the present disclosure is not limited thereto.

[0133] In some embodiments, the core network device can be one device including one or more network elements, or can be multiple devices or device groups including all or part of the one or more network elements. The network element can be virtual or physical. The core network includes at least one of an evolved packet core (EPC), a 5G core network (5GCN), and a next-generation core (NGC), for example.

[0134] In some embodiments, the one or more network elements described above can include AMF, UPF, MME, etc., and can also include other network elements such as policy control function (PCF), application function (AF), network application function (NAF), authentication and key management for applications anchor function (AAnF), bootstrapping server function (BSF), session management function (SMF), etc.

[0135] It can be understood that the communication system described in the embodiments of the present disclosure is for more clearly illustrating the technical solutions of the embodiments of the present disclosure, and does not constitute a limitation on the technical solutions proposed by the embodiments of the present disclosure. Those skilled in the art can know that, with the evolution of system architecture and the appearance of new business scenarios, the technical solutions proposed by the embodiments of the present disclosure are also applicable to similar technical problems.

[0136] The following embodiments of the present disclosure can be applied to the communication system 100 shown in FIG. 1 or part of the subject, but are not limited thereto. The subjects shown in FIG. 1 are illustrative, and the communication system can include all or part of the subjects in FIG. 1, or other subjects other than FIG. 1. The number and form of each subject is arbitrary, and the connection relationship between the subjects is illustrative. The subjects can be connected or not connected, and the connection can be in any way, can be direct connection or indirect connection, can be wired connection or wireless connection.

[0137] 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 (Bluetooth (registered trademark)), Public Land Mobile Network (PLMN) network, Device-to-Device (D2D) system, Machine to Machine (M2M) system, Internet of Things (IoT) system, Vehicle-to-Everything (V2X), system using other communication methods, next-generation system expanded based thereon, and the like. Further, a plurality of systems can be applied in combination (for example, combination of LTE or LTE-A and 5G, and the like).

[0138] The wide application of the 5th Generation Mobile Communication Technology (5G) brings great changes to all aspects of people's life. 5G will penetrate into all fields of future society to build a comprehensive information ecosystem centered on users. Among them, the 5G user experience rate can reach 100 Mbit / s-1 Gbit / s, which can support mobile virtual reality and other extreme business experience; the 5G peak rate can reach 10 Gbit / s-20 Gbit / s, and the traffic density can reach 10 Mbit / s / m 2 , which can effectively support the growth of mobile business traffic by thousands of times in the future; the 5G connection density can reach 1 million / m 2 , which can effectively support a large number of Internet of Things devices; the 5G transmission delay can reach the order of milliseconds, which can meet the stringent requirements of vehicle networking and industrial control; 5G can support a mobile speed of 500 km / h, which can meet good user experience in a high-speed rail environment. It can be imagined that 5G as a new type of infrastructure representative will rebuild the future information society.

[0139] FIG. 2 is an interaction diagram of a communication method according to an embodiment of the present disclosure. As shown in FIG. 2, the embodiment of the present disclosure relates to a communication method for a communication system 100, which can include a first device 101 and a second device 102. In the following description of the embodiments, a first device is taken as an example of a terminal, and a second device is taken as an example of a network device. It should be understood that the first device can be a network device, and the second device can be a terminal. The above method includes:

[0140] Step 2101, the second device sends first information to the first device.

[0141] In some embodiments, the first information is used to indicate at least one of the time domain information, the quantization information, the model training information, the training network environment information, and the model performance monitoring information for training the first model and / or the second model.

[0142] In some embodiments, the first information is used for model training and / or model performance monitoring of the CSI compression recovery model. For example, the first information can be used for bilateral model training, such as the above-mentioned training Type2 and Type3. It should be understood that the first information can also be used for unilateral model training, such as the above-mentioned training Type1, and the present disclosure is not limited in this regard.

[0143] In some embodiments, the first information can be referred to as "additional information", which can represent other information used to train the CSI compression recovery model in addition to the spatial-frequency domain information, and the present disclosure is not limited in this regard.

[0144] In some embodiments, the first model is used for the first device to perform CSI compression. For example, the first model can be a “CSI generation partial model”, a “CSI compression model”, or the like, without limitation. For example, the first model can be referred to as an encoder.

[0145] In some embodiments, the second model is used for the second device to perform CSI recovery. For example, the first model can be a “CSI recovery partial model”, a “CSI recovery model”, or the like, without limitation. For example, the second model can be referred to as a decoder.

[0146] In some embodiments, the time domain information comprises at least one of: first indication information indicating time information of input information of the first model; second indication information indicating time information of output information of the first model; third indication information indicating time information of input information of the second model; fourth indication information indicating time information of output information of the second model.

[0147] In the above embodiments, the time information described in the first indication information comprises at least one of: fifth indication information indicating N historical measurement time instants, N≥1; sixth indication information indicating M predicted future time instants, M≥1; seventh indication information indicating a time interval between two historical measurement time instants; eighth indication information indicating a time interval between two future time instants; ninth indication information indicating a starting time instant of the future time instants.

[0148] In the above embodiments, the two historical measurement time instants described in the seventh indication information can be any two historical measurement time instants, which can be adjacent historical measurement time instants, or two specific non-adjacent historical measurement time instants, without limitation.

[0149] In the above embodiments, for the one or more historical time instants utilized, the number of time instants adopted by the first model and the second model can be the same or different.

[0150] In the above embodiments, the quantization information comprises at least one of: tenth indication information indicating a quantization manner adopted by the first model in a training process; eleventh indication information indicating a dequantization manner adopted by the second model in the training process.

[0151] In the above embodiments, quantization refers to quantizing the output information of the first model. For the second model, its input is the dequantized information of the quantized information. In other words, the second model can recover to the quantized value according to the quantization information.

