Information exchange method, apparatus, and readable storage medium

Abstract

This application relates to the field of mobile communications and can be applied to protocol frameworks such as LTE, NR, or 6G, and in particular relates to information exchange methods, apparatus, and readable storage media. The method comprises the step of a base station transmitting first information to an UE to determine the UE's historical state information when transmission of uplink feedback information fails. The UE inputs the first information and the historical state information determined based on currently measured or predicted channel information into an encoder for processing to obtain feedback information and transmit the feedback information to the base station. According to embodiments of this application, the state information on the UE side (or input by the encoder) can maintain consistency with the state information on the base station side (or input by the decoder), thereby improving the decoding performance of the base station side (or decoder), reducing communication performance loss, and improving communication quality.

Description

[Technical Field]

[0001] This application claims priority to Chinese Patent Application No. 202310128738.5, titled "Information Exchange Method, Apparatus and Readable Storage Medium," filed with the China National Intellectual Property Administration on 6 February 2023, which is incorporated herein by reference in its entirety.

[0002] This application relates to the field of communication technology, particularly to methods, apparatus, and readable storage media for information exchange. [Background technology]

[0003] With the advancement of wireless communication technology, the scale of antenna arrays is continuously increasing, and the number of supported frequency bands is also expanding, in order to support more services and meet higher requirements regarding metrics such as system capacity and communication latency. As a result, communication systems are becoming more complex. Therefore, improving the performance of complex communication systems by using artificial intelligence (AI), such as deep learning (DL), has become an important research direction. For example, the application value of AI in many wireless communication technologies, such as channel state information (CSI) feedback, beam management, and pilot design management, is continuously being revealed through thorough research in the academic field. Based on this, the combination of AI and wireless communication is gradually shifting from academic research to practical application.

[0004] In wireless communication links, the channels of medium and low-speed users continuously change over time. Therefore, communication performance can be improved by mining channel time-domain correlations. For example, channel prediction can be implemented by mining channel time-domain correlations to counteract the channel aging problem; or, channel information can be compressed by mining channel time-domain correlations, reducing the overhead of feeding back channel information. For example, when both user equipment (UE) and base station (BS) perform data processing using channel time-domain correlations, the UE may input the current channel information and the state information previously output by the encoder into the encoder for processing, and output feedback information and new state information. Correspondingly, the base station may input the currently received feedback information and the state information previously output by the decoder into the decoder for processing, and output restored (or predicted) channel information and new state information.

[0005] Currently, channel time-domain correlation mining benefits from the synchronous updates of state information output by the UE's encoder and the base station's decoder. When the transmission of one piece of feedback information from the UE fails due to reasons such as low instantaneous channel quality, the base station (BS) cannot update its state information, and as a result, the base station's decoding performance may degrade. [Overview of the Initiative]

[0006] Embodiments of the present invention provide an information exchange method, apparatus, and readable storage medium, which enable consistency between state information on the UE side (or input by the encoder) and state information on the base station side (or input by the decoder), thereby improving the decoding performance of the base station side (or decoder), reducing communication performance loss, and improving communication quality.

[0007] The present invention will be described below in terms of different embodiments. It should be understood that the following implementations and beneficial effects of different embodiments can be referenced from one another.

[0008] According to a first aspect, the present invention provides an information exchange method. The method comprises the step of an encoding device (e.g., UE) receiving first information transmitted by a decoding device (e.g., base station), wherein the first information is historical state information of the encoding device e his This is for determining the historical state information e based on the first information. his Determine the history status information e his The first channel information may be input to the encoder for processing to obtain the first feedback information. Next, the encoding device transmits the first feedback information to the decoding device, where the first feedback information includes encoded information of the first channel information or encoded information of the predicted channel information. History status information e his This reflects one or more historical channel information obtained before the first channel information is obtained.

[0009] In some scenarios, the first channel information may be channel information obtained through measurement, for example, channel information obtained by an encoding device by measuring a currently received reference signal. In this case, the first feedback information may be encoded information (e.g., compressed information) of the first channel information, or encoded information (e.g., compressed information) of channel information predicted based on the first channel information. In other words, when the first channel information is channel information obtained through actual measurement, the encoder may be configured to perform prediction and compression, or to perform compression. In some other scenarios, the first channel information may be predicted channel information. In this case, the first feedback information may be encoded information (e.g., compressed information) of the first channel information. In other words, when the first channel information itself is predicted channel information, the encoder may be configured to compress the first channel information.

[0010] After receiving the first information, the encoding device of the present application may no longer use the previously acquired state information as an input to the encoder during the current time of execution. However, the historical state information e his can be used as an input for the current execution of the encoder to generate and transmit the first feedback information. Therefore, the decoding device can control the state information input by the encoder in the encoding device. As a result, the state information input by the encoder can maintain consistency with the state information input by the decoder, thereby improving the decoding performance, reducing the communication performance loss, and improving the communication quality.

[0011] Referring to the first aspect, in a possible implementation, the first state information may be the historical state information e his and the first channel information can be obtained by inputting them into the encoder for processing. The first state information may reflect one or more historical channel information including the first channel information.

[0012] Referring to the first aspect, in a possible implementation, the first channel information may be determined based on the CSI.

[0013] The channel information in the present application may be for representing a channel and can be understood as an expression of the channel status. Details will not be further described below. For example, the channel information in the present application may be CSI. CSI may be a channel response matrix, an eigenvector obtained by performing singular value decomposition on the channel response matrix, a matrix including a plurality of eigenvectors, or a projection coefficient obtained by projecting the eigenvector into the spatial frequency domain. This is not limited in the present application.

[0014] Referring to the first aspect, in a possible implementation, the encoder may be an AI model.

[0015] Referring to the first aspect, in a possible implementation, before the encoding device receives the first information transmitted by the decoding device, the method further includes: the encoding device inputs the second channel information and the state information e t-1 into the encoder for processing to obtain the second feedback information; and the encoding device transmits the second feedback information to the decoding device. The state information e t-1 may reflect one or more historical channel information obtained before the second channel information is obtained.

[0016] Optionally, after the second channel information and the state information e t-1 are input into the encoder for processing, the second state information is further output. The second state information reflects one or more historical channel information including the second channel information.

[0017] Optionally, the first feedback information is the k-th feedback information after the second feedback information is transmitted, where k is a positive integer.

[0018] Referring to the first aspect, in a possible implementation, before the encoding device receives the first information transmitted by the decoding device, the method further includes: the encoding device receives the second information transmitted by the decoding device, where the second information indicates one or more of whether the encoding device performs periodic memory, the memory period, or the start time of the memory period; and when the second information instructs the encoding device to perform periodic memory, the encoding device periodically stores the state information output by the encoder based on the instruction of the second information.

[0019] Optionally, the encoding device periodically storing the state information output by the encoder based on the instruction of the second information means that the encoding device stores the state information e obtained by the encoding device during the (n(T / S)-k)-th feedback period n(T / S)-kTo temporarily store (in the nth memory cycle); the encoding device receiving third information transmitted by the decoding device in the (n(T / S))th feedback period, where the third information instructs the encoding device to store the state information stored by the encoding device in the ((n-1)*(T / S))th feedback period, or the third information is state information e acquired in the (n(T / S)-k)th feedback period n(T / S)-k The encoding device is instructed to store the information; and the encoding device stores the corresponding state information based on the instruction for the third piece of information. For specific implementations, see the description of Embodiment 3 of the Method below, which provides only a brief description.

[0020] For example, different meanings can be expressed by using the value of the third piece of information. When the value of the third piece of information is the first value, the encoding device stores the state information stored in the ((n-1)*(T / S))th feedback period in the (n(T / S))th feedback period. When the value of the third piece of information is the second value, the encoding device stores the state information e acquired in the (n(T / S)-k)th feedback period in the (n(T / S))th feedback period. n(T / S)-k Remember this.

[0021] For example, if the (n(T / S)-k)th feedback of the encoding device is successful, the third information may be set to the second value; if the (n(T / S)-k)th feedback of the encoding device fails, the third information may be set to the first value. The first value is 0 and the second value is 1; or the first value is 1 and the second value is 0. This is not limited to the present invention.

[0022] n, k, S, and T are all positive integers, where T represents the memory period and S represents the feedback period. A memory period T of 1 is an integer multiple of a feedback period S of 1, and a feedback period of 1 is used to describe the transmission time interval between two adjacent feedback pieces of information.

[0023] The “feedback period” as referred to in this application may be a short period, and feedback information must be fed back once during the feedback period. Further details will not be provided below. The “feedback period” as referred to in this application may be understood as periodic, and the time interval between two adjacent feedback periods may be understood as one feedback period. Further details will again not be provided below. For example, the interval between the end of the first feedback period and the start of the second feedback period in two adjacent feedback periods may be understood as one feedback period. Alternatively, the interval between the transmission or reception of two adjacent feedback pieces of information may be understood as one feedback period. The feedback period in this application can be set flexibly and is not limited to the above description.

[0024] Optionally, after the encoding device receives the first information transmitted by the decoding device, the method further: history state information e his The encoding process includes a step in which the encoding device determines, before receiving the first piece of information, that it is state information stored in the previous memory cycle.

[0025] The encoding device in this application periodically stores state information based on instructions from the decoding device. As a result, the encoding device can roll back the state information, reducing the complexity of the encoding device's operation. In addition, for the same feedback, the state information input by the encoder is consistent with the state information input by the decoder, thereby improving decoding performance, reducing communication performance loss, and improving communication quality.

[0026] Referring to the first aspect, in a possible implementation, before the encoding device receives the first information transmitted by the decoding device (specifically, before the encoding device transmits the second feedback information), the method further: the encoding device receives the fourth information transmitted by the decoding device in the tth feedback period, where the fourth information instructs the encoding device to store the state information acquired in the feedback period prior to the tth feedback period, where t is a positive integer; and the encoding device, based on the instruction of the fourth information, stores the state information acquired by the encoding device in the feedback period prior to the tth feedback period (i.e., the (t-1)th feedback period). t-1 The method includes a step of storing the following: For example, after the encoding device receives the first information transmitted by the decoding device, the method further includes: history state information e his This is state information e stored after the encoding device receives the fourth piece of information. t-1 The encoding device includes a step in which it determines that the encoding device is. For specific implementations, refer to the description of Embodiment 5 of the method below, where only a brief description is provided. In another example, the encoding device determines the historical state information e his status information e t-1 Without any operation or step to determine that, the state information e stored after the encoding device receives the fourth information after receiving the first information transmitted by the decoding device. t-1 The first channel information can be input to an encoder for processing to obtain the first feedback information.

[0027] The encoding device in this application stores state information at a specific point in time based on instructions from the decoding device (i.e., fourth information). As a result, the encoding device can roll back the state information when it fails to transmit feedback information, and further reduces the complexity of the encoding device's operation. In addition, the encoding device determines historical state information based on instructions from the decoding device. In this way, for the same feedback, the state information input by the encoder can be consistent with the state information input by the decoder, thereby improving decoding performance, reducing communication performance loss, and improving communication quality.

[0028] Referring to the first aspect, in a possible implementation, before the encoding device receives the first information transmitted by the decoding device (specifically, after the encoding device has transmitted the second feedback information), the method further: the encoding device receives the fourth information transmitted by the decoding device in the tth feedback period, where the fourth information instructs the encoding device to store the state information obtained in the feedback period prior to the tth feedback period, where t is a positive integer; the encoding device, based on the instruction of the fourth information, stores the state information obtained by the encoding device in the feedback period prior to the tth feedback period (i.e., the (t-1)th feedback period). t-1 A step in which the encoding device temporarily stores the state information e, which was temporarily stored after the fourth information was received in the tth feedback period; a step in which the encoding device receives the third information transmitted by the decoding device during the (t+k-1)th feedback period, where the third information is the state information e, which was temporarily stored after the fourth information was received during the tth feedback period. t-1 The encoding device is instructed to store the third information, or the third information instructs the encoding device to store the state information stored when the previous third information was received; and the encoding device stores the corresponding state information based on the instruction of the third information. For specific implementations, see the description of Embodiment 6 of the Method below, which provides only a brief description.

[0029] For example, different meanings can be expressed by using the value of the third piece of information. When the value of the third piece of information is the first value, the encoding device stores the state information stored when the previous piece of third information was received. When the value of the third piece of information is the second value, the encoding device stores the state information e temporarily stored after the fourth piece of information was received in the tth feedback period. t-1 Remember this. k is a positive integer.

[0030] Optionally, after the encoding device receives the first information transmitted by the decoding device, the method further: history status information e his The encoding device determines that the third piece of information is state information stored after it has been received. Optionally, the encoding device determines that the historical state information e his The encoder may, after receiving the first information transmitted by the decoder, input the first channel information and the state information stored after the encoder received the third information to the encoder for processing, without any operation or step in which the encoder determines that the third information is state information stored after the encoder has received it, in order to obtain the first feedback information.

[0031] The encoding device in this application stores state information at a specific point in time based on instructions from the decoding device (fourth information). As a result, the encoding device can roll back the state information when the transmission of feedback information fails, and further reduces the complexity of the encoding device's operation. Furthermore, the encoding device in this application can temporarily store the state information, and as a result, can handle the impact of delays in the detection and distribution of the first information by the decoding device on the state information rollback. In addition, the encoding device further determines whether to use the historical state information as input to the encoder based on instructions from the decoding device (i.e., the first information). In this way, for the same feedback, the state information input by the encoder can be consistent with the state information input by the decoder, thereby improving decoding performance, reducing communication performance loss, and improving communication quality.

[0032] Referring to the first aspect, in a possible implementation, before the encoding device receives the first information transmitted by the decoding device, the method further includes: the encoding device receiving the second channel information and history state information e his The process includes the steps of inputting the data to an encoder for processing and obtaining second feedback information, and the encoding device transmitting the second feedback information to a decoding device. Optionally, second channel information and history state information e his After the data is input to the encoder for processing, a second state information is output. (History state information e) his This is the historical state information output by the encoder during a specific time of execution; in the next feedback, the historical state information e his Whether to replace it with the second state information is instructed by the decoding device. History state information e his The first channel information may reflect one or more historical channel information acquired before the second channel information was acquired, and the second state information may reflect one or more historical channel information including the second channel information.

[0033] Optionally, after the encoding device receives the first information transmitted by the decoding device, the method further: the encoding device transmits the historical state information e his The process includes a step of updating the state information output by the encoder during the feedback period prior to the current time. For specific implementations, see the description of Embodiment 4 of the method below. Details are not described here.

[0034] The encoding device in this application always stores the historical state information e his The encoding device uses the following as input to the encoder. In this way, when the feedback information from the encoding device fails to be transmitted to the decoding device, the encoding device does not use the mismatched state information as input to the encoder. Therefore, the state information input to the encoder is consistent with the state information input to the decoder, thereby improving decoding performance, reducing communication performance loss, and improving communication quality. In addition, the encoding device uses the instructions of the decoding device (i.e., the first information) to input the historical state information e hisThe history status information e is updated, and as a result, his This includes recent historical channel information, thereby enabling the mining of channel time-domain correlations.

[0035] Referring to the first aspect, in a possible implementation, the encoding device receives first information during the q-th feedback period (or after the (q-1)-th feedback period), where the first information includes or indicates the step size m of the state information rollback, where m is a positive integer. History state information e his This is the state information e input by the encoder in the (qm)th step. q-m-1 It could be, that is, e his =e q-m-1 This is the history status information e. his For specific implementations, please refer to the description in Embodiment 2 of the method below. Details are not explained here. The state information input by the encoder on the qth time is the historical state information e his Therefore, q is a positive integer greater than m.

[0036] The decoding device in this application uses specific historical state information e his The encoder of the encoding device is instructed to roll back. In this way, for the same feedback, the state information input by the encoder is consistent with the state information input by the decoder, thereby improving decoding performance, reducing communication performance loss, and improving communication quality.

[0037] Referring to the first aspect, in a possible implementation, before the encoding device receives the first information transmitted by the decoding device, the method further comprises: the step of the encoding device receiving the fifth information transmitted by the decoding device, the fifth information instructing the encoding device to receive the first information with a delay of feedback period k after transmitting the feedback information, where k is a positive integer.

[0038] Optionally, k is greater than or equal to the step size (or amount) m of the state information rollback.

[0039] In this application, the fifth piece of information indicates the latest time at which the first piece of information can be received, and as a result, the encoding device then determines whether the feedback was successful or unsuccessful.

[0040] According to a second aspect, the present invention provides an information exchange method. The method is as follows: a decoding device (e.g., a base station) transmits first information to an encoding device (e.g., a UE), where the first information is the history state information of the encoding device e his This is for determining; and the step in which the decoding device receives first feedback information transmitted by the encoding device, where the first feedback information is first channel information and history state information of the encoding device e his Determined based on (for example, the first channel information and the history state information of the encoding device e) his It includes (which is output after it is input to the encoder), first feedback information and history state information d of the decoding device. his Both are input to the decoder for processing, and the third channel information is obtained. In other words, the decoder receives the first feedback information and the decoder's history status information d his The data can be input to the decoder for processing to obtain third channel information. Historical state information e his This reflects one or more historical channel information acquired before the first channel information was acquired, and historical status information d his This reflects one or more historical feedback pieces acquired before the first feedback piece is acquired. The first feedback piece includes encoded information for the first channel information or encoded information for the predicted channel information.

[0041] For example, if the transmission of feedback information fails, the decoding device sends the first information to the encoding device. Naturally, if the transmission of feedback information is successful, the decoding device may also send the first information to the encoding device. The scenarios in which the decoding device sends the first information are not limited in this application.

[0042] The decoding device in this application controls the input to the encoder in the encoding device by distributing information (the first information described above), and as a result, the state information input by the encoder can maintain consistency with the state information input by the decoder, thereby improving decoding performance, reducing communication performance loss, and improving communication quality.

[0043] Referring to the second aspect, in a possible implementation, the first feedback information and the history state information d his However, this data is input to the decoder for processing, and a third state information is obtained. The third state information may reflect one or more historical feedback pieces of information, including the first feedback information.

[0044] Referring to the second aspect, in a possible implementation, the first channel information may be determined based on the CSI.

[0045] Referring to the second aspect, in a possible implementation, the encoder may be the first AI model and the decoder may be the second AI model.

[0046] Referring to the second aspect, in a possible implementation, before the decoding device transmits the first information to the encoding device, the method further comprises: the step of the decoding device transmitting the second information to the encoding device, where the second information indicates whether the encoding device performs periodic storage, the storage period, or the start time of the storage period, one or more of the following. If the second information instructs the encoding device to perform periodic storage, the decoding device periodically stores the state information output by the decoder based on the storage period and / or the start time of the storage period.

[0047] Optionally, the decoding device periodically stores state information output by the decoder based on the memory cycle and / or the start time of the memory cycle: the decoding device stores state information d acquired by the decoding device during the (n(T / S)-k)th feedback period. n(T / S)-kThis includes temporarily storing (in the nth memory cycle). The decoding device transmits a third piece of information to the encoding device before the (n(T / S))th feedback period, where the third piece of information instructs the encoding device to store the state information stored in the ((n-1)*(T / S))th feedback period, or the third piece of information is the state information e acquired in the (n(T / S)-k)th feedback period. n(T / S)-k The encoding device is instructed to store the following. The decoding device, based on the third information, stores the state information stored by the decoding device during the ((n-1)*(T / S))th feedback period, or the state information d obtained by the decoding device during the (n(T / S)-k)th feedback period. n(T / S)-k It stores this information. For specific implementations, please refer to the description of Embodiment 3 of the method below; only a brief description is provided here.

[0048] For example, if the decoder successfully receives the (n(T / S)-k)th feedback information (or the (n(T / S)-k)th feedback), the decoder sets the third piece of information to the second value, transmits the third piece of information to the encoder, and receives the state information output by the decoder on the (n(T / S)-k)th time, i.e., d n(T / S)-k The decoding device may store the following: If the decoding device does not receive the (n(T / S)-k)th feedback information, the decoding device sets the third piece of information to the first value, transmits the third piece of information to the encoding device, and stores the state information stored during the ((n-1)*(T / S))th feedback period. For example, the first value is 0 and the second value is 1; or the first value is 1 and the second value is 0. This is not limited to the present invention.

[0049] n, k, S, and T are all positive integers, where T represents the memory period and S represents the feedback period. A memory period T of 1 is an integer multiple of a feedback period S of 1, and a feedback period of 1 is used to describe the transmission time interval between two adjacent feedback pieces of information.

[0050] Optionally, after the decoding device transmits the first information to the encoding device, the method further: history state information d his The decoding device includes a step in which it determines that the decoding device is state information stored in the previous memory cycle before it transmits the first information. Optionally, the decoding device may instead transmit the historical state information d his The decoding device may obtain third channel information by inputting first feedback information and state information stored in the previous memory cycle before the decoding device transmitted the first information into the decoder for processing, without any operation or step of determining that the decoding device is state information stored in the previous memory cycle before the decoding device transmits the first information.

[0051] In this invention, after the decoding device instructs the encoding device to periodically store state information (i.e., second information), the decoding device also periodically stores state information, and as a result, the decoding device rolls back the state information.

[0052] Referring to the second aspect, in a possible implementation, before the decoder transmits the first information to the encoder, the method further comprises: the step of the decoder transmitting a fourth piece of information to the encoder before the tth feedback period, where the fourth piece of information instructs the encoder to store the state information acquired in the feedback period before the tth feedback period, where t is a positive integer. The decoder then stores the state information d acquired by the decoder in the feedback period before the tth feedback period (i.e., the (t-1)th feedback period). t-1 It stores the following. For example, after the decoding device sends the first information to the encoding device, the method further: history state information d his This is the state information d stored after the decoding device transmits the fourth piece of information. t-1 The decoding device includes a step in which it determines that this is the case. For specific implementations, refer to the description of Embodiment 5 of the method below, where only a brief description is provided. In another example, the decoding device alternatively uses historical state information d his is state information d t-1Without any operation or step to determine that, the first information is transmitted to the encoding device, followed by the first feedback information, and the state information d stored after the decoding device transmits the fourth information. t-1 This can be input into a decoder for processing to obtain third channel information.

[0053] Referring to the second aspect, in a possible implementation, before the decoder transmits the first information to the encoder, the method further comprises: the step of the decoder transmitting a fourth piece of information to the encoder before the tth feedback period, where the fourth piece of information instructs the encoder to store the state information acquired in the feedback period before the tth feedback period, where t is a positive integer. The decoder then stores the state information d acquired by the decoder in the feedback period before the tth feedback period. t-1 The decoding device temporarily stores the state information e before the (t+k-1)th feedback period, where the third information is the state information e temporarily stored after the fourth information was received during the tth feedback period. t-1 The decoding device is instructed to store the state information d that was stored when the previous third information was received. Based on the third information, the decoding device stores the state information d that was temporarily stored after the decoding device transmitted the fourth information. t-1 It stores the state information stored when the decoding device transmitted the previous third information. k is a positive integer. For specific implementations, see the description of Embodiment 6 of the method below, where only a brief description is provided.

[0054] For example, if the transmission of the second feedback information is successful, the decoding device sets the value of the third information to the second value, transmits the third information to the encoding device, and temporarily stores state information d during the tth feedback period. t-1It stores the following. If the transmission of the second feedback information fails, the decoding device sets the value of the third information to the first value, sends the third information to the encoding device, and stores the state information that was stored when the previous third information was transmitted. k is a positive integer.

[0055] Optionally, after the decoding device transmits the first information to the encoding device, the method further: history state information d his The process includes a step in which the decoding device determines that the third piece of information is state information stored after it has been transmitted. Optionally, the decoding device may, alternatively, determine the historical state information d his The decoding device may, without any operation or step of determining that the decoding device has stored state information after transmitting the third information, input the first feedback information and the state information stored after the decoding device has transmitted the third information to the decoder for processing to obtain the third channel information.

[0056] Referring to the second aspect, in a possible implementation, after the decoding device transmits the first information to the encoding device, the method further: the decoding device transmits the history state information d his The process includes a step of updating the state information output by the decoder during the feedback period prior to the current time. For specific implementations, see the description of Embodiment 4 of the method below. Details are not described here.

[0057] Referring to the second aspect, in a possible implementation, the decoder transmits first information before the qth feedback period, where the first information includes or indicates the step size m of the state information rollback, where m is a positive integer. History state information d his This is the state information d input by the decoder in the (qm)th step. q-m-1 It could be, that is, d his =d q-m-1 This is the history status information d. his For specific implementations, please refer to the description in Embodiment 2 of the method below. Details are not explained here. The state information input by the decoder on the qth time is the history state information dhis Here, q is a positive integer greater than m.

[0058] Referring to the second aspect, in a possible implementation, before the decoding device transmits the first information to the encoding device, the method further comprises: the step of the decoding device transmitting the fifth information to the encoding device, where the fifth information instructs the encoding device to receive the first information after transmitting the feedback information, with a delay of feedback period k, where k is a positive integer.

[0059] Optionally, k is greater than or equal to the step size (or amount) m of the state information rollback.

[0060] According to a third aspect, the present invention provides an encoding device comprising a transceiver unit and a processing unit. The transceiver unit is configured to receive first information transmitted by a decoding device, wherein the first information is the history state information of the encoding device e his This is for determining the history status information e based on the first information. his And the first channel information is input to the encoder for processing and configured to obtain the first feedback information, where the historical state information e his This reflects one or more historical channel information acquired before the first channel information is acquired. The transceiver unit is further configured to transmit first feedback information to a decoder, where the first feedback information includes encoded information of the first channel information or encoded information of the predicted channel information.

