CN114726413A - Channel information acquisition method, device and related equipment - Google Patents
Channel information acquisition method, device and related equipment Download PDFInfo
- Publication number
- CN114726413A CN114726413A CN202110001498.3A CN202110001498A CN114726413A CN 114726413 A CN114726413 A CN 114726413A CN 202110001498 A CN202110001498 A CN 202110001498A CN 114726413 A CN114726413 A CN 114726413A
- Authority
- CN
- China
- Prior art keywords
- information
- feedback
- terminal
- model
- channel matrix
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 73
- 239000011159 matrix material Substances 0.000 claims abstract description 129
- 238000012549 training Methods 0.000 claims description 26
- 238000005259 measurement Methods 0.000 claims description 15
- 238000004891 communication Methods 0.000 claims description 10
- 230000008859 change Effects 0.000 claims description 6
- 230000006835 compression Effects 0.000 claims description 5
- 238000007906 compression Methods 0.000 claims description 5
- 238000001514 detection method Methods 0.000 description 14
- 230000008569 process Effects 0.000 description 11
- 238000010586 diagram Methods 0.000 description 10
- 238000011084 recovery Methods 0.000 description 10
- 238000004422 calculation algorithm Methods 0.000 description 9
- 238000013528 artificial neural network Methods 0.000 description 5
- 230000009286 beneficial effect Effects 0.000 description 5
- 230000006870 function Effects 0.000 description 4
- 238000005457 optimization Methods 0.000 description 4
- 230000003044 adaptive effect Effects 0.000 description 3
- 239000000284 extract Substances 0.000 description 3
- 238000004590 computer program Methods 0.000 description 2
- 230000007613 environmental effect Effects 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 238000012545 processing Methods 0.000 description 2
- 230000005540 biological transmission Effects 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 238000013135 deep learning Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 238000000605 extraction Methods 0.000 description 1
- 230000008713 feedback mechanism Effects 0.000 description 1
- 230000003993 interaction Effects 0.000 description 1
- 238000010801 machine learning Methods 0.000 description 1
- 238000012423 maintenance Methods 0.000 description 1
- 230000007246 mechanism Effects 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 230000000737 periodic effect Effects 0.000 description 1
- 238000010187 selection method Methods 0.000 description 1
- 230000011664 signaling Effects 0.000 description 1
Images
Classifications
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04B—TRANSMISSION
- H04B7/00—Radio transmission systems, i.e. using radiation field
- H04B7/02—Diversity systems; Multi-antenna system, i.e. transmission or reception using multiple antennas
- H04B7/04—Diversity systems; Multi-antenna system, i.e. transmission or reception using multiple antennas using two or more spaced independent antennas
- H04B7/0413—MIMO systems
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04B—TRANSMISSION
- H04B7/00—Radio transmission systems, i.e. using radiation field
- H04B7/02—Diversity systems; Multi-antenna system, i.e. transmission or reception using multiple antennas
- H04B7/04—Diversity systems; Multi-antenna system, i.e. transmission or reception using multiple antennas using two or more spaced independent antennas
- H04B7/06—Diversity systems; Multi-antenna system, i.e. transmission or reception using multiple antennas using two or more spaced independent antennas at the transmitting station
- H04B7/0613—Diversity systems; Multi-antenna system, i.e. transmission or reception using multiple antennas using two or more spaced independent antennas at the transmitting station using simultaneous transmission
- H04B7/0615—Diversity systems; Multi-antenna system, i.e. transmission or reception using multiple antennas using two or more spaced independent antennas at the transmitting station using simultaneous transmission of weighted versions of same signal
- H04B7/0619—Diversity systems; Multi-antenna system, i.e. transmission or reception using multiple antennas using two or more spaced independent antennas at the transmitting station using simultaneous transmission of weighted versions of same signal using feedback from receiving side
- H04B7/0621—Feedback content
- H04B7/063—Parameters other than those covered in groups H04B7/0623 - H04B7/0634, e.g. channel matrix rank or transmit mode selection
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L1/00—Arrangements for detecting or preventing errors in the information received
- H04L1/02—Arrangements for detecting or preventing errors in the information received by diversity reception
- H04L1/06—Arrangements for detecting or preventing errors in the information received by diversity reception using space diversity
- H04L1/0618—Space-time coding
- H04L1/0675—Space-time coding characterised by the signaling
- H04L1/0681—Space-time coding characterised by the signaling adapting space time parameters, i.e. modifying the space time matrix
Landscapes
- Engineering & Computer Science (AREA)
- Computer Networks & Wireless Communication (AREA)
- Signal Processing (AREA)
- Physics & Mathematics (AREA)
- Mathematical Physics (AREA)
- Mobile Radio Communication Systems (AREA)
Abstract
The application provides a channel information acquisition method, a channel information acquisition device and related equipment. The method performed by the terminal includes: receiving first information sent by network side equipment; acquiring a first coding model of an ith version according to the first information, wherein i is a positive integer; under the condition that second information sent by the network side equipment is received and used for indicating the terminal to feed back the compressed channel matrix, inputting the measured first channel matrix into the first coding model of the ith version so as to compress the first feedback bit corresponding to the first channel matrix; and sending first feedback information to the network side equipment, wherein the first feedback information comprises the first feedback bit. The network side equipment can acquire the original high-dimensional channel information, so that the reliability of acquiring the channel information can be improved.
Description
Technical Field
The embodiment of the application relates to the technical field of communication, in particular to a channel information acquisition method, a channel information acquisition device and related equipment.
Background
Multiple-input-Multiple-output (MIMO) technology can effectively improve the diversity and/or spatial multiplexing gain of the system. In the MIMO system, acquiring Channel State Information (CSI) is a key condition for improving transmission performance.
In a Frequency Division multiplexing (FDD) system, a network side device cannot acquire downlink Channel information through the mutual difference of uplink and downlink channels, and can support a plurality of Channel Adaptive (Channel Adaptive) schemes only through a terminal uplink feedback mode. Under the existing feedback mechanism, the network side device can only obtain quantized indicator (indicator) information, and cannot obtain original high-dimensional channel information (i.e. complete channel matrix). Therefore, the reliability of the existing channel information acquisition is low.
Disclosure of Invention
The embodiment of the application provides a channel information acquisition method, a channel information acquisition device and related equipment, and aims to solve the problem that the existing channel information acquisition is low in reliability.