[0152] In some embodiments, the model training information comprises at least one of: twelfth indication information for indicating a model training type of the first model and / or the second model, the model training type comprising at least one of a first training type Type 1, a second training type Type 2, and a third training type Type 3; thirteenth indication information for indicating dataset distribution information of the second device training the first model and / or the second model; fourteenth indication information for indicating a dataset size of the second device training the first model and / or the second model; fifteenth indication information for indicating a size of each sample in the dataset of the second device training the first model and / or the second model; sixteenth indication information for indicating a format of input information of the first model; seventeenth indication information for indicating a format of output information of the first model; eighteenth indication information for indicating a type of input information of the first model; nineteenth indication information for indicating a type of output information of the first model; twentieth indication information for indicating a format of input information of the second model; twenty-first indication information for indicating a format of output information of the second model; twenty-second indication information for indicating a type of input information of the second model; twenty-third indication information for indicating a type of output information of the second model; and twenty-fourth indication information for indicating whether the first model and / or the second model is trained as a scalable model, the scalable model having a same model structure under different configuration conditions.

[0153] In the above embodiments, the dataset distribution indication information described in the thirteenth indication information may, for example, be that the dataset on the second device side is a mixed dataset of Uma or indoor, and the dataset distribution ratio of the two scenarios is 6:4, etc., which is not limited in the present disclosure.

[0154] In the above embodiments, the scalable model described in the twenty-fourth indication information refers to using one same first model / second model or model structure under different configuration conditions such as different port numbers, bandwidth sizes, etc.

[0155] In some embodiments, the training network environment information comprises at least one of: twenty-fifth indication information for indicating identification information associated with the network information; and twenty-sixth indication information for indicating cell identification information of multiple cells having the same network information.

[0156] It should be understood that the second device can provide the training network environment information to the first device, so that the first device knows that certain models are trained under which network environment / network conditions, so that the first device can consider under which network conditions the model is applicable when performing model retraining or model inference.

[0157] In the above embodiments, the identification information associated with the network information described in the twenty-fifth indication information can be an Associated ID.

[0158] In the above embodiments, the cell identification information described in the twenty-sixth indication information can refer to cell identification of a plurality of cells for training the first model and / or the second model under the condition that the network information is the same.

[0159] In the above embodiments, the network information described in the twenty-fifth indication information and the twenty-sixth indication information can include all information related to network side privacy, i.e., information that is usually invisible to the terminal, and the specific range and type of the network information are not limited by the present disclosure.

[0160] In the above embodiments, the network information described in the twenty-fifth indication information and the twenty-sixth indication information includes at least one of the following: location information of a network cell; identification information of a network analog beam; an urban macro station model UMA; a rural macro station model RMA; a micro station model UMI; a physical downtilt angle.

[0161] In some embodiments, the model performance monitoring information includes at least one of the following: twenty-seventh indication information for indicating T time instants at which performance measurement is performed, T≥1; twenty-eighth indication information for indicating at least one time instant of M future time instants at which performance monitoring is performed; twenty-ninth indication information for indicating X performance indicators, X≥1; thirtieth indication information for indicating output information of the second model; thirty-first indication information for indicating whether the first device performs performance monitoring using the output information of the second model sent by the second device; thirty-second indication information for indicating a performance criterion.

[0162] In the above embodiments, the purpose of the second device providing the model performance monitoring information to the first device is to enable the first device to verify the performance of the trained model, such as under what circumstances the model training meets the requirements, etc.

[0163] In the above embodiments, the performance criterion described in the thirty-second indication information can be, for example, a systematic analysis (symptom-target-goal-cause-solution, SGCS), a normalized mean squared error (NMSE), etc., and the present disclosure is not limited thereto.

[0164] In some embodiments, the first information can be carried by a physical downlink shared channel (PDSCH) or a physical downlink control channel (PDCCH).

[0165] The first information is triggered by a first message, and the first message comprises at least one of radio resource control (RRC) signaling, a MAC control element (MAC-CE), and DCI.

[0166] In some embodiments, the first device (terminal) can also send the above-mentioned additional information (first information) to the second device (network device).

[0167] In step 2102, the first device and / or the second device train the first model and / or the second model and / or perform model performance monitoring based on the first information.

[0168] In some embodiments, the first information can be used for unilateral training or bilateral training of the first model and / or the second model and / or model performance monitoring.

[0169] For example, the first device can perform unilateral training of the first model and / or the second model by the first training type Type1 based on the first information. Similarly, the second device can also perform unilateral training of the first model and / or the second model by the first training type Type1 based on the first information.

[0170] For example, the first device and the second device can perform joint training or bilateral training of the first model and / or the second model by the second training type Type2 or the third training type Type3 based on the first information.

[0171] In some embodiments, the first device and / or the second device can perform model performance monitoring to determine whether the training performance of the first model and / or the second model is reasonable or meets certain conditions.

[0172] In some embodiments, the training of the first model and / or the second model by the first device and / or the second device can be based on a dataset measured by the first device, e.g., based on channel information measured by the first device within an observation window, so as to predict CSI at one or more future time instants, e.g., CSI within a prediction window, using the trained model.

[0173] It should be understood that the first device and the second device improve the performance of the first model and / or the second model by considering the first information, and train and / or monitor the performance of the first model and / or the second model, so as to ensure consistency of the models on both sides of the first device and the second device.

[0174] In some embodiments, step 2102 is an optional step.

[0175] The method related to the embodiments of the present disclosure can include at least one of steps 2101-2102. For example, steps 2101+2102 can be implemented as an independent embodiment, and step 2101 can be implemented as an independent embodiment, which is not limited in the present disclosure.

[0176] FIG. 3a is a flow diagram illustrating a communication method according to an embodiment of the present disclosure. As shown in FIG. 3a, the embodiments of the present disclosure relate to a communication method for a first device, and the above method comprises:

[0177] Step 3101, receiving first information sent by a second device.

[0178] Optional implementation of step 3101 can refer to optional implementation of step 2101 of FIG. 2 and other associated parts in the embodiments related to FIG. 2, which will not be repeated here.