[0061] Referring to the third aspect, in a possible implementation, the first state information is the history state information e his The first channel information can be obtained by inputting it into an encoder for processing. The first state information may reflect one or more historical channel information, including the first channel information.

[0062] Referring to the third aspect, in a possible implementation, the first channel information may be determined based on the CSI.

[0063] Referring to the third aspect, in a possible implementation, the encoder may be an AI model.

[0064] Referring to the third aspect, in a conceivable implementation, the transceiver unit is further configured to transmit second feedback information to a decoding device, where the second feedback information comprises second channel information and state information e t-1 This is feedback information that is output after the data is input to the encoder for processing, and is state information e t-1 This reflects one or more historical channel information acquired before the second channel information is acquired. The encoder further processes the input second channel information and state information e t-1 Based on this, a second state information is output, and the second state information reflects one or more historical channel information, including the second channel information.

[0065] Optionally, the first feedback information is the kth feedback information sent after the second feedback information has been sent, where k is a positive integer.

[0066] Referring to a third aspect, in a conceivable implementation, the transceiver unit is further configured to receive second information transmitted by the decoding device, where the second information indicates whether the encoding device performs periodic storage, the storage period, or one or more start points of the storage period. The processing unit is further configured to periodically store state information output by the encoding device based on the indications of the second information.

[0067] Optionally, the processing unit specifically processes the state information e acquired by the encoding device during the (n(T / S)-k)th feedback period. n(T / S)-kThe transceiver unit is configured to temporarily store state information, where n, k, S, and T are all positive integers, T represents the storage period, S represents the feedback period, one storage period T is an integer multiple of one feedback period S, and one feedback period is used to describe the transmission time interval between two adjacent pieces of feedback information. The transceiver unit is further configured to receive a third piece of information transmitted by the decoder during the (n(T / S))th feedback period, where the third piece of information instructs the encoder to store the state information stored during the ((n-1)*(T / S))th feedback period, or the third piece of information is the state information e acquired during the (n(T / S)-k)th feedback period. n(T / S)-k The encoding device is instructed to store the following. The processing unit is further configured to store the corresponding state information based on the instruction of the third piece of information. For example, the processing unit specifically stores the state information stored in the ((n-1)*(T / S))th feedback period when the value of the third piece of information is the first value; and when the value of the third piece of information is the second value, the state information e acquired in the (n(T / S)-k)th feedback period when the (n(T / S))th feedback period is stored. n(T / S)-k It is configured to store information.

[0068] Optionally, the processing unit further processes the historical status information e his The transceiver unit is configured to determine that the first piece of information is state information stored in the previous memory cycle before it receives it.

[0069] Referring to the third aspect, in a conceivable implementation, the transceiver unit is further configured to receive a fourth piece of information transmitted by the decoder during the tth feedback period, where the fourth piece of information instructs the encoder to store state information acquired during the feedback period preceding the tth feedback period, where t is a positive integer. The processing unit further stores state information e acquired by the encoder during the feedback period preceding the tth feedback period (i.e., the (t-1)th feedback period) based on the instructions of the fourth piece of information. t-1 It is configured to store the following: The processing unit further stores the history state information e his This is state information e stored after the encoding device receives the fourth piece of information. t-1 It is configured to determine that it is so.

[0070] Referring to the third aspect, in a conceivable implementation, the transceiver unit is further configured to receive a fourth piece of information transmitted by the decoder during the tth feedback period, where the fourth piece of information instructs the encoder to store state information acquired during the feedback period preceding the tth feedback period, where t is a positive integer. The processing unit further stores state information e acquired by the encoder during the feedback period preceding the tth feedback period (i.e., the (t-1)th feedback period) based on the instructions of the fourth piece of information. t-1 It is configured to temporarily store the following. The transceiver unit is further configured to receive a third piece of information transmitted by the decoder during the (t+k-1)th feedback period, where the third piece of information is state information e that was temporarily stored after the fourth piece of information was received during the tth feedback period. t-1 The encoding device is instructed to store the third piece of information, or the third piece of information is instructed to store the state information stored when the previous third piece of information was received, where k is a positive integer. The processing unit is further configured to store the corresponding state information based on the instructions of the third piece of information.

[0071] Optionally, the processing unit further includes historical state information e his is configured to determine that it is the state information stored after the third information is received.

[0072] Referring to the third aspect, in a possible implementation, the processing unit further includes historical state information e his is configured to update it to the state information output by the encoder during the feedback period before the current time.

[0073] Referring to the third aspect, in a possible implementation, the first information includes or indicates the step size m of the state information rollback, where m is a positive integer. The historical state information e his is the same as the state information e input by the encoder at the (q - m)-th time, and the state information input by the encoder at the q-th time is the historical state information e q-m-1 where q is a positive integer greater than m. his

[0074] Referring to the third aspect, in a possible implementation, the transceiver unit is further configured to receive the fifth information transmitted by the decoding device, where the fifth information instructs the encoding device to receive the first information with a delay of k feedback periods after transmitting the feedback information, where k is a positive integer.

[0075] Optionally, k is greater than or equal to the step size (or amount) m of the state information rollback.

[0076] According to the fourth aspect, the present application provides a decoding device, where the decoding device includes a transceiver unit and a processing unit. The transceiver unit is configured to transmit the first information to the encoding device, where the first information is the historical state information e of the encoding device his ​It is for determining. The transceiver unit is further configured to receive the first feedback information transmitted by the encoding device, where the first feedback information is the first channel information and the historical state information e of the encoding device his is determined based on (for example, the first feedback information is output after the first channel information and the historical state information e his of the encoding device are input to the encoder for processing), where the historical state information e his reflects one or more historical channel information obtained before the first channel information is obtained, and the first feedback information includes the encoded information of the first channel information or the encoded information of the predicted channel information. The first feedback information and the historical state information d of the decoding device his are both input to the decoder for processing, and the third channel information is obtained. In other words, the processing unit is configured to input the first feedback information and the historical state information d of the decoding device his to the decoder for processing to obtain the third channel information. The historical state information d his reflects one or more historical feedback information obtained before the first feedback information is obtained.

[0077] Referring to the fourth aspect, in a possible implementation, the first feedback information and the historical state information d his are input to the decoder for processing, and the third state information is obtained. The third state information may reflect one or more historical feedback information including the first feedback information.

[0078] Referring to the fourth aspect, in a possible implementation, the first channel information may be determined based on the CSI.

[0079] Referring to the fourth aspect, in a possible implementation, the encoder may be the first AI model, and the decoder may be the second AI model.

[0080] Referring to the fourth aspect, in a possible implementation, the transceiver unit is further configured to transmit second information to the encoding device, where the second information indicates whether the encoding device performs periodic storage, the storage period, or one or more start times of the storage period. The processing unit is configured to periodically store state information output by the decoder based on the storage period and / or start times of the storage period.

[0081] Optionally, the processing unit specifically processes the state information d acquired by the decoder during the (n(T / S)-k)th feedback period. n(T / S)-k The transceiver unit is configured to temporarily store state information, where n, k, S, and T are all positive integers, T represents the storage period, S represents the feedback period, one storage period T is an integer multiple of one feedback period S, and one feedback period is used to describe the transmission time interval between two adjacent pieces of feedback information. The transceiver unit is further configured to transmit a third piece of information to the encoding device before the (n(T / S))th feedback period, where the third piece of information instructs the encoding device to store the state information stored during the ((n-1)*(T / S))th feedback period, or the third piece of information is the state information e acquired during the (n(T / S)-k)th feedback period. n(T / S)-k The encoding device is instructed to store the following. The processing unit further stores the state information stored by the decoding device during the ((n-1)*(T / S))th feedback period, or the state information d acquired by the decoding device during the (n(T / S)-k)th feedback period, based on the third information. n(T / S)-k It is configured to store information.

[0082] For example, the processing unit, specifically, when the transceiver unit successfully receives the (n(T / S)-k)th feedback information (or the (n(T / S)-k)th feedback), sets the third piece of information to the second value, transmits the third piece of information using the transceiver unit, and transmits the state information, i.e., the d output by the decoder on the (n(T / S)-k)th time. n(T / S)-k The system is configured to store the following information; and, when the transceiver unit does not receive the (n(T / S)-k)th feedback piece (or the (n(T / S)-k)th feedback), to set the third piece of information to the first value, transmit the third piece of information using the transceiver unit, and store the state information stored during the ((n-1)*(T / S))th feedback period.

[0083] Optionally, the processing unit further processes the history state information d his The decoding device is configured to determine that the first information is state information stored in the previous memory cycle before transmitting it.

[0084] Referring to the fourth aspect, in a possible implementation, the transceiver unit is further configured to transmit a fourth piece of information to the encoding device before the tth feedback period, where the fourth piece of information instructs the encoding device to store the state information acquired in the feedback period before the tth feedback period, where t is a positive integer. The processing unit further stores the state information d acquired by the decoding device in the feedback period before the tth feedback period. t-1 It is configured to store the history state information d. his This is the state information d stored after the decoding device transmits the fourth piece of information. t-1 It is configured to determine that it is so.

[0085] Referring to the fourth aspect, in a possible implementation, the transceiver unit is further configured to transmit a fourth piece of information to the encoding device before the tth feedback period, where the fourth piece of information instructs the encoding device to store the state information acquired in the feedback period before the tth feedback period, where t is a positive integer. The processing unit further stores the state information d acquired by the decoding device in the feedback period before the tth feedback period. t-1 The transceiver unit is configured to temporarily store the state information e that was temporarily stored after the fourth information was received during the tth feedback period. t-1 The encoding device is instructed to store the state information stored when the previous third information was received, where k is a positive integer. The processing unit further instructs the encoding device to store the state information d temporarily stored after the decoding device has transmitted the fourth information, based on the third information. t-1 It is configured to store the previous third piece of information, or to store the state information that was stored when the decoding device transmitted the previous third piece of information.

[0086] Optionally, the processing unit further processes the history state information d his It is configured to determine that the third piece of information is state information stored after it has been transmitted.

[0087] Referring to the fourth aspect, in a possible implementation, the processing unit further includes history state information d his It is configured to update the state information output by the decoder during the feedback period prior to the current time.

[0088] Referring to the fourth aspect, in a possible implementation, the first information includes or indicates the step size m of the state information rollback, where m is a positive integer. The history state information d his This is the state information d that is input by the decoder in the (qm)th step.q-m-1 It is identical to the previous state information, and the state information input by the decoder on the qth time is the historical state information d his Here, q is a positive integer greater than m.

[0089] Referring to the fourth aspect, in a conceivable implementation, the transceiver unit is further configured to transmit a fifth piece of information to an encoding device, which instructs the encoding device to receive the first piece of information after transmitting the feedback information, with a delay of k feedback periods, where k is a positive integer.

[0090] Optionally, k is greater than or equal to the step size (or amount) m of the state information rollback.

[0091] According to a fifth aspect, the present invention provides an encoding device. The encoding device may comprise a processor, a transceiver, and memory. The memory is configured to store a computer program, the transceiver is configured to receive / transmit various information, and the computer program includes program instructions. When the processor executes the program instructions, the encoding device can perform the method according to the first aspect or any one of the possible implementations of the first aspect. The transceiver may be a radio frequency module in a communication device, a combination of a radio frequency module and an antenna, or an input / output interface of a chip or circuit.

[0092] According to a sixth aspect, the present invention provides a decoding device. The decoding device may comprise a processor, a transceiver, and memory. The memory is configured to store a computer program, and the transceiver is configured to receive / transmit various information, the computer program including program instructions. When the processor executes the program instructions, the decoding device can perform the method according to a second aspect or any one of possible implementations of the second aspect. The transceiver may be a radio frequency module in a communication device, a combination of a radio frequency module and an antenna, or an input / output interface of a chip or circuit.

[0093] According to the seventh aspect, the present invention provides a readable storage medium that stores program instructions. When the program instructions are executed on a computer, the computer can perform a method according to the first aspect, the second aspect, or any one of the possible implementations of the first or second aspect.

[0094] According to the eighth aspect, the present application provides a program product including program instructions. When the program product is executed, a method according to the first aspect, the second aspect, or any one of the possible implementations of the first or second aspect is performed.

[0095] According to the ninth aspect, the present invention provides an apparatus, which may be implemented as a chip or as a device. The apparatus includes a processor, which is configured to read a program stored in memory, execute the program, and perform a timeout packet discard method according to one or more of the first, second, or possible implementations of the first or second aspects. Optionally, the apparatus further includes memory, which is connected to the processor by the use of circuitry. Optionally, the apparatus further includes a communication interface, which the processor is connected to. The communication interface is configured to receive information to be processed. The processor obtains information from the communication interface, processes the information, and outputs the processing results through the communication interface. The communication interface may be an input / output interface.

[0096] Optionally, the processor and memory may be physically separate units, or the memory may be integrated into the processor.

[0097] According to a tenth aspect, the present invention provides a wireless communication system. The wireless communication system comprises an encoding device and a decoding device. The encoding device is configured to perform a method according to the first aspect or a possible implementation thereof. The decoding device is configured to perform a method according to the second aspect or a possible implementation thereof.

[0098] The technical effects achieved in the above embodiments are to be discussed by mutual reference, or by reference to the beneficial effects in the embodiments of the following methods. Further details are not described herein. [Brief explanation of the drawing]

[0099] To more clearly explain the technical solution in the embodiments of this application, the accompanying drawings illustrating the embodiments are briefly described below.

[0100] [Figure 1] This is a simplified diagram of a wireless communication system according to an embodiment of the present invention.

[0101] [Figure 2] This is a simplified diagram of the structure of the UE and base station according to the embodiment of the present invention.

[0102] [Figure 3] This is a diagram of a neural network according to an embodiment of the present invention.

[0103] [Figure 4] This is a diagram showing the structure of a neuron according to an embodiment of the present invention.

[0104] [Figure 5] This is a schematic flowchart of the time-domain correlation processing based on the two-sided AI model according to the embodiment of the present invention.

[0105] [Figure 6] This is a schematic flowchart of the processing of the bidirectional AI model after an uplink transmission failure according to the embodiment of the present invention.

[0106] [Figure 7] This is a first schematic flowchart of the information exchange method according to the embodiment of the present invention.

[0107] [Figure 8] This is a second schematic flowchart of the information exchange method according to the embodiment of the present invention.

[0108] [Figure 9] Figure 9a is a first schematic flowchart of the processing of the encoding and decoding devices according to the embodiment of the present invention. Figure 9b is a second schematic flowchart of the processing of the encoding and decoding devices according to the embodiment of the present invention.

[0109]

[0110] [Figure 10] This is a third schematic flowchart of the information exchange method according to the embodiment of the present invention.

[0111] [Figure 11] Figure 11a is a third schematic flowchart of the processing of the encoding and decoding devices according to the embodiment of the present invention. Figure 11b is a fourth schematic flowchart of the processing of the encoding and decoding devices according to the embodiment of the present invention.

[0112]

[0113] [Figure 12] This is a fourth schematic flowchart of the information exchange method according to the embodiment of the present invention.

[0114] [Figure 13] This is a fifth schematic flowchart of the processing of the encoding device and decoding device according to the embodiment of the present invention.

[0115] [Figure 14] This is a fifth schematic flowchart of the information exchange method according to the embodiment of the present invention.

[0116] [Figure 15] This is a sixth schematic flowchart of the processing of the encoding device and decoding device according to the embodiment of the present invention.

[0117] [Figure 16] This is a sixth schematic flowchart of the information exchange method according to the embodiment of the present invention.

[0118] [Figure 17] This is a seventh schematic flowchart of the processing of the encoding device and decoding device according to the embodiment of the present invention.

[0119] [Figure 18] This is a diagram showing the structure of an encoding device or decoding device according to an embodiment of the present invention.

[0120] [Figure 19] This is a diagram showing the structure of a communication device according to an embodiment of the present invention.

[0121] [Figure 20] This is another diagram showing the structure of a communication device according to an embodiment of the present invention. [Modes for carrying out the invention]

[0122] The technical solutions in the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings.

[0123] In the description of this application, the terms “first,” “second,” and similar are merely intended to distinguish between different subjects and do not limit the number or order of execution, nor do they indicate any clear distinction. For example, “first channel information and second channel information,” “first feedback information and second feedback information,” and similar are merely used to distinguish between different information and do not limit the order of the first channel information and second channel information, or the order of the first feedback information and second feedback information. In addition, terms such as “include” and “have,” and all other variations thereof, are intended to include non-exclusive inclusion. For example, a process, method, system, product, or device comprising a set of steps or units is not limited to the listed steps or units, but rather optionally includes further steps or units not listed, or optionally includes other steps or units specific to these processes, methods, products, or devices.

[0124] In the description herein, " / " indicates "or" unless otherwise specified. For example, A / B may indicate A or B. The term "and / or" in this specification describes only the relationship between the related subjects and indicates that three relationships may exist. For example, A and / or B may represent three cases: when only A exists, when both A and B exist, and when only B exists. In addition, "at least one (item)", "one or more of the following items", or similar expressions indicate any combination of these items, including any single item or any combination of multiple items. For example, at least one of a, b, or c may represent a, b, c, a and b, a and c, b and c, or a, b and c. a, b, and c may each be singular or plural.

[0125] In the description of this application, words such as “example” or “for example” are used to provide examples, illustrations, or descriptions. Any embodiment or design scheme described in this application as “example,” “etc.” or “for example” should not be described as being preferable to or having more features than another embodiment or design scheme. Strictly speaking, the use of words such as “example,” “etc.” or “for example” is intended to present relevant concepts in a particular manner.

[0126] In the description of this application, both "when" and "in the case" mean that the device performs the corresponding process in an objective case, and are not intended to limit the time, nor do they require a decision action during the implementation of the device, nor do they imply that there are any other limitations.

[0127] In this application, "simultaneously" can be understood as the same point in time, within a certain period, or within the same period, and more specifically, it can be understood by referring to the context.

[0128] In this application, elements expressed in the singular form are intended to represent "one or more," and unless otherwise specified, do not represent "one and one only."

[0129] In addition, the terms "system" and "network" may be used interchangeably in this specification.

[0130] In the embodiments of this application, determining B based on A does not mean that B is determined solely on A. It can be understood that B may alternatively be determined based on A and / or other information.

[0131] The technical solutions in the embodiments of this application can be applied to a variety of communication systems, including long-term evolution (LTE) systems, worldwide interoperability for microwave access (WiMAX®) communication systems, fifth-generation (5G) systems, new radio access technology (NR) systems, networks integrating multiple systems, Internet of Things systems, Internet of Vehicles systems, and future communication systems such as 6G systems.

[0132] It should be understood that the network architecture described in the embodiments of this application is intended to more clearly illustrate the technical solutions in the embodiments of this application and does not constitute a limitation on the technical solutions provided in the embodiments of this application. Those skilled in the art will know that as network architectures evolve, the technical solutions provided in the embodiments of this application may also be applicable to similar technical problems.

[0133] Please refer to Figure 1. Figure 1 is a simplified diagram of a wireless communication system according to an embodiment of the present invention. As shown in Figure 1, the wireless communication system includes a wireless access network 100. The wireless access network 100 may be a next-generation (e.g., 6G, or higher version) wireless access network or a conventional (e.g., 5G, 4G, 3G, or 2G) wireless access network. One or more terminal devices (120a to 120j, collectively referred to as 120) may be interconnected or connected to one or more network devices (110a and 110b, collectively referred to as 110) in the wireless access network 100. Optionally, Figure 1 is merely a diagram. The wireless communication system may further include other devices, for example, core network devices, wireless relay devices, and / or wireless backhaul devices, which are not shown in Figure 1.

[0134] Optionally, in actual application, a wireless communication system may include multiple network devices (also referred to as access network devices) or multiple terminal devices. One network device may provide services to one or more terminal devices. One terminal device may also access one or more network devices. The number of terminal devices and network devices included in a wireless communication system is not limited to the embodiments of this application.

[0135] A network device may be an entity configured to transmit or receive signals on the network side, such as a base station (BS). A network device is also a device deployed in a radio access network that can perform wireless communication with terminals. Base stations can take various forms, such as macro base stations, micro base stations, relay stations, and access points. For example, a base station in the embodiments of this application may be a base station in 5G or an evolved node B (eNB) in LTE. A base station in 5G may also be referred to as a transmission reception point (TRP) or a 5G base station (next-generation node B, gNB). Base stations may also be replaced by the following names: radio access point, node B, transmitting point (TP), master station (MeNB), secondary station (SeNB), multi-standard radio (MSR) node, home base station, network controller, access node, radio node, access point (AP), transmission node, transceiver node, baseband unit (BBU), remote radio unit (RRU), active antenna unit (AAU), remote radio head (RRH), central unit (CU), distributed unit (DU), positioning node, IAB donor, and similar.

[0136] Base stations (BS) can be stationary or mobile. For example, base stations 110a and 110b are stationary and are responsible for radio transmission and reception in one or more cells from terminal devices 120. The helicopter or unmanned aerial vehicle 120i shown in Figure 1 may be configured to function as a mobile base station, and one or more cells may move based on the location of the mobile base station 120i. In another example, the helicopter or unmanned aerial vehicle (120i) may be configured to function as a terminal device communicating with base station 110a.

[0137] The network device in the embodiments of this application may be an integrated base station, or a base station comprising a central unit (CU) and a distributed unit (DU). A base station comprising a CU and a DU may also be referred to as a base station in which the CU and DU are separated. For example, the base station comprises a gNB-CU and a gNB-DU. The CU may further be separated into a CU control plane (CU-CP) and a CU user plane (CU-CP). For example, the base station comprises a gNB-CU-CP, a gNB-CU-UP, and a gNB-DU. Alternatively, the network device in the embodiments of this application may be a radio unit (RU). Alternatively, the network device in the embodiments of this application may be an open radio access network (ORAN) architecture or similar. The specific deployment method of the network device is not limited to the embodiments of this application. For example, when the network device is an ORAN architecture, the network device in the embodiments of this application may be an access network device in ORAN, a module in an access network device, or similar. In the ORAN system, CU may also be called open (O)CU, CU-CP may also be called O-CU-CP, CU-UP may also be called O-CU-UP, and RU may also be called O-RU.

[0138] In embodiments of the present application, a device configured to implement network device functionality may be a network device, or a device capable of supporting a network device in implementing functionality, such as a chip system, communication module, or modem. The device may be installed on the network device. In the technical solutions provided in embodiments of the present application, the solutions are illustrated by using the example that the device configured to implement network device functionality is a network device and the network device is a base station. The base station may support the network using the same or different access technologies. Specific technologies and device configurations used for the network device are not limited to embodiments of the present application.

[0139] A terminal device may be referred to as a terminal, user equipment (UE), mobile station (MS), mobile terminal (MT), or similar, and may be an entity configured to receive or transmit signals on the user side, such as a mobile phone. Terminal devices may be deployed indoors, outdoors, handheld, or on land, including in-vehicle devices; on water (e.g., on a ship); or in the air (e.g., on an airplane, balloon, or satellite). Terminal devices may be configured to connect to people, objects, and machines. The terminal device 120 can be widely used in various scenarios, such as cellular communication, device-to-device (D2D), vehicle-to-everything (V2X), peer-to-peer (P2P), machine-to-machine (M2M), machine-type communication (MTC), Internet of Things (IoT), virtual reality (VR), augmented reality (AR), industrial control, autonomous driving, telemedicine, smart grids, smart furniture, smart offices, smart wearables, smart transportation, smart cities, smart homes, unmanned aerial vehicles, robots, remote detection, passive detection, positioning, navigation and tracking, and self-delivery and mobility.The terminal device 120 may be a user equipment (UE) under the 3rd generation partnership project (3GPP®) standards, a fixed device, a mobile device, a handheld device, a wearable device, a cellular phone, a smartphone, a session initiation protocol (SIP) phone, a notebook computer, a personal computer, a smartbook, a vehicle, a satellite, a global positioning system (GPS) device, a target tracking device, an unmanned aerial vehicle, a helicopter, an aircraft, a ship, a remote control device, a smart home device, or an industrial device. Alternatively, the terminal device may be a communication device in a future wireless communication system.

[0140] In embodiments of the present application, a device configured to implement terminal functions may be a terminal, or a device capable of supporting a terminal in the implementation of functions, such as a chip system, a communication module, or a modem. The device may be installed within the terminal. In embodiments of the present application, a chip system may include a chip, or a chip and another discrete component. In the technical solutions provided in embodiments of the present application, the technical solutions provided in embodiments of the present application are illustrated by using the example that a device configured to implement terminal functions is a terminal and the terminal is a UE. Specific technologies used by terminal devices and specific device forms are not limited to embodiments of the present application.

[0141] Optionally, the UE can be configured to function as a base station. For example, the UE can function as a scheduling entity providing sidelink signals between UEs in V2X, D2D, or P2P. As shown in Figure 1, the cellular phone 120a and the car 120b communicate with each other using sidelink signals. The cellular phone 120a communicates with the smart home device 120d without relaying communication signals by using the base station 110a.

[0142] Optionally, the UE may also be configured to function as a relay node. For example, the UE may function as a relay device or an integrated access and backhaul (IAB) node, configured to provide wireless backhaul services for terminal devices.

[0143] Optionally, AI network elements or modules may be further introduced into the network to support machine learning capabilities in the wireless network. When AI network elements are introduced, they correspond to independent network elements. When AI modules are introduced, they may be located within network elements, for example, within terminal devices and / or network devices.

[0144] In the embodiments of this application, the term "wireless communication" may be abbreviated to "communication," and the term "communication" may also be described as "data transmission," "information transmission," or "transmission."