To solve the above problem, the present application is implemented as follows:
in a first aspect, an embodiment of the present application provides a channel information obtaining method, which is executed by a terminal, and the method includes:
receiving first information sent by network side equipment;
acquiring a first coding model of an ith version according to the first information, wherein i is a positive integer;
under the condition that second information sent by the network side equipment is received and used for indicating the terminal to feed back the compressed channel matrix, inputting the measured first channel matrix into the first coding model of the ith version so as to compress the first feedback bit corresponding to the first channel matrix;
and sending first feedback information to the network side equipment, wherein the first feedback information comprises the first feedback bit.
In a second aspect, an embodiment of the present application provides a channel information obtaining method, which is executed by a network side device, and the method includes:
sending first information to a terminal, wherein the first information is used for the terminal to obtain a first coding model of an ith version, and i is a positive integer;
receiving first feedback information sent by the terminal, wherein the first feedback information comprises first feedback bits, and the first feedback bits are obtained by compressing the first coding model;
inputting the first feedback bit into a first decoding model of an ith version corresponding to a first coding model of the ith version to recover and obtain a second channel matrix corresponding to the first feedback bit;
and the first coding model of the ith version and the first decoding model of the ith version are obtained by joint training of the network side equipment.
In a third aspect, an embodiment of the present application further provides a channel information acquiring apparatus, including:
the first transceiver is used for receiving first information sent by network side equipment;
the first processor is used for acquiring a first coding model of an ith version according to the first information, wherein i is a positive integer;
under the condition that second information sent by the network side equipment is received and used for indicating the terminal to feed back the compressed channel matrix, inputting the measured first channel matrix into the first coding model of the ith version so as to compress the first feedback bit corresponding to the first channel matrix;
the first transceiver is further configured to send first feedback information to the network side device, where the first feedback information includes the first feedback bit.
In a fourth aspect, an embodiment of the present application further provides a channel information acquiring apparatus, including:
the second transceiver is used for sending first information to a terminal, the first information is used for the terminal to obtain a first coding model of an ith version, and i is a positive integer;
receiving first feedback information sent by the terminal, wherein the first feedback information comprises first feedback bits, and the first feedback bits are obtained by compressing the first coding model;
a second processor, configured to input the first feedback bit into a first decoding model of an ith version corresponding to the first coding model of the ith version, so as to recover and obtain a second channel matrix corresponding to the first feedback bit;
and the first coding model of the ith version and the first decoding model of the ith version are obtained by joint training of the network side equipment.
In a fifth aspect, an embodiment of the present application further provides a communication device, including: a transceiver, a memory, a processor, and a program stored on the memory and executable on the processor; wherein the processor is configured to read a program in the memory to implement the steps of the method according to the first aspect; or, a step in a method as described in the second aspect above.
In a sixth aspect, the present embodiments also provide a readable storage medium for storing a program, where the program implements the steps in the method according to the first aspect, or implements the steps in the method according to the second aspect, when the program is executed by a processor.
In the embodiment of the application, the network side equipment issues a coding model to the terminal, and the terminal compresses the high-dimensional channel information by using the coding model and feeds the compressed high-dimensional channel information back to the network side equipment; and the network side equipment recovers the compressed high-dimensional channel information by using a decoding model jointly trained with the coding model to obtain the original high-dimensional channel information. Therefore, according to the embodiment of the application, the network side equipment can acquire the original high-dimensional channel information, so that the reliability of acquiring the channel information can be improved.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present application, the drawings needed to be used in the description of the embodiments of the present application will be briefly described below, and it is obvious that the drawings in the following description are only some embodiments of the present application, and it is obvious for those skilled in the art to obtain other drawings based on these drawings without inventive exercise.
Fig. 1 is a schematic structural diagram of a network system to which an embodiment of the present application is applicable;
fig. 2 is a schematic flowchart of a channel information obtaining method according to an embodiment of the present application;
FIG. 3 is a schematic diagram of a model provided by an embodiment of the present application;
fig. 4 is a second flowchart of a channel information obtaining method according to an embodiment of the present application;
fig. 5 is a schematic processing diagram of channel information provided by an embodiment of the present application;
fig. 6 is a third schematic flowchart of a channel information obtaining method according to an embodiment of the present application;
fig. 7 is a schematic structural diagram of a channel information acquisition apparatus provided in this application;
fig. 8 is a second schematic structural diagram of a channel information acquisition apparatus according to an embodiment of the present application;
fig. 9 is a schematic structural diagram of a communication device provided in this application.
Detailed Description
The technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the drawings in the embodiments of the present application, and it is obvious that the described embodiments are some, but not all, embodiments of the present application. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present application.
The terms "first," "second," and the like in the embodiments of the present application are used for distinguishing between similar elements and not necessarily for describing a particular sequential or chronological order. Furthermore, the terms "comprises," "comprising," and "having," and any variations thereof, are intended to cover a non-exclusive inclusion, such that a process, method, system, article, or apparatus that comprises a list of steps or elements is not necessarily limited to those steps or elements expressly listed, but may include other steps or elements not expressly listed or inherent to such process, method, article, or apparatus. Further, as used herein, "and/or" means at least one of the connected objects, e.g., a and/or B and/or C, means 7 cases including a alone, B alone, C alone, and both a and B present, B and C present, both a and C present, and A, B and C present.
Referring to fig. 1, fig. 1 is a structural diagram of a network system to which the embodiment of the present application is applicable, and as shown in fig. 1, the network system includes a terminal 11 and a network side device 12. Communication is possible between the terminal 11 and the network-side device 12.
The terminal 11 may also be called a User Equipment (UE), and in practical applications, the terminal may be a Mobile phone, a Tablet Personal Computer (Tablet Personal Computer), a Laptop Computer (Laptop Computer), a Personal Digital Assistant (PDA), a Mobile Internet Device (MID), a Wearable Device (Wearable Device), or a vehicle-mounted Device. The network side device 12 may be a base station, an access point, or other network elements.
In the embodiment of the present application, the channel matrix, which may also be referred to as a high-dimensional channel matrix, may be understood as: original high-dimensional channel information. The channel bits, which may also be referred to as a low-dimensional channel matrix, may be understood as: compressed high-dimensional channel information.
The coding model and the decoding model have a corresponding relationship, and the coding model and the decoding model having the corresponding relationship are jointly trained during training, namely are trained as a whole.
The following describes a channel acquisition method provided in an embodiment of the present application.