[0179] Step 3102, training a first model and / or a second device based on the first information and / or monitoring the performance of the model.

[0180] Optional implementation of step 3102 can refer to optional implementation of step 2102 of FIG. 2 and other associated parts in the embodiments related to FIG. 2, which will not be repeated here.

[0181] FIG. 3b is a flow diagram illustrating a communication method according to an embodiment of the present disclosure. As shown in FIG. 3b, the embodiments of the present disclosure relate to a communication method for a first device, and the above method comprises:

[0182] Step 3201, receiving first information sent by a second device.

[0183] The optional implementation of step 3201 can refer to the optional implementation of step 2101 in FIG. 2, the optional implementation of step 3101 in FIG. 3a, and other associated parts in the embodiments involved in FIG. 2 and FIG. 3a, which are not described here again.

[0184] FIG. 4a is a flow diagram of a communication method according to an embodiment of the present disclosure. As shown in FIG. 4a, the embodiment of the present disclosure relates to a communication method, for a second device, the method comprising:

[0185] Step 4101, sending first information to the first device.

[0186] The optional implementation of step 4101 can refer to the optional implementation of step 2101 in FIG. 2, and other associated parts in the embodiments involved in FIG. 2, which are not described here again.

[0187] Step 4102, training and / or performing model performance monitoring on the first model and / or the second model based on the first information.

[0188] The optional implementation of step 4102 can refer to step 2102 in FIG. 2, step 3102 in FIG. 3a, and other associated parts in the embodiments involved in FIG. 2 and FIG. 3a, which are not described here again.

[0189] FIG. 4b is a flow diagram of a communication method according to an embodiment of the present disclosure. As shown in FIG. 4b, the embodiment of the present disclosure relates to a communication method, for a second device, the method comprising:

[0190] Step 4201, sending first information to the first device.

[0191] The optional implementation of step 4201 can refer to the optional implementation of step 2101 in FIG. 2, and other associated parts in the embodiments involved in FIG. 2, which are not described here again.

[0192] FIG. 5 is a flow diagram of a communication method according to an embodiment of the present disclosure. As shown in FIG. 5, the embodiment of the present disclosure relates to a communication method, for a communication system comprising a first device and a second device, the method comprising:

[0193] Step 5101, the second device sends first information to the first device.

[0194] The optional implementation of step 5101 can refer to the optional implementation of step 2101 in FIG. 2, step 3101 in FIG. 3a, step 3201 in FIG. 3b, step 4101 in FIG. 4a, step 4201 in FIG. 4b, and other associated parts in the embodiments involved in FIG. 2, FIG. 3a, FIG. 3b, FIG. 4a, and FIG. 4b, which are not described here again.

[0195] The following is an exemplary introduction to the above method.

[0196] The method shown in the embodiments of the present disclosure relates to a communication method. Specifically, the present disclosure proposes an additional information content design method for bilateral AI model collaborative training. The complete content of the method is as follows.

[0197] The present disclosure takes Case 2 and Case 3 in the CSI compression use case as an example for the following description.

[0198] 1. Bilateral model training between equipment vendors: the additional information includes one or more of the following information contents:

[0199] Information content 1-1: time information of input or output information of the encoder / decoder model, which includes at least one or more of the following: 1≤N historical measurement time points, 1≤M predicted future time points, the interval d1 between adjacent time points for each historical time point, the interval d2 between adjacent time points for the predicted future time points, and the starting time point of the predicted future time points. For one or more historical time points used, the number of time points used by the encoder and the decoder can be the same or different.

[0200] Information content 1-2: quantization method indication information.

[0201] Information content 1-3: bilateral collaborative training type indication information, such as indicating that the UE uses training Type 1 or Type 2 training.

[0202] Information content 1-4: dataset distribution indication information, dataset size, or size of each sample of the training encoder / decoder on the NW side. For example, the dataset on the NW side is a mixed dataset of Uma and indoor, and the dataset distribution ratio of the two scenarios is 6:4, etc.

[0203] Information content 1-5: input or output information format or type of the encoder / decoder.

[0204] Information content 1-6: whether to train as an extensible encoder / decoder. Extensible means that under different port number, bandwidth size, and other configuration conditions, a same encoder / decoder model or model structure is used.

[0205] 2. The additional information includes NW side additional condition messages, specifically one or more of the following information contents:

[0206] Information content 2-1: Associated ID associated with the NW side additional condition information, including network cell location, network simulation beam, UMA, UMI, etc.

[0207] Information content 2-2: If the Associated IDs of multiple cells are the same for the NW side additional condition message, the multiple cell IDs are also indicated to the UE.

[0208] 3. Performance monitoring: The additional condition information contains one or more of the following information contents.

[0209] Information content 3-1: Indication information of 1≤T time instants for performance measurement

[0210] Information content 3-2: Indication information of part of time instants for monitoring in the future M time instants (for case 3)

[0211] Information content 3-3: Indication information of X performance indicators, where the X performance indicators are the performance indicators corresponding to different time instants in the future M time instants.

[0212] Information content 3-4: NW side decoder output information

[0213] Information content 3-5: Indication information of whether the UE side uses the decoder output information sent by the NW to the UE for performance monitoring

[0214] Information content 3-6: Performance criteria, such as SGCS, NMSE

[0215] It should be understood that the above additional condition information can be sent to the UE through one or more of RRC / MAC-CE / DCI signaling.

[0216] It should be understood that the above is that the NW sends the additional condition information to the UE. Similarly, the UE can also send the above additional condition information to the NW.

[0217] The following is specifically described in the form of examples, in the following examples, the first device is described as the UE, the second device is described as the NW, the first model is described as the encoder, and the second model is described as the decoder:

[0218] Example 1 (Case 2):

[0219] It is assumed that the spatial-time domain CSI compression feedback of downlink channel information is realized through Case 2. At each current measurement time instant, the UE compresses and feeds back the measured channel information as shown in FIG. 1a. At the same time, the input data of the encoder contains not only the downlink channel information but also the input information of N historical time instants. Correspondingly, the input data of the decoder contains not only the CSI feedback information but also the input information of N historical time instants, as shown in FIG. 1b.