[0145] Please refer to Figure 2. Figure 2 is a simplified diagram of the structure of the UE and base station according to an embodiment of the present invention. For simplicity, Figure 2 shows only the main components of the base station 110 and UE 120. In actual applications, the structure of the base station and UE may include more or fewer components than those shown in Figure 2, or may include only the components shown in Figure 2. It should be understood that the base station shown in Figure 2 may use a CU-DU partitioned architecture, a non-CU-DU partitioned architecture, or an ORAN architecture. The components in Figure 2 are briefly described below.

[0146] Base station 110 includes interface 111 and processor 112. Processor 112 may optionally store program 114. Base station 110 also includes memory 113. Memory 113 may optionally store program 115. UE 120 includes interface 121 and processor 122. Processor 122 may optionally store program 124. UE 120 also includes memory 123. Memory 123 may optionally store program 125. These components work together to provide various functions described herein. For example, processor 112 and interface 111 work together to provide a wireless connection between base station 110 and UE 120. Processor 122 and interface 121 work together to implement downlink and / or uplink transmission of UE 120.

[0147] A processor (e.g., processor 112 and / or processor 122) may comprise one or more processors and be implemented as a combination of computing devices. A processor (e.g., processor 112 and / or processor 122) may individually comprise one or more of the following: microprocessors, microcontrollers, digital signal processors (DSPs), digital signal processing devices (DSP devices, DSPDs), application-specific integrated circuits (ASICs), field programmable gate arrays (FPGAs), programmable logic devices (PLDs), gating logic, transistor logic, discrete hardware circuits, processing circuits, or appropriate combinations of hardware and firmware and / or hardware and software, and may be configured to perform various functions described herein. A processor (e.g., processor 112 and / or processor 122) may be a general-purpose processor or a dedicated processor. For example, processor 112 and / or processor 122 may be a baseband processor or a central processing unit. A baseband processor may be configured to process communication protocols and communication data. The central processing unit may be configured to enable the base station 110 and / or UE 120 to execute a software program and process data within that software program.

[0148] The interface (e.g., interface 111 and / or 121) may include an interface for implementing communication with one or more computer devices (e.g., UE, BS, and / or network nodes). In some embodiments, the interface may include wires for connecting wired connections, or pins for connecting wireless transceivers, or chips and / or pins for wireless connections. In some embodiments, the interface may include transmitters, receivers, transceivers, and / or antennas. The interface may be configured to use any available protocol (e.g., 3rd Generation Partnership Project (3GPP®) standards).

[0149] The term "program" in this application refers to software in a broad sense. Non-limiting examples of software include program code, programs, subprograms, instructions, instruction sets, code, code segments, software modules, application programs, or software application programs. The program may be executed in a processor and / or computer, and as a result, the base station 110 and / or UE120 perform various functions and / or processes described herein.

[0150] Memory (e.g., memory 113 and / or memory 123) may store data that is manipulated by processors 112 and 122 when the software is executed. Memory 113 and 123 may be implemented using any storage technology. For example, memory may be any available storage medium accessible by the processor and / or computer. Non-limiting examples of storage mediums include RAM, ROM, EEPROM, CD-ROM, removable media, optical disk memory, magnetic disk storage medium, magnetic storage device, flash memory, registers, state memory, remote-mount memory, local or remote storage components, or any other medium that can hold or store software, data, or information and is accessible by the processor / computer.

[0151] Memory (e.g., memory 113 and / or memory 123) and processor (e.g., processor 112 and / or processor 122) may be located separately or integrated. Memory may be configured to be connected to a processor, so that the processor can read information from memory, store information in memory, and / or write information to memory. Memory 113 may be integrated with processor 112. Memory 123 may be integrated with processor 122. Processors (e.g., processor 112 and / or processor 122) and memory (e.g., memory 113 and / or memory 123) may be located in an integrated circuit (e.g., the integrated circuit may be located in a UE, base station, or another network node).

[0152] The above describes the system architecture in the embodiments of the present invention. To better understand the technical solutions in the embodiments of the present invention, several terms or nouns related to the present invention are briefly explained below.

[0153] 1. Artificial intelligence (AI), machine learning, and neural networks

[0154] Artificial intelligence (AI) enables machines to learn, accumulate experience, and solve problems such as natural language comprehension, image recognition, and chess games that humans can solve through experience. Typically, AI is a technology that demonstrates human intelligence through the use of standard computer programs. AI can be defined as a machine or computer that mimics humans and possesses cognitive functions related to human thought, such as learning and problem-solving. AI can learn from past experiences to make rational decisions and respond quickly. The goal of AI is to understand intelligence by constructing symbolic reasoning or computer programs for reasoning.

[0155] Machine learning is an implementation of artificial intelligence. Specifically, machine learning is used as a means to solve problems in artificial intelligence. Machine learning is a way to give machines the ability to "learn," enabling them to perform functions that cannot be implemented by direct programming. In practice, machine learning is a method for training a model by using data, and then using that model for prediction.

[0156] An AI model is an algorithm or computer program capable of implementing AI functionality. An AI model represents a mapping relationship between the model's inputs and outputs. An AI model can be a neural network or another machine learning model.

[0157] A neural network (NN) is a specific implementation of machine learning, simulating the human brain and implementing machine learning techniques similar to those used in artificial intelligence. According to general approximation theorems, a neural network can theoretically approximate any continuous function, and as a result, it has the ability to learn any mapping. Therefore, neural networks can accurately execute abstract models for complex, high-dimensional problems.

[0158] A neural network typically includes an input layer, a hidden layer, and an output layer. Each layer has one or more logical decision units, which are called neurons. Common neural network structures include feedforward neural networks (FNNs), convolutional neural networks (CNNs), recurrent neural networks (RNNs), and similar structures. These network structures are based on neurons. The input layer of a neural network performs neuronal processing on the received input and then forwards the result to an intermediate hidden layer. The hidden layer forwards the computation result to an output layer or an adjacent hidden layer. Finally, the output layer obtains the output result of the neural network. A single neural network may include one or more sequentially connected hidden layers. The number of hidden layers in a neural network is not limited in this application. See Figure 3. Figure 3 is a diagram of a neural network according to an embodiment of this application. As shown in Figure 3, the neural network includes one input layer, one hidden layer, and one output layer. The input layer has 3 neurons, the hidden layer has 4 neurons, and the output layer has 2 neurons. It should be understood that the number of layers in the neural network shown in Figure 3, and the number of neural network elements in each layer, are merely examples.

[0159] Each connection line between neurons corresponds to a weight (the value is called the weight value), and the weight values ​​can be updated through training. Each neuron may also correspond to an offset, and the offset can also be updated through training. Updating a neural network refers to updating these weight values ​​and offsets. Once the structure of the neural network is known, i.e., how the output of the previous neuron is input to the subsequent neuron, and the weight values ​​and offsets are known, all the information about the neural network becomes known.

[0160] Figure 3 shows that each neuron may have multiple input connections, and each neuron calculates an output based on its input. For example, each neuron performs an additive summation operation on the neuron's input values ​​and generates an output using an activation function (e.g., a nonlinear activation function) based on the result of the weighted sum. Each neuron may have multiple output connections, and the output of one neuron is used as the input to the next neuron. The input layer has only output connections, and each neuron in the input layer is a value input to the neural network, and it should be understood that the value of each neuron is used as the input to all output connections. The output layer has only input connections.

[0161] Please refer to Figure 4. Figure 4 is a diagram of the structure of a neuron according to an embodiment of the present invention. As shown in Figure 4, the input to the neuron is x=[x0,x1,...,x n ] and the weights corresponding to the input are w=[w0,w1,...,w n Assuming that the offset corresponding to the neuron is b, and assuming that the activation function is represented by f(z), the output y of the neuron shown in Figure 4 is as follows.

number

[0162] The offset b can be any value, such as a decimal, an integer (0, a positive integer, or a negative integer), or a complex number. The activation functions of different neurons in a neural network may be the same or different.

[0163] The form of the activation function f(z) can be diverse. Assuming that the activation function f(z) of a neuron is max(0,z), the output of the neuron is

number

number

[0164] A loss function can be defined during the training process of a neural network. The loss function explains the difference between the neural network's output and the target data. A smaller loss function indicates that the neural network's output better fits the target data. An example where the mean squared error is used as the loss function is as follows: Loss=(y out -y target ) 2 (1-2)

[0165] y out represents the output of the neural network, and y target represents the target data, and the minimization loss function (i.e., the loss in equation (1-2)) is given by two values ​​(i.e., y out and y target The purpose is to minimize the difference between ). It should be understood that, in addition to the mean squared error loss function, the loss function may alternatively be a cross-entropy loss function or an absolute value loss function. The type of loss function is not limited in this application. The neural network training process is the process of adjusting neural network parameters such as the number and width of layers in the neural network, the weights of neurons, or the parameters in the activation function of neurons, so that the value of the loss function is less than a threshold or satisfies the target requirements.

[0166] A deep neural network is a neural network that has multiple hidden layers.

[0167] Deep learning is a form of machine learning that is based on deep neural networks.

[0168] 2. Two-sided (transmitter and receiver) AI model based on time-domain correlation

[0169] In wireless communication links, the channels for medium and low-speed users change continuously over time. Therefore, communication performance can be improved by mining channel time-domain correlation. When both the base station and the UE perform data processing based on channel time-domain correlation, the processing procedure is shown in Figure 5. Figure 5 is a schematic flowchart of the processing of a two-sided AI model based on time-domain correlation according to an embodiment of the present invention. As shown in Figure 5, the UE processes the current channel information H t (For example, CSI), and state information e previously obtained by UE t-1 The data is input to an encoder for processing, and the corresponding feedback information c t It may output new state information e. Optionally, the UE may further output new state information e. t It outputs the following, and then the feedback information c t This information can be fed back to the base station. For example, channel information H t When is CSI, feedback information c t This could be CSI compression information. For example, each time the encoder runs, there can be two outputs: one is feedback information and the other is state information obtained during this run. For example, channel information H t and status information e t-1 This is input to an encoder for processing, and two outputs may be obtained: one is feedback information c t The other is state information e t Therefore, the state information e obtained last time by the UE t-1 This is the feedback information c output by the encoder during the previous execution. t-1 It could refer to a real matrix other than (i.e., the first output) (i.e., the second output). Alternatively, it could refer to the state information e previously obtained by the UE. t-1This can be obtained by inputting multiple historical channel information into the computation module and is not used as the second output of the encoder during the previous run. The state information e input to the encoder this time t-1 (i.e., state information previously obtained by the UE) is channel information at a past point in time (i.e., H1, H2, H3, ..., and H t-1 ) can be determined by. Therefore, the time-domain correlation of channel information is determined by state information e t-1 , and the current channel information H t It can be mined based on this. The encoder can be implemented by using an AI model.

[0170] The base station has received feedback information c t , and the status information d previously acquired by the base station t-1 The data is input to the decoder for processing, and the channel information H t Outputs ', and optionally, new state information d t It may further output the channel information H output by the decoder. Optionally, channel information H output by the decoder may be output. t 'and channel information H input to the encoder t These are identical, or have specific (or slight) differences (these differences may be negligible in some scenarios). For example, feedback information c t When this is CSI compressed information, the channel information H output by the decoder t ' is feedback information c t Or it is the CSI restored based on the predicted CSI. For example, each time the decoder runs, there may be two outputs: one is channel information and the other is state information obtained during this run. For example, feedback information c t and status information d t-1 The signal is fed into a decoder for processing, and two outputs may be obtained: one is channel information H t ' and the other is state information d t Therefore, the status information d that was previously acquired by the base station t-1This is the channel information H output by the decoder during the previous execution. t-1 This could refer to a real matrix other than '(i.e., the first output) (i.e., the second output). Alternatively, it could refer to the state information d previously acquired by the base station. t-1 This can be obtained by inputting multiple historical channel information acquired by the base station through decoding into the computing module, or by inputting multiple historical feedback information into the computing module. The state information d input by the decoder this time t-1 (i.e., the state information previously acquired by the base station) is the feedback information received at a past point in time (i.e., c1, c2, c3, ..., and c t-1 ) can be determined based on. Therefore, the time-domain correlation of feedback information is determined by the state information d t-1 , and feedback information received at this time c t It can be mined based on this. Decrypters can also be implemented by using AI models.

[0171] Optionally, t may represent the number of feedbacks or the feedback period. The “feedback period” as referred to herein may be a short period, and it may be understood that the feedback information needs to be fed back once during the feedback period. t is a positive integer. When t is equal to 1, e t-1 =e0 and d t-1 = d0, where e0 may represent the initial state information of the UE-side encoder, and d0 may represent the initial state information of the base station-side decoder. For example, e0 and d0 can be predefined.

[0172] From Figure 5, feedback information c t When generating, the UE-side encoder also updates the UE-side state information, for example, e t-1 from e t It can be seen that it will be changed to . Similarly, when processing the received information, the base station decoder also synchronously updates the base station state information, for example, the state information d t-1 from dt Change it.

[0173] In the two-sided AI model shown in Figure 5, the channel time-domain correlation is the state information e on the UE side. t-1 and base station status information d t-1 Mining is performed by synchronously updating the data. However, due to reasons such as low instantaneous channel quality, feedback information c t When transmission fails, the base station cannot synchronously update its state information, which can lead to mismatches in subsequent processing processes on both sides (i.e., the transmission end and the reception end), and degradation of the base station's decoding performance, resulting in a loss of communication performance. For example, channel information compression is implemented by using channel time-domain correlation. Feedback information c t Channel information H t and status information e t-1 Based on, feedback information c t is the status information e t-1 Channel information H for t This can be understood as increment information. Correspondingly, the base station provides feedback information c t and status information d t-1 Based on channel information H t Restore the feedback information c. t If transmission fails, the base station will send status information d t-1 d t Unable to update, as a result the state information includes the channel information from the tth time, and therefore the received feedback information c t+1 Based on channel information H t+1 It cannot be restored. In this case, the base station cannot obtain the slowest channel information and cannot allocate resources to the UE based on the slowest channel information, which can affect subsequent data transmission and cause a degradation in communication performance.

[0174] In a possible implementation, if the transmission of one piece of feedback information from the UE fails due to a momentary degradation of channel quality, the base station may input the unupdated state information to the decoder for processing. See, for example, Figure 6. Figure 6 is a schematic flowchart of the processing of a bidirectional AI model after an uplink transmission failure according to an embodiment of the present invention. As shown in Figure 6, assuming that the transmission of the feedback information c3 (or third feedback period) of the third feedback to the base station is unsuccessful, the base station cannot update the state information based on the third feedback. Therefore, in the fourth feedback (or fourth feedback period), the encoder on the UE side uses the state information e3 output third time as input, and the decoder on the base station side uses the state information d2 output second time as input. Since the channels of medium and low speed users change slightly within a short period of time, and the state information also changes slightly within a short period of time, the unupdated state information (e.g., state information d2) can be used as input to the decoder.

[0175] A mismatch between the transmission and reception ends (for example, the UE using state information e3 output third time by the encoder as the encoder input, and the base station using state information d2 output second time by the decoder as the decoder input) may have a small effect in the short term, but the errors caused by the mismatch between the transmission and reception ends accumulate over time. This can lead to a significant deterioration in the decoding and communication performance on the base station side. For example, channel information compression is implemented by using channel time-domain correlation. If the feedback information c3 fed back third time by the UE fails to be successfully transmitted to the base station, the feedback information c4 fed back fourth time by the UE is obtained based on channel information H4 and state information e3 output third time by the encoder. Therefore, c4 can be understood as increment information of channel information H4 with respect to state information e3, that is, c4 is increment information of channel information H4 with respect to historical channel information H3 and earlier historical channel information. In addition, the base station decoder uses feedback information c4 and state information d2 output a second time by the decoder as input, and since information related to the historical channel information H3 is missing, the channel information H4' reconstructed by the base station is not as accurate as the channel information H4 measured by the UE. Therefore, the resources allocated to the UE by the base station (e.g., modulation and coding scheme, MCS) may not match the actual channel conditions. As a result, performance deteriorates, and communication performance deteriorates significantly over time. Therefore, effective solutions for matching the receiving and transmitting ends are needed to address problems such as mismatch between the receiving and transmitting ends, deterioration of the base station's decoding performance, and significant deterioration of communication performance caused by feedback information transmission failure.

[0176] In view of this, embodiments of the present invention provide an information exchange method, apparatus, and readable storage medium, which enable the state information on the UE side (or input by the encoder) to maintain consistency with the state information on the base station side (or input by the decoder), thereby improving the decoding performance of the base station side (or decoder), reducing communication performance loss, and improving communication quality.

[0177] The technical solutions provided in this application will be described in detail below with reference to more attached drawings.

[0178] The technical solutions provided in this application will be described in detail using several embodiments. For details, please refer to the descriptions of the embodiments below. It should be understood that the technical solutions described in the following embodiments of this application may be randomly combined to form new embodiments, and parts relating to the same or similar concepts or solutions may be referenced or combined with each other. Each embodiment will be described in detail below.

[0179] In this Application, unless otherwise specified, identical or similar parts of an embodiment or implementation are to be referenced to one another. In the embodiments and implementation examples / methods of implementation in these embodiments, unless otherwise specified or unless there is a logical contradiction, terminology and / or descriptions are consistent, and mutual references are permitted between different embodiments and between implementation examples / methods of implementation in these embodiments. Technical features and implementation examples / methods of implementation in different embodiments may be combined based on their internal logical relationships to form new embodiments, implementations, or methods of implementation. The following implementations of this Application are not intended to limit the scope of protection of this Application.

[0180] In this application, the encoding device may be a terminal device (e.g., a UE) or a network device (e.g., a base station). Correspondingly, the decoding device may be a network device (e.g., a base station) or a terminal device (e.g., a UE). It can be understood that the encoding device and decoding device are for both communication partners. In a communication process, one communication partner is the encoding device and the other communication partner is the decoding device. For example, in one data transmission process, the encoding device is a UE and the decoding device is a base station; in another data transmission process, the encoding device is a base station and the decoding device is a UE.

[0181] For example, to simplify the description, the following example uses a case where the encoding device is the UE and the decoding device is the base station.

[0182] Optionally, the encoder in this application may be a module or chip in an encoding device, e.g., an AI module or AI chip; the decoder in this application may be a module or chip in a decoding device, e.g., an AI module or AI chip. When both the encoder and decoder are implemented using an AI model, the encoder and decoder are typically trained together and can be used in a matching scheme. Embodiment 1

[0183] Please refer to Figure 7. Figure 7 is a first schematic flowchart of an information exchange method according to an embodiment of the present invention. As shown in Figure 7, the information exchange method includes, but is not limited to, the following steps.

[0184] S101: The decoding device (e.g., base station) transmits first information to the encoding device (e.g., UE), where the first information is the encoding device's historical state information e his This is for the purpose of making a decision.

[0185] In response, the encoding device (e.g., UE) receives the first piece of information.

[0186] It can be understood that a base station may configure a reference signal resource for the UE, and that the reference signal resource may be periodic. For example, the reference signal resource may include a time-frequency resource for the reference signal and a time-frequency resource for feedback information. The base station may transmit a reference signal (e.g., a CSI reference signal) over the time-frequency resource for the reference signal. The UE may perform channel measurements based on the received reference signal to obtain channel information (e.g., downlink channel information), and then feed back the obtained channel information to the base station by using the time-frequency resource for feedback information configured by the base station.

[0187] Therefore, the encoding device (UE) may periodically transmit feedback information to the decoding device (base station). If the decoding device (base station) does not receive (or demodulate) specific feedback information on the time-frequency resource of the feedback information, it indicates that the transmission of the feedback information has failed. In this case, the decoding device (base station) may transmit first information to the encoding device (UE). First information is the encoding device's (UE) historical state information e his The first information may be for determining, or the first information may be for determining state information to be input to the encoder after the first information has been received. The first information may further be for notifying that the feedback information has failed to transmit, and the first information may further indicate a mismatch between the transmitting and receiving ends, or similar.

[0188] S102: The encoding device (e.g., UE) receives the historical status information of the encoding device e based on the first information. his The first channel information is input to the encoder for processing, and the first feedback information is obtained, where the historical state information e his This reflects one or more historical channel information obtained before the first channel information is obtained.

[0189] S103: The encoding device (e.g., UE) transmits first feedback information to the decoding device (e.g., base station), where the first feedback information includes encoded information of first channel information or encoded information of predicted channel information.

[0190] In response, the decoding device (e.g., a base station) receives the first feedback information.

[0191] Optionally, after receiving the first information, the encoding device (UE) uses the first information to generate the encoding device's historical state information e his The encoding device (UE) can determine the channel information by performing a channel measurement based on the received reference signal. The encoding device (UE) then obtains the historical state information e his The first channel information can be input to the encoder of the encoding device for processing to obtain the first feedback information. History state information e his This may reflect one or more historical channel information acquired before the first channel information is acquired. Optionally, historical state information e his After the first channel information is input to the encoder for processing, new state information (referred to as the first state information for ease of description) is further output. The new state information (i.e., the first state information) may reflect one or more historical channel information, including the first channel information. The encoding device (UE) may further transmit the first feedback information to the decoding device (base station). For example, the encoding device (UE) may perform operations such as quantization and modulation on the first feedback information output by the encoder, and then transmit the first feedback information.

[0192] It can be understood that the encoding device (UE) may transmit first feedback information when the feedback period arrives, or that the encoding device (UE) may generate and transmit first feedback information during the feedback period. In other words, step S102 may be completed before the feedback period arrives, step S103 may be performed when the feedback period arrives, or steps S102 and S103 may be completed during the feedback period.

[0193] The “feedback period” as referred to in this application may be a short period, and feedback information must be fed back once during the feedback period. Further details will not be provided below. The “feedback period” as referred to in this application may be understood as periodic, and the time interval between two adjacent feedback periods may be understood as one feedback period. Further details will again not be provided below. For example, the interval between the end of the first feedback period and the start of the second feedback period in two adjacent feedback periods may be understood as one feedback period. Alternatively, the interval between the transmission or reception of two adjacent feedback pieces of information may be understood as one feedback period. The feedback period in this application can be set flexibly and is not limited to the above description.

[0194] In a possible implementation, the first piece of information includes or indicates the step size (or number) m (where m is a positive integer) of the state information rollback. The encoding device (UE) receives the first piece of information during the qth feedback period, and the encoding device's historical state information e his This is the state information e input to the encoder at the (qm)th time. q-m-1 This indicates that q is a positive integer greater than m, and it is assumed that q is a positive integer greater than m. Specifically, the first piece of information and the history state information of the encoding device e based on the first piece of information. his For the implementation of determining this, please refer to the following description in Embodiment 2. Further details are not provided here.

[0195] In another possible implementation, the encoding device (UE) periodically stores state information output by the encoder, and the decoding device (base station) also periodically stores state information d output by the decoder. The encoding device's historical state information e his This may be the state information previously stored by the encoding device (UE). Specifically, the first information and the history state information of the encoding device based on the first information e his For the implementation of determining this, please refer to the following description in Embodiment 3. Further details are not provided here.

[0196] In yet another possible implementation, the encoder of the encoding device (UE) and the decoder of the decoding device (base station) always use historical state information output in a particular execution process as input, and the encoding device (UE) updates the historical state information input to the encoder based on instructions from the decoder (base station) (i.e., the first information). In other words, the historical state information of the encoding device e his This may be the state information last updated by the encoding device. Specifically, the first information and the history state information of the encoding device based on the first information e his For the implementation of determining this, please refer to the following description in Embodiment 4. Further details are not provided here.

[0197] In yet another possible implementation, the encoding device (UE) stores state information output by the encoder at a specific point in time, based on instructions from the decoding device (base station). This is the historical state information of the encoding device. his This may be state information stored by the encoding device (UE) before the first information is received. Specifically, this may include signaling exchange between the encoding device (UE) and the decoding device (base station), the first information, and the historical state information of the encoding device based on the first information. his For the implementation of determining this, please refer to the following description in Embodiment 5 or Embodiment 6. Further details are not described here.

[0198] In this application, channel information may represent a channel and may be understood as a representation of the channel status. Further details are not provided below. For example, channel information in this application may be a CSI. A CSI may be a channel response matrix, eigenvectors obtained by performing singular value decomposition on the channel response matrix, a matrix containing multiple eigenvectors, or projection coefficients obtained by projecting eigenvectors into the spatial frequency domain. This is not limited to this application.

[0199] In some scenarios, the first channel information may be channel information obtained through measurement, for example, channel information obtained by an encoding device (UE) by measuring a currently received reference signal. In this case, the first feedback information may be encoded information (e.g., compressed information) of the first channel information, or encoded information (e.g., compressed information) of channel information predicted based on the first channel information. In other words, when the first channel information is channel information obtained through actual measurement, the encoder may be configured to perform prediction and compression, or to perform compression. In some other scenarios, the first channel information may be predicted channel information. In this case, the first feedback information may be encoded information (e.g., compressed information) of the first channel information. In other words, when the first channel information itself is predicted channel information, the encoder may be configured to compress the first channel information.

[0200] Optionally, after step S103, the information exchange method may further include the following steps.

[0201] S104: The decoding device (e.g., base station) receives the first feedback information and the decoding device's historical state information d his The data is input to the decoder for processing to obtain the third channel information, where the historical state information d his This reflects one or more historical feedback pieces of information obtained before the first feedback piece was acquired.