Referring to fig. 2, fig. 2 is a schematic flowchart of a channel information acquiring method according to an embodiment of the present application. The channel information acquisition method shown in fig. 2 may be performed by a terminal.
As shown in fig. 2, the channel information acquiring method may include the steps of:
In this embodiment of the present application, the first information is used for the terminal to obtain the first coding model of the ith version, where i is a positive integer.
Optionally, the first information may include, but is not limited to, any one of the following:
a) a first coding model of version i;
b) first identification information for identifying a first coding model and first update model information including model information of an i-th version of the first coding model updated with respect to an untrained first coding model.
In the first implementation manner that the first information includes a), the network side device directly issues the complete first coding model of the ith version to the terminal. In this way, the terminal can directly extract the first coding model of the ith version from the first information, and the acquisition efficiency of the first coding model of the ith version can be improved.
In the second implementation manner in which the first information includes a), the network side device may issue the Index number (Index) of the first coding model to the terminal, and issue the updated model information in a differential manner based on the untrained first coding model (i.e., the original first coding model). Thus, compared to the first implementation, the signaling overhead of the first information can be saved.
It should be noted that when i is equal to 1, the first coding model of the ith version is the untrained first coding model. For the second implementation manner, the first information may only include the first identification information.
In practical applications, the first information may be carried in a control channel or a data channel, which may be determined according to practical situations, and this is not limited in this embodiment of the present application.
In a specific implementation, for the first implementation, the terminal may extract the first coding model of the ith version from the first information.
For the second implementation manner, the terminal may obtain the untrained first coding model based on the first identification information, for example: acquiring an untrained first coding model from a communication protocol based on the first identification information; or, based on the first identification information, determining an untrained first coding model from a plurality of coding models which are obtained in advance and are not limited thereto; and then, adjusting the untrained first coding model by using the first updated model information to obtain the ith version of the first coding model.
In this embodiment, the network side device may instruct the terminal to feed back an uncompressed channel matrix, that is, an original channel matrix, according to its own requirement, or instruct the terminal to feed back a compressed channel matrix.
After receiving the information, i.e., the second information, sent by the network side device and used for indicating feedback of the compressed channel matrix, the terminal may compress the measured channel matrix using the first coding model of the ith version, and feed back the compressed channel matrix. In a specific implementation, the input of the ith version of the first coding model is the first channel matrix, and the output is the first feedback bit.
In a specific implementation, the first feedback information may only include the first feedback bit, or may include other information besides the first feedback bit, such as auxiliary information that can help recover a channel matrix, and the like.
In implementation, the network side device may further indicate at least one item when indicating the terminal to feed back the compressed channel matrix: the bit length of the feedback information, the feedback resource of the feedback information (e.g., the feedback channel for carrying the feedback information, the Modulation and Coding Scheme (MCS) of the feedback information), and the format of the feedback information. Thus, the terminal can perform feedback of the feedback information according to at least one item.
Such as: and under the condition that the network side equipment indicates that the bit length of the feedback information exists, the bit length of the first feedback information fed back by the terminal is the same as the bit length of the feedback information indicated by the network side equipment.
When the network side device indicates a feedback resource with feedback information, the terminal may perform feedback of the first feedback information according to the indicated feedback resource.
Under the condition that the network side equipment indicates the format of the feedback information, the terminal can determine the information structure of the first feedback information based on the indicated format, for example, the sequence of each piece of information in the first feedback information is determined, so that the network side equipment can conveniently distinguish each piece of information in the feedback information, and the extraction efficiency of feedback bits in the feedback information is improved.
In the channel information obtaining method of the embodiment of the application, the terminal obtains the coding model based on the first information issued by the network side device, and when the network side device indicates to feed back the compressed channel matrix, the coding model is used to compress the channel matrix to obtain the feedback bit, and then the feedback bit is reported to the network side device. Thus, after receiving the feedback bits, the network side device can recover the feedback bits by using the decoding model jointly trained with the coding model to obtain the original channel matrix, thereby improving the reliability of channel information acquisition.
In this embodiment of the present application, optionally, the method further includes:
sending second feedback information to the network side equipment under the condition that a first condition is met, wherein the second feedback information comprises the first channel matrix;
wherein the meeting the first condition comprises any one of:
1) receiving third information sent by the network side equipment, wherein the third information is used for indicating the terminal to feed back an uncompressed channel matrix;
2) and the environment state change information of the terminal meets the preset condition.
Under the condition that the first condition is met and the condition comprises 1), the terminal reports the second feedback information based on the indication of the network side equipment; and under the condition that the first condition is met, wherein the condition comprises 2), the terminal can autonomously trigger the report of the second feedback information when detecting that the environmental state change information meets a preset condition.
Optionally, the condition that the environmental state change information of the terminal meets the preset condition may include: and the moving distance value of the terminal in the first time length is greater than the distance threshold value, and the terminal performs cell switching and the like.
In this optional embodiment, the second feedback information includes the first channel matrix, that is, an uncompressed channel matrix, and may be used for the network side device to perform model tuning and model accuracy detection.
After receiving the second feedback information, the network side device may determine whether to send fifth information to the terminal according to the first channel matrix and the second channel matrix, where the fifth information is used for the terminal to obtain the i +1 th version of the first coding model or the p-th version of the second coding model, and p is a positive integer.
During specific implementation, the network side device may tune at least one of the first coding model of the ith version and the first decoding model of the ith version according to the first channel matrix and the second channel matrix to obtain the first coding model of the (i + 1) th version and the first decoding model of the (i + 1) th version; and then, performing precision detection on the adjusted models, namely the first coding model of the i +1 th version and the first decoding model of the i +1 th version.
If the precision detection result of the adjusted model is smaller than the preset precision threshold, it indicates that the reliability of obtaining the channel information through the first coding model and the first decoding model is low, and the network side device may reselect the second coding model and the second decoding model to obtain the channel information, and issue the second coding model of the p-th version to the terminal through the fifth information.
If the precision detection result of the adjusted model is greater than or equal to the preset precision threshold, it indicates that the reliability of obtaining the channel information through the first coding model and the first decoding model is higher, and the network side device may not change the model for obtaining the channel information. And under the condition that the tuned and optimized model comprises the first coding model, the network side equipment can issue the first coding model of the (i + 1) th version to the terminal through the fifth information.