[0220] If the UE and the NW implement the bilateral model of cooperative training by using Option 3a, the NW has completed the training of the encoder#1 and the decoder#1 according to the collected data set, and the NW sends the model parameters of the encoder#1 to the UE. The UE can further update and train the encoder#1 based on the encoder#1 and the measured data set to obtain the encoder#2. Finally, the UE and the NW perform inference by using the encoder#2 and the decoder#1, respectively. In order to train the encoder#2, the NW needs to send to the UE how many pieces of historical time information are used to train the encoder#1, so that the UE trains an encoder compatible with the decoder#1. If the NW trains the encoder and the decoder by using N=5 pieces of historical time information of the channel, and the interval of each time is d=1 slot, the NW sends the information indicating N=5 and d=1 to the UE as auxiliary information, and the UE also uses N=5 pieces of historical time information of the channel when training the encoder#2. In addition, if the quantization manner of the model trained by the NW is scalar quantization, and the number of quantized bits is 2 bits, the input information format of the encoder is the feature vector of the downlink channel information, the trained encoder is an expandable model, the expandable model supports the transmission of antenna port numbers P=2, 4, 8, 12, 16, 24 or 32 ports, the bandwidth range is any bandwidth ranging from 24 to 100 PRBs, and the feedback overhead of the encoder output is 60 bits, 120 bits and 240 bits. The NW also indicates the indication information of these contents to the UE as auxiliary information, and the UE trains the encoder#2 model similar to the function of the encoder#1 trained by the NW according to the received auxiliary information.

[0221] The data set measured by the UE is usually obtained under a certain NW configuration condition, and therefore, the model trained by the UE is more suitable for the NW configuration condition. However, some NW configuration conditions are private information of the NW and are not displayed to the UE, and the NW indicates the additional condition information of the NW to the UE, and the additional condition information is associated with an associated ID, and the NW only needs to send the indication information of the associated ID to the UE. Under different NWs, the additional condition information of the NW corresponding to the same associated ID can be the same or different. In the same case, the NW only needs to indicate the cells associated with the same additional condition information of the same associated ID to the UE, and after the UE switches to the corresponding cell, the UE can determine whether to re-measure the data for model training or directly use the previously trained encoder#2 for inference according to the received indication information.

[0222] The trained model also needs to guarantee certain performance, and the performance requirement can also be notified to the UE by the NW through sending assistance information. For example, the performance criterion of the NW side training encoder #1 and decoder #1 is SGCS, and when the feedback overhead is 60 bits, the SGCS of this model is 0.7, which is between the performance indicators [0.65, 0.75], and can meet the performance requirement. Alternatively, the NW can also indicate the minimum performance indicator of the UE under a certain feedback overhead. As shown in the following table.

[0223] Table 1

[0224] The information in the above table can be determined by protocol predefinition, or the NW can indicate the mapping relationship of the table to the UE. The UE can calculate the SGCS through the encoder and decoder on the UE side or the AI / ML model deployed on the UE side to estimate the SGCS. Alternatively, the UE can also send the information output by the decoder #1 to the UE for the calculation of the SGCS based on the NW. The NW sends the above information as assistance information to the UE, and the UE can train the encoder #2 that meets the performance requirement through the received assistance information.

[0225] The above is an example of Option 3a. For other training cooperation options, such as Option 4 or Option 5, the above similar method can also be used to train a reliable encoder or decoder.

[0226] Example 2 (Case 3):

[0227] If the UE realizes the space-frequency-time CSI compression feedback of the downlink channel information through the Case 3 method. The UE side needs to predict the channel information of one or more future time based on the information of multiple measured historical time, and then compress and feedback the predicted channel information, as shown in FIG. 1c.

[0228] Similar to Example 1, still taking the UE and the NW to realize the cooperative training of the bilateral model by adopting Option 3a, the NW has completed the training of encoder #1 and decoder #1 according to the collected data set, and the NW sends the model parameters of encoder #1 to the UE. The UE can further update and train encoder #2 based on the encoder #1 and the measured data set. Finally, the UE and the NW respectively use encoder #2 and decoder #1 for inference. The NW side sends the time information of training encoder #1 and decoder #1 to the UE, and the time information includes:

[0229] The NW adopts N=4 channel information of historical time to infer and predict M=2 channel information of future time by an AI / ML model, and the interval of the future M time is d2=2 slots.

[0230] The auxiliary information for training the model of the encoder #2 includes, for example, a quantization manner, a training model manner, an input data format of the encoder, and supportable scalable function information. Similar to the example 1, the auxiliary information is not described herein. The NW side additional condition information indication manner for training the model is similar to the example 1.

[0231] For performance monitoring, the SGCS is taken as an example of the performance criterion. The performance indicators can include X=2, and each performance indicator corresponds to M=2 future time. Alternatively, the NW indicates that the UE monitors the performance corresponding to the second future time of the M=2 time. Other possible auxiliary information is similar to the example 1. Based on the performance monitoring manner, the UE trains the encoder #2 with reliable performance.

[0232] FIG. 6a is a structural schematic diagram of the first device 101 according to an embodiment of the present disclosure. As shown in FIG. 6a, the first device 101 includes a transceiver module 6101 configured to receive first information sent by a second device, the first information being used to indicate at least one of time domain information, quantization information, model training information, training network environment information, and model performance monitoring information for training a first model and / or a second model, the first model being used for CSI compression performed by the first device, and the second model being used for CSI recovery performed by the second device. Alternatively, the transceiver module is configured to perform the steps related to the processing performed by the first device 101 in any of the above methods, which are not described herein.