[0202] Optionally, the decoding device (base station) receives historical status information d his After determining and receiving the first feedback information, the first feedback information and history status information d his The data is input to the decoder for processing (e.g., restoration) and the third channel information is obtained. Historical state information d his This may reflect one or more historical feedback pieces acquired before the first feedback piece was acquired. Optionally, the first feedback piece and historical status information d his After the data is input to the decoder for processing, new state information (referred to as third state information for ease of description) is further output. The new state information (i.e., third state information) may reflect one or more historical feedback pieces, including the first feedback information.

[0203] History status information d his This may be determined based on the first information, and the history status information of the decoding device d his This is the history status information of the encoding device e his This is consistent with the encoding device's historical state information e his However, the state information e input to the (qm)th time by the encoder q-m-1 If so, the history status information of the decryption device d his This is the state information d input by the decoder at the (qm)th time. q-m-1 In another example, the history status information of the encoding device e his However, if it is the state information previously stored by the encoding device, then the history state information d of the decoding device his It is also the state information previously stored by the decoding device; or the historical state information of the encoding device e his However, if it is the state information that was last updated by the encoding device, then the history state information d of the decoding device his This is also the state information last updated by the decoding device. In another example, the historical state information of the encoding device e his However, if the first information is state information stored by the encoding device before it is received, then the decoding device's history state information d hisThis is state information stored by the decryption device before the first information is transmitted. Examples are not listed one by one here. For specific implementations, please refer to the relevant descriptions in Embodiments 2 to 6 below.

[0204] The decoding device in this embodiment of the present invention controls the input to the encoder in the encoding device by distributing information (the first information described above), and as a result, the state information on the UE side (or input by the encoder) can maintain consistency with the state information on the base station side (or input by the decoder), thereby improving the decoding performance of the base station side (or decoder), reducing communication performance loss, and improving communication quality.

[0205] In an optional embodiment, a decoding device (e.g., a base station) may transmit first information to an encoding device (e.g., a UE), where the first information is the encoding device's historical state information e his This is for determining the encoding device (e.g., UE) after receiving the first information, based on the first information, the encoding device's historical state information e his The encoding device (e.g., UE) can determine the historical state information e his Based on this, the first feedback information is determined. The first feedback information may be used to determine the third channel information. History status information e his This may reflect one or more historical channel information. For example, the encoding device may reflect historical state information e his The first feedback information is obtained by inputting it into the encoder of the encoding device for processing. The encoder may be an AI model. For example, the first feedback information is historical state information e his Alternatively, it may be channel information predicted based on the encoded information (e.g., compressed information) of the predicted channel information. The encoding device (e.g., UE) transmits the first feedback information to the decoding device (e.g., base station). The decoding device (e.g., base station) receives the historical state information d his After determining and receiving the first feedback information, the first feedback information and history status information d hisBased on this, the third channel information is determined. For example, a decoding device (e.g., a base station) determines the first feedback information and the historical state information d his The data can be input to a decoder for processing (e.g., restoration) to obtain third channel information. Historical state information d his This may reflect one or more historical feedback pieces of information. The third channel information may be used by a decoding device (e.g., a base station) to allocate resources to an encoding device (e.g., a UE).

[0206] The decoding device in this embodiment of the present invention controls the input to the encoder in the encoding device by distributing information (the first information described above), and as a result, the state information on the UE side (or input by the encoder) can maintain consistency with the state information on the base station side (or input by the decoder), thereby improving the decoding performance of the base station side (or decoder), reducing communication performance loss, and improving communication quality.

[0207] The information exchange method provided in this application is briefly described in Embodiment 1 above. Embodiments 2 to 6 below describe in detail the information exchange method provided in this application in different cases (for example, when a base station transmits different instructions). Embodiment 2

[0208] Embodiment 2 of the present invention primarily describes a case in which a decoding device (e.g., a base station) instructs an encoding device (e.g., a UE) to use state information prior to the feedback information transmission failure as input to an encoding device (i.e., a first AI model). Correspondingly, the decoding device (e.g., a base station) also uses state information prior to the feedback information transmission failure as input to an encoding device (i.e., a second AI model). Thus, time-domain correlation mining can be implemented by using historical channel information contained in the historical state information, thereby reducing the impact of mismatches between the receiving and transmitting ends on communication performance.

[0209] Please refer to Figure 8. Figure 8 is a second schematic flowchart of an information exchange method according to an embodiment of the present invention. As shown in Figure 8, the information exchange method includes, but is not limited to, the following steps.

[0210] S201: The decoding device (e.g., base station) transmits a fifth piece of information to the encoding device (e.g., UE), which instructs the encoding device to receive the first piece of information after transmitting the feedback information, with a delay of k feedback period.

[0211] In response, the encoding device (e.g., UE) receives the fifth piece of information.

[0212] Optionally, the fifth piece of information includes the number of delayed feedback periods k, where k is a positive integer. Alternatively, the fifth piece of information includes the delay, where the unit of delay is a time unit such as seconds, microseconds, milliseconds, or nanoseconds, and k =

number

number

number

number

number

[0213] Optionally, the encoding device may expand a memory space for storing one or more historical state information, and as a result, after a failure in transmitting feedback information, the state information input to the encoder may be rolled back to the historical state information output by the encoder at a specific time. For example, the encoding device may store the state information output by the encoder each time by using the expanded memory space. For example, in the tth (t is a positive integer) feedback period (or the tth feedback), the state information stored by the encoding device is {e0, e1, e2, ..., e t-1 This includes}. In another example, the encoding device may determine the value of k after receiving the fifth piece of information and, by using the expanded memory space, may store at least k of the latest historical state information. In this way, memory space can be saved and the complexity of the encoding device can be reduced. For example, in the tth (t is a positive integer) feedback period (or the tth feedback), the input to the encoding device is the previously acquired state information e t-1 This includes, in this case, at least k state information stored in the encoding device, {e t-1-k ,e t-k ,...,e t-2} includes. When the encoder completes its execution, new state information e t The output is e t It is updated to {e t-k ,e t-k+1 ,...,e t-1 It will be updated to}.

[0214] For example, k is equal to 1 and t is equal to 3. In this case, during the third feedback period (or third feedback), the input to the encoder contains the previously acquired state information e2, and the state information stored in the encoder is {e1}. When the new state information e3 is output after the encoder has finished its execution, the state information stored in the encoder also needs to be updated to {e2}. In another example, k is equal to 2 and t is equal to 4. In this case, during the fourth feedback period (or fourth feedback), the input to the encoder contains the previously acquired state information e3, and the state information stored in the encoder is at least two items {e1, e2}. When the new state information e4 is output after the encoder has finished its execution, the state information stored in the encoder also needs to be updated to at least two items {e2, e3}.

[0215] The encoder in this embodiment of the present application may be a first AI model.

[0216] In an optional embodiment, the number of delayed feedback periods k or the delay can be predetermined. In this case, step S201 may not exist. In other words, the information exchange method in this embodiment of the application may not include step S201. However, in this case, the encoding device still needs to store at least k of the latest historical state information. See the above description for details. Further details will not be explained here.

[0217] In this application, "defining in advance" can be understood as setting, setting in advance, defining beforehand, storing, storing in advance, negotiating in advance, configuring in advance, fixing, or writing in advance.

[0218] S202: The encoding device (e.g., UE) receives the second feedback information c t This is transmitted to a decoding device (e.g., a base station), where the second feedback information c t This is the second channel information Ht , and the state information e previously acquired by the encoding device t-1 This is feedback information output after the data has been input to the encoder for processing.

[0219] Optionally, the encoding device may perform a channel measurement based on the received reference signal to obtain channel information, where the channel information is, for the sake of clarity, a second channel information H. t This is shown as follows. Next, the encoding device receives the second channel information H t , and the state information e previously acquired by the encoding device t-1 The data is input to an encoder for processing, and feedback information can be obtained, where the feedback information is second feedback information c for ease of description. t This is shown as follows. When the feedback period arrives, the encoding device receives the second feedback information c t The encoding device may transmit the second feedback information c to the decoding device. For example, the encoding device may transmit the second feedback information c t Operations such as quantization and modulation are performed on it, and then the second feedback information c t It may transmit the second channel information H that was input. Optionally, the encoder may further transmit the second channel information H t , and the state information e previously acquired by the encoding device t-1 Based on this, new state information e t Outputs (referred to as the second state information for ease of description). The state information previously acquired by the encoding device can be understood as the state information previously output by the encoder. State information e previously acquired by the encoding device t-1 This is the second channel information H t Reflects one or more historical channel information obtained before the acquisition of the new state information e t (i.e., the second state information) is the second channel information H t It reflects one or more historical channel information, including t, where t is a positive integer and H t This can be understood as the tth channel information, c tThis can be understood as the tth piece of feedback information, e t-1 This can be understood as state information output by the encoder during the (t-1)th feedback period (or the (t-1)th feedback), e t This can be understood as state information output by the encoder during the tth feedback period (or the tth feedback).

[0220] For example, assuming t is equal to 3, as shown in Figure 6, the Encoder (UE) inputs the second channel information H3 and the state information e2 previously acquired by the Encoder (UE) into the encoder for processing, and outputs the second feedback information c3 and new state information e3 (i.e., second state information). The new state information e3 (i.e., second state information) can also be used as input to the encoder in the next feedback. In other words, the new state information e3 (i.e., second state information) can be used as input for the encoder to generate the next feedback information.

[0221] S203: The decoding device (e.g., base station) transmits first information to the encoding device (e.g., UE), where the first information includes or indicates the step size m of the state information rollback, and the first information includes the history state information e of the encoding device. his This is to determine m, where m is a positive integer.

[0222] In response, the encoding device (e.g., UE) receives the first piece of information.

[0223] S204: The encoding device (e.g., UE) receives the historical status information of the encoding device e based on the first information. his and the first channel information H q The first feedback information c is input to the encoder for processing. q The history status information e is obtained here. his This is the first channel information H q It reflects one or more historical channel information acquired before the current information was obtained.

[0224] Optionally, the encoding device receives second feedback information c t After sending the second feedback information c to the decoding device, the decoding device then receives the second feedback information c t Second feedback information c on the time-frequency resource t When it receives (or demodulates) the second feedback information c t This indicates that the transmission of the first information was successful. In this case, the decoding device may not transmit the second feedback information c t , and the state information d previously acquired by the decoding device t-1 The channel information H is input to the decoder for processing. t It is possible to obtain '.

[0225] The decoding device receives the second feedback information c t Second feedback information c on the time-frequency resource t If it is not received (or demodulated), it is the second feedback information c t This indicates that the transmission of the first information failed. In this case, the decoding device may send the first information to the encoding device. Naturally, the second feedback information c t If the transmission fails, step S201 above shows that the encoding device can receive the first information delivered by the decoding device at the latest, with a delay of k feedback period (i.e., the (t+k)th feedback period). Therefore, the decoding device needs to send the first information to the encoding device before the (t+k)th feedback period. The first information is the encoding device's historical state information e his The first information may be for determining the state information that is input to the encoder after the first information is received. The first information may also be second feedback information c t This may be a notification that transmission has failed, and the first information may further indicate a mismatch between the transmitting and receiving ends, or similar. The first information may include or indicate the step size (or number) m of the state information rollback, where m is a positive integer.

[0226] Assuming the decoding device transmits the first information to the encoding device before the q-th feedback period, the encoding device can then receive the first information during the q-th feedback period (or after the (q-1)-th feedback period), where q is a positive integer greater than t and less than or equal to t+k. Correspondingly, the encoding device receives the first information during or before the q-th feedback period (i.e., before the q-th feedback). After receiving the first information, the encoding device generates historical state information e based on the first information. his This can be determined. For example, the history state information of the encoding device e his This is the state information e input by the encoder in the (qm)th step. q-m-1 It could be, that is, e his =e q-m-1 In other words, the history status information e his This is the current state information e q-1 This is the state information after it has been rolled back m times, i.e. q-1-m Here, q is greater than m, and m is less than or equal to k. At least k state information stored by the encoding device during the q-th feedback period (i.e., the q-th feedback) or before the q-th feedback period (i.e., before the q-th feedback) is {e q-1-k ,e q-k ,...,e q-2 It can be understood that}. Since m is less than or equal to k, the encoding device receives the historical state information e his =e q-m-1 It is stored in memory. Therefore, the second feedback information c t After a transmission failure, the encoding device may perform a state information rollback based on instructions from the decoding device (e.g., the first information), and as a result, the state information input by the encoding device will be consistent with the state information input by the decoding device.

[0227] In some scenarios, the second feedback information c t Even if the transmission of the first information is successful, the decoding device may send the first information to the encoding device, and as a result, the encoding device will roll back the state information. In other words, the rollback of the state information may be controllable by the decoding device. The decoding device may also send the first information when it tries to get the encoding device to perform a state information rollback, but it is not limited to sending the first information only when the transmission of the feedback information has failed.

[0228] Optionally, the encoding device receives historical state information e his Without any operation or step to determine the first channel information H, after receiving the first information transmitted by the decoder, perform a channel measurement based on the received reference signal to obtain the first channel information H q It is possible to obtain state information e q-m-1 and the first channel information H q This can be input into an encoder for processing.

[0229] Optionally, the encoding device performs a channel measurement based on the received reference signal to obtain first channel information H q It is possible to obtain, and then, the history status information e his and the first channel information H q The first feedback information c is input to the encoder for processing. q It is possible to obtain the following: History status information e his This is the first channel information H q It reflects one or more historical channel information obtained before it is obtained. For example, historical status information e his This reflects the history channel information that precedes the (qm)th feedback. Optionally, the history state information e his and the first channel information H q After the new state information e is input to the encoder for processing, q (i.e., the first state information) is output again. New state information e q (That is, the first state information) is the first channel information H qIt may reflect one or more historical channel information including new state information e. q (That is, the first state information) is the first channel information H q , and reflect the historical channel information prior to the (qm)th feedback.

[0230] For example, k is equal to 1 and m is also equal to 1. Specifically, after the encoding device has performed the current feedback, the encoding device may, at the latest in the next feedback, determine whether the previous feedback was successful. For example, the encoding device may, in the tth feedback period (or the tth feedback), receive the second feedback information c t After transmitting, the encoding device, at the latest during the (t+1)th feedback period (or (t+1)th feedback), receives the second feedback information c t It is possible to determine whether the transmission of the first feedback information c was successful. In this case, q = t + k = t + 1. In other words, the first feedback information c q =c t+1 This is the second feedback information c t This is the next feedback information. In addition, during the (t+1)th feedback period (or (t+1)th feedback), the state information stored in the encoding device is {e t-1}

[0231] Please refer to Figure 9a. Figure 9a is a first schematic flowchart of the processing of the encoding device and decoding device according to an embodiment of the present invention. As shown in Figure 9a, t is equal to 3. If the transmission of the second feedback information c3 fails and the decoding device notifies the encoding device that the step size (or number) m of the state information rollback is equal to 1 by using the first information, the history state information of the encoding device is e his =e q-m-1 =e t-1 = e². In the fourth feedback period (or fourth feedback), the input to the encoder is e his=It includes e2 and the first channel information H4, and the output of the encoder is the new state information e4 (i.e., the first state information) and the first feedback information c4. Since the transmission of the second feedback information c3 fails and the encoder receives the first information before the fourth feedback, in the fourth feedback, the encoder no longer uses the previously obtained state information e3 as the input, but rolls back the state information to e2 and uses the state information e2 output by the encoder in the second feedback as the input of the encoder in the fourth feedback. Thus, for the fourth feedback, the state information e2 input by the encoder is consistent with the state information d2 input by the decoder. This not only improves the decoding performance on the base station side (or decoder), but also reduces the communication performance loss and improves the communication quality.

[0232] In another example, k is equal to 3 and m is equal to 2. Specifically, after the encoder transmits the second feedback information c t in the t-th feedback period (or the t-th feedback), the encoder can determine at the latest in the (t + 3)-th feedback period (or the (t + 3)-th feedback) whether the transmission of the second feedback information c t is successful, where t < q ≤ t + k = t + 3. Specifically, the first feedback information c q is the (q - t)-th feedback information after the second feedback information c t . Assuming that q is equal to t + 2, the encoder receives the first information in the (t + 2)-th feedback period (or the (t + 2)-th feedback). In addition, in the (t + 2)-th feedback period (or the (t + 2)-th feedback), the three state information stored in the encoder are {e t-2 ,e t-1 ,e t}.

[0233] Please refer to Figure 9b. Figure 9b is a second schematic flowchart of the processing of the encoding and decoding devices according to an embodiment of the present invention. As shown in Figure 9b, t is equal to 2. If the transmission of the second feedback information c2 fails and the decoding device notifies the encoding device that the step size m of the state information rollback is equal to 2 by using the first information in the fourth feedback period (or fourth feedback), the history state information of the encoding device is e his =e q-m-1 =e t-1 =e1. In the fourth feedback period (or fourth feedback), the input to the encoder is e his =e1 and the first channel information H4 are included, and the output of the encoder is the new state information e4 (i.e., the first state information) and the first feedback information c4. In the third feedback, it can be understood that the input to the encoder includes the previously acquired state information e2, and the output of the encoder includes the state information e3. However, in the fourth feedback, when the encoder receives the first information, the encoder does not use the previously acquired state information e3 as input, but rolls back the state information to e1, and uses the state information e1 output by the encoder in the first feedback as input to the encoder in the fourth feedback. Thus, for the fourth feedback, the state information e1 input by the encoder is consistent with the state information d1 input by the decoder.

[0234] S205: The encoding device (e.g., UE) receives the first feedback information c q This is transmitted to a decoding device (e.g., a base station), where the first feedback information c q This is the first channel information H q The encoded information or the predicted channel information includes encoded information.

[0235] Correspondingly, the decoding device (e.g., base station) receives the first feedback information c q Receive.

[0236] Optionally, the first feedback information c q After obtaining the first feedback information c, the encoding device performs operations such as quantization and modulation. q It is executed against, and then the first feedback information c q It can send.

[0237] Optionally, when the q-th feedback period arrives, the encoding device receives the first feedback information c q The transmitting or encoding device transmits the first feedback information c during the q-th feedback period. q This may be generated and transmitted. This is not limited to the present embodiment of the application.

[0238] Optionally, the first channel information H q and first feedback information c q For the relationship between these two, please refer to the relevant description in Embodiment 1. Further details will not be explained here.

[0239] Optionally, after step S205, the information exchange method may further include the following steps.

[0240] S206: The decoding device (e.g., base station) receives the first feedback information c q and the history status information of the decoding device d his The third channel information H is input to the decoder for processing. q ' is obtained, and here the history status information d his This is the first feedback information c q Reflects one or more historical feedback pieces of information obtained before the current data was acquired.

[0241] Optionally, the decoder may also deploy a memory space for storing one or more historical state information, and as a result, historical state information output by the decoder at a specific time after a failure to transmit feedback information may be used to decode the feedback information received thereafter. For example, the decoder may store the state information output by the decoder each time by using the deployed memory space. For example, in the tth (t is a positive integer) feedback period (or the tth feedback), the state information stored in the decoder is {d0, d1, d2, ..., d t-1 This includes}. In another example, the decoder can store at least k of the latest historical state information by using the expanded memory space. In this way, memory space can be saved and the complexity of the decoder can be reduced. For example, in the tth (t is a positive integer) feedback period (or the tth feedback), the input to the decoder is the previously acquired state information d t-1 This includes, in this case, at least k state information stored in the decryption device, {d t-1-k d t-k ,...,d t-2} includes. When the decoder completes its execution, new state information d t The output is d. In other words, the state information is d t It is updated to {d t-k d t-k+1 ,...,d t-1 It will be updated to}.

[0242] Optionally, the decoding process of the decoding device (e.g., step S206) may be the reverse process of the encoding process of the encoding device (e.g., step S204). Specifically, the decoding device, based on the first information, processes the historical state information d his This can be determined by assuming that the decoder sends the first piece of information to the encoding device before the q-th feedback period, where q is a positive integer greater than t and less than or equal to t+k. For example, the history state information d of the decoder. hisThis is the state information d input by the decoder in the (qm)th step. q-m-1 It could be, that is, d his =d q-m-1 In other words, the history status information d his This is the current state information d q-1 This is state information obtained after m rollbacks, i.e., d q-1-m Here, q is greater than m, and m is less than or equal to k. The decoder in this embodiment of the present application may be a second AI model. Next, the decoding device receives the first feedback information c in the q-th feedback period. q and historical status information d his The third channel information H is input to the decoder for processing. q It may obtain the following. Optionally, the decoder can also obtain the historical state information d his Without any operation or step to determine the first information, the first feedback information c received in the qth feedback period after the first information has been transmitted. q and status information d q-m-1 This can be input to the decoder for processing.

[0243] For example, history status information d his This refers to one or more historical feedback pieces of information c obtained before the first feedback piece was obtained. q This reflects the historical status information d. his This reflects the historical feedback information that preceded the (qm)th feedback. Optionally, historical state information d his and first feedback information c q After the data is input to the decoder for processing, new state information d q (i.e., a third state information) is output. New state information d q (That is, the third state information) is the first feedback information c q It may reflect one or more historical feedback pieces of information, including new state information d. q (That is, the third state information) is the first feedback information H q, and reflects the historical feedback information prior to the (qm)th feedback.

[0244] For example, as shown in Figure 9a, k is equal to 1, m is also equal to 1, t is equal to 3, and q = t + 1 = 4. If the transmission of the second feedback information c3 fails, the history status information of the decoding device is d his =d q-m-1 =d t-1 = d2. In this case, for the fourth feedback, the decoder input is d his =d2 and the first feedback information c4 are included, and the decoder output is the new state information d4 (i.e., the third state information) and the third channel information H4'. The third channel information H4' can be understood as the channel information reconstructed based on the first feedback information c4.

[0245] In another example, as shown in Figure 9b, k is equal to 3, m is equal to 2, t is equal to 2, and q = t + 2 = 4. If the transmission of the second feedback information c2 fails, the history state information of the decoding device is d his =d q-m-1 =d t-1 =d1. In this case, for the fourth feedback, the decoder input is history state information d his = d1 and the first feedback information c4 are included, and the decoder output is the new state information d4 (i.e., the third state information) and the third channel information H4'. The third channel information H4' can be understood as the channel information restored based on the first feedback information c4. Optionally, for the third feedback, if the transmission of feedback information c3 is successful, the decoder input may include the state information d1 and feedback information c3 output by the decoder the first time, and the decoder output is the new state information d3 and channel information H3'. However, state information d3 is not used as the next input to the decoder.

[0246] In an ideal case, the decoder receives the first channel information H processed by the encoder. qIt can be understood that it can be completely restored. In this case, the first feedback information c q and historical status information d his Third channel information H recovered by the decoder based on q ' is the first channel information H input by the encoder. q It is identical to, or the first channel information H q This is identical to the channel information predicted by the encoder based on the first channel information H processed by the encoder. However, in actual application, the decoder uses the first channel information H processed by the encoder. q It is not possible to fully restore it. Therefore, in actual application, the third channel information H q ', and the first channel information H input by the encoder q This has certain (or slight) differences, or third channel information H q ', and the first channel information H q The channel information predicted by the encoder based on this has certain (or slight) differences. In some scenarios, these differences can be ignored.

[0247] The decoding device in the embodiment of the present invention processes state information into specific historical state information e his The encoder of the encoding device is instructed to roll back. In this way, for the same feedback, the state information input by the encoder is consistent with the state information input by the decoder, thereby improving the decoding performance on the base station side (or decoder), reducing communication performance loss, and improving communication quality. Embodiment 3

[0248] Embodiment 3 of the present invention primarily describes a case in which an encoding device (e.g., a UE) periodically stores state information based on instructions from a decoding device (e.g., a base station) or according to predefined rules, and as a result, the encoding device performs a state information rollback based on instructions from the decoding device.

[0249] Please refer to Figure 10. Figure 10 is a third schematic flowchart of an information exchange method according to an embodiment of the present invention. As shown in Figure 10, the information exchange method includes, but is not limited to, the following steps.

[0250] S301: The decoding device (e.g., base station) transmits a fifth piece of information to the encoding device (e.g., UE), which instructs the encoding device to receive the first piece of information after transmitting the feedback information, with a delay of k feedback period.

[0251] In response, the encoding device (e.g., UE) receives the fifth piece of information.

[0252] Optionally, the fifth piece of information includes the number of delayed feedback periods k, where k is a positive integer. Alternatively, the fifth piece of information includes the delay, where the unit of delay is a time unit such as seconds, microseconds, milliseconds, or nanoseconds, and k =

number

number

[0253] In an optional embodiment, the number of delayed feedback periods k or the delay can be predetermined. In this case, step S301 may not exist. In other words, the information exchange method in this embodiment of the present application may not include step S301.

[0254] S302: The decoding device (e.g., base station) transmits second information to the encoding device (e.g., UE), where the second information indicates whether the encoding device performs periodic memory, the memory period, or one or more start points of the memory period.

[0255] In response, the encoding device (e.g., UE) receives the second piece of information.

[0256] S303: The encoding device (e.g., UE) periodically stores the state information output by the encoder based on the instructions of the second piece of information.

[0257] The encoding device may deploy a memory space for storing one or more historical state information, and as a result, it can be understood that after a failure to transmit feedback information, the state information input to the encoder may be rolled back to the historical state information stored at a specific time. Similarly, the decoding device may also deploy a memory space for storing one or more historical state information, and as a result, after a failure to transmit feedback information, the historical state information output by the decoder at a specific time may be used to decode the feedback information received thereafter.