The tuning of the model is explained below:
in specific implementation, the network side device may obtain a loss function according to the first channel matrix and the second channel matrix, and then optimize the network weight of at least one of the first coding model of the ith version and the first decoding model of the ith version by using the loss function to obtain the first coding model of the (i + 1) th version and the first decoding model of the (i + 1) th version.
Optionally, the network side device may freeze the first coding model of the ith version, and optimize the network weight in the first decoding model of the ith version by using the loss function to obtain the first coding model of the (i + 1) th version and the first decoding model of the (i + 1) th version, where the first coding model of the (i + 1) th version is the same as the first coding model of the ith version. In this way, the first coding model is not updated, and therefore, the network side device does not need to send the coding model to the terminal, thereby reducing the overhead of air interface resources.
The optimization algorithm can be a classical neural network training algorithm, such as a gradient descent algorithm, and the like, and can be determined according to actual conditions, which is not limited in the embodiment of the present application.
The following describes the accuracy detection of the model:
during specific implementation, the network side device may input the first channel matrix into the first coding model of the i +1 th version to obtain a second feedback bit corresponding to the first channel matrix through compression; inputting the second feedback bit into the first decoding model of the (i + 1) th version to recover and obtain a third channel matrix corresponding to the second feedback bit; comparing the first channel matrix with the third channel matrix to obtain a matching value; and determining an accuracy detection result according to the matching value. The network side device may preset a corresponding relationship between the obtained matching value and the accuracy detection result, so that after the matching value is obtained, the corresponding accuracy detection result may be determined by searching the corresponding relationship, but is not limited thereto.
It is to be understood that, in the case that the fifth information is used by the terminal to obtain the pth version of the second coding model, the fifth information may include, but is not limited to, any one of the following: a second coding model of the p-th version; second identification information for identifying a second coding model and second update model information comprising model information of a p-th version of the second coding model updated with respect to an untrained second coding model. In a case where the fifth information is used for the terminal to obtain the i +1 th version of the first coding model, the fifth information may include, but is not limited to, any one of: a first coding model of version i + 1; the first identification information is used for identifying the first coding model, and the third updating model information comprises model information of the i +1 th version of the first coding model which is updated relative to the untrained second coding model. The manner of obtaining, by the terminal, the first coding model of the i +1 th version according to the fifth information is the same as the manner of obtaining, by the terminal, the first coding model of the i +1 th version according to the first information, which may specifically refer to the foregoing description, and details are not repeated here.
In other embodiments, the terminal may also perform accuracy detection of the model, and in these embodiments, the network side device needs to issue a coding model and a decoding model of joint training, and after the terminal compresses the channel matrix through the coding model to obtain the feedback bits, the terminal may recover the feedback bits through the decoding matrix to obtain the channel matrix, and then calculate the matching value according to the channel matrix compressed by the coding model and the channel matrix recovered by the decoding matrix to obtain the accuracy detection result. When the accuracy detection result is smaller than the preset accuracy threshold, it indicates that the reliability of the current coding model and decoding model for acquiring the channel information is low, and the terminal may send a model update request to the network side device, and request the network side device to send the fifth information.
In this embodiment of the present application, optionally, before receiving the first information sent by the network side device, the method further includes:
and under the condition of receiving fourth information sent by network side equipment, sending third feedback information to the network side equipment, wherein the third feedback information comprises a fourth channel matrix obtained by measurement, and the fourth information is used for indicating the terminal to feed back an uncompressed channel matrix.
In practical application, the network side device may store N pairs of encoding networks and decoding networks having a corresponding relationship in advance, where the first encoding network and the first decoding network are one of the N pairs, and N is an integer greater than 1.
The network side device may instruct the terminal to feed back the uncompressed channel matrix, so as to perform model selection according to the uncompressed channel matrix fed back by the terminal. It can be seen that in this alternative embodiment, the third feedback information is used for model selection.
After the network side device obtains the fourth channel matrix, the network side device may process the fourth channel matrix by using the N pairs of encoding networks and decoding networks to obtain N recovery accuracies, wherein, in the process of processing, each pair of encoding networks and decoding networks of the encoding networks and decoding networks compresses the fourth channel matrix, the decoding networks recover the compressed information, and the recovery accuracy is calculated based on the original channel matrix and the recovered channel matrix. The terminal can select a coding network and a decoding network pair with the highest recovery precision, in the embodiment of the application, the coding network and the decoding network are the first coding network and the first decoding network, and then the first coding network is issued to the terminal through the first information.
Further, the network side device may also use the fourth channel matrix to tune the selected pair of the encoding network and the decoding network, and the tuning manner may refer to the foregoing description, which is not described herein again.
In addition, when the network side device groups the N pairs of coding networks and decoding networks, a packet with the highest matching degree with the terminal information may be determined first, and then each pair of coding network and decoding network in the group may be used to process the fourth channel matrix. In this way, the efficiency of model selection may be improved.
In specific implementation, the network side device may group the N pairs of coding networks and decoding networks according to different feedback situations, such as: different numbers of feedback bits, different dimensions of the channel matrix, etc. As shown in fig. 3, models that apply to the same port and the same feedback bit length are grouped into the same packet.
Referring to fig. 4, fig. 4 is a second flowchart of a channel information acquiring method according to an embodiment of the present application. The channel information acquiring method of the embodiment of the application can be executed by network side equipment.
As shown in fig. 4, the channel information acquisition method may include the steps of:
And the first coding model of the ith version and the first decoding model of the ith version are obtained by joint training of the network side equipment.
In the channel information obtaining method of this embodiment, the network side device may send the first information to the terminal, so that the terminal obtains the coding model, and when the network side device instructs to feed back the compressed channel matrix, the coding model is used to compress the channel matrix to obtain the feedback bit, and then the feedback bit is reported to the network side device. Thus, after receiving the feedback bits, the network side device can recover the feedback bits by using the decoding model jointly trained with the coding model to obtain the original channel matrix, thereby improving the reliability of channel information acquisition.
Optionally, the first information includes any one of:
a first coding model of version i;
first identification information for identifying a first coding model and first update model information including model information of an i-th version of the first coding model updated with respect to an untrained first coding model.
Optionally, the method further includes:
receiving second feedback information sent by the terminal, wherein the second feedback information comprises a first channel matrix;
and determining whether to send fifth information to the terminal according to the first channel matrix and the second channel matrix, wherein the fifth information is used for the terminal to obtain a first coding model of an i +1 version or a second coding model of a p version, and p is a positive integer.