[0233] In some embodiments, the time domain information includes at least one of the following: first indication information used to indicate time information of input information of the first model; second indication information used to indicate time information of output information of the first model; third indication information used to indicate time information of input information of the second model; and fourth indication information used to indicate time information of output information of the second model.

[0234] In some embodiments, the time information includes at least one of the following: fifth indication information used to indicate N historical measurement time, N≥1; sixth indication information used to indicate M predicted future time, M≥1; seventh indication information used to indicate a time interval between two historical measurement time; eighth indication information used to indicate a time interval between two future time; and ninth indication information used to indicate a starting time of the future time.

[0235] In some embodiments, the quantization information comprises at least one of: tenth indication information indicating a quantization manner adopted by the first model in a training process; and eleventh indication information indicating a dequantization manner adopted by the second model in a training process.

[0236] In some embodiments, the model training information comprises at least one of: twelfth indication information indicating a model training type of the first model and / or the second model, the model training type comprising at least one of a first training type Type 1, a second training type Type 2, and a third training type Type 3; thirteenth indication information indicating dataset distribution information of the first model and / or the second model trained by the second device; fourteenth indication information indicating a dataset size of the first model and / or the second model trained by the second device; fifteenth indication information indicating a size of each sample in the dataset of the first model and / or the second model trained by the second device; sixteenth indication information indicating a format of input information of the first model; seventeenth indication information indicating a format of output information of the first model; eighteenth indication information indicating a type of input information of the first model; nineteenth indication information indicating a type of output information of the first model; twentieth indication information indicating a format of input information of the second model; twenty-first indication information indicating a format of output information of the second model; twenty-second indication information indicating a type of input information of the second model; twenty-third indication information indicating a type of output information of the second model; and twenty-fourth indication information indicating whether the first model and / or the second model is trained as a scalable model, the scalable model having a same model structure under different configuration conditions.

[0237] In some embodiments, the training network environment information comprises at least one of: twenty-fifth indication information indicating identification information associated with network information; and twenty-sixth indication information indicating cell identification information of a plurality of cells having the same network information.

[0238] In some embodiments, the network information comprises at least one of: location information of a network cell; identification information of a network analog beam; an urban macro station model UMA; a rural macro station model RMA; a micro station model UMI; and a physical downtilt angle.

[0239] In some embodiments, the model performance monitoring information comprises at least one of: twenty-seventh indication information indicating T time instants at which performance measurement is performed, T≥1; twenty-eighth indication information indicating at least one of M future time instants at which performance monitoring is performed; twenty-ninth indication information indicating X performance indicators, X≥1; thirtieth indication information indicating output information of the second model; thirty-first indication information indicating whether the first device performs performance monitoring using the output information of the second model sent by the second device; and thirty-second indication information indicating performance criteria.

[0240] In some embodiments, the first information is triggered by a first message, and the first message comprises at least one of radio resource control (RRC) signaling, a medium access control (MAC)-control element (CE), and downlink control information (DCI).

[0241] In some embodiments, the first device 101 further comprises a processing module configured to train the first model and / or the second model based on the first information and / or perform model performance monitoring.

[0242] In the above method, the first device can receive additional information sent by the second device to indicate model training or model performance monitoring, thereby improving the effectiveness of training or performance monitoring of the model for CSI compression and recovery, ensuring consistency of the bilateral model trained by the two devices, and improving the application accuracy of the trained model.

[0243] FIG. 6b is a structural schematic diagram of the second device 102 according to an embodiment of the present disclosure. As shown in FIG. 6b, the second device 102 comprises a transceiver module 6201 configured to send first information to the first device, the first information being used to indicate at least one of time domain information, quantization information, model training information, training network environment information, and model performance monitoring information for training a first model and / or a second model, the first model being used for the first device to perform channel state information (CSI) compression, and the second model being used for the second device to perform CSI recovery. Optionally, the transceiver module is configured to perform the steps of receiving and / or the like performed by the second device 102 in any of the above methods, which will not be described herein.

[0244] In some embodiments, the time domain information comprises at least one of: first indication information indicating time information of input information of the first model; second indication information indicating time information of output information of the first model; third indication information indicating time information of input information of the second model; and fourth indication information indicating time information of output information of the second model.

[0245] In some embodiments, the time information comprises at least one of: fifth indication information used to indicate N historical measurement time instants, N≥1; sixth indication information used to indicate M predicted future time instants, M≥1; seventh indication information used to indicate a time interval between two historical measurement time instants; eighth indication information used to indicate a time interval between two future time instants; ninth indication information used to indicate a starting time instant of the future time instants.

[0246] In some embodiments, the quantization information comprises at least one of: tenth indication information used to indicate a quantization manner adopted by the first model during a training process; eleventh indication information used to indicate a dequantization manner adopted by the second model during a training process.

[0247] In some embodiments, the model training information comprises at least one of: twelfth indication information used to indicate a model training type of the first model and / or the second model, the model training type comprising at least one of a first training type Type1, a second training type Type2, and a third training type Type3; thirteenth indication information used to indicate dataset distribution information of the first model and / or the second model trained by the second device; fourteenth indication information used to indicate a dataset size of the first model and / or the second model trained by the second device; fifteenth indication information used to indicate a size of each sample in the dataset of the first model and / or the second model trained by the second device; sixteenth indication information used to indicate a format of input information of the first model; seventeenth indication information used to indicate a format of output information of the first model; eighteenth indication information used to indicate a type of input information of the first model; nineteenth indication information used to indicate a type of output information of the first model; twentieth indication information used to indicate a format of input information of the second model; twenty-first indication information used to indicate a format of output information of the second model; twenty-second indication information used to indicate a type of input information of the second model; twenty-third indication information used to indicate a type of output information of the second model; twenty-fourth indication information used to indicate whether the first model and / or the second model is trained as a scalable model, the scalable model having a same model structure under different configuration conditions.