[0258] Optionally, the decoding device transmits second information to the encoding device, which may indicate one or more of the following: whether the encoding device performs periodic storage, the storage period, or the start time of the storage period. When the second information instructs the encoding device to perform periodic storage, the storage period and / or the start time of the storage period may be predetermined or may be instructed by the decoding device using the second information. In other words, the second information may further indicate one or more of the following: the storage period or the start time of the storage period. After receiving the second information, the encoding device may periodically store the state information output by the encoder based on the instructions in the second information. For example, the encoding device may store the state information output by the encoder at intervals of storage period T, starting from the start time of the storage period. For example, the start of the memory cycle may be the time of the first feedback, or the time of the first feedback plus an offset, or the time of initializing state information e0, or the time of initializing state information e0 plus an offset, or the time of the first execution of the encoder, or the time of the first execution of the encoder plus an offset. The start of the memory cycle is not limited to this embodiment of the present application.

[0259] The memory period T can be understood as the interval between two adjacent memories. A memory operation is performed when the memory period arrives. The memory period T can be an integer multiple of the feedback period S. Further details are not described below. For ease of description, the following example uses the point in time when the start of the memory period is the point in time when the encoder begins execution. When second information indicates that the encoder does not perform periodic memory, the encoder may use the memory scheme described in Embodiment 2 above, for example, storing at least k of the latest historical state information or storing state information output each time by the encoder, or may use another memory scheme. This is not limited to the present embodiment of the Application. This embodiment of the Application focuses primarily on periodic memory.

[0260] Specifically, the encoding device periodically stores the state information output by the encoder: the encoding device stores the state information e obtained in the (n(T / S)-k)th feedback. n(T / S)-k This includes temporarily storing (in the nth memory cycle). The encoding device receives the third piece of information transmitted by the decoding device during the (n(T / S))th feedback period. When the value of the third piece of information is the first value, the encoding device stores the state information stored during the ((n-1)*(T / S))th feedback period during the (n(T / S))th feedback period. When the value of the third piece of information is the second value, the encoding device stores the state information e acquired during the (n(T / S)-k)th feedback period during the (n(T / S))th feedback period during the (n(T / S))th feedback period. n(T / S)-k The following is stored, where n is 1, 2, 3, ... The first value is 0 and the second value is 1; or the first value is 1 and the second value is 0. This is not limited to the present embodiment of the present application. For example, if the (n(T / S)-k)th feedback of the encoding device is successful, the third information may be set to the second value; if the (n(T / S)-k)th feedback of the encoding device fails, the third information may be set to the first value.

[0261] For example, T is equal to S, i.e., T / S = 1, and k is equal to 1. Assume the first value is 0 and the second value is 1. In the nth feedback period (or the nth feedback), the input to the encoder is the state information e obtained previously. n-1 The encoding device includes the previously acquired state information e n-1It can temporarily store the state information e. n-1 Remember this.

[0262] In another example, T is twice S, i.e., T / S = 2, and k is equal to 2. Assume the first value is 0 and the second value is 1. During the (2n-1)th feedback period (or the (2n-1)th feedback), the input to the encoder is the previously acquired state information e 2n-2 The encoding device includes state information e 2n-2 It can be temporarily stored. During the (2n)th feedback period (or the (2n)th feedback), the encoding device receives the third piece of information transmitted by the decoding device. If the value of the third piece of information is 1, it is the same as the feedback information c transmitted during the second-to-last feedback period (i.e., the (2n-2)th feedback period). 2n-2 This indicates that the transmission was successful, that is, the decoding device receives the status information of the encoding device e 2n-2 Matching state information d 2n-2 The encoding device has state information e acquired during the (2n-2)th feedback period. 2n-2 It can store the following. If the value of the third piece of information is 0, it means that the feedback information c sent in the second to last feedback period (i.e., the (2n-2)th feedback period) 2n-2This indicates that the transmission of the data failed. In this case, the encoding device stores the state information stored by the encoding device during the (2n-1)th feedback period (or the (2n)th feedback) during the (2n)th feedback period, and temporarily stores the state information e 2n-2 It can be deleted.

[0263] Optionally, the encoding and decoding devices may use the same storage method. When second information instructs the encoding device to perform periodic storage, the decoding device may also periodically store the state information output by the decoder. The storage periods of the decoding and encoding devices are the same and both are T, and the storage period T is an integer multiple of the feedback period S. The start times of the storage periods of the decoding and encoding devices are also consistent. For example, the start time of the encoding device's storage period is when the encoder starts execution, and correspondingly, the start time of the decoding device's storage period is when the decoder starts execution. Alternatively, the start time of the encoding device's storage period is the time of the first feedback, or the time of the first feedback plus an offset. Correspondingly, the start time of the decoding device's storage period is the time when the feedback information is received for the first time, or the time when the feedback information is received for the first time plus an offset. Alternatively, the start time of the encoding device's storage period is the time when the state information e0 is initialized, or the time when the state information e0 is initialized plus an offset. Correspondingly, the start of the memory cycle of the decryption device is the time when state information d0 is initialized, or the time when state information d0 is initialized plus an offset. Examples are not listed one by one here.

[0264] For example, starting from the beginning of the decoding device's memory cycle, the decoding device stores the state information output by the decoder at intervals of memory cycle T. For example, when the decoding device receives the (n(T / S)-k)th feedback information (or the (n(T / S)-k)th feedback), the decoding device sets the third piece of information to the second value, transmits the third piece of information to the encoding device, and the decoding device stores the state information output by the decoder for the (n(T / S)-k)th time, i.e., dn(T / S)-k The decoding device can store the state information stored during the ((n-1)*(T / S))th feedback period, where n is 1, 2, 3... Naturally, if the decoding device does not receive the (n(T / S)-k)th feedback information, it sets the third piece of information to the first value, sends the third piece of information to the encoding device, and stores the state information stored during the ((n-1)*(T / S))th feedback period.

[0265] In an optional embodiment, both the encoding and decoding devices may perform periodic storage, and the storage period T and the start time of the storage period may also be predefined. In this case, step S302 may not exist. In other words, the information exchange method in this embodiment of the application may not include step S302, and step S303 may be replaced by the encoding device (e.g., UE) periodically storing state information output by the encoder based on a predefined storage period T and the start time of the storage period. Similarly, the decoding device may also periodically store state information output by the decoder based on a predefined storage period T and the start time of the storage period.

[0266] If both step S302 and step S301 exist, it can be understood that the execution order of steps S301 and S302 may not be limited. For example, step S302 may be executed before step S301, step S302 may be executed after step S301, or steps S301 and S302 may be executed simultaneously. This is not limited to this embodiment of the present application.

[0267] S304: The encoding device (e.g., UE) receives the second feedback information c t This is transmitted to a decoding device (e.g., a base station), where the second feedback information c t This is the second channel information H t , and the state information e previously acquired by the encoding device t-1 This is feedback information output after the data has been input to the encoder for processing.

[0268] For the implementation of step S304 in this embodiment of the present application, please refer to the implementation of step S202 in Embodiment 2. Further details will not be explained here.

[0269] S305: The decoding device (e.g., base station) transmits first information to the encoding device (e.g., UE), where the first information is the encoding device's historical status information e his This is for the purpose of making a decision.

[0270] In response, the encoding device (e.g., UE) receives the first information, and the historical state information e his It is determined that this is state information stored in the previous memory cycle.

[0271] S306: The encoding device (e.g., UE) uses the first information to obtain the history status information of the encoding device e his and the first channel information H t+k The first feedback information c is input to the encoder for processing. t+k The history status information e is obtained here. his This is the first channel information H t+k It reflects one or more historical channel information acquired before the current information was obtained.

[0272] Optionally, the encoding device receives second feedback information c t After sending the second feedback information c to the decoding device, the decoding device then receives the second feedback information c t Second feedback information c on the time-frequency resource t When the first information is received (or demodulated), it indicates that the transmission of the second feedback information c has been successful. In this case, the decoding device may not transmit the first information, but the second feedback information c t , and the state information d previously acquired by the decoding device t-1 The channel information H is input to the decoder for processing. t It is possible to obtain '.

[0273] The decoding device receives the second feedback information ct Second feedback information c on the time-frequency resource t If it is not received (or demodulated), it is the second feedback information c t This indicates that the transmission of the first information failed. In this case, the decoding device may send the first information to the encoding device. Naturally, the second feedback information c t If transmission fails, from step S301 above, it can be seen that the encoding device can receive the first information delivered by the decoding device at the latest, with a delay of the feedback period k. Therefore, the decoding device must send the first information to the encoding device before the (t+k)th feedback period, and as a result, the encoding device can receive the first information during the (t+k)th feedback period (or after the (t+k-1)th feedback period). The first information is the encoding device's historical state information e his The first information may be for determining the state information that is input to the encoder after the first information is received. The first information may also be second feedback information c t This may be intended to notify that transmission has failed, and the first information may further indicate a mismatch between the transmitting and receiving ends, or similar. In some scenarios, the second feedback information c t Even if the transmission of the first information is successful, the decoding device may send the first information to the encoding device, and as a result, the encoding device will roll back the state information. In other words, the rollback of the state information may be controllable by the decoding device. The decoding device may also send the first information when it tries to get the encoding device to perform a state information rollback, but it is not limited to sending the first information only when the transmission of the feedback information has failed.

[0274] The decoding device is assumed to transmit the first information to the encoding device before the (t+k)th feedback period. Correspondingly, the encoding device receives the first information during the (t+k)th feedback period. Optionally, the encoding device receives the historical state information e hisWithout any operation or step to determine the first channel information H, after receiving the first information transmitted by the decoder, perform a channel measurement based on the received reference signal to obtain the first channel information H q It is possible to obtain the state information stored in the previous memory cycle and the first channel information H q This can be input into an encoder for processing.

[0275] Optionally, after receiving the first information, the encoding device generates historical status information e based on the first information. his The encoding device can determine the historical state information e based on the first information it receives. his However, it is determined that this is state information stored in the previous memory cycle.

[0276] For example, the (t+k)th feedback period or the (t+k)th feedback is precisely a time node in the encoding device's periodic memory, i.e., t+k=n(T / S). In this case, after receiving the first information in the (n(T / S))th feedback period, the encoding device receives the historical state information e his It can be determined that this is state information stored by the encoding device during the ((n-1)*(T / S))th feedback period. In another example, the (t+k)th feedback period or the (t+k)th feedback is not a time node for the encoding device's periodic storage, i.e., t+k is not equal to n(T / S). In this case, after receiving the first information during the (t+k)th feedback period, the encoding device stores the historical state information e his This can be determined to be state information stored by the encoding device in the memory cycle prior to the (t+k)th feedback period.

[0277] The encoding device performs a channel measurement based on the received reference signal and obtains the first channel information H t+k Obtain the historical status information e his and the first channel information H t+k The first feedback information c is input to the encoder for processing.t+k It is possible to obtain the following: History status information e his This is the first channel information H t+k It reflects one or more historical channel information obtained before it is obtained. Optionally, historical status information e his and the first channel information H t+k After the new state information e is input to the encoder for processing, t+k (i.e., the first state information) is output again. New state information e t+k (That is, the first state information) is the first channel information H t+k It may reflect one or more historical channel information, including [specific information].

[0278] For example, if k is equal to 1, it indicates that after the encoder performs the current feedback, the encoder may, at the latest, determine whether the previous feedback was successful before the next feedback. Assume that T is equal to S, i.e., T / S = 1. If, during the nth feedback period (or the nth feedback), the encoder has not yet received the first information, the encoder will determine the state information e obtained last time. n-1 (i.e., the (n-1)th feedback) and channel information H n The data is input to the encoder for processing, and feedback information c n The encoding device may obtain and transmit feedback information. If the encoding device receives the first information during the nth feedback period (or nth feedback), the encoding device will obtain the history state information e his However, it can be determined that this is state information stored by the encoding device during the (n-1)th feedback period (or the (n-1)th feedback). Assume that T is the second of S, i.e., T / S = 2. If the encoding device has not yet received the first information during the (2n)th feedback period (or the (2n)th feedback) (where n is 1, 2, 3...), the encoding device will determine that the state information e acquired in the previous (i.e., the (2n-1)th feedback) is stored. 2n-1 and channel information H2n The data can be input to the encoder for processing, and feedback information c 2n The encoder receives the first information during the (2n)th feedback period (or (2n)th feedback), and transmits the historical state information e. his This can be determined to be state information stored by the encoding device during the (2(n-1))th feedback period (or (2(n-1))th feedback).

[0279] Please refer to Figure 11a. Figure 11a is a third schematic flowchart of the processing of the encoding and decoding devices according to an embodiment of the present invention. As shown in Figure 11a, when k is equal to 1 and t is equal to 3, the transmission of the second feedback information c3 fails, and the decoding device notifies the encoding device that the transmission of the second feedback information c3 has failed by using the first information before the fourth feedback. When T / S=1, when n is equal to 4, i.e., in the fourth feedback period (or fourth feedback), after receiving the first information, the encoding device receives the history status information e his It can be determined that this is state information stored by the encoding device during the third feedback period (or third feedback). If the value of the third piece of information received by the encoding device during the third feedback period is the second value, then the state information stored by the encoding device during the third feedback period (or third feedback) is e2. In this case, the historical state information e hisis equal to e2. If the value of the third piece of information received by the encoder during the third feedback period is the first value, it indicates that the transmission of feedback information c2 also failed, and the state information stored by the encoder during the third feedback period (or third feedback) is the state information stored by the encoder during the second feedback period. The state information stored by the encoder during the second feedback period depends on the value of the third piece of information received by the encoder during the second feedback period.

[0280] When T / S=2, and n is equal to 2, that is, during the fourth feedback period (or fourth feedback), the encoding device, after receiving the first information, receives the historical state information e his It can be determined that this is state information stored by the encoding device during the second feedback period (or second feedback). If the value of the third piece of information received by the encoding device during the second feedback period is the second value, then the state information stored by the encoding device during the second feedback period (or second feedback) is e1, i.e., historical state information e his This is equal to e1. ​​If the value of the third piece of information received by the encoding device during the second feedback period is the first value, then the state information stored by the encoding device during the second feedback period (or second feedback) is the initial state information e0 of the encoding device.

[0281] Therefore, if the transmission of the second feedback information c3 fails, in the fourth feedback, the encoder no longer uses the state information e3 obtained previously (i.e., in the third feedback) as input, and the state information is replaced with the historical state information e his Roll back to the previous state.

[0282] Please refer to Figure 11b. Figure 11b is a fourth schematic flowchart of the processing of the encoding and decoding devices according to an embodiment of the present invention. As shown in Figure 11b, when k is equal to 2 and t is equal to 3, the transmission of the second feedback information c3 fails, and the decoding device notifies the encoding device that the transmission of the second feedback information c3 has failed by using the first information before the fifth feedback. When T / S=1, when n is equal to 4, i.e., in the fifth feedback period (or fifth feedback), after receiving the first information, the encoding device receives the history status information e his It can be determined that this is state information stored by the encoding device during the fourth feedback period (or fourth feedback). If the value of the third piece of information received by the encoding device during the fourth feedback period is the second value, then the state information stored by the encoding device during the fourth feedback period (or fourth feedback) is e2, i.e., the historical state information e his is equal to e2. If the value of the third piece of information received by the encoding device in the fourth feedback period is the first value, it indicates that the transmission of feedback information c2 also failed, and the state information stored by the encoding device in the fourth feedback period (or fourth feedback) is the state information stored by the encoding device in the third feedback period. The state information stored by the encoding device in the fourth feedback period depends on the value of the third piece of information received by the encoding device in the third feedback period.

[0283] If T / S=2, and n is equal to 2, that is, if the value of the third piece of information received by the encoding device in the fourth feedback period (or fourth feedback) is the second value, then the state information stored by the encoding device in the fourth feedback period (or fourth feedback) is e2. In the fifth feedback period (or fifth feedback), the encoding device receives the first piece of information and the historical state information ehis This is the state information stored by the encoding device in the memory cycle prior to the fifth feedback period (i.e., the state information stored in the fourth feedback period), i.e., the historical state information e his It can be determined that e2. If the value of the third piece of information received by the encoding device in the fourth feedback period is the first value, it indicates that the transmission of feedback information c2 also failed, and the state information stored by the encoding device in the fourth feedback period (or fourth feedback) is the state information stored by the encoding device in the third feedback period.

[0284] Therefore, if the transmission of the second feedback information c3 fails, in the fifth feedback, the encoder no longer uses the state information e4 obtained previously (i.e., in the fourth feedback) as input, and instead uses the state information as historical state information e his Roll back to the previous state.

[0285] In several possible implementations, the third piece of information and the first piece of information may be the same piece of information, or they may, of course, be different pieces of information. When the third piece of information is different from the first piece of information, the third piece of information and the first piece of information may be carried in one signaling or in different signaling. When the third piece of information and the first piece of information are the same piece of information, the functions of the two pieces of information may be combined. In other words, one piece of information not only instructs the encoding device to store state information, but also determines the history state information of the encoding device. Details are not explained here. In addition, when the third piece of information and the first piece of information are the same piece of information, the fifth piece of information (i.e., step S301) may not exist, or it may, of course, exist. When the fifth piece of information exists, one piece of information may be received with a delay of k feedback period, regardless of whether the feedback is successful or not (the information has the functions of both the third piece of information and the first piece of information).

[0286] S307: The encoding device (e.g., UE) receives the first feedback information c t+k This is transmitted to a decoding device (e.g., a base station), where the first feedback information c t+k This is the first channel information H t+k The encoded information or the predicted channel information includes encoded information.

[0287] Correspondingly, the decoding device (e.g., base station) receives the first feedback information c t+k Receive.

[0288] For the implementation of step S307 in this embodiment of the present application, please refer to the implementation of step S205 in Embodiment 2. Further details will not be explained here.

[0289] Optionally, after step S307, the information exchange method may further include the following steps.

[0290] S308: The decoding device (e.g., base station) receives the first feedback information c t+k and the history status information of the decoding device d his The third channel information H is input to the decoder for processing. t+k ' is obtained, and here the history status information d his This is the first feedback information c t+k Reflects one or more historical feedback pieces of information obtained before the current data was acquired.

[0291] Optionally, the decoding process of the decoding device (e.g., step S308) may be the reverse process of the encoding process of the encoding device (e.g., step S306). Specifically, the second feedback information c t If the transmission fails, the decoder will send historical state information d for the (t+k)th feedback. his It can be determined that this is state information stored in the previous memory cycle. Next, the decoding device receives the first feedback information c t+k and historical status information d his The third channel information H is input to the decoder for processing.t+k ' can be obtained. History status information d his This is the first feedback information c t+k It reflects one or more historical feedback pieces of information obtained before it was obtained. Optionally, it reflects historical status information d his and first feedback information c t+k After the data is input to the decoder for processing, new state information d t+k (i.e., a third state information) is output. New state information d t+k (That is, the third state information) is the first feedback information c t+k It may reflect one or more historical feedback pieces of information, including the historical state information d.Optionally, the decoder may reflect the historical state information d his Without any operation or step to determine the second feedback information c t If transmission fails, the decoding device will retrieve the first feedback information c stored in the memory cycle prior to the current time. t+k And state information can be input to the decoder for processing.

[0292] For example, as shown in Figure 11a, k is equal to 1 and t is equal to 3. The second feedback information c3 fails to transmit. If T / S=1, for the fourth feedback, the decoder receives the history state information d his It is determined that this is the state information stored by the decoding device in the third feedback. If the second feedback is successful, the state information stored by the decoding device in the third feedback is d2, i.e., the historical state information d his d is equal to d2. If T / S=2, for the fourth feedback, the decoder receives the history state information d his It is determined that this is the state information stored by the decoding device in the second feedback. If the first feedback is successful, the state information stored by the decoding device in the second feedback is d1, i.e., the historical state information d his This is equal to d1.

[0293] In another example, as shown in Figure 11b, k is equal to 2 and t is equal to 3. The second feedback information c3 fails to transmit. If T / S=1, for the fifth feedback, the decoder receives the history state information d his It is determined that this is the state information stored by the decoder in the fourth feedback. If the second feedback is successful, the state information stored by the decoder in the fourth feedback is d2. In this case, the historical state information d his d is equal to d2. If T / S=2, for the fifth feedback, the decoder receives the history state information d his However, it is determined that this is the state information stored by the decoding device in the memory cycle prior to the fifth feedback (i.e., the state information stored in the fourth feedback). If the second feedback is successful, the state information stored by the decoding device in the memory cycle prior to the fifth feedback is d2. In this case, the historical state information d his This is equal to d2.

[0294] In an ideal case, the decoder receives the first channel information H processed by the encoder. t+k It can be understood that it can be completely restored. In this case, the first feedback information c t+k and historical status information d his Third channel information H recovered by the decoder based on t+k ' is the first channel information H input by the encoder. t+k It is identical to, or the first channel information H t+k This is identical to the channel information predicted by the encoder based on the first channel information H processed by the encoder. However, in actual application, the decoder uses the first channel information H processed by the encoder. t+k It is not possible to fully restore it. Therefore, in actual application, the third channel information H t+k ', and the first channel information H input by the encoder t+k This has certain (or slight) differences, or third channel information H t+k ', and the first channel information Ht+k The channel information predicted by the encoder based on this has certain (or slight) differences. In some scenarios, these differences can be ignored.

[0295] The encoding device in this embodiment of the present invention periodically stores state information based on instructions from the decoding device or according to predefined rules, thereby reducing the operational complexity of the encoding device. In addition, the decoding device also periodically stores state information, and as a result, the encoding device and decoding device perform state information rollback. Furthermore, for the same feedback, the state information input by the encoding device is consistent with the state information input by the decoding device, thereby improving the decoding performance on the base station side (or decoder), reducing communication performance loss, and improving communication quality. Embodiment 4

[0296] Embodiment 4 of this application mainly involves an encoding device (e.g., UE) storing historical state information e his The encoder always uses the stored historical state information d as input, and similarly, the decoder (e.g., base station) always uses the stored historical state information d his The case where is used as input to the decoder is explained. In this way, when the feedback information from the encoding device is not successfully transmitted to the decoder, the encoding device does not use the mismatch state information as input to the encoder. In addition, the encoding device (e.g., UE) uses the historical state information e based on instructions from the decoder (e.g., base station). his The history status information e is updated, and as a result, his This includes recent historical channel information and implements channel time-domain correlation mining.

[0297] Please refer to Figure 12. Figure 12 is a fourth schematic flowchart of the information exchange method according to an embodiment of the present invention. As shown in Figure 12, the information exchange method includes, but is not limited to, the following steps.

[0298] S401: The decoding device (e.g., base station) transmits a fifth piece of information to the encoding device (e.g., UE), where the fifth piece of information instructs the encoding device to transmit feedback information and then receive the first piece of information with a delay of k feedback period, where k is equal to 1.

[0299] In response, the encoding device (e.g., UE) receives the fifth piece of information.

[0300] Optionally, the fifth piece of information includes the number of delayed feedback periods k, where k is a positive integer. Alternatively, the fifth piece of information includes the delay, where the unit of delay is a time unit such as seconds, microseconds, milliseconds, or nanoseconds, and k =

number

number

[0301] In an optional embodiment, the number of delayed feedback periods k or the delay can be predetermined. In this case, step S401 may not exist. In other words, the information exchange method in this embodiment of the present application may not include step S401.

[0302] S402: The encoding device (e.g., UE) receives the second feedback information c t This is transmitted to a decoding device (e.g., a base station), where the second feedback information c t This is the second channel information H t and historical status information e his This is feedback information that is output after the data has been input to the encoder for processing.

[0303] Optionally, the encoding device may perform a channel measurement based on the received reference signal to obtain channel information, where the channel information is, for the sake of clarity, a second channel information H. t This is shown as follows. Next, the encoding device receives the second channel information H t and historical status information e his The data is input to an encoder for processing, and feedback information can be obtained, where the feedback information is, for the sake of clarity, second feedback information c tThis is shown as follows. When the feedback period arrives, the encoding device receives the second feedback information c t The encoding device may transmit the second feedback information c to the decoding device. For example, the encoding device may transmit the second feedback information c t Operations such as quantization and modulation are performed on it, and then the second feedback information c t It may transmit the second channel information H that was input. Optionally, the encoder may further transmit the second channel information H t and historical status information e his Based on this, new state information e t Outputs the history status information e. his This is the historical state information output by the encoder during a specific time of execution; in the next feedback, the historical state information e his new state information e t Whether to replace it or not is instructed by the decoding device. History status information e his This is the second channel information H t It may reflect one or more historical channel information acquired before it was acquired, and new state information e t This is the second channel information H t This may reflect one or more historical channel information, including t, where t is a positive integer and H t This can be understood as the tth channel information, c t This can be understood as the tth piece of feedback information, e t This can be understood as state information output by the encoder during the tth feedback period (or the tth feedback).

[0304] For example, second feedback information c t If the first k pieces of feedback information (i.e., those transmitted during the tkth feedback period) are successfully transmitted, the decoder transmits the first information to the encoder. After the encoder receives the first information during the tth feedback period (or the tth feedback), it transmits the history state information e his This is the state information e output by the encoder during the (tk)th feedback period (or (tk)th feedback).t-k Update to e his =e t-k In other words, the second feedback information c t This is the second channel information H t and status information e t-k It is obtained by inputting it into an encoder for processing.

[0305] S403: The decoding device (e.g., base station) transmits first information to the encoding device (e.g., UE), where the first information is the encoding device's historical state information e his This is for the purpose of making a decision.

[0306] In response, the encoding device (e.g., UE) receives the first piece of information.

[0307] S404: The encoding device (e.g., UE) uses the first information to obtain the history status information of the encoding device e his and the first channel information H t+k The first feedback information c is input to the encoder for processing. t+k The history status information e is obtained here. his This is the first channel information H t+k It reflects one or more historical channel information acquired before the current information was obtained.