Optionally, when the network-side device includes N pairs of an encoding network and a decoding network having a corresponding relationship, where N is an integer greater than 1, before the first information is sent to the terminal, the method further includes:
sending fourth information to the terminal, wherein the fourth information is used for indicating the terminal to feed back an uncompressed channel matrix;
receiving third feedback information sent by the terminal based on the fourth information, wherein the third feedback information comprises a fourth channel matrix measured by the terminal;
selecting a first encoding network and a first decoding network from the N pairs of encoding networks and decoding networks having a corresponding relationship by using the fourth channel matrix;
acquiring a first coding network of an ith version and a first decoding network of the ith version;
and generating the first information according to the first coding model of the ith version.
It should be noted that, the present embodiment is implemented as a network side device corresponding to the foregoing method embodiment, and therefore, reference may be made to the relevant description in the foregoing method embodiment, and the same beneficial effects may be achieved. To avoid repetition of the description, the description is omitted.
The various optional implementations described in the embodiments of the present application may be implemented in combination with each other or implemented separately without conflicting with each other, and the embodiments of the present application are not limited to this.
For ease of understanding, examples are illustrated below:
in the following description, a network side device is taken as a base station for illustration, but it is understood that the representation form of the network side device is not limited thereby.
The embodiment of the present application provides a machine learning-based high-dimensional channel information feedback scheme suitable for FDD downlink, and the general idea of the scheme is as shown in fig. 5. Firstly, the terminal uses a coding model to compress high-dimensional channel information, the compressed channel information is fed back to the base station through an uplink, and finally, the original high-dimensional channel information is recovered by using a decoding model at the base station. The protocol can be divided into three main steps:
1) model selection and feedback parameter determination: the base station and the terminal confirm the used model to keep synchronization through negotiation, including the number of applicable ports, the number of feedback bits, and the like;
2) channel information compression and feedback: the terminal uses the previously determined model to compress the CSI (channel matrix) and generate feedback information, and then reports the feedback information to the base station through an uplink, and the base station extracts corresponding CSI compressed information (feedback bits) from the received feedback information and inputs the CSI compressed information (feedback bits) into a decoding network to recover the original CSI.
3) Model maintenance and updating: the base station and the terminal keep the usability of the model through interaction. Specifically, when the base station or the terminal detects that the feedback accuracy is lower than a certain threshold, or the terminal environment has changed significantly (e.g. significant location movement or even cell handover occurs), the base station and the terminal may renegotiate the selection model.
In the embodiment of the application, the compression and the recovery of the channel matrix are completed by using a deep neural network based on an auto-encoder structure. As shown in fig. 5, the self-encoder neural network belongs to an unsupervised learning network, and its input and output are the same high-dimensional channel matrix, which can be better matched with the channel matrix compression-recovery process. When using a self-encoder network, one part of the network is typically considered as an encoding network, the remaining part is considered as a decoding network, and the signals between the two parts (i.e. the output of the encoding network and the input of the decoding network) are compressed channel matrices that require feedback. When the network is trained, the whole self-encoder is regarded as a whole to be trained, namely a loss function is calculated on the output side of the self-encoder, the gradient of each weight in the network is calculated through the back propagation of the gradient, and finally the network weight is optimized according to the gradient value. Due to the characteristics of the whole training of the self-encoder network, the encoding network and the decoding network have the characteristic of one-to-one correspondence, namely, the channel information compressed by a certain encoding network can only be recovered from the decoding network corresponding to the channel information with high precision. In training, a classical back propagation gradient descent algorithm in deep learning, such as random gradient descent, an adaptive matrix estimation (ADAM) optimizer and the like, can be adopted. The training data of the network is a complete channel matrix, and the data can be from the measured historical channel information of the cell.
Considering that more model degrees of freedom are introduced, so as to support certain capability of optimizing the model according to real-time data, the standard document can only specify the structure of the network model or give a model set after certain pre-training, even only give a data set for model pre-training. Further optimization of the model will then be based on real-time data (or semi-real-time cell history measurement data). A schematic diagram of the model set for channel feedback is shown in fig. 3. Under this assumption, the model synchronization between the base station and the terminal will involve the process of the base station issuing the relevant model to the terminal, and will bring some changes to the model synchronization flow. The channel feedback flow chart at this time is shown in fig. 6.
Step 1, the base station performs model pre-training.
In specific implementation, the base station may perform model pre-training according to the historical channel information of the cell, that is, the training data is the historical channel data of the cell. The result of the pre-training is a set of models comprising a plurality of models for different feedback situations (e.g. different number of feedback bits, different dimensionality of the channel matrix, etc.). The above models will be grouped primarily according to their applicable scenarios and applicable feedback configurations, e.g. models applicable to the same port and the same feedback bit length are grouped into the same subgroup in the manner of fig. 3.
And step 2, the base station informs the terminal to feed back an uncompressed channel matrix (high-dimensional CSI) and issues related feedback configuration.
In this step, the feedback configuration may include a channel for feedback, MCS information for feedback, and the like.
And 3, configuring the periodic measurement signal by the base station.
In a specific implementation, the base station may periodically transmit a measurement Signal, such as a CSI Reference Signal (CSI-RS), for the terminal to perform channel measurement.
And 4, reporting the uncompressed channel matrix by the terminal.
In specific implementation, the terminal estimates a channel according to the reference signal, and feeds back a measurement result, i.e., an uncompressed channel matrix, according to the feedback information of the uncompressed channel matrix. The channel estimation method may use typical square sum of error (LS), square sum of error (MMSE), and other estimation methods.
And 5, the base station selects a model according to the uncompressed channel matrix reported by the terminal and optimizes the selected model.
During specific implementation, the base station selects a model from the alternative model set according to the uncompressed channel matrix reported by the terminal, and further optimizes the selected model, wherein the optimized data is the channel matrix fed back in real time. The method for selecting the model in the step comprises the following steps: 1) selecting a type of model subset which is most matched with the current terminal information from the model candidate set, wherein the selection method is mainly a table lookup method; 2) and sequentially using each model (including a coding network and a decoding network) in the model subset to compress and recover the uncompressed channel information reported by the terminal, calculating recovery precision, and finally selecting the model with the highest recovery precision of the current channel information as the model used in the current stage. The base station further continues to perform fine tuning on the selected model on the basis of the pre-training result, the fine tuning method is to train the self-encoder model by using real-time channel information (the training algorithm can use a classical neural network training algorithm, such as gradient descent and the like), so as to improve the recovery precision, and note that in the training process, a part of network weight can be frozen, and only the rest part is updated to a certain extent, so that the calculation overhead in the training process is reduced.