[0248] In some embodiments, the training network environment information comprises at least one of: twenty-fifth indication information used to indicate identification information associated with network information; twenty-sixth indication information used to indicate cell identification information of a plurality of cells having same network information.

[0249] In some embodiments, the network information comprises at least one of: location information of a network cell; identification information of a network analog beam; urban macro station model UMA; rural macro station model RMA; micro station model UMI; physical downtilt angle.

[0250] In some embodiments, the model performance monitoring information comprises at least one of: twenty-seventh indication information indicating T time instants at which performance measurement is performed, T≥1; twenty-eighth indication information indicating at least one of M future time instants at which performance monitoring is performed; twenty-ninth indication information indicating X performance indicators, X≥1; thirtieth indication information indicating output information of the second model; thirty-first indication information indicating whether the first device performs performance monitoring using the output information of the second model sent by the second device; thirty-second indication information indicating performance criteria.

[0251] In some embodiments, the first information is triggered by a first message, and the first message comprises at least one of: radio resource control (RRC) signaling, media access control-control element (MAC-CE), and downlink control information (DCI).

[0252] In some embodiments, the second device 101 can further comprise a processing module, which can be configured to train the first model and / or the second model based on the first information and / or perform model performance monitoring.

[0253] In the above method, the second device can send additional information related to model training or model performance monitoring to the first device, thereby improving the effectiveness of training or performance monitoring of the model for CSI compression and recovery, ensuring consistency of the bilateral model trained by the two devices, and improving the application accuracy of the trained model.

[0254] As shown in FIG. 7a, the communication device 7100 comprises one or more processors 7101. The processor 7101 can be a general-purpose processor or a special-purpose processor, for example, a baseband processor or a central processing unit. The baseband processor can be configured to process communication protocols and communication data, and the central processing unit can be configured to control the communication device (e.g., a base station, a baseband chip, a terminal device, a terminal device chip, a DU or a CU, etc.), execute programs, and process data of the programs. The processor 7101 is configured to invoke instructions to enable the communication device 7100 to perform any of the above methods.

[0255] In some embodiments, the communication device 7100 further comprises one or more memories 7102 configured to store instructions. Alternatively, all or part of the memory 7102 can also be outside the communication device 7100.

[0256] In some embodiments, the communication device 7100 further includes one or more transceivers 7103. When the communication device 7100 includes one or more transceivers 7103, the communication steps in the above methods, such as sending and receiving, are performed by the transceiver 7103, and other steps are performed by the processor 7101.

[0257] In some embodiments, the transceiver can include a receiver and a transmitter, which can be separate or integrated together. Optionally, the terms transceiver, transceiving unit, transceiver, transceiving circuit, etc. can be replaced by each other, the terms transmitter, transmitting unit, transmitter, transmitting circuit, etc. can be replaced by each other, and the terms receiver, receiving unit, receiver, receiving circuit, etc. can be replaced by each other.

[0258] Optionally, the communication device 7100 further includes one or more interface circuits 7104 connected to the memory 7102, which can be used to receive signals from the memory 7102 or other devices, and can be used to send signals to the memory 7102 or other devices. For example, the interface circuit 7104 can read the instructions stored in the memory 7102 and send them to the processor 7101.

[0259] The communication device 7100 described in the above embodiments can be a network device or a terminal, but the scope of the communication device 7100 described in the present disclosure is not limited thereto, and the structure of the communication device 7100 can not be limited by Figure 7a. The communication device can be a standalone device or can be part of a larger device. For example, the communication device can be: 1) a standalone integrated circuit (IC), or a chip, or a chip system or subsystem; (2) a set of one or more ICs, which can optionally also include storage components for storing data, programs; (3) an ASIC, such as a Modem; (4) a module that can be embedded in other devices; (5) a receiver, terminal device, smart terminal device, cellular phone, wireless device, handset, mobile unit, vehicle-mounted device, network device, cloud device, artificial intelligence device, etc.; (6) others, etc.

[0260] Figure 7b is a structural schematic diagram of a chip 7200 according to an embodiment of the present disclosure. For the case where the communication device 7100 is a chip or a chip system, the structural schematic diagram of the chip 7200 shown in Figure 7b can be referred to, but is not limited thereto.

[0261] The chip 7200 includes one or more processors 7201, which are used to invoke instructions to cause the chip 7200 to perform any of the above methods.

[0262] In some embodiments, chip 7200 further includes one or more interface circuits 7202 that are connected to memory 7203, which can be used to receive signals from or send signals to memory 7203 or other devices. For example, interface circuit 7202 can read instructions stored in memory 7203 and send the instructions to processor 7201. Alternatively, the terms interface circuit, interface, transceiver pin, transceiver, etc. can be replaced by each other.

[0263] In some embodiments, chip 7200 further includes one or more memories 7203 for storing instructions. Alternatively, all or part of memory 7203 can be outside of chip 7200.

[0264] The disclosure also proposes a storage medium, which has instructions stored thereon, and when the instructions run on communication device 7100, communication device 7100 performs any of the above methods. Alternatively, the storage medium is an electronic storage medium. Alternatively, the storage medium is a computer readable storage medium, but is not limited to this, and it can also be a storage medium readable by other devices. Alternatively, the storage medium can be a non-transitory storage medium, but is not limited to this, and it can also be a transitory storage medium.

[0265] The disclosure also proposes a program product, which is executed by communication device 7100, so that communication device 7100 performs any of the above methods. Alternatively, the program product is a computer program product.

[0266] The disclosure also proposes a computer program, which, when running on a computer, causes the computer to perform any of the above methods.

[0267] In the above embodiments, all or part of the embodiments can be implemented by software, hardware, firmware or any combination thereof. When implemented by software, all or part of the embodiments can be implemented in the form of a computer program product. The computer program product includes one or more computer programs. When the computer programs are loaded on a computer and executed, all or part of the processes or functions described in the embodiments of the present disclosure are generated. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable devices. The computer programs can be stored in a computer-readable storage medium or transferred from one computer-readable storage medium to another computer-readable storage medium, for example, the computer programs can be transferred from one website, computer, server or data center to another website, computer, server or data center through wired (such as coaxial cable, optical fiber, digital subscriber line (DSL)) or wireless (such as infrared, wireless, microwave, etc.) mode. The computer-readable storage medium can be any available medium that can be accessed by a computer or a data storage device such as a server, data center, etc. that includes one or more available media sets. The available media can be magnetic media (such as floppy disk, hard disk, magnetic tape), optical media (such as high-density digital video disc (digital video disc, DVD)), or semiconductor media (such as solid state disk (solid state disk, SSD)) and the like.

[0268] The correspondence relationship shown in each table in the present disclosure can be configured or predefined. The values of the information in each table are only examples, and other values can be configured, and the present disclosure does not limit. When configuring the correspondence relationship between the information and each parameter, it is not necessarily required to configure all the correspondence relationships shown in each table. For example, the correspondence relationship shown in some rows in the table in the present disclosure can also not be configured. For another example, the above table can be appropriately deformed and adjusted, for example, split, merged, etc. The parameter name shown in the title of each table above can also use other names understandable by the communication device, and the parameter value or representation method can also use other values or representation methods understandable by the communication device. Each table above can also use other data structures when implemented, for example, arrays, queues, containers, stacks, linear tables, pointers, linked lists, trees, graphs, structures, classes, heaps, hash tables or hash tables, etc.

[0269] The predefinition in the present disclosure can be understood as definition, predefinition, storage, prestorage, prenegotiation, preconfiguration, solidification or pre-burning.

[0270] Those skilled in the art can clearly understand that the units and algorithm steps of each example described in combination with the embodiments disclosed herein can be realized by electronic hardware or a combination of computer software and electronic hardware. Whether the functions are realized in hardware or software manner depends on specific application and design constraints of the technical solution. The skilled person can use different methods to realize the described functions for each specific application, but such implementation should not be considered beyond the scope of the disclosure.

[0271] Those skilled in the art can clearly understand that, for the convenience and brevity of the description, the specific working processes of the above-described system, device and unit can refer to the corresponding processes in the foregoing method embodiments, which will not be described here.

[0272] The above is only a specific implementation of the present disclosure, but the protection scope of the present disclosure is not limited thereto, and any person skilled in the art can easily think of changes or replacements within the technical scope disclosed by the present disclosure, which should be covered within the protection scope of the present disclosure. Therefore, the protection scope of the present disclosure should be subject to the protection scope of the claims.

Claims

1. A communication method characterized by comprising: The method is performed by a first device, comprising: receiving first information sent by a second device, the first information being used to indicate at least one of time domain information, quantization information, model training information, training network environment information, model performance monitoring information for training a first model and / or a second model, the first model being used for the first device to perform channel state information (CSI) compression, and the second model being used for the second device to perform CSI recovery.

2. The method of claim 1, wherein, The time domain information comprises at least one of: first indication information used to indicate time information of input information of the first model; second indication information used to indicate time information of output information of the first model; third indication information used to indicate time information of input information of the second model; fourth indication information used to indicate time information of output information of the second model.

3. The method of claim 2, wherein, The time information comprises at least one of: fifth indication information used to indicate N historical measurement time instants, N≥1; sixth indication information used to indicate M predicted future time instants, M≥1; seventh indication information used to indicate a time interval between two historical measurement time instants; eighth indication information used to indicate a time interval between two future time instants; ninth indication information used to indicate a starting time instant of the future time instants.

4. The method according to any one of claims 1 to 3, characterized in that, The quantization information comprises at least one of: tenth indication information used to indicate a quantization manner adopted by the first model in a training process; eleventh indication information used to indicate a dequantization manner adopted by the second model in the training process.

5. The method according to any one of claims 1 to 4, characterized in that, The model training information comprises at least one of: twelfth indication information used to indicate a model training type of the first model and / or the second model, the model training type comprising at least one of a first training type Type 1, a second training type Type 2, and a third training type Type 3; thirteenth indication information used to indicate dataset distribution information of the second device for training the first model and / or the second model; fourteenth indication information used to indicate a dataset size of the second device for training the first model and / or the second model; fifteenth indication information used to indicate a size of each sample in the dataset of the second device for training the first model and / or the second model; sixteenth indication information used to indicate a format of input information of the first model; seventeenth indication information used to indicate a format of output information of the first model; eighteenth indication information used to indicate a type of input information of the first model; nineteenth indication information used to indicate a type of output information of the first model; twentieth indication information used to indicate a format of input information of the second model; twenty-first indication information used to indicate a format of output information of the second model; twenty-second indication information used to indicate a type of input information of the second model; twenty-third indication information used to indicate a type of output information of the second model; The twenty-fourth indication information is used for indicating whether the first model and / or the second model is trained as an extensible model, and a model structure of the extensible model is same under different configuration conditions.

6. The method according to any one of claims 1 to 5, characterized in that, The training network environment information comprises at least one of: The twenty-fifth indication information is used for indicating identification information associated with the network information; The twenty-sixth indication information is used for indicating cell identification information of a plurality of cells with same network information.

7. The method of claim 6, wherein, The network information comprises at least one of: Position information of a network cell; Identification information of a network analog beam; An urban macro station model (UMA); A rural macro station model (RMA); A micro station model (UMI); A physical downtilt angle.

8. The method according to any one of claims 1 to 7, characterized in that, The model performance monitoring information comprises at least one of: The twenty-seventh indication information is used for indicating T time instants at which performance measurement is performed, and T is greater than or equal to 1; The twenty-eighth indication information is used for indicating at least one time instant of M future time instants at which performance monitoring is performed; The twenty-ninth indication information is used for indicating X performance indicators, and X is greater than or equal to 1; The thirtieth indication information is used for indicating output information of the second model; The thirty-first indication information is used for indicating whether the first device performs performance monitoring by using the output information of the second model sent by the second device; The thirty-second indication information is used for indicating a performance criterion.

9. The method of any one of claims 1-8, wherein the first information is triggered by a first message comprising at least one of radio resource control (RRC) signaling, medium access control-control element (MAC-CE), or downlink control information (DCI). The method further comprises:

10. The method according to any one of claims 1 to 9, characterized in that, training and / or performing model performance monitoring on the first model and / or the second model based on the first information. The method is performed by a second device and comprises:

11. A communication method, comprising: sending, to a first device, first information used for indicating at least one of time domain information, quantization information, model training information, training network environment information, or model performance monitoring information for training a first model and / or a second model, the first model being used for performing channel state information (CSI) compression by the first device, and the second model being used for performing CSI recovery by the second device. The time domain information comprises at least one of:

12. The method of claim 11, wherein, first indication information used for indicating time information of input information of the first model; second indication information used for indicating time information of output information of the first model; third indication information used for indicating time information of input information of the second model; fourth indication information used for indicating time information of output information of the second model. The time information comprises at least one of:

13. The method of claim 12, wherein, fifth indication information used for indicating N historical measurement time instants, N being greater than or equal to 1; sixth indication information used for indicating M predicted future time instants, M being greater than or equal to 1; seventh indication information used for indicating a time interval between two historical measurement time instants; eighth indication information used for indicating a time interval between two future time instants; ninth indication information used for indicating a starting time instant of the future time instants. The quantization information comprises at least one of:

14. The method according to any one of claims 11 to 13, characterized in that, ​ The tenth indication information is used to indicate a quantization manner adopted by the first model in a training process. The eleventh indication information is used to indicate a dequantization manner adopted by the second model in a training process.

15. The method according to any one of claims 11 to 14, characterized in that, The model training information comprises at least one of the following: The twelfth indication information is used to indicate a model training type of the first model and / or the second model, and the model training type comprises at least one of a first training type Type 1, a second training type Type 2, and a third training type Type 3. The thirteenth indication information is used to indicate dataset distribution information of the first model and / or the second model trained by the second device. The fourteenth indication information is used to indicate a dataset size of the first model and / or the second model trained by the second device. The fifteenth indication information is used to indicate a size of each sample in the dataset of the first model and / or the second model trained by the second device. The sixteenth indication information is used to indicate a format of input information of the first model. The seventeenth indication information is used to indicate a format of output information of the first model. The eighteenth indication information is used to indicate a type of input information of the first model. The nineteenth indication information is used to indicate a type of output information of the first model. The twentieth indication information is used to indicate a format of input information of the second model. The twenty-first indication information is used to indicate a format of output information of the second model. The twenty-second indication information is used to indicate a type of input information of the second model. The twenty-third indication information is used to indicate a type of output information of the second model. The twenty-fourth indication information is used to indicate whether the first model and / or the second model is trained as a scalable model, and the scalable model has a same model structure under different configuration conditions.

16. The method according to any one of claims 11 to 15, characterized in that, The training network environment information comprises at least one of the following: The twenty-fifth indication information is used to indicate identification information associated with network information. The twenty-sixth indication information is used to indicate cell identification information of a plurality of cells with same network information.

17. The method of claim 16, wherein, The network information comprises at least one of the following: Position information of a network cell; Identification information of a network analog beam; An urban macro station model UMA; A rural macro station model RMA; A micro station model UMI; A physical downtilt angle.

18. The method according to any one of claims 11 to 17, characterized in that, The model performance monitoring information comprises at least one of the following: The twenty-seventh indication information is used to indicate T time instants at which performance measurement is performed, and T≥1. The twenty-eighth indication information is used to indicate at least one time instant of M future time instants at which performance monitoring is performed. The twenty-ninth indication information is used to indicate X performance indexes, and X≥1. The thirtieth indication information is used to indicate output information of the second model. The thirty-first indication information is used to indicate whether the first device performs performance monitoring by using the output information of the second model sent by the second device. The thirty-second indication information is used to indicate a performance criterion.

19. The method of any one of claims 11 to 18, wherein The first information is triggered by a first message, and the first message comprises at least one of radio resource control (RRC) signaling, a medium access control-control element (MAC-CE), and downlink control information (DCI).

20. The method of any one of claims 11 to 19, wherein, The method further comprises: training and / or model performance monitoring of the first model and / or the second model based on the first information.

21. A first device, comprising: Comprise: a transceiver configured to receive first information transmitted by a second device, the first information being used to indicate at least one of time domain information, quantization information, model training information, training network environment information, and model performance monitoring information for training a first model and / or a second model, the first model being used for channel state information (CSI) compression performed by the first device, and the second model being used for CSI recovery performed by the second device.

22. A second device, comprising: Comprise: a transceiver configured to transmit first information to a first device, the first information being used to indicate at least one of time domain information, quantization information, model training information, training network environment information, and model performance monitoring information for training a first model and / or a second model, the first model being used for channel state information (CSI) compression performed by the first device, and the second model being used for CSI recovery performed by the second device.

23. A communication system, characterized by Comprise: a first device, a transmitting entity of a first protocol layer of the first device being configured to perform the method according to any one of claims 1 to 10; a second device, a receiving entity of a first protocol layer of the second device being configured to perform the method according to any one of claims 11 to 20.

24. A communication device, wherein, Comprise: a transceiver; a memory; a processor connected to the transceiver and the memory, respectively, and configured to control wireless signal transceiving of the transceiver by executing computer executable instructions on the memory, and to implement the method according to any one of claims 1 to 20.

25. A computer storage medium, wherein, The computer storage medium stores computer executable instructions; the computer executable instructions are executed by the processor to implement the method according to any one of claims 1 to 20. The computer storage medium stores computer executable instructions; the computer executable instructions are executed by the processor to implement the method according to any one of claims 1 to 20.

Images