[0308] Optionally, the encoding device receives second feedback information c t After sending the second feedback information c to the decoding device, the decoding device then receives the second feedback information c t Second feedback information c on the time-frequency resource t When it receives (or demodulates) the second feedback information c t This indicates that the transmission was successful. In this case, the decoding device may send the first information to the encoding device. The first information is the encoding device's historical status information e hisThe first information may be for determining the state information that is input to the encoder after the first information is received. The encoding device receives the first information during the (t+k)th feedback period (or after the (t+k-1)th feedback period). After receiving the first information, the encoding device inputs the historical state information e his This is the state information e output by the encoder during the tth feedback period (or the tth feedback). t It can be updated to: When k is equal to 1, the encoding device, after receiving the first information in the (t+1)th feedback period, records the historical state information e his This is the state information e output by the encoder during the feedback period (i.e., the tth feedback) prior to the current time (i.e., the (t+1)th feedback period). t (or, the state information e previously acquired by the encoding device) t It can be understood that this should be updated to ).

[0309] Optionally, the encoding device receives second feedback information c t After sending the second feedback information c to the decoding device, the decoding device receives the second feedback information c t Second feedback information c on the time-frequency resource t If it is not received (or demodulated), it is the second feedback information c t The decoding device may indicate that the transmission failed and may not transmit the first information. In this case, the encoding device's historical status information e his It is not updated in the (t+k)th feedback period (or the tth feedback).

[0310] The encoding device performs channel measurements based on the received reference signal to obtain first channel information H t+k It is possible to obtain, and then, the history status information e his and the first channel information H t+k The first feedback information c is input to the encoder for processing. t+kIt is possible to obtain the following: History status information e his This is the first channel information H t+k It reflects one or more historical channel information obtained before it is obtained. Optionally, historical status information e his and the first channel information H t+k After the new state information e is input to the encoder for processing, t+k (i.e., the first state information) is output again. New state information e t+k (That is, the first state information) is the first channel information H t+k It may reflect one or more historical channel information, including [specific information].

[0311] For example, k is equal to 1. See Figure 13. Figure 13 is a fifth schematic flowchart of the processing of the encoding and decoding devices according to the embodiment of the present invention. As shown in Figure 13, the input to the encoder is history state information e his The decoder input includes historical state information d his This includes. When t is equal to 1 and the transmission of feedback information c1 is successful, the encoding device receives the first information in the second feedback and the history state information e his Update to e1, and history status information e his (=e1) and channel information H2 are input to the encoder for processing, and feedback information c2 and new state information e2 are output. Transmission of feedback information c2 fails, and the encoder does not receive the first information in the third feedback. In this case, historical state information e his It is not updated and remains e1. In other words, in the third feedback, the encoding device receives the historical state information e his (=e1) and channel information H3 are input to the encoder for processing, and feedback information c3 and new state information e3 are output. When the transmission of feedback information c3 is successful, the encoder receives the first information in the fourth feedback and the history state information e his Update to e3, and history status information e his(=e3) and channel information H4 are input to the encoder for processing, and feedback information c4 and new state information e4 are output.

[0312] S405: The encoding device (e.g., UE) receives the first feedback information c t+k This is transmitted to a decoding device (e.g., a base station), where the first feedback information c t+k This is the first channel information H t+k The encoded information or the predicted channel information includes encoded information.

[0313] Correspondingly, the decoding device (e.g., base station) receives the first feedback information c t+k Receive.

[0314] For the implementation of step S405 in this embodiment of the present application, please refer to the implementation of step S205 in Embodiment 2. Further details will not be explained here.

[0315] Optionally, after step S405, the information exchange method further comprises the following steps.

[0316] S406: The decoding device (e.g., base station) receives the first feedback information c t+k and the history status information of the decoding device d his The third channel information H is input to the decoder for processing. t+k ' is obtained, and here the history status information d his This is the first feedback information c t+k Reflects one or more historical feedback pieces of information obtained before the current data was acquired.

[0317] Optionally, the decoding process of the decoding device (e.g., step S406) may be the reverse process of the encoding process of the encoding device (e.g., step S404). Specifically, the second feedback information c t If the transmission is successful, the decoder will send the historical state information d for the (t+k)th feedback. hisThis is the state information d output by the decoder during the tth feedback period (or the tth feedback). t It can be updated. When k is equal to 1, for the (t+1)th feedback, the decoder receives the history state information d his The state information d that was previously output by the decoder t (or, the state information d previously obtained by the decoding device) t ) can be understood as being able to be updated. Second feedback information c t If the transmission fails, the decoding device will send the history state information d for the (t+k)th feedback. his The decoding device does not update the first feedback information c. t+k After receiving the historical status information d his and the first feedback information received c t+k The third channel information H is input to the decoder for processing. t+k It may output '. History status information d his This is the first feedback information c t+k It reflects one or more historical feedback pieces of information obtained before it was obtained. Optionally, it reflects historical status information d his and first feedback information c t+k After the data is input to the decoder for processing, new state information d t+k (i.e., a third state information) is output. New state information d t+k (That is, the third state information) is the first feedback information c t+k It may reflect one or more historical feedback pieces of information, including the following.

[0318] For example, as shown in Figure 13, k is equal to 1, and the input to the encoder is the history state information e his The decoder input includes historical state information d his This includes. When t is equal to 1, the transmission of feedback information c1 is successful, and the decoding device transmits the first information. In this case, in the second feedback, the decoding device transmits the history state information d hisUpdate to d1. Since the transmission of feedback information c2 failed, the decoder does not transmit the first information. Therefore, for the third feedback, the history state information d of the decoder is used. his It is not updated and remains d1. In other words, for the third feedback, the decoding device has the history state information d his (=d1) and feedback information c3 are input to the decoder for processing, and channel information H3' and new state information d3 are output. When the transmission of feedback information c3 is successful, the decoder transmits the first information. For the fourth feedback, the decoder transmits the history state information d his Update to d3, and history status information d his (=d3) and feedback information c4 are input to the decoder for processing, and channel information H4' and new state information d4 are output.

[0319] In an ideal case, the decoder receives the first channel information H processed by the encoder. t+k It can be understood that it can be completely restored. In this case, the first feedback information c t+k and historical status information d his Third channel information H recovered by the decoder based on t+k ' is the first channel information H input by the encoder. t+k It is identical to, or the first channel information H t+k This is identical to the channel information predicted by the encoder based on the first channel information H processed by the encoder. However, in actual application, the decoder uses the first channel information H processed by the encoder. t+k It is not possible to fully restore it. Therefore, in actual application, the third channel information H t+k ', and the first channel information H input by the encoder t+k This has certain (or slight) differences, or third channel information H t+k ', and the first channel information H t+k The channel information predicted by the encoder based on this has certain (or slight) differences. In some scenarios, these differences can be ignored.

[0320] The encoding device in this embodiment of the present application always stores the historical state information e his The encoder uses this as input, and the decoder always uses the stored historical state information d his The encoding device uses the historical state information e as input to the decoder. In this way, when the feedback information from the encoding device is not successfully transmitted to the decoder, the encoding device does not use the mismatched state information as input to the encoding device. Therefore, the state information input by the encoding device is consistent with the state information input by the decoder, thereby improving the decoding performance on the base station side, reducing communication performance loss, and improving communication quality. In addition, the encoding device uses the historical state information e based on the instructions of the decoder. his The history status information e is updated, and as a result, his This includes recent historical channel information, thereby enabling the mining of channel time-domain correlations. Embodiment 5

[0321] Embodiment 5 of the present invention mainly describes a case in which, when k is equal to 1, an encoding device (e.g., a UE) stores state information at a specific point in time based on instructions from a decoding device (e.g., a base station), and as a result, the encoding device performs a state information rollback based on instructions from the decoding device.

[0322] Refer to Figure 14. Figure 14 is a fifth schematic flowchart of an information exchange method according to an embodiment of the present invention. As shown in Figure 14, the information exchange method includes, but is not limited to, the following steps.

[0323] S501: The decoding device (e.g., base station) transmits a fifth piece of information to the encoding device (e.g., UE), where the fifth piece of information instructs the encoding device to transmit feedback information and then receive the first piece of information with a delay of feedback period k, where k is equal to 1.

[0324] In response, the encoding device (e.g., UE) receives the fifth piece of information.

[0325] Optionally, the fifth piece of information includes the number of delayed feedback periods k, where k is a positive integer. Alternatively, the fifth piece of information includes the delay, where the unit of delay is a time unit such as seconds, microseconds, milliseconds, or nanoseconds, and k =

number

number

[0326] In an optional embodiment, the number of delayed feedback periods k or the delay can be predetermined. In this case, step S501 may not exist. In other words, the information exchange method in this embodiment of the present application may not include step S501.

[0327] S502: The decoding device (e.g., base station) transmits a fourth piece of information to the encoding device (e.g., UE) before the tth feedback period, instructing the encoding device to store the state information acquired in the feedback period prior to the tth feedback period, where t is a positive integer.

[0328] Accordingly, the encoding device (e.g., UE) receives the fourth piece of information during the tth feedback period.

[0329] S503: The encoding device (e.g., UE) stores the state information acquired by the encoding device during the feedback period preceding the t-th feedback period, based on the instructions of the fourth piece of information.

[0330] In some scenarios, when the decoder recognizes that the channel quality does not meet a predetermined condition, it indicates that the channel quality is low. The decoder may transmit a fourth piece of information to the encoder before the tth feedback period (or the tth feedback), instructing the encoder to store the state information obtained in the feedback period before the tth feedback period (or the feedback before the tth feedback). Alternatively, in some scenarios, upon successful feedback, the decoder (e.g., base station) transmits a fourth piece of information to the encoder (e.g., UE) before the tth feedback period (or the tth feedback), instructing the encoder to store the state information obtained in the feedback period before the tth feedback period (or the feedback before the tth feedback). After receiving the fourth piece of information in the tth feedback period, the encoder may, based on the instructions of the fourth piece of information, store the state information obtained by the encoder in the feedback period before the tth feedback period (i.e., the (t-1)th feedback period or the (t-1)th feedback). In some possible implementations, the fourth piece of information may also instruct the encoding device to store historical state information output by the encoder at a specific time. Naturally, after receiving the fourth piece of information, the encoding device will, in response, store the historical state information output by the encoder at that specific time. For example, the decoding device may perform uplink channel estimation to obtain the received signal-to-noise ratio and then determine the probability of successfully receiving feedback information based on the received signal-to-noise ratio. If the probability of successfully receiving feedback information is less than a preset threshold, it indicates that the channel quality is low or the probability of the next feedback failure is high, and the decoding device may transmit the fourth piece of information to the encoding device. Naturally, in addition to the received signal-to-noise ratio, the channel quality may be determined in other ways not listed one by one in this embodiment of the present application.

[0331] For example, the decoding device receives feedback information c of the (t-1)th feedback. t-1 If, after receiving, the decoder recognizes that the channel quality is low, it may send the fourth piece of information to the encoder before the tth feedback (or the tth feedback period), and as a result, the encoder can receive the fourth piece of information during the tth feedback (or the tth feedback period). After receiving the fourth piece of information, the encoder, based on the instructions of the fourth piece of information, receives the state information e that was previously (i.e., the (t-1)th time) acquired by the encoder. t-1 It can be stored for subsequent use.

[0332] Optionally, after the decoder transmits the fourth piece of information to the encoder, the decoder may also store the corresponding state information. For example, the decoder may store the state information obtained by the decoder in the feedback period prior to the tth feedback period (i.e., the (t-1)th feedback period), or it may store the historical state information output by the decoder at a specific time. For example, the decoder transmits the fourth piece of information to the encoder before the tth feedback (or the tth feedback period), and then stores the state information d obtained previously (i.e., the (t-1)th time). t-1 Store it for future use.

[0333] S504: The encoding device (e.g., UE) receives the second feedback information c t This is transmitted to a decoding device (e.g., a base station), where the second feedback information c t This is the second channel information H t , and the state information e previously acquired by the encoding device t-1 This is feedback information output after the data has been input to the encoder for processing.

[0334] For the implementation of step S504 in this embodiment of the present application, please refer to the implementation of step S202 in Embodiment 2. Further details will not be explained here.

[0335] S505: The decoding device (e.g., base station) transmits first information to the encoding device (e.g., UE), where the first information is the encoding device's historical status information e his This is for the purpose of making a decision.

[0336] In response, the encoding device (e.g., UE) receives the first information, and the historical state information e his It is determined that this is state information stored after the fourth piece of information was received.

[0337] S506: The encoding device (e.g., UE) uses the first information to obtain the history status information of the encoding device e his and the first channel information H t+1 The first feedback information c is input to the encoder for processing. t+1 The history status information e is obtained here. his This is the first channel information H t+1 It reflects one or more historical channel information obtained before the current information is acquired.

[0338] Optionally, the encoding device receives second feedback information c t After sending the second feedback information c to the decoding device, the decoding device then receives the second feedback information c t Second feedback information c on the time-frequency resource t When it receives (or demodulates) the second feedback information c t This indicates that the transmission of the first information was successful. In this case, the decoding device may not transmit the second information c. t Second feedback information c on the time-frequency resource t If it is not received (or demodulated), it is the second feedback information c t This indicates that the transmission failed. In this case, the decoding device may send the first information to the encoding device. The first information is the encoding device's history status information e hisThe first information may be for determining the state information that is input to the encoder after the first information is received. The first information may also be second feedback information c t This may be intended to notify that transmission has failed, and the first information may further indicate a mismatch between the transmitting and receiving ends, or similar. In some scenarios, the second feedback information c t Even if the transmission of the first information is successful, the decoding device may send the first information to the encoding device, and as a result, the encoding device will roll back the state information. In other words, the rollback of the state information may be controllable by the decoding device. The decoding device may also send the first information when it tries to get the encoding device to perform a state information rollback, but it is not limited to sending the first information only when the transmission of the feedback information has failed.

[0339] The encoding device receives the first information during the (t+1)th feedback period (or after the tth feedback period). Optionally, after receiving the first information, the encoding device receives the history state information e his The encoding device determines that this is state information stored after receiving the fourth piece of information. The encoding device performs a channel measurement based on the received reference signal to obtain the first channel information H t+1 It is possible to obtain, and then, the history status information e his and the first channel information H t+1 The first feedback information c is input to the encoder for processing. t+1 Obtain the historical status information e. his This is the first channel information H t+1 It reflects one or more historical channel information acquired before it is acquired. Optionally, the encoding device may, after receiving the first information, acquire historical state information e without any operation or step determining that it is stored state information after the encoding device has received the fourth information. his The first channel information and state information stored after the encoding device receives the fourth information can be input to the encoder for processing.

[0340] For example, history status information e his This reflects the history channel information prior to the (t-1)th feedback. Optionally, the history state information e his and the first channel information H t+1 After the new state information e is input to the encoder for processing, t+1 (i.e., the first state information) is output again. New state information e t+1 (That is, the first state information) is the first channel information H t+1 It may reflect one or more historical channel information including new state information e. t+1 (That is, the first state information) is the first channel information H t+1 , and reflect the historical channel information prior to the (t-1)th feedback.

[0341] For example, see Figure 15. Figure 15 is a sixth schematic flowchart of the processing of the encoding and decoding devices according to an embodiment of the present invention. As shown in Figure 15, t is equal to 4. If the transmission of feedback information c3 is successful, the decoding device transmits the fourth information. After receiving the fourth information, the encoding device stores the state information e3 that was output by the encoder last time (i.e., the third time). In the fourth feedback period, the encoding device inputs the state information e3 that was output by the encoder last time and the second channel information H4 to the encoder for processing and outputs the second feedback information c4 and new state information e4 (i.e., the second state information). If the transmission of the second feedback information c4 fails, the decoding device transmits the first information. After receiving the first information, the encoding device stores the history state information e his The value of is determined to be the state information e3 that was stored after the fourth piece of information was last received. During the fifth feedback period, the encoding device determines the historical state information e his (=e3) and the first channel information H5 are input to the encoder for processing, and the first feedback information c5 and new state information e5 (i.e., the first state information) are output.

[0342] S507: The encoding device (e.g., UE) receives the first feedback information c t+1 This is transmitted to a decoding device (e.g., a base station), where the first feedback information c t+1 This is the first channel information H t+1 The encoded information or the predicted channel information includes encoded information.

[0343] Correspondingly, the decoding device (e.g., base station) receives the first feedback information c t+1 Receive.

[0344] For the implementation of step S507 in this embodiment of the present application, please refer to the implementation of step S205 in Embodiment 2. Further details will not be explained here.

[0345] Optionally, after step S507, the information exchange method may further include the following steps.

[0346] S508: The decoding device (e.g., base station) receives the first feedback information c t+1 and the history status information of the decoding device d his The third channel information H is input to the decoder for processing. t+1 ' is obtained, and here the history status information d his This is the first feedback information c t+1 Reflects one or more historical feedback pieces of information obtained before the current data was acquired.

[0347] Optionally, the decoding process of the decoding device (e.g., step S508) may be the reverse process of the encoding process of the encoding device (e.g., step S506). Specifically, the second feedback information c t If the transmission fails, the decoding device will output the state information d from the decoder on the tth time. t It does not store the first feedback information c. t+1 After receiving the historical status information d his It can be determined that this is state information stored after the previous successful transmission (or the previous transmission of the fourth piece of information), and that the historical state information dhis and the first feedback information received c t+1 The third channel information H is input to the decoder for processing. t+1 ' can be obtained. Optionally, the decoder can also obtain history state information d his Without any operation or step to determine the first feedback information c t+1 After receiving the first information, the state information stored after the decoding device transmits the fourth information, and the first feedback information c t+1 This can then be input to the decoder for processing.

[0348] For example, history status information d his This is the first feedback information c t+1 It reflects one or more historical feedback pieces of information obtained before it was obtained. Optionally, it reflects historical status information d his and first feedback information c t+1 After the data is input to the decoder for processing, new state information d t+1 (i.e., a third state information) is output. New state information d t+1 (That is, the third state information) is the first feedback information c t+1 It may reflect one or more historical feedback pieces of information, including the following.

[0349] For example, as shown in Figure 15, t is equal to 4, and the transmission of feedback information c3 is successful. After the decoding device sends the fourth piece of information to the encoding device, the decoding device stores the state information d3 output by the decoder on the third attempt. If the transmission of the second piece of feedback information c4 fails, the decoding device does not store the state information d4 output by the decoder on the fourth attempt. For the fifth piece of feedback, after receiving the first piece of feedback information c5, the decoding device stores the historical state information d his It is determined that this is the state information d3 stored after the previous successful transmission (i.e., the successful transmission of feedback information c3), and then the historical state information d his(=d3) and the first feedback information c5 are input to the decoder for processing, and the third channel information H5' and the new state information d5 (i.e., the third state information) are output.

[0350] In an ideal case, the decoder receives the first channel information H processed by the encoder. t+1 It can be understood that it can be completely restored. In this case, the first feedback information c t+1 and historical status information d his Third channel information H recovered by the decoder based on t+1 ' is the first channel information H input by the encoder. t+1 It is identical to, or the first channel information H t+1 This is identical to the channel information predicted by the encoder based on the first channel information H processed by the encoder. However, in actual application, the decoder uses the first channel information H processed by the encoder. t+1 It is not possible to fully restore it. Therefore, in actual application, the third channel information H t+1 ', and the first channel information H input by the encoder t+1 This has certain (or slight) differences, or third channel information H t+1 ', and the first channel information H t+1 The channel information predicted by the encoder based on this has certain (or slight) differences. In some scenarios, these differences can be ignored.

[0351] In this embodiment of the present invention, the encoding device stores state information at a specific point in time based on instructions from the decoding device. As a result, the encoding device can roll back the state information when it fails to transmit feedback information, and further reduces the complexity of the encoding device's operation. In addition, the encoding device determines historical state information based on instructions from the decoding device. In this way, for the same feedback, the state information input by the encoder can be consistent with the state information input by the decoder, thereby improving the decoding performance on the base station side (or decoder), reducing communication performance loss, and improving communication quality. Embodiment 6

[0352] Embodiment 6 of the present invention mainly describes a case in which, when k is greater than 1, an encoding device (e.g., a UE) stores state information at a specific point in time based on instructions from a decoding device (e.g., a base station), and as a result, the encoding device performs a state information rollback based on instructions from the decoding device.

[0353] Please refer to Figure 16. Figure 16 is a sixth schematic flowchart of an information exchange method according to an embodiment of the present invention. As shown in Figure 16, the information exchange method includes, but is not limited to, the following steps.

[0354] S601: The decoding device (e.g., base station) transmits a fifth piece of information to the encoding device (e.g., UE), which instructs the encoding device to receive the first piece of information after transmitting the feedback information, with a delay of k feedback period. k is an integer greater than 1.

[0355] For the implementation of step S601 in this embodiment of the present application, please refer to the implementation of step S301 in Embodiment 3. Further details will not be explained here.

[0356] S602: The encoding device (e.g., UE) receives the second feedback information c t-1 This is transmitted to a decoding device (e.g., a base station), where the second feedback information c t-1 This is the second channel information H t-1 , and the state information e previously acquired by the encoding device t-2 This is feedback information output after the data has been input to the encoder for processing.

[0357] For the implementation of step S602 in this embodiment of the present application, please refer to the implementation of step S202 in Embodiment 2. Further details will not be explained here.

[0358] S603: The decoding device (e.g., base station) transmits a fourth piece of information to the encoding device (e.g., UE) before the tth feedback period, instructing the encoding device to store the state information acquired during the feedback period prior to the tth feedback period.

[0359] In response, the encoding device (e.g., UE) receives the fourth piece of information.

[0360] S604: Based on the instructions of the fourth information, the encoding device (e.g., UE) uses the state information e acquired by the encoding device in the feedback period preceding the tth feedback period. t-1 Temporarily store this information.

[0361] In some scenarios, when the decoder recognizes that the channel quality does not meet a predetermined condition, it indicates that the channel quality is low. The decoder may send a fourth piece of information to the encoder before the tth feedback period (or the tth feedback) to instruct the encoder to store the state information acquired in the feedback period before the tth feedback period (or the feedback before the tth feedback). Alternatively, in some scenarios, when the feedback is successful, the decoder (e.g., base station) sends a fourth piece of information to the encoder (e.g., UE) before the tth feedback period (or the tth feedback) to instruct the encoder to store the state information acquired in the feedback period before the tth feedback period (or the feedback before the tth feedback). After receiving the fourth piece of information in the tth feedback period, the encoder, based on the instructions of the fourth piece of information, stores the state information acquired by the encoder in the feedback period before the tth feedback period (i.e., the (t-1)th feedback period or the (t-1)th feedback). t-1This can be temporarily stored. For example, the decoder may perform uplink channel estimation to obtain the received signal-to-noise ratio, and then, based on the received signal-to-noise ratio, determine the probability of successfully receiving feedback information. If the probability of successfully receiving feedback information is less than a preset threshold, it indicates that the channel quality is low or the probability of the next feedback failure is high, and the decoder may transmit fourth information to the encoder. Of course, in addition to the received signal-to-noise ratio, the channel quality can be determined in other ways that are not individually listed in this embodiment of the present application.

[0362] For example, the encoding device receives second feedback information c t-1 If, after transmitting to the decoder, the decoder recognizes that the channel quality is low, the decoder may transmit the fourth piece of information to the encoder before the tth feedback (or the tth feedback period), and as a result, the encoder can receive the fourth piece of information during the tth feedback (or the tth feedback period). After receiving the fourth piece of information, the encoder, based on the instructions of the fourth piece of information, receives the state information e that was previously (i.e., the (t-1)th time) acquired by the encoder. t-1 It can be temporarily stored for subsequent use.

[0363] Optionally, during the tth feedback (or tth feedback period), the encoding device processes channel information H t , and the state information e previously acquired by the encoding device t-1 This is input to the encoder for processing, and feedback information c t and new status information e t The encoding device outputs further feedback information c. t This can be transmitted to the decoding device.

[0364] S605: The decoding device (e.g., base station) transmits third information to the encoding device (e.g., UE), where the third information instructs the encoding device to store state information that was temporarily stored after the fourth information was received, or the third information instructs the encoding device to store state information that was stored when the previous third information was received.

[0365] In response, the encoding device (e.g., UE) receives the third piece of information.

[0366] S606: The encoding device (e.g., UE) stores the corresponding state information based on the instructions of the third piece of information.

[0367] Optionally, the encoding device receives second feedback information c t-1 After transmitting to the decoding device, during the (t+k-1)th feedback period, the decoding device may transmit the third information to the encoding device, and the encoding device stores the corresponding state information based on the instructions of the third information. For example, if the encoding device receives the third information during the (t+k-1)th feedback period and the value of the third information is the first value, the encoding device stores the state information that was stored when the previous third information was received, that is, the encoding device stores the previously stored (temporarily unstored) state information again. Optionally, the state information e temporarily stored in step S604 t-1 This may be further deleted. If the value of the third piece of information is the second value, the encoding device stores the state information temporarily stored after the fourth piece of information is received, i.e., the state information temporarily stored after the fourth piece of information is received in the tth feedback period e t-1 The first value is 0 and the second value is 1; or the first value is 1 and the second value is 0. This is not limited to the present embodiment of the present application. For example, the second feedback information c t-1 If the transmission is successful, the third piece of information is set to the second value; or the second feedback information c t-1 If the transmission fails, the third piece of information is set to the first value.