And 6, the base station issues a coding network model.
In specific implementation, the method for the base station to issue the coding model for compressing the channel matrix includes: 1) directly issuing a complete model; 2) and issuing the index of the model in the set, and issuing the updated model information in a differential mode based on the original pre-training model. Considering that the overhead of sending the complete model information is significantly higher than the index sent down, and is not necessarily suitable for being performed on the control channel, it can be considered to complete the procedure on the data channel.
And 7, the base station informs the terminal of feeding back the compressed channel matrix and configuring corresponding feedback parameters.
Step 7 corresponds to step 2, and the main purpose is to inform the terminal of the switching of the CSI feedback mode.
In this step, the feedback parameters may include a feedback bit length, a feedback channel, a feedback information format, and the like. The feedback parameters include quantities already specified by a part of the related art, such as feedback bit length, channel resources and MCS used for feedback, etc., or quantities not yet introduced in the related art, such as feedback data format for full channel matrix feedback, etc.
And step 8, the base station sends the reference signal of the channel measurement.
In a specific implementation, the reference signal may be a CSI-RS or the like. This step can be performed in the manner already existing in NR.
And 9, the terminal obtains a channel matrix according to the reference signal measurement and compresses the channel matrix by using the selected coding network.
In specific implementation, the channel measurement result may be input to the coding network to obtain compressed bits.
And step 10, the terminal reports the compressed channel matrix.
And in specific time, the terminal feeds back the compressed channel information bits according to the feedback information configured in the step 7. The compressed channel matrix may be in the form of a bit stream.
And step 11, the base station recovers to obtain the channel matrix by using the selected decoding network.
In specific implementation, the base station inputs the received bits into a decoding network to recover the original channel matrix information.
And step 12, the base station periodically configures the terminal to feed back the uncompressed channel measurement result.
For judging the model compression accuracy. The type of reference signal for measurement may be selected from CSI-RS, etc.
And step 13, calculating the model recovery precision by the base station, and judging whether the model needs to be issued again.
In specific implementation, the base station can perform model tuning and model precision detection according to the uncompressed channel measurement result fed back in real time. When the model is tuned and optimized, the decoding network is optimized firstly, the optimization mode is that the complete channel matrix fed back in real time is used as the input and the output of the self-encoder network, meanwhile, the weight of the encoding network is frozen, only the weight of the decoding network is trained, and the optimization algorithm can select a classical neural network training algorithm, such as a gradient descent algorithm and the like. The reason for only adjusting the decoding network is that the encoding network does not need to be sent to the terminal again, so that the overhead of air interface resources is reduced. The model accuracy detection can be performed simultaneously with the model tuning process, that is, the channel information recovery accuracy after model tuning is regarded as the model accuracy. And comparing the model precision detection result with a precision threshold value specified in advance, and if the precision of the adjusted and optimized model is still lower than the threshold value, judging that the model does not meet the precision requirement, and triggering an updating mechanism of the terminal model.
And 14, if the base station judges that the model selection needs to be carried out again, the newly selected model is sent to the terminal.
The specific issuing mode may be performed with reference to the description in step 6.
In the embodiment of the application, the high-dimensional channel information is compressed by using a coding network model on one end device, the compressed channel information is fed back to the other end device, and the high-dimensional channel information is recovered by using a decoding network model on the other end device. And the coding network and the decoding network used by the two-end equipment are optimized in a joint training mode.
Referring to fig. 7, fig. 7 is a structural diagram of a channel information acquiring apparatus according to an embodiment of the present application. As shown in fig. 7, the channel information acquiring apparatus 700 includes:
a first transceiver 701, configured to receive first information sent by a network side device;
a first processor 702, configured to obtain, according to the first information, an ith version of the first coding model, where i is a positive integer;
under the condition that second information sent by the network side equipment is received and used for indicating the terminal to feed back the compressed channel matrix, inputting the measured first channel matrix into the first coding model of the ith version so as to compress the first feedback bit corresponding to the first channel matrix;
the first transceiver 701 is further configured to send first feedback information to the network side device, where the first feedback information includes the first feedback bit.
Optionally, the first information includes any one of:
a first coding model of the ith version;
first identification information for identifying a first coding model and first update model information including model information of an i-th version of the first coding model updated with respect to an untrained first coding model.
Optionally, the first transceiver 701 is further configured to:
sending second feedback information to the network side equipment under the condition that a first condition is met, wherein the second feedback information comprises the first channel matrix;
wherein the meeting the first condition comprises any one of:
receiving third information sent by the network side equipment, wherein the third information is used for indicating the terminal to feed back an uncompressed channel matrix;
and the environment state change information of the terminal meets the preset condition.
Optionally, the first transceiver 701 is further configured to:
and sending third feedback information to the network side equipment under the condition of receiving fourth information sent by the network side equipment, wherein the fourth information is used for indicating the terminal to feed back an uncompressed channel matrix, and the third feedback information comprises a fourth channel matrix obtained by measurement.
The channel information obtaining apparatus 700 can implement each process of the method embodiment in fig. 2 in the embodiment of the present application, and achieve the same beneficial effects, and for avoiding repetition, details are not described here again.
Referring to fig. 8, fig. 8 is a second structural diagram of a channel information acquiring apparatus according to an embodiment of the present application. As shown in fig. 8, the channel information acquiring apparatus 800 includes:
a second transceiver 801, configured to send first information to a terminal, where the first information is used for the terminal to obtain a first coding model of an ith version, and i is a positive integer;
receiving first feedback information sent by the terminal, wherein the first feedback information comprises first feedback bits, and the first feedback bits are obtained by compressing the first coding model;
a second processor 802, configured to input the first feedback bit into a first decoding model of an ith version corresponding to the first coding model of the ith version, so as to recover and obtain a second channel matrix corresponding to the first feedback bit;
and the first coding model of the ith version and the first decoding model of the ith version are obtained by joint training of the network side equipment.
Optionally, the first information includes any one of:
a first coding model of the ith version;
first identification information for identifying a first coding model and first update model information including model information of an i-th version of the first coding model updated with respect to an untrained first coding model.
Optionally, the second transceiver 801 is further configured to receive second feedback information sent by the terminal, where the second feedback information includes a first channel matrix;
the second processor 802 is further configured to determine whether to send fifth information to the terminal according to the first channel matrix and the second channel matrix, where the fifth information is used for the terminal to obtain the i +1 th version of the first coding model or the p th version of the second coding model, and p is a positive integer.
Optionally, the network-side device includes N pairs of encoding networks and decoding networks having a corresponding relationship, where N is an integer greater than 1, the second transceiver 801 is further configured to:
sending fourth information to the terminal, wherein the fourth information is used for indicating the terminal to feed back an uncompressed channel matrix;
receiving third feedback information sent by the terminal based on the fourth information, wherein the third feedback information comprises a fourth channel matrix measured by the terminal;
the second processor 802 is further configured to:
selecting a first encoding network and a first decoding network from the N pairs of encoding networks and decoding networks having a corresponding relationship by using the fourth channel matrix;
acquiring a first coding network of an ith version and a first decoding network of the ith version;
and generating the first information according to the first coding model of the ith version.
The channel information obtaining apparatus 800 can implement each process of the method embodiment in fig. 4 in the embodiment of the present application, and achieve the same beneficial effects, and for avoiding repetition, details are not described here again.
The embodiment of the application also provides communication equipment. Referring to fig. 9, a communication device may include a processor 901, a memory 902, and a program 9021 stored on the memory 902 and operable on the processor 901.
In a case that the communication device is a terminal, when the program 9021 is executed by the processor 901, any step in the method embodiment corresponding to fig. 2 may be implemented and the same beneficial effect may be achieved, which is not described herein again.
In the case that the communication device is a network-side device, when being executed by the processor 901, the program 9021 may implement any step in the method embodiment corresponding to fig. 4 and achieve the same beneficial effect, which is not described herein again.
Those skilled in the art will appreciate that all or part of the steps of the method according to the above embodiments may be implemented by hardware associated with program instructions, and the program may be stored in a readable medium. An embodiment of the present application further provides a readable storage medium, where a computer program is stored on the readable storage medium, and when the computer program is executed by a processor, any step in the method embodiment corresponding to fig. 2 or fig. 4 may be implemented, and the same technical effect may be achieved, and in order to avoid repetition, details are not repeated here.
The storage medium may be a Read-Only Memory (ROM), a Random Access Memory (RAM), a magnetic disk or an optical disk.
While the foregoing is directed to the preferred embodiment of the present application, it will be appreciated by those skilled in the art that various changes and modifications may be made therein without departing from the principles of the application, and it is intended that such changes and modifications be covered by the scope of the application.
Claims (12)
1. A channel information acquisition method performed by a terminal, the method comprising:
receiving first information sent by network side equipment;
acquiring a first coding model of an ith version according to the first information, wherein i is a positive integer;
under the condition that second information sent by the network side equipment is received and used for indicating the terminal to feed back the compressed channel matrix, inputting the measured first channel matrix into the first coding model of the ith version so as to compress the first feedback bit corresponding to the first channel matrix;
and sending first feedback information to the network side equipment, wherein the first feedback information comprises the first feedback bit.
2. The method of claim 1, wherein the first information comprises any one of:
a first coding model of version i;
first identification information for identifying a first coding model and first update model information including model information of an i-th version of the first coding model updated with respect to an untrained first coding model.
3. The method of claim 1, further comprising:
sending second feedback information to the network side equipment under the condition that a first condition is met, wherein the second feedback information comprises the first channel matrix;
wherein the meeting the first condition comprises any one of:
receiving third information sent by the network side equipment, wherein the third information is used for indicating the terminal to feed back an uncompressed channel matrix;
and the environment state change information of the terminal meets the preset condition.
4. The method according to claim 1, wherein before receiving the first information sent by the network-side device, the method further comprises:
and sending third feedback information to the network side equipment under the condition of receiving fourth information sent by the network side equipment, wherein the fourth information is used for indicating the terminal to feed back an uncompressed channel matrix, and the third feedback information comprises a fourth channel matrix obtained by measurement.
5. A channel information acquisition method is executed by a network side device, and is characterized by comprising the following steps:
sending first information to a terminal, wherein the first information is used for the terminal to obtain a first coding model of an ith version, and i is a positive integer;
receiving first feedback information sent by the terminal, wherein the first feedback information comprises first feedback bits, and the first feedback bits are obtained by compressing the first coding model;
inputting the first feedback bit into a first decoding model of an ith version corresponding to a first coding model of the ith version to recover and obtain a second channel matrix corresponding to the first feedback bit;
and the first coding model of the ith version and the first decoding model of the ith version are obtained by joint training of the network side equipment.
6. The method of claim 5, wherein the first information comprises any one of:
a first coding model of version i;
first identification information for identifying a first coding model and first update model information including model information of an i-th version of the first coding model updated with respect to an untrained first coding model.
7. The method of claim 5, further comprising:
receiving second feedback information sent by the terminal, wherein the second feedback information comprises a first channel matrix;
and determining whether to send fifth information to the terminal according to the first channel matrix and the second channel matrix, wherein the fifth information is used for the terminal to obtain the first coding model of the (i + 1) th version or the second coding model of the p-th version, and p is a positive integer.
8. The method according to claim 5, wherein in a case that the network side device includes N pairs of an encoding network and a decoding network having a correspondence relationship, where N is an integer greater than 1, before the transmitting the first information to the terminal, the method further includes:
sending fourth information to the terminal, wherein the fourth information is used for indicating the terminal to feed back an uncompressed channel matrix;
receiving third feedback information sent by the terminal based on the fourth information, wherein the third feedback information comprises a fourth channel matrix measured by the terminal;
selecting a first encoding network and a first decoding network from the N pairs of encoding networks and decoding networks having a corresponding relationship by using the fourth channel matrix;
acquiring a first coding network of an ith version and a first decoding network of the ith version;
and generating the first information according to the first coding model of the ith version.
9. A channel information acquisition apparatus, characterized by comprising:
the first transceiver is used for receiving first information sent by network side equipment;
the first processor is used for acquiring a first coding model of an ith version according to the first information, wherein i is a positive integer;
under the condition that second information sent by the network side equipment is received and used for indicating a terminal to feed back a compressed channel matrix, inputting a first channel matrix obtained through measurement into a first coding model of an ith version so as to obtain a first feedback bit corresponding to the first channel matrix through compression;
the first transceiver is further configured to send first feedback information to the network side device, where the first feedback information includes the first feedback bit.