[0368] For example, k is equal to 2. The encoding device receives the second feedback information c during the (t-1)th feedback period. t-1 The decoder transmits the fourth piece of information to the encoder before the tth feedback period, and after the encoder receives the fourth piece of information, it transmits the previously acquired state information e t-1 The second feedback information c is temporarily stored. During the (t+1)th feedback period, the decoding device transmits the third piece of information to the encoding device. t-1 If the transmission of the third information fails, the third information is set to the first value. After receiving the third information, the encoding device stores the previously stored (not temporarily stored) state information, and in the tth feedback period, the state information e temporarily stored by the encoding device t-1 This may be deleted. Second feedback information c t-1 If the transmission is successful, the third piece of information is set to the second value. After receiving the third piece of information, the encoding device stores the state information that was temporarily stored after the fourth piece of information was received, i.e., the state information e t-1 Remember this.

[0369] Optionally, after the decoding device transmits the fourth piece of information to the encoding device, the decoding device also transmits the state information d obtained previously (i.e., the (t-1)th time). t-1 This can be temporarily stored for subsequent use. Second feedback information c t-1 If the transmission is successful, during the (t+k-1)th feedback period, the decoder sends the third piece of information (whose value is the second value) to the encoder, and then temporarily stores the state information d t-1 It can remember the second feedback information c. t-1 If the transmission fails, during the (t+k-1)th feedback period, the decoder stores the state information that was stored when the previous third piece of information was transmitted, after the decoder has sent the third piece of information (whose value is the first value) to the encoder; that is, the decoder stores the previously stored (temporarily unstored) state information again.

[0370] S607: The decoding device (e.g., base station) transmits first information to the encoding device (e.g., UE), where the first information is the historical state information e of the encoding device (e.g., UE). his This is for the purpose of making a decision.

[0371] In response, the encoding device (e.g., UE) receives the first information, and the historical state information e his It is determined that this is state information stored after the third piece of information was received.

[0372] S608: The encoding device (e.g., UE) receives the historical status information of the encoding device e based on the first information. his and the first channel information H t+k-1 The first feedback information c is input to the encoder for processing. t+k-1 The history status information e is obtained here. his This is the first channel information H t+k-1 It reflects one or more historical channel information obtained before the current information is acquired.

[0373] Optionally, the encoding device receives second feedback information c t-1 After sending the second feedback information c to the decoding device, the decoding device then receives the second feedback information c t-1 Second feedback information c on the time-frequency resource t-1 When it receives (or demodulates) the second feedback information c t-1 This indicates that the transmission of the first information was successful. In this case, the decoding device may not transmit the second feedback information c t-1 , and the state information d previously acquired by the decoding device t-2 The channel information H is input to the decoder for processing. t-1 ' can be obtained. In this case, during the (t+k-1)th feedback period (or (t+k-1)th feedback), the encoding device obtains the first channel information H t+k-1 , and state information e acquired by the encoding device in the previous instance (i.e., the (t+k-2)th instance) t+k-2The first feedback information c is input to the encoder for processing. t+k-1 and new status information e t+k-1 The decoder obtains the first feedback information c. t+k-1 After receiving the first feedback information c t+k-1 , and state information d acquired by the decoding device in the previous instance (i.e., the (t+k-2)th instance) t+k-2 The third channel information H is input to the decoder for processing. t+k-1 'and new status information d t+k-1 Obtain it.

[0374] The decoding device receives the second feedback information c t-1 Second feedback information c on the time-frequency resource t-1 If it is not received (or demodulated), it is the second feedback information c t-1 This indicates that the transmission of the first information failed. In this case, the decoding device may send the first information to the encoding device. Naturally, the second feedback information c t-1 If the transmission fails, from step S601 above, it can be seen that the encoding device can receive the first information delivered by the decoding device at the latest, with a delay of the feedback period k. Therefore, the decoding device must send the first information to the encoding device before the (t+k-1)th feedback period, and as a result, the encoding device can receive the first information in the (t+k-1)th feedback period (or the (t+k-1)th feedback). The first information is the encoding device's historical state information e his The first information may be for determining the state information that is input to the encoder after the first information is received. The first information may also be second feedback information c t-1 This may be intended to notify that transmission has failed, and the first information may further indicate a mismatch between the transmitting and receiving ends, or similar. In some scenarios, the second feedback information c t-1Even if the transmission of the first information is successful, the decoding device may send the first information to the encoding device, and as a result, the encoding device will roll back the state information. In other words, the rollback of the state information may be controllable by the decoding device. The decoding device may also send the first information when it tries to get the encoding device to perform a state information rollback, but it is not limited to sending the first information only when the transmission of the feedback information has failed.

[0375] The encoding device receives the first information during the (t+k-1)th feedback period (or after the (t+k-2)th feedback period). After receiving the first information, the encoding device receives the history state information e his It is determined that the third piece of information is state information stored after the third piece of information is received. The encoding device performs a channel measurement based on the received reference signal to obtain the first channel information H t+k-1 It is possible to obtain, and then, the history status information e his and the first channel information H t+k-1 The first feedback information c is input to the encoder for processing. t+k-1 It is possible to obtain the following: History status information e his This is the first channel information H t+k-1 It reflects one or more historical channel information obtained before it is obtained. Optionally, historical status information e his and the first channel information H t+k-1 After the new state information e is input to the encoder for processing, t+k (i.e., the first state information) is output again. New state information e t+k (That is, the first state information) is the first channel information H t+k-1 It may reflect one or more historical channel information, including [specific information].

[0376] For example, k is equal to 2. See Figure 17. Figure 17 is a seventh schematic flowchart of the processing of the encoding and decoding devices according to an embodiment of the present invention. As shown in Figure 17, t is equal to 3. The encoding device receives the fourth information in the third feedback period and temporarily stores the previously acquired state information e2. Next, the encoding device inputs the channel information H3 and the state information e2 acquired by the encoding device in the third feedback period (or third feedback) to the encoder for processing and outputs the feedback information c3 and the new state information e3. In the fourth feedback period (or fourth feedback), the encoding device receives the third information. If the value of the third information is the second value, the encoding device stores the state information e2 temporarily stored in the third feedback period. If the value of the third information is the first value, the encoding device deletes the state information e2 temporarily stored in the third feedback period and stores the state information stored when the previous third information was received. If, during the fourth feedback period (or fourth feedback), the encoding device receives the first information after receiving the third information (indicating that the transmission of the second feedback information c2 failed), the encoding device receives the history status information e his It can be determined that the third piece of information is state information stored after the third piece of information has been received. Next, the encoding device receives the first channel information H4 and the history state information e his The first feedback information c4 and the new state information e4 (i.e., the first state information) are input to the encoder for processing. If the transmission of the second feedback information c2 is successful, the encoder does not receive the first information during the fourth feedback period (or fourth feedback), and the encoder inputs the first channel information H4 and the state information e3 previously acquired by the encoder to the encoder for processing, and may output the first feedback information c4 and the new state information e4.

[0377] In several possible implementations, the third piece of information and the first piece of information may be the same piece of information, or they may, of course, be different pieces of information. When the third piece of information is different from the first piece of information, the third piece of information and the first piece of information may be carried in one signaling or in different signaling. When the third piece of information and the first piece of information are the same piece of information, the functions of the two pieces of information may be combined. In other words, one piece of information not only instructs the encoding device to store state information, but also determines the history state information of the encoding device. Details are not explained here. In addition, when the third piece of information and the first piece of information are the same piece of information, the fifth piece of information (i.e., step S601) may not exist, or it may, of course, exist. When the fifth piece of information exists, one piece of information may be received with a delay of k feedback period, regardless of whether the feedback is successful or not (the information has the functions of both the third piece of information and the first piece of information).

[0378] S609: The encoding device (e.g., UE) receives the first feedback information c t+k-1 This is transmitted to a decoding device (e.g., a base station), where the first feedback information c t+k-1 This is the first channel information H t+k-1 The encoded information or the predicted channel information includes encoded information.

[0379] Correspondingly, the decoding device (e.g., base station) receives the first feedback information c t+k-1 Receive.

[0380] For the implementation of step S609 in this embodiment of the present application, please refer to the implementation of step S205 in Embodiment 2. Further details will not be explained here.

[0381] Optionally, after step S609, the information exchange method further comprises the following steps.

[0382] S610: The decoding device (e.g., base station) receives the first feedback information c t+k-1 and the history status information of the decoding device dhis The third channel information H is input to the decoder for processing. t+k-1 ' is obtained, and here the history status information d his This is the first feedback information c t+k-1 Reflects one or more historical feedback pieces of information obtained before the current data was acquired.

[0383] Optionally, the decoding process of the decoding device (e.g., step S610) may be the reverse process of the encoding process of the encoding device (e.g., step S608). Specifically, the second feedback information c t-1 If transmission fails, the decoder will send historical state information d for the (t+k-1)th feedback. his It can be determined that the third piece of information is state information stored after the third piece of information has been transmitted. The decoding device then receives the first feedback information c t+k-1 After receiving the historical status information d his and first feedback information c t+k-1 The third channel information H is input to the decoder for processing. t+k-1 ' can be obtained. Optionally, the decoder can also obtain history state information d his Without any operation or step to determine the first feedback information c t+k-1 After receiving the first feedback information c, the state information stored after the decoding device transmits the third information is also stored. t+k-1 This can then be input to the decoder for processing.

[0384] For example, history status information d his This is the first feedback information c t+k-1 It reflects one or more historical feedback pieces of information obtained before it was obtained. Optionally, it reflects historical status information d his and first feedback information c t+k-1 After the data is input to the decoder for processing, new state information d t+k-1 (i.e., a third state information) is output. New state information d t+k-1 (That is, the third state information) is the first feedback information c t+k-1It may reflect one or more historical feedback pieces of information, including the following.

[0385] For example, as shown in Figure 17, k is equal to 2 and t is equal to 3. In the third feedback period, the decoder transmits the fourth piece of information to the encoder and temporarily stores the state information d2 acquired in the previous (i.e., second) instance for subsequent use. In the fourth feedback period (or fourth feedback), the decoder transmits the third piece of information to the encoder. If the transmission of the second piece of feedback c2 is successful, the third piece of information is set to the second value, and the state information d2 temporarily stored by the decoder in the third feedback period may be stored. If the transmission of the second piece of feedback c2 fails, the third piece of information is set to the first value. In this case, the decoder deletes the state information d2 temporarily stored in the third feedback period and may store the state information stored when the previous piece of third information was transmitted. In addition, if the transmission of the second piece of feedback c2 fails, the decoder further delivers the first piece of information to the encoder in the fourth feedback period (or fourth feedback). Next, regarding the fourth feedback, the decoding device receives the history state information d his It is determined that the third piece of information is state information stored after the transmission of the third piece of information, and the received first feedback information c4 and history state information d his The data is input to the decoder for processing, and the third channel information H4' and new state information d4 (i.e., the third state information) are output.

[0386] In an ideal case, the decoder receives the first channel information H processed by the encoder. t+k-1 It can be understood that it can be completely restored. In this case, the first feedback information c t+k-1 and historical status information d his Third channel information H recovered by the decoder based on t+k-1 ' is the first channel information H input by the encoder. t+k-1 It is identical to, or the first channel information H t+k-1This is identical to the channel information predicted by the encoder based on the first channel information H processed by the encoder. However, in actual application, the decoder uses the first channel information H processed by the encoder. t+k-1 It is not possible to fully restore it. Therefore, in actual application, the third channel information H t+k-1 ', and the first channel information H input by the encoder t+k-1 This has certain (or slight) differences, or third channel information H t+k-1 ', and the first channel information H t+k-1 The channel information predicted by the encoder based on this has certain (or slight) differences. In some scenarios, these differences can be ignored.

[0387] The encoding device in this embodiment of the present application stores state information at a specific point in time based on instructions from the decoding device. As a result, the encoding device can roll back the state information when it fails to transmit feedback information, and further reduces the complexity of the encoding device's operation. Furthermore, the encoding device in this embodiment of the present application can temporarily store the state information, and as a result can handle the impact of delays in the decoding device's detection and distribution of the first information on the state information rollback. In addition, the encoding device further determines, based on instructions from the decoding device, whether to use the historical state information as input to the encoder. In this way, for the same feedback, the state information input by the encoder can be consistent with the state information input by the decoder, thereby improving the decoding performance on the base station side (or decoder), reducing communication performance loss, and improving communication quality.

[0388] The above description details the method provided in this application. To facilitate the implementation of the above solution in the embodiments of this application, embodiments of this application further provide corresponding apparatus or devices.

[0389] In this application, the encoding and decoding devices are divided into functional modules based on embodiments of the method described above. For example, functional modules may be obtained through divisions corresponding to various functions, or two or more functions may be integrated into a single processing module. The integrated module may be implemented in hardware form or in the form of a software functional module. Note that in this application, the module division is merely an example and is only a logical functional division. In actual implementations, other division methods may be used. The encoding and decoding devices in embodiments of this application will be described in detail below with reference to Figures 18 to 20.

[0390] Please refer to Figure 18. Figure 18 is a diagram showing the structure of an encoding or decoding device according to an embodiment of the present invention. As shown in Figure 18, the encoding or decoding device may include a transceiver unit 10 and a processing unit 20.

[0391] In some embodiments of the present application, Figure 18 is a diagram of the structure of an encoding device. The encoding device may be a UE or a chip or circuit located in the UE. The encoding device may be configured to perform steps, functions or similar that are performed by the encoding device in the embodiments of the method described above.

[0392] The transceiver unit 10 is configured to receive first information transmitted by the decoding device, where the first information is the history state information e of the encoding device. his This is for determining the history state information of the encoding device e based on the first information. his And the first channel information is input to the encoder for processing and configured to obtain the first feedback information, where the historical state information e his This reflects one or more historical channel information acquired before the first channel information is acquired. The transceiver unit 10 is further configured to transmit first feedback information to a decoding device, where the first feedback information includes encoded information of the first channel information or encoded information of the predicted channel information.

[0393] For example, the first state information is the history state information e his The first channel information can be obtained by inputting it into an encoder for processing. The first state information may reflect one or more historical channel information, including the first channel information.

[0394] For example, the transceiver unit 10 is further configured to transmit a second feedback information to the decoding device, where the second feedback information is a second channel information and a state information e t-1 This is feedback information output after the data has been input to the encoder for processing, and it is state information e t-1 This reflects one or more historical channel information acquired before the second channel information is acquired.

[0395] For example, the transceiver unit 10 is further configured to receive second information transmitted by the decoding device, where the second information indicates one or more of the following: whether the encoding device performs periodic storage, the storage period, or the start time of the storage period. The processing unit 20 is further configured to periodically store state information output by the encoder based on the instructions of the second information received by the transceiver unit 10.

[0396] For example, the processing unit 20 specifically receives state information e acquired by the encoding device during the (n(T / S)-k)th feedback period. n(T / S)-k It is configured to temporarily store the state information. The transceiver unit 10 is further configured to receive a third piece of information transmitted by the decoder during the (n(T / S))th feedback period, where the third piece of information instructs it to store the state information stored during the ((n-1)*(T / S))th feedback period, or the third piece of information is the state information e acquired during the (n(T / S)-k)th feedback period. n(T / S)-kThe processing unit 20 is instructed to store the following. The processing unit 20 is further configured to store the corresponding state information based on the instruction of the third information received by the transceiver unit 10. For example, the processing unit 20 specifically stores the state information stored in the ((n-1)*(T / S))th feedback period when the value of the third information is the first value, and when the value of the third information is the second value, the state information acquired in the (n(T / S)-k)th feedback period is stored in the (n(T / S))th feedback period. n(T / S)-k It is configured to store information.

[0397] n, k, S, and T are all positive integers, where T represents the memory period and S represents the feedback period. A memory period T of 1 is an integer multiple of a feedback period S of 1, and a feedback period of 1 is used to describe the transmission time interval between two adjacent feedback pieces of information.

[0398] For example, the processing unit 20 further provides history status information e his The encoding device is configured to determine that the first piece of information is state information stored in the previous memory cycle before it receives it.

[0399] For example, the transceiver unit 10 is further configured to receive a fourth piece of information transmitted by the decoding device during the tth feedback period, where the fourth piece of information instructs the encoding device to store state information acquired during the feedback period prior to the tth feedback period, where t is a positive integer. The processing unit 20 further, based on the instructions of the fourth piece of information received by the transceiver unit 10, stores state information e acquired by the encoding device during the feedback period prior to the tth feedback period. t-1 It is configured to store the history status information e. his This is state information e stored after the encoding device receives the fourth piece of information. t-1It is configured to determine that it is so.

[0400] For example, the transceiver unit 10 is further configured to receive a fourth piece of information transmitted by the decoding device during the tth feedback period, where the fourth piece of information instructs the encoding device to store state information acquired during the feedback period prior to the tth feedback period, where t is a positive integer. The processing unit 20 further, based on the instructions of the fourth piece of information received by the transceiver unit 10, stores state information e acquired by the encoding device during the feedback period prior to the tth feedback period. t-1 It is configured to temporarily store the following. The transceiver unit 10 is further configured to receive a third piece of information transmitted by the decoder during the (t+k-1)th feedback period, where the third piece of information is the state information e temporarily stored after the fourth piece of information was received during the tth feedback period. t-1 The encoding device is instructed to store the third piece of information, or the third piece of information is instructed to store the state information stored when the previous third piece of information was received, where k is a positive integer. The processing unit 20 is further configured to store the corresponding state information based on the instructions of the third piece of information received by the transceiver unit 10.

[0401] For example, the processing unit 20 further processes the history status information e his It is configured to determine that the third piece of information is state information that was stored after it was received.

[0402] For example, the processing unit 20 further provides history status information e his It is configured to update this with state information output by the encoder during the feedback period prior to the current time.

[0403] For example, the transceiver unit 10 is further configured to receive a fifth piece of information transmitted by the decoding device, the fifth piece of information instructing the encoding device to receive the first piece of information after transmitting the feedback information, with a delay of k feedback period, where k is a positive integer.

[0404] In this embodiment of the present application, the first information, the second information, the third information, the fourth information, the fifth information, and the history status information e his For details regarding the description of feedback information and similar information, please refer to the descriptions in the embodiments of the above method (including Figures 7, 8, 10, 12, 14, 16, or similar). Further details will not be explained here.

[0405] It should be understood that the specific descriptions of the transceiver unit and processing unit described in this embodiment of the present application are merely examples. For specific functions of the transceiver unit and processing unit, steps performed, or similar, please refer to the embodiments of the method described above. Further details will not be described here.

[0406] In some other embodiments of the present application, Figure 18 is a diagram of the structure of a decoding device. The decoding device may be a base station, or a chip or circuit located in a base station. The decoding device may be configured to perform steps, functions, or similar that are performed by the decoding device in the embodiments of the method described above.

[0407] The transceiver unit 10 is configured to transmit first information to the encoding device, where the first information is the history status information e of the encoding device. his This is for determining the following. The transceiver unit 10 is further configured to receive first feedback information transmitted by the encoding device, where the first feedback information is first channel information and history status information of the encoding device e his Determined based on, here is the history status information e hisThis reflects one or more historical channel information acquired before the first channel information was acquired, and the first feedback information includes encoded information of the first channel information or encoded information of the predicted channel information. The first feedback information and the historical state information d of the decoder. his These are input to the decoder for processing, and the third channel information is obtained, where the historical state information d his This reflects one or more historical feedback pieces of information obtained before the first feedback piece was acquired.

[0408] For example, the processing unit 20 receives first feedback information and history status information d of the decoding device. his The data is input to a decoder for processing and configured to obtain third channel information, where the historical state information d his This reflects one or more historical feedback pieces of information obtained before the first feedback piece was acquired.

[0409] For example, the first feedback information and the history status information d of the decoding device his This is input to the decoder for processing, and a third state information is obtained, where the third state information reflects one or more historical feedback pieces of information, including the first feedback information.

[0410] For example, the transceiver unit 10 is further configured to transmit a second piece of information to the encoding device, where the second piece of information indicates whether the encoding device performs periodic storage, the storage period, or one or more of the start time of the storage period. The processing unit 20 is further configured to periodically store state information output by the decoder based on the storage period and / or the start time of the storage period.

[0411] For example, the processing unit 20 specifically receives state information d acquired by the decoder during the (n(T / S)-k)th feedback period. n(T / S)-kThe transceiver unit 10 is configured to temporarily store the state information. The transceiver unit 10 is further configured to transmit a third piece of information to the encoding device before the (n(T / S))th feedback period, where the third piece of information instructs the encoding device to store the state information stored during the ((n-1)*(T / S))th feedback period, or the third piece of information is the state information d acquired during the (n(T / S)-k)th feedback period. n(T / S)-k The encoding device is instructed to store the following. The processing unit 20 further stores the state information stored by the decoding device during the ((n-1)*(T / S))th feedback period, or the state information d acquired by the decoding device during the (n(T / S)-k)th feedback period, based on the third information. n(T / S)-k It is configured to store information.

[0412] n, k, S, and T are all positive integers. T represents the memory period, and S represents the feedback period. A memory period T of 1 is an integer multiple of a feedback period S of 1, and a feedback period of 1 is used to describe the transmission time interval between two adjacent feedback pieces of information.

[0413] For example, the processing unit 20 further processes the history status information d his The decoding device is configured to determine that the first information is state information stored in the previous memory cycle before transmitting it.

[0414] For example, the transceiver unit 10 is further configured to transmit a fourth piece of information to the encoding device before the tth feedback period, where the fourth piece of information instructs the encoding device to store the state information acquired in the feedback period before the tth feedback period, where t is a positive integer. The processing unit 20 further transmits the state information d acquired by the decoding device in the feedback period before the tth feedback period. t-1 It is configured to store the history state information d. The processing unit 20 further stores the history state information d hisThis is the state information d stored after the decoding device transmits the fourth piece of information. t-1 It is configured to determine that it is so.

[0415] For example, the transceiver unit 10 is further configured to transmit a fourth piece of information to the encoding device before the tth feedback period, where the fourth piece of information instructs the encoding device to store the state information acquired in the feedback period before the tth feedback period, where t is a positive integer. The processing unit 20 further transmits the state information d acquired by the decoding device in the feedback period before the tth feedback period. t-1 The transceiver unit 10 is configured to temporarily store the state information e that was temporarily stored after the fourth information was received during the tth feedback period. t-1 The encoding device is instructed to store the state information stored when the previous third information was received, where k is a positive integer. The processing unit 20 further stores the state information d temporarily stored after the decoding device has transmitted the fourth information, based on the third information. t-1 It is configured to store the previous third piece of information, or to store the state information that was stored when the decoding device transmitted the previous third piece of information.

[0416] For example, the processing unit 20 further processes the history status information d his It is configured to determine that the third piece of information is state information stored after it has been transmitted.

[0417] For example, the processing unit 20 further includes history status information d his It is configured to update the state information output by the decoder during the feedback period prior to the current time.

[0418] For example, the transceiver unit 10 is further configured to transmit fifth information to the encoding device, where the fifth information instructs the encoding device to receive the first information with a delay of k feedback periods after transmitting the feedback information, where k is a positive integer.

[0419] In the present embodiment of the present application, the first information, the second information, the third information, the fourth information, the fifth information, the history state information e his , the history state information d his For the descriptions of the feedback information and the like, reference may be made to the descriptions in the embodiments of the above method (including FIGS. 7, 8, 10, 12, 14, 16, or the like). Details will not be described again here.

[0420] It can be understood that the specific descriptions of the transceiver unit and the processing unit described in the present embodiment of the present application are merely examples. For the specific functions, executed steps or the like of the transceiver unit and the processing unit, reference may be made to the embodiments of the above method. Details will not be described again here.

[0421] Above, the encoding device and the decoding device in the embodiments of the present application are described. Below, possible product forms of the encoding device and the decoding device will be described. Any form of a product having the functions of the encoding device or the decoding device described in FIG. 18 should be understood to be included in the protection scope of the embodiments of the present application. It should be further understood that the following description is merely an example and does not limit the product forms of the encoding device and the decoding device in the embodiments of the present application.

[0422] In a possible implementation, in the encoding or decoding device shown in Figure 18, the processing unit 20 may be one or more processors, the transceiver unit 10 may be a transceiver, or the transceiver unit 10 may be a transmitting unit and a receiving unit. The transmitting unit may be a transmitter, and the receiving unit may be a receiver. The transmitting unit and the receiving unit are integrated into a single component, for example, a transceiver. In embodiments of the present application, the processor and the transceiver may be coupled, or similar arrangements may be made. The connection method between the processor and the transceiver is not limited to embodiments of the present application. In the process of performing the above method, the process of transmitting information in the above method may be understood as the process of outputting information by the processor. When outputting information, the processor outputs the information to the transceiver, and as a result, the transceiver transmits the information. After the information has been output by the processor, further processing may need to be performed on the information before the information reaches the transceiver. Similarly, the process of receiving information in the above method may be understood as the process of receiving input information by the processor. When the processor receives input information, the transceiver receives the information and inputs it to the processor. Furthermore, after the transceiver receives the information, other processing may need to be performed on the information before it is input to the processor.

[0423] Please refer to Figure 19. Figure 19 is a diagram of the structure of a communication device according to an embodiment of the present invention. The communication device may be an encoding device or a decoding device. Figure 19 shows only the main components of the communication device. In addition to the processor 1001 and transceiver 1002, the communication device may further include a memory 1003 and an input / output device (not shown in this figure).

[0424] The processor 1001 is primarily configured to process communication protocols and data, control the entire communication device, execute software programs, and process data within the software programs. The memory 1003 is primarily configured to store software programs and data. The transceiver 1002 may include a control circuit and an antenna. The control circuit is primarily configured to perform conversions between baseband signals and radio frequency signals and to process radio frequency signals. The antenna is primarily configured to receive / transmit radio frequency signals in the form of electromagnetic waves. Input / output devices, such as touchscreens, displays, or keyboards, are primarily configured to receive data entered by the user and output data to the user.

[0425] After the communication device is powered on, the processor 1001 can read the software program in the memory 1003, interpret and execute the instructions of the software program, and process the data of the software program. When data needs to be transmitted wirelessly, the processor 1001 performs baseband processing on the data to be transmitted and outputs a baseband signal to the radio frequency circuit. The radio frequency circuit performs radio frequency processing on the baseband signal and then transmits the radio frequency signal to the outside in the form of electromagnetic waves through the antenna. When data is transmitted to the communication device, the radio frequency circuit receives the radio frequency signal through the antenna, converts the radio frequency signal to a baseband signal, and outputs the baseband signal to the processor 1001. The processor 1001 converts the baseband signal into data and processes this data.

[0426] In an alternative implementation, the radio frequency circuitry and antennas may be located independently of the processor performing baseband processing. For example, in a distributed scenario, the radio frequency circuitry and antennas may be located remotely and independently of the communication equipment.

[0427] The transceiver 1002 may include a receiver and a transmitter. The receiver is configured to perform a receiving function (or operation), and the transmitter is configured to perform a transmitting function (or operation). In addition, the transceiver is configured to communicate with another device / device through a transmission medium.

[0428] The processor 1001, transceiver 1002, and memory 1003 can be connected via a communication bus.

[0429] For example, when a communication device is configured to perform steps, methods, or functions performed by an encoding device, the transceiver 1002 is configured to receive first information transmitted by a decoding device, where the first information is the history status information e of the encoding device. his This is for determining the history state information of the encoding device e based on the first information. his And the first channel information is input to the encoder for processing and configured to obtain the first feedback information, where the historical state information e his This reflects one or more historical channel information acquired before the first channel information is acquired. The transceiver 1002 is further configured to transmit first feedback information to a decoding device, where the first feedback information includes encoded information of the first channel information or encoded information of the predicted channel information.

[0430] For example, when a communication device is configured to perform steps, methods, or functions performed by a decoding device, the transceiver 1002 is configured to transmit first information to an encoding device, where the first information is the history status information e of the encoding device. his This is for determining the following. The transceiver 1002 is further configured to receive first feedback information transmitted by the encoding device, where the first feedback information is first channel information and history status information of the encoding device e his Determined based on, here is the history status information e hisreflects one or more pieces of historical channel information obtained before the first channel information is obtained, and the first feedback information includes encoded information of the first channel information or encoded information of predicted channel information. The first feedback information and the historical state information d of the decoding device his are both input to the decoder for processing, and the third channel information is obtained. Here, the historical state information d his reflects one or more pieces of historical feedback information obtained before the first feedback information is obtained.

[0431] Optionally, the processor 1001 is configured to input the first feedback information and the historical state information d of the decoding device his to the decoder for processing to obtain the third channel information. Here, the historical state information d his reflects one or more pieces of historical feedback information obtained before the first feedback information is obtained.

[0432] In the present embodiment of the present application, for the description of the first information, the historical state information e his , the historical state information d his , the feedback information, the encoding device, the decoding device, and the like, please refer to the description in the embodiments of the above method (including FIGS. 7, 8, 10, 12, 14, 16, or the like). Details will not be described again here. For the specific description of the processor and the transceiver, it can be understood that reference should be made to the description of the processing unit and the transceiver unit shown in FIG. 18. Details will not be described again here.

[0433] Optionally, the processor 1001 may include a transceiver configured to implement receive and transmit functions. For example, the transceiver may be a transceiver circuit, an interface, or an interface circuit. The transceiver circuit, interface, or interface circuit configured to implement receive and transmit functions may be separate or integrated together. The transceiver circuit, interface, or interface circuit may be configured to read and write code / data. Alternatively, the transceiver circuit, interface, or interface circuit may be configured to transmit or transfer signals.

[0434] Optionally, the processor 1001 may store instructions. These instructions may be computer programs. The computer programs are executed on the processor 1001, enabling the communication device to perform the method described in the embodiment of the above method. The computer programs may be fixed on the processor 1001. In this case, the processor 1001 may be implemented in hardware.

[0435] In implementation, the communication device may include a circuit. The circuit may implement the transmission, reception, or communication functions in the embodiments of the above-described method. The processors and transceivers described herein may be mounted on integrated circuits (ICs), analog ICs, radio frequency integrated circuits (RFICs), mixed-signal ICs, application-specific integrated circuits (ASICs), printed circuit boards (PCBs), electronic devices, or similar. Alternatively, the processors and transceivers may be manufactured using various IC technologies, such as complementary metal-oxide-semiconductors (CMOS), N-channel metal-oxide-semiconductors (NMOS), positive-channel metal-oxide-semiconductors (PMOS), bipolar junction transistors (BJTs), bipolar CMOS (BiCMOS), silicon germanium (SiGe), and gallium arsenide (GaAs).

[0436] It can be understood that the communication device described in this embodiment of the Application may have more components and similar ones than those shown in Figure 19. This is not limited to the embodiments of the Application. The above method performed by the processor and transceiver is merely an example. For specific steps performed by the processor and transceiver, please refer to the description in the embodiment of the above method.

[0437] In another possible implementation, in the encoding or decoding device shown in Figure 18, the processing unit 20 may be one or more logic circuits, and the transceiver unit 10 may be an input / output interface, also referred to as a communication interface, interface circuit, interface, or similar. Alternatively, the transceiver unit 10 may be a transmit unit and a receive unit. The transmit unit may be an output interface, and the receive unit may be an input interface. The transmit unit and the receive unit are integrated into a single unit, for example, an input / output interface. Refer to Figure 20. Figure 20 is another diagram of the structure of a communication device according to an embodiment of the present application. The communication device may be an encoding device or a decoding device. As shown in Figure 20, the communication device shown in Figure 20 includes a logic circuit 901 and an interface 902. That is, the processing unit 20 may be implemented via the logic circuit 901, and the transceiver unit 10 may be implemented via the interface 902. The logic circuit 901 may be a chip, a processing circuit, an integrated circuit, a system on a chip (SoC), or similar. Interface 902 may be a communication interface, an input / output interface, a pin, or something similar. For example, Figure 20 shows an example where the communication device is a chip. The chip includes logic circuits 901 and interface 902.

[0438] In these embodiments of the Application, logic circuits and interfaces can be coupled to one another. The specific arrangement of connections between logic circuits and interfaces is not limited to these embodiments of the Application.

[0439] For example, when a communication device is configured to perform a method, function, or step performed by an encoding device, interface 902 is configured to receive first information transmitted by a decoding device, where the first information is the encoding device's historical state information e his This is for determining the history state information of the encoding device e based on the first information. The logic circuit 901 determines the history state information of the encoding device e hisAnd the first channel information is input to the encoder for processing and configured to obtain the first feedback information, where the historical state information e his This reflects one or more historical channel information acquired before the first channel information is acquired. Interface 902 is further configured to transmit first feedback information to the decoder, where the first feedback information includes encoded information of the first channel information or encoded information of the predicted channel information.

[0440] For example, when a communication device is configured to perform steps, methods, or functions performed by a decoding device, interface 902 is configured to transmit first information to an encoding device, where the first information is the encoding device's historical state information e his This is for determining the following. Interface 902 is further configured to receive first feedback information transmitted by the encoding device, where the first feedback information is first channel information and history state information of the encoding device e his Determined based on, here is the history status information e his This reflects one or more historical channel information acquired before the first channel information was acquired, and the first feedback information includes encoded information of the first channel information or encoded information of the predicted channel information. The first feedback information and the historical state information d of the decoder. his These are input to the decoder for processing, and the third channel information is obtained, where the historical state information d his This reflects one or more historical feedback pieces of information obtained before the first feedback piece was acquired.

[0441] Optionally, the logic circuit 901 receives first feedback information and history state information d of the decoding device. his The data is input to a decoder for processing and configured to obtain third channel information, where the historical state information d his This reflects one or more historical feedback pieces of information obtained before the first feedback piece was acquired.

[0442] In this embodiment of the present application, the first information, history status information e his , history status information d his For descriptions of feedback information, encoding devices, decoding devices, and similar devices, please refer to the descriptions in the embodiments of the above method (including Figures 7, 8, 10, 12, 14, 16, or similar). Further details will not be explained here. For specific descriptions of the logic circuit 901 and interface 902, it is understandable to refer to the descriptions of the processing unit and transceiver unit shown in Figure 18. Further details will not be explained here.

[0443] It can be understood that the communication device shown in this embodiment of the present application may implement the method provided in this embodiment in hardware form, or may implement the method provided in this embodiment in software form. This is not limited to this embodiment of the present application.

[0444] For specific implementations of the embodiment shown in Figure 20, please refer to the embodiments described above. Further details will not be explained here.

[0445] Embodiments of the present invention further provide a wireless communication system. The wireless communication system comprises an encoding device and a decoding device. The encoding device and the decoding device may be configured to perform the method in any one of the above embodiments (Figures 7, 8, 10, 12, 14, or 16).

[0446] In addition, the present application further provides a computer program used to implement the operations and / or processes performed by the encoding device in the method provided in the present application.

[0447] The present application further provides a computer program used to implement the operations and / or processes performed by the decoding device in the method provided herein.

[0448] The present application further provides a computer-readable storage medium for storing computer code. When the computer code is executed on a computer, the computer is able to perform operations and / or processes performed by an encoding device in the manner provided in the present application.

[0449] The present application further provides a computer-readable storage medium for storing computer code. When the computer code is executed on a computer, the computer is able to perform operations and / or processes performed by a decoding device in the manner provided in the present application.

[0450] The present application further provides a computer program product, which includes computer code or a computer program. When the computer code or computer program is executed on a computer, operations and / or processes performed by an encoding device in the manner provided in the present application are performed.

[0451] The present application further provides a computer program product, which includes computer code or a computer program. When the computer code or computer program is executed on a computer, operations and / or processes performed by a decoding device in the manner provided in the present application are performed.

[0452] It should be understood that in some embodiments provided herein, the disclosed systems, apparatus and methods may be implemented in other ways. For example, the embodiments of the apparatus described are merely examples. For example, the division into multiple units is merely a logical functional division, and other divisions may be used in actual implementations. For example, multiple units or components may be combined or integrated into another system, or some features may be ignored or not performed. In addition, the interconnections or direct connections or communication connections shown or discussed may be implemented via several interfaces, indirect connections or communication connections between apparatus or units, or electrical connections, mechanical connections, or other forms of connections.

[0453] Units described as separate parts may or may not be physically separate, and parts shown as units may or may not be physical units, and may be located in one location or distributed across multiple network units. Some or all of the units may be selected based on actual requirements, thereby implementing the technical effects of the solution provided in the embodiments of this application.

[0454] In addition, each functional unit in the embodiments of the present invention may be integrated into a single processing unit, and each of these units may exist physically independently, or two or more units may be integrated into a single unit. The integrated unit may be implemented in the form of hardware, or in the form of a software functional unit.

[0455] When an integrated unit is implemented in the form of a software function unit and sold or used as an independent product, the integrated unit may be stored on a computer-readable storage medium. Based on such understanding, the technical solution of the present application, in essence, or in part, contributes to the prior art, or all or part of the technical solution may be implemented in the form of a software product. A computer software product is stored on a computer-readable storage medium and includes a number of instructions for instructing a computer device (which may be a personal computer, server, or network device) to perform all or part of the steps of the method described in the embodiments of the present application. The computer-readable storage medium includes any medium capable of storing program code, such as a USB flash drive, a removable hard disk, read-only memory (ROM), random access memory (RAM), a magnetic disk, or an optical disk.

[0456] The foregoing description is merely a specific implementation of the present application and is not intended to limit the scope of protection of the present application. Any changes or substitutions that are readily conceivable to a person skilled in the art within the scope of the technical scope disclosed herein shall fall within the scope of protection of the present application. Accordingly, the scope of protection of the present application shall be subject to the scope of protection of the claims.

Claims

1. The encoding device receives the first information transmitted by the decoding device, where the first information is the history state information e of the encoding device. ｈｉｓ This is for determining; The encoding device provides the encoding device's history state information e ｈｉｓ The step of determining the first feedback information based on; and In the step of transmitting the first feedback information to the decoding device by the encoding device, the first feedback information is for determining the third channel information. An information exchange method that includes the following features.

2. The method according to claim 1, wherein the third channel information is historical channel information restored by the decoder of the decoding device, or predicted channel information restored by the decoder of the decoding device.

3. The encoding device provides the encoding device's history state information e ｈｉｓ The step of determining the first feedback information based on the above is: Based on the first information, the encoder of the encoding device generates the history state information e of the encoding device. ｈｉｓ and the first channel information is determined as the first feedback information, where the history state information e ｈｉｓ This reflects one or more historical channel information acquired before the first channel information was acquired. This includes, here The first feedback information includes encoded information of the first channel information or encoded information of the predicted channel information. The method according to claim 1.

4. The encoding device has the history state information e of the encoding device based on the first information. ｈｉｓ The method according to claim 3, wherein the first channel information is input to the encoder for processing to obtain first state information, wherein the first state information reflects one or more historical channel information including the first channel information.

5. The method according to claim 3 or 4, wherein the first channel information is determined based on channel state information CSI.

6. The method according to any one of claims 3 to 5, wherein the encoder is a first artificial intelligence (AI) model.

7. Prior to the step of receiving the first information transmitted by the decoding device using the encoding device, the method further: The encoding device transmits the second feedback information to the decoding device, where the second feedback information is the second channel information and the state information e ｔ－１ The feedback information is output after the state information e is input to the encoder for processing, and the state information e ｔ－１ This reflects one or more historical channel information acquired before the second channel information was acquired. The method according to any one of claims 1 to 6, comprising:

8. The method according to claim 7, wherein the first feedback information is the kth feedback information after the second feedback information, where k is a positive integer.

9. Prior to the step of receiving the first information transmitted by the decoding device using the encoding device, the method further: The encoding device receives the second information transmitted by the decoding device, wherein the second information indicates one or more of the following: whether the encoding device performs periodic storage, the storage period, or the start time of the storage period; and The encoding device periodically stores the state information output by the encoder based on the instruction of the second information. The method according to any one of claims 1 to 8, comprising:

10. The step of periodically storing the state information output by the encoder based on the instructions of the second information using the encoding device is as follows: The step of temporarily storing the state information e obtained by the encoding device during the (n(T / S) - k)-th feedback period by the encoding device ｎ（Ｔ／Ｓ）－ｋ where n, k, S, and T are all positive integers, T represents a storage period, S represents a feedback period, one storage period T is an integer multiple of one feedback period S, and one feedback period is for explaining the transmission time interval between two adjacent feedback information; The encoding device receives the third information transmitted by the decoding device during the (n(T / S))th feedback period, wherein the third information instructs the encoding device to store the state information stored during the ((n-1)*(T / S))th feedback period, or the third information is the state information e acquired during the (n(T / S)-k)th feedback period. ｎ（Ｔ／Ｓ）－ｋ Instruct the encoding device to store; and The encoding device stores the corresponding state information based on the instruction of the third piece of information. The method according to claim 9, including the method described in claim 9.

11. After the encoding device receives the first information transmitted by the decoding device, the method further: The encoding device generates the history state information e ｈｉｓ This includes a step, before the encoding device receives the first information, of determining that it is state information stored in the previous storage cycle. The method according to claim 9.

12. Prior to the step of receiving the first information transmitted by the decoding device using the encoding device, the method further: The coding device receives the fourth information transmitted by the decoding device, wherein the coding device is instructed to store the state information acquired in the feedback period prior to the tth feedback period, where t is a positive integer; and Based on the instructions of the fourth information, the encoding device obtains the state information e acquired by the encoding device during the feedback period prior to the t-th feedback period. ｔ－１ The stage of memorizing Equipped with; After the encoding device receives the first information transmitted by the decoding device, the method further: The encoding device generates the history state information e ｈｉｓ The state information e stored after the encoding device receives the fourth information is the state information e ｔ－１ The stage of deciding that The method according to any one of claims 1 to 8, comprising:

13. Prior to the step of receiving the first information transmitted by the decoding device using the encoding device, the method further: The coding device receives a fourth piece of information transmitted by the decoding device, wherein the coding device is instructed to store state information acquired in the feedback period preceding the t-th feedback period, where t is a positive integer; Based on the instructions of the fourth information, the encoding device obtains the state information e acquired by the encoding device during the feedback period prior to the t-th feedback period. ｔ－１ The stage of temporarily storing information; The encoding device receives the third information transmitted by the decoding device during the (t+k-1)th feedback period, where the third information is the state information e temporarily stored after the fourth information was received during the tth feedback period. ｔ－１ The encoding device is instructed to store the above, or the third information is instructed to store the state information stored when the previous third information was received, where k is a positive integer; and The encoding device stores the corresponding state information based on the instruction of the third piece of information. The method according to any one of claims 1 to 8, comprising:

14. After the encoding device receives the first information transmitted by the decoding device, the method further: The encoding device generates the history state information e ｈｉｓ This is the step of determining that the third piece of information is state information that was stored after it was received. The method according to claim 13, comprising:

15. After the encoding device receives the first information transmitted by the decoding device, the method further: The encoding device generates the history state information e ｈｉｓ The step of updating this with the state information output by the encoder during the feedback period prior to the current time. The method according to any one of claims 1 to 6, comprising:

16. The first piece of information includes or indicates the step size m of the state information rollback, where m is a positive integer; and The aforementioned history status information e ｈｉｓ This is the state information e input by the encoder at the (q-m)th time. ｑ－ｍ－１ It is identical to the above, and the state information input by the encoder on the qth time is the history state information e ｈｉｓ The method according to any one of claims 1 to 8, wherein q is a positive integer greater than m.

17. Prior to the step of receiving the first information transmitted by the decoding device using the encoding device, the method further: In the step of receiving the fifth information transmitted by the decoding device using the encoding device, the fifth information instructs the encoding device to receive the first information with a delay of a feedback period of k after transmitting the feedback information, where k is a positive integer. The method according to any one of claims 1 to 16, comprising:

18. The method according to claim 17, wherein k is greater than or equal to the step size m of the state information rollback.

19. The decoding device transmits the first information to the encoding device, where the first information is the history state information e of the encoding device. ｈｉｓ This is for determining, and The decoding device receives the first feedback information transmitted by the encoding device, where the first feedback information is the history state information e of the encoding device. ｈｉｓ Determined based on, Equipped with, here, The first feedback information is for determining the third channel information. Information exchange methods.

20. The first feedback information is for determining the third channel information: The decoder of the decoding device receives the first feedback information and the history status information d of the decoding device. ｈｉｓ Based on this, the third channel information is determined, where the history state information d ｈｉｓ This reflects one or more historical feedback pieces acquired before the first feedback piece was acquired. The method according to claim 19, including the method described in claim 19.

21. The method according to claim 19 or 20, wherein the third channel information is historical channel information restored by the decoder of the decoding device, or predicted channel information restored by the decoder of the decoding device.

22. The first feedback information is the history state information e of the encoding device. ｈｉｓ The decision based on this is: The first feedback information includes the first channel information and the history state information e of the encoding device. ｈｉｓ This is determined based on the aforementioned history status information e ｈｉｓ This reflects one or more historical channel information acquired before the first channel information is acquired, and the first feedback information includes encoded information of the first channel information or encoded information of the predicted channel information. The method according to claim 19 or 20, including the method described in claim 19 or 20.

23. The first feedback information and the history state information d of the decoding device ｈｉｓ The method according to any one of claims 19 to 22, wherein the information is input to the decoder for processing, and a third state information is obtained, wherein the third state information reflects one or more historical feedback pieces of information, including the first feedback information.

24. The method according to claim 22, wherein the first channel information is determined based on channel state information CSI.

25. The method according to claim 20, wherein the decoder is a second AI model.

26. Before the decoding device transmits the first information to the encoding device, the method further: The decoding device transmits the second information to the encoding device, where the second information indicates one or more of the following: whether the encoding device performs periodic storage, the storage period, or the start time of the storage period; and The decoding device periodically stores the state information output by the decoder based on the memory cycle and / or the start time of the memory cycle. The method according to any one of claims 19 to 25, comprising:

27. The decoding device periodically stores the state information output by the decoder based on the memory cycle and / or the start time of the memory cycle: The decoding device acquires state information d during the (n(T / S)-k)th feedback period. ｎ（Ｔ／Ｓ）－ｋ The temporary storage stage, where n, k, S, and T are all positive integers, T represents the storage period, S represents the feedback period, one storage period T is an integer multiple of one feedback period S, and one feedback period is used to describe the transmission time interval between two adjacent pieces of feedback information; The decoding device transmits third information to the encoding device before the (n(T / S))th feedback period, wherein the third information instructs the encoding device to store the state information stored during the ((n-1)*(T / S))th feedback period, or the third information is the state information d acquired during the (n(T / S)-k)th feedback period. ｎ（Ｔ／Ｓ）－ｋ The encoding device is instructed to store the following: The decoding device stores the state information stored by the decoding device during the ((n-1)*(T / S))th feedback period, based on the third information, or the state information d acquired by the decoding device during the (n(T / S)-k)th feedback period. ｎ（Ｔ／Ｓ）－ｋ The stage of memorizing The method according to claim 26, including the method described in claim 26.

28. After the decoding device transmits the first information to the encoding device, the method further: The decoding device provides the history state information d ｈｉｓ This is the step in which the decoding device determines that the information is state information stored in the previous storage cycle before the step in which it transmits the first information. The method according to claim 27, comprising:

29. Before the decoding device transmits the first information to the encoding device, the method further: The decoding device transmits the fourth information to the encoding device, wherein the fourth information instructs the encoding device to store state information acquired in the feedback period prior to the tth feedback period, where t is a positive integer; and The decoding device acquires state information d during the feedback period preceding the t-th feedback period. ｔ－１ The stage of memorizing Equipped with; After the decoding device transmits the first information to the encoding device, the method further: The decoding device provides the history state information d ｈｉｓ This refers to the state information d stored after the decoding device has transmitted the fourth information. ｔ－１ The stage of deciding that The method according to any one of claims 19 to 25, comprising:

30. Before the decoding device transmits the first information to the encoding device, the method further: In the step of the decoding device transmitting the fourth information to the encoding device, the fourth information instructs the encoding device to store state information acquired in the feedback period preceding the t-th feedback period, where t is a positive integer; The decoding device obtains state information d during the feedback period preceding the t-th feedback period. ｔ－１ The stage of temporarily storing information; The decoding device transmits the third information to the encoding device before the (t+k-1)th feedback period, where the third information is state information e temporarily stored after the fourth information was received during the tth feedback period. ｔ－１ The encoding device is instructed to store the above, or the third information is instructed to store the state information stored when the previous third information was received, where k is a positive integer; and The decoding device, based on the third information, temporarily stores the state information d after the decoding device transmits the fourth information. ｔ－１ A step of storing the above, or storing the state information stored when the decoding device transmits the above third information. The method according to any one of claims 19 to 25, comprising:

31. After the decoding device transmits the first information to the encoding device, the method further: The decoding device provides the history state information d ｈｉｓ This is the step of determining that the third piece of information is state information stored after it has been transmitted. The method according to claim 30, comprising:

32. After the decoding device transmits the first information to the encoding device, the method further: The decoding device provides the history state information d ｈｉｓ The step of updating this with the state information output by the decoder during the feedback period prior to the current time. The method according to any one of claims 19 to 25, comprising:

33. The first piece of information includes or indicates the step size m of the state information rollback, where m is a positive integer; and The aforementioned history status information d ｈｉｓ This is the state information d input by the decoder in the (q-m)th time. ｑ－ｍ－１ It is identical to the above, and the state information input by the decoder on the qth time is the history state information d ｈｉｓ Here, q is a positive integer greater than m. The method according to any one of claims 19 to 25.

34. Before the decoding device transmits the first information to the encoding device, the method further: In the step where the decoding device transmits the fifth information to the encoding device, the fifth information instructs the encoding device to receive the first information with a delay of a feedback period of k after transmitting the feedback information, where k is a positive integer. The method according to any one of claims 19 to 33, comprising:

35. The method according to claim 34, wherein k is greater than or equal to the step size m of the state information rollback.

36. An encoding device comprising a module or unit configured to perform the method described in any one of claims 1 to 18.

37. A decoding device comprising a module or unit configured to perform the method described in any one of claims 19 to 35.

38. An encoding device, One or more processors, wherein the one or more processors are coupled to one or more memories. Equipped with; The one or more memories are configured to store a computer program, and the one or more processors are configured to execute the computer program stored in the one or more memories, enabling the encoding device to perform the method according to any one of claims 1 to 18. Encoding device.

39. A decoding device, One or more processors, wherein the one or more processors are coupled to one or more memories. Equipped with; The one or more memories are configured to store a computer program, and the one or more processors are configured to execute the computer program stored in the one or more memories, enabling the decoding device to perform the method according to any one of claims 19 to 35. Decoding device.

40. A wireless communication system comprising an encoding device configured to perform the method described in any one of claims 1 to 18, and a decoding device configured to perform the method described in any one of claims 19 to 35.

41. A readable storage medium configured to store a program, wherein the program is executed by one or more processors, and the device including the one or more processors enables the method according to any one of claims 1 to 35.

42. A computer program product wherein, when the computer program product is executed, the method described in any one of claims 1 to 35 is executed.

Images