10. A channel information acquisition apparatus, characterized by comprising:
the second transceiver is used for sending first information to a terminal, wherein the first information is used for the terminal to obtain a first coding model of an ith version, and i is a positive integer;
receiving first feedback information sent by the terminal, wherein the first feedback information comprises first feedback bits, and the first feedback bits are obtained by compressing the first coding model;
a second processor, configured to input the first feedback bit into a first decoding model of an ith version corresponding to the first coding model of the ith version, so as to recover and obtain a second channel matrix corresponding to the first feedback bit;
and the first coding model of the ith version and the first decoding model of the ith version are obtained by joint training of network side equipment.
11. A communication device, comprising: a transceiver, a memory, a processor, and a program stored on the memory and executable on the processor; the processor is configured to read a program in the memory to implement the steps in the channel information acquisition method according to any one of claims 1 to 4; or, the steps in the channel information acquisition method according to any of claims 5 to 8.
12. A readable storage medium storing a program, wherein the program when executed by a processor implements the steps in the channel information acquisition method according to any one of claims 1 to 4; or, the steps in the channel information acquisition method according to any of claims 5 to 8.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110001498.3A CN114726413A (en) | 2021-01-04 | 2021-01-04 | Channel information acquisition method, device and related equipment |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110001498.3A CN114726413A (en) | 2021-01-04 | 2021-01-04 | Channel information acquisition method, device and related equipment |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN114726413A true CN114726413A (en) | 2022-07-08 |
Family
ID=82233850
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110001498.3A Pending CN114726413A (en) | 2021-01-04 | 2021-01-04 | Channel information acquisition method, device and related equipment |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114726413A (en) |
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2024031701A1 (en) * | 2022-08-12 | 2024-02-15 | 富士通株式会社 | Data acquisition method and apparatus |
| WO2024031456A1 (en) * | 2022-08-10 | 2024-02-15 | 北京小米移动软件有限公司 | Communication method, apparatus and device, storage medium, chip, and program product |
| WO2024051564A1 (en) * | 2022-09-07 | 2024-03-14 | 维沃移动通信有限公司 | Information transmission method, ai network model training method, apparatus, and communication device |
| WO2024088162A1 (en) * | 2022-10-27 | 2024-05-02 | 维沃移动通信有限公司 | Information transmission method, information processing method, apparatus, and communication device |
| WO2024097693A1 (en) * | 2022-11-04 | 2024-05-10 | Google Llc | Managing machine learning based channel state information reporting at a network |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109672464A (en) * | 2018-12-13 | 2019-04-23 | 西安电子科技大学 | Extensive mimo channel state information feedback method based on FCFNN |
| CN111464220A (en) * | 2020-03-10 | 2020-07-28 | 西安交通大学 | Channel state information reconstruction method based on deep learning |
| WO2020180221A1 (en) * | 2019-03-06 | 2020-09-10 | Telefonaktiebolaget Lm Ericsson (Publ) | Compression and decompression of downlink channel estimates |
-
2021
- 2021-01-04 CN CN202110001498.3A patent/CN114726413A/en active Pending
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109672464A (en) * | 2018-12-13 | 2019-04-23 | 西安电子科技大学 | Extensive mimo channel state information feedback method based on FCFNN |
| WO2020180221A1 (en) * | 2019-03-06 | 2020-09-10 | Telefonaktiebolaget Lm Ericsson (Publ) | Compression and decompression of downlink channel estimates |
| CN111464220A (en) * | 2020-03-10 | 2020-07-28 | 西安交通大学 | Channel state information reconstruction method based on deep learning |
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2024031456A1 (en) * | 2022-08-10 | 2024-02-15 | 北京小米移动软件有限公司 | Communication method, apparatus and device, storage medium, chip, and program product |
| WO2024031701A1 (en) * | 2022-08-12 | 2024-02-15 | 富士通株式会社 | Data acquisition method and apparatus |
| WO2024051564A1 (en) * | 2022-09-07 | 2024-03-14 | 维沃移动通信有限公司 | Information transmission method, ai network model training method, apparatus, and communication device |
| WO2024088162A1 (en) * | 2022-10-27 | 2024-05-02 | 维沃移动通信有限公司 | Information transmission method, information processing method, apparatus, and communication device |
| WO2024097693A1 (en) * | 2022-11-04 | 2024-05-10 | Google Llc | Managing machine learning based channel state information reporting at a network |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN114726413A (en) | Channel information acquisition method, device and related equipment | |
| CN101971585B (en) | Method using differentially encoded feedback information in precoded mimo-ofdm systems | |
| KR101481391B1 (en) | Channel state information feedback method and system thereof | |
| EP1568155A2 (en) | Low complexity beamformers for multiple transmit and receive antennas | |
| CN111756457B (en) | Channel prediction method, device and computer storage medium | |
| JP6000305B2 (en) | Channel state information feedback | |
| CN102273154A (en) | Method and apparatus for channel estimation using multiple description codes | |
| CN107566305A (en) | A kind of millimeter-wave systems channel estimation methods of low complex degree | |
| CN108631830B (en) | Method for determining transmitted beam, transmitting end and receiving end | |
| CN114726412B (en) | Channel information acquisition method and device and related equipment | |
| CN102130746B (en) | Network coding feedback method for coordinated multi-point transmission system | |
| WO2023246618A1 (en) | Channel matrix processing method and apparatus, and terminal and network side device | |
| WO2022184010A1 (en) | Information reporting method and apparatus, first device, and second device | |
| WO2009039765A1 (en) | A resisting feedback error method, system and device | |
| CN113067787B (en) | Wireless energy transmission system precoding method based on limited feedback | |
| CN108880642B (en) | Channel vector limited feedback quantization method based on direction marker | |
| KR101997822B1 (en) | Methods for cooperative transmission in multi-cell cooperation systems | |
| CN114598365A (en) | Transmission method, device, equipment and readable storage medium | |
| CN114492784A (en) | Neural network testing method and device | |
| CN101997584B (en) | Method, system and device for determining code word | |
| EP4318990A1 (en) | Network parameter set information transmission method and apparatus, terminal, base station, and medium | |
| WO2023179476A1 (en) | Channel feature information reporting and recovery methods, terminal and network side device | |
| WO2024140422A1 (en) | Ai unit performance monitoring method, terminal and network side device | |
| WO2023179473A1 (en) | Channel feature information reporting method, channel feature information recovery method, terminal and network side device | |
| CN109245810B (en) | Communication processing method, base station and mobile communication terminal |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination |