CN116458094A - Received information processing method, device, computer equipment and storage medium - Google Patents

Received information processing method, device, computer equipment and storage medium Download PDF

Info

Publication number
CN116458094A
CN116458094A CN202180075039.8A CN202180075039A CN116458094A CN 116458094 A CN116458094 A CN 116458094A CN 202180075039 A CN202180075039 A CN 202180075039A CN 116458094 A CN116458094 A CN 116458094A
Authority
CN
China
Prior art keywords
information
transmission mode
received
processing
receiver
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
Application number
CN202180075039.8A
Other languages
Chinese (zh)
Inventor
田文强
肖寒
刘文东
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Guangdong Oppo Mobile Telecommunications Corp Ltd
Original Assignee
Guangdong Oppo Mobile Telecommunications Corp Ltd
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by Guangdong Oppo Mobile Telecommunications Corp Ltd filed Critical Guangdong Oppo Mobile Telecommunications Corp Ltd
Publication of CN116458094A publication Critical patent/CN116458094A/en
Pending legal-status Critical Current

Links

Classifications

    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04B—TRANSMISSION
    • H04B10/00—Transmission systems employing electromagnetic waves other than radio-waves, e.g. infrared, visible or ultraviolet light, or employing corpuscular radiation, e.g. quantum communication
    • H04B10/50—Transmitters
    • H04B10/516—Details of coding or modulation

Landscapes

  • Physics & Mathematics (AREA)
  • Electromagnetism (AREA)
  • Engineering & Computer Science (AREA)
  • Computer Networks & Wireless Communication (AREA)
  • Signal Processing (AREA)
  • Mobile Radio Communication Systems (AREA)

Abstract

The application discloses a received information processing method, a received information processing device, computer equipment and a storage medium, and belongs to the technical field of wireless communication. The method comprises the following steps: performing wireless signal reception to obtain reception information; acquiring transmission mode information corresponding to the received information; determining a receiver model according to the transmission mode information; processing the received information through the receiver model to obtain first information; the receiver model is a machine learning model obtained after training according to the received information samples and the information processing samples. By the scheme, the receiving end equipment can use different receiver models to process data according to different transmission modes of the received information for different received information, so that the accuracy of data processing is improved.

Description

Received information processing method, device, computer equipment and storage medium Technical Field
The present invention relates to the field of wireless communications technologies, and in particular, to a method and apparatus for processing received information, a computer device, and a storage medium.
Background
In a wireless communication system, in order to realize normal transmission of data in free space, a transmitting end needs to encode the data to be transmitted through a transmitter, the data is transmitted to space through an antenna, and electromagnetic signals received by an antenna of a receiving end are sent to a receiver for decoding, so that normal transmission of the data is realized.
In the prior art, the workflow is that a transmitter encodes, modulates, encrypts and the like an information source at a transmitting end to form transmitting information to be transmitted. The sending information is transmitted to the receiving end through the wireless space, the receiving end decodes, decrypts and demodulates the received receiving information, and finally recovers the information source. The receiver has decoding, demodulating, decrypting and other modules separately, and the decoding, demodulating, decrypting and other modules correspond to the encoding, modulating, encrypting and other modules of the transmitter so as to realize normal processing of data.
In the scheme, each module of the receiver is designed corresponding to each module of the transmitter, and the error rate of the receiver during data processing is high.
Disclosure of Invention
The embodiment of the application provides a received information processing method, a received information processing device, computer equipment and a storage medium. The technical scheme is as follows:
In one aspect, an embodiment of the present application provides a method for processing received information, where the method is used for a receiving end device, and the method includes:
performing wireless signal reception to obtain reception information;
acquiring transmission mode information corresponding to the received information;
determining a receiver model according to the transmission mode information;
processing the received information through the receiver model to obtain first information; the receiver model is a machine learning model obtained after training according to the received information samples and the information processing samples.
In still another aspect, an embodiment of the present application provides a received information processing apparatus, where the apparatus is configured to receive a device, and the apparatus includes:
the wireless signal receiving module is used for executing wireless signal receiving to obtain receiving information;
the transmission mode information acquisition module is used for acquiring transmission mode information corresponding to the received information;
the model determining module is used for determining a receiver model according to the transmission mode information;
the first information acquisition module is used for processing the received information through the receiver model to acquire first information; the receiver model is a machine learning model obtained after training according to the received information samples and the information processing samples.
In yet another aspect, an embodiment of the present application provides a computer device, where the computer device is a receiving end device, and the receiving end device includes a processor, a memory, and a transceiver, where the memory stores a computer program, and the computer program is configured to be executed by the processor to implement the above-mentioned received information processing method.
In yet another aspect, embodiments of the present application further provide a computer readable storage medium having a computer program stored therein, the computer program being loaded and executed by a processor to implement the above-described received information processing method.
In another aspect, embodiments of the present application also provide a computer program product or computer program comprising computer instructions stored in a computer-readable storage medium. The processor of the terminal reads the computer instructions from the computer-readable storage medium, and the processor executes the computer instructions so that the terminal performs the above-described reception information processing method.
The technical scheme provided by the embodiment of the application can bring the following beneficial effects:
the receiving end device takes a machine learning model trained through training samples as a receiver model, and processes received information according to the receiver model to obtain first information. By the scheme, the neural network model is applied to the processing mode of the received information, and the receiver model for processing the received information is different according to the different transmission mode information, namely, for different received information, different receiver models can be used for data processing according to the different transmission modes of the received information, so that the accuracy of data processing is improved.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present application, the drawings that are needed in the description of the embodiments will be briefly introduced below, and it is obvious that the drawings in the following description are only some embodiments of the present application, and that other drawings may be obtained according to these drawings without inventive effort for a person skilled in the art.
Fig. 1 is a schematic diagram of a network architecture of a communication system according to an embodiment of the present application.
Fig. 2 shows a signaling flow diagram in a wireless communication system.
Fig. 3 shows a flowchart of a received information processing method provided in an embodiment of the present application.
Fig. 4 shows a flowchart of a received information processing method provided in an embodiment of the present application.
Fig. 5 shows a schematic diagram of a fully connected network involved in the embodiment shown in fig. 4.
Fig. 6 shows a schematic diagram of a convolutional neural network involved in the embodiment shown in fig. 4.
Fig. 7 illustrates a model of a receiver neural network to which the embodiment of fig. 4 relates.
Fig. 8 illustrates a model of a receiver neural network to which the embodiment of fig. 4 relates.
Fig. 9 is a flowchart illustrating a method for processing received information implemented by a receiving end device according to an exemplary embodiment of the present application.
Fig. 10 is a flowchart illustrating a method for processing received information implemented by a receiving end device according to an exemplary embodiment of the present application.
Fig. 11 shows a block diagram of a received information processing apparatus provided in one embodiment of the present application.
Fig. 12 is a schematic structural diagram of a computer device according to an embodiment of the present application.
Detailed Description
For the purpose of making the objects, technical solutions and advantages of the present application more apparent, the embodiments of the present application will be described in further detail below with reference to the accompanying drawings.
The network architecture and the service scenario described in the embodiments of the present application are for more clearly describing the technical solution of the embodiments of the present application, and do not constitute a limitation on the technical solution provided in the embodiments of the present application, and those skilled in the art can know that, with the evolution of the network architecture and the appearance of the new service scenario, the technical solution provided in the embodiments of the present application is also applicable to similar technical problems.
Referring to fig. 1, a schematic diagram of a network architecture of a communication system according to an embodiment of the present application is shown. The network architecture may include: terminal 10, network side equipment 20.
The number of terminals 10 is typically plural, and one or more terminals 10 may be distributed in a cell managed by each network-side device (base station) 20. The terminal 10 may include various handheld devices, vehicle mount devices, wearable devices, computing devices, or other processing devices connected to a wireless modem, as well as various forms of User Equipment (UE), mobile Station (MS), terminal devices (terminal devices), etc. having wireless communication capabilities. For convenience of description, in the embodiment of the present application, the above-mentioned devices are collectively referred to as a terminal.
The network-side device 20 is a means deployed in the access network to provide wireless communication functions for the terminal 10. The network-side device 20 may include various forms of macro network-side devices, micro network-side devices, relay stations, access points, and the like. In systems employing different Radio access technologies, the names of devices with network side device functions may be different, for example, in a 5G New Radio (NR) system, the network side device (i.e., a base station) is called a gndeb or a gNB. As communication technology evolves, the name "base station" may change. For convenience of description, in the embodiments of the present application, the above-mentioned devices for providing the wireless communication function for the terminal 10 are collectively referred to as network side devices.
Optionally, not shown in fig. 1, the network architecture further includes other network devices, such as: a central control node (Central network control, CNC), session management functions (Session management function, SMF), user plane functions (User Plane Function, UPF) devices or AMF (Access and Mobility Management Function, access and mobility management functions) devices, and so on.
The "5G NR system" in the embodiments of the present disclosure may also be referred to as a 5G system or an NR system, but a person skilled in the art may understand the meaning thereof. The technical scheme described in the embodiment of the disclosure can be applied to a 5G NR system and also can be applied to a subsequent evolution system of the 5G NR system.
Referring to fig. 2, a signaling flow diagram in a wireless communication system is shown. As shown in fig. 2, in the wireless communication system, a transmitter device 201 transmits source information 200 in a processing manner such as encoding, modulation, encryption, etc., then transmits transmission information 202 corresponding to the source information 200 to an external free space via a transmission antenna, and after the transmission information propagates in the free space, the transmission information is affected by a channel environment and interference noise in the free space, and is received by a receiving antenna, and is converted into a receiving signal 203 recognizable by a receiver, and transmitted to a receiver device 204, and the receiver device 204 decodes, demodulates, decrypts, etc. the receiving signal 203, and then restores the data processing manner to source information or restoration information 205, and the restoration information can be restored to source information by further data processing.
Referring to fig. 3, a flowchart of a method for processing received information according to an embodiment of the present application is shown, where the method may be performed by a receiving end device, and the receiving end device may be the terminal 10 or the network side device 20 in the network architecture shown in fig. 1. The method may comprise the following steps:
step 310, wireless signal reception is performed to obtain reception information.
The receiving end device is a device for implementing all or part of functions of a receiver in a wireless communication system, that is, the receiving end device may be used for implementing part or all of functions such as decoding, demodulation, and decryption.
In one possible implementation, the received information is digital signal information formed by digital-to-analog conversion of an analog signal formed by the receiving antenna after receiving an electromagnetic wave signal in free space.
In one possible implementation, the received information is a quasi-modulation symbol.
In a wireless communication system, a transmitter modulates and encodes source information to form a modulation symbol, and the modulation symbol is transmitted to a spatial channel in free space through an antenna and transmitted to a receiving end device. The receiving signal received by the receiving end device is a quasi-modulation symbol which is received by the receiving end device through an antenna and subjected to analog-to-digital conversion after the modulation symbol is transmitted through a space channel and is subjected to noise interference.
Step 320, obtaining the transmission mode information corresponding to the received information.
In one possible implementation manner, the transmission mode information is used to indicate a transmission scheme corresponding to the received information. The transmission scheme is a configuration scheme used by the transmitting end device to transmit the received information.
Step 330, determining a receiver model according to the transmission mode information.
For different transmission mode information, different receiver models can exist in the receiving end device, so that the processing of the received information of the different transmission mode information can be realized according to the different receiver models.
Step 340, processing the received information through the receiver model to obtain first information; the receiver model is a machine learning model obtained after training according to the received information samples and the information processing samples.
The receiver model may be obtained by training with the received information samples as input and the information processing samples as labels.
Wherein the received information sample is the same type of information as the received information and the information processing sample is the same type of information as the first information.
In summary, according to the scheme shown in the embodiment of the present application, the receiving end device uses the machine learning model trained by the training sample as the receiver model, and processes the received information according to the receiver model, so as to obtain the first information. By the scheme, the neural network model is applied to the processing mode of the received information, and the receiver model for processing the received information is different according to the different transmission mode information, namely, for different received information, different receiver models can be used for data processing according to the different transmission modes of the received information, so that the accuracy of data processing is improved.
Referring to fig. 4, a flowchart of a method for processing received information according to an embodiment of the present application is shown, where the method may be performed by a receiving end device, and the receiving end device may be the terminal 10 or the network side device 20 in the network architecture shown in fig. 1. The method may comprise the following steps:
step 401, performing wireless signal reception to obtain reception information.
In one possible implementation manner, when the receiving end device is a terminal, the received information may be information formed by channel interference and device noise of the receiving end device after information sent by the network side device.
In another possible implementation manner, when the receiving end device is a network side device, the received information may be information formed by the information uploaded by the terminal after channel interference and device noise of the receiving end device on the network side.
Step 402, obtaining transmission mode information corresponding to the received information.
In one possible implementation, the transmission mode information includes at least one of modulation mode and Multiple-In Multiple-Out (MIMO) configuration information.
The modulation mode is a modulation mode corresponding to the received information, that is, the transmitting end equipment corresponding to the received information modulates the information source information to be transmitted according to the modulation mode, and then the received information can be formed after channel interference and equipment noise of the receiving end equipment. The MIMO configuration information is information of an antenna port and a precoding scheme used when the transmitting end device corresponding to the receiving information transmits the information corresponding to the receiving information.
In one possible implementation manner, when the receiving end device is a network side device, determining a transmission manner corresponding to the received information; the transmission mode is a transmission mode used by a terminal for transmitting the sending information corresponding to the receiving information; the transmission mode is issued to the terminal; and acquiring the transmission mode information corresponding to the received information according to the transmission mode.
When the receiving end device is a network side device, that is, the network side device needs to receive the receiving information and process the receiving information, at this time, the network side device indicates the communication configuration between the terminal and the network side device in advance, that is, determines the transmission mode between the network side device and the terminal, and then issues the transmission mode to the terminal, so as to instruct the terminal to send the sending information obtained after the information source information is coded and the like according to the transmission mode to the spatial channel.
The network side equipment can receive the receiving information formed by the transmitting information after being interfered by space channels and the like, and simultaneously determines the transmission mode information corresponding to the receiving information according to the transmission mode corresponding to the receiving information.
For example, the interaction process between the network side device and the terminal may be performed as follows: the network side equipment firstly designates a transmission mode of the sending information corresponding to the terminal, and sends the transmission mode to the terminal through a downlink signaling, for example, a broadcast message or an RRC (Radio Resource Control ) message is sent to the terminal, after the terminal receives the downlink signaling, the terminal configures the transmission mode of the network side equipment according to the configuration information in the downlink signaling, processes the information source information through the transmission mode, and sends the obtained sending information to a free space; the network side equipment receives the receiving information formed by the sending information after interference, and determines the transmission mode information (for example, the identification information corresponding to the transmission mode) corresponding to the transmission mode according to the transmission mode of the receiving information.
In another possible implementation manner, when the receiving end device is a terminal, the transmission mode information sent by the network side device is received.
Step 403, determining a receiver model according to the transmission mode information.
In one possible implementation, the receiver model is stored in the receiving device, and after determining the transmission mode information, the receiver model is directly selected in the receiving device according to the transmission mode information.
In another possible implementation manner, the receiver model is stored in a corresponding sender device, and after determining the transmission mode information, the receiver device may send a model acquisition request to the sender device, so that the sender device issues the model.
In one possible implementation, the model structure and/or model parameters of the receiver model are determined from the transmission mode information.
After determining the transmission mode information of the received information, determining a model structure of the receiver model according to the transmission mode information; or model parameters of the receiver model may be determined based on the transmission mode; or the model structure and model parameters of the receiver model may be determined based on the transmission scheme.
In one possible implementation manner, transmission characteristic information corresponding to the received information is obtained; and determining the receiver model according to the transmission mode information and the transmission characteristic information.
In one possible implementation manner, the transmission characteristic information includes at least one of data characteristic information of the received information and channel information corresponding to the received information; the data characteristic information is used for indicating the data type of the received information; the channel information is used to indicate channel conditions of a channel used to transmit the received information.
In a possible implementation manner, when the receiving end device is a terminal, the transmission characteristic information is determined by the terminal according to source information corresponding to the receiving information and a transmission channel corresponding to the receiving information, for example, the data characteristic information may be determined according to the source information corresponding to the receiving information, and the channel information may be determined according to a condition of the transmission channel corresponding to the receiving information detected by the terminal.
In one possible implementation, the channel condition may be used to indicate the attenuation of the signal in the transmission channel to which the received information corresponds. For example, the channel information may be channel state information CSI (Channel State Information), i.e., the channel information may be a channel property of the communication link, where the channel state of the channel may indicate attenuation factors (i.e., signal scattering, environmental attenuation, distance attenuation, etc.) of the signal on the various transmission paths of the channel.
In one possible implementation, the data characteristic information may be used to indicate at least one of a data size, a data priority, and a data type of the source information corresponding to the received information.
The priority of the data is used for indicating the importance degree of the information source information corresponding to the received information; the data type is used for indicating type information corresponding to the source information, for example, the data type is used for indicating that the source information corresponding to the receiving information is configuration information or request information.
The transmission characteristic information corresponding to the received information may be issued through downlink signaling.
In another possible implementation manner, when the receiving end device is a network side device, the transmission characteristic information may be uploaded to the network side device after the terminal determines.
Step 404, processing the received information by the receiver model to obtain first information.
In one possible implementation manner, the first information is information source information corresponding to the received information; or, the first information is used for recovering the information source information corresponding to the received information.
The receiver model may be used to implement all or part of functions of the receiver, when the receiver model is used to implement all functions of the receiver, that is, when the receiver model may implement all operations such as decoding, decrypting, demodulating, etc. on the received information, the first information obtained after the received information is processed by the receiver model is the information source information corresponding to the received information, where the receiver model may be equivalently used as the receiver to process the received signal.
When the receiver model is used for realizing part of functions of the receiver, the receiver model can realize part of operations in decoding, decrypting and demodulating the received information, namely, the first information obtained after the received information is processed by the receiver model needs to be further processed to recover the information source information corresponding to the received information, and the receiver model can be equivalent to a part of modules of the receiver to process the received signal.
In one possible implementation, the receiver model is a fully connected neural network model consisting of N fully connected layers, N is greater than or equal to 1, and N is an integer.
The receiver model may employ a fully-connected network, please refer to fig. 5, which illustrates a fully-connected network schematic diagram according to an embodiment of the present application. As shown in fig. 5, the fully connected network constitutes an AI (Artificial Intelligence ) receiver. The fully-connected network is composed of N fully-connected layers 502, and the number of neurons of each fully-connected layer is Cn. An AI receiver configured by a fully-connected network may be used to implement processing of the received information 501 into the first information 503 to implement all or part of the receiver's functionality.
In one possible implementation, the receiver model is a convolutional neural network model consisting of M convolutional layers, M.gtoreq.1, and M is an integer.
The receiver model may also adopt a convolutional neural network, and fig. 6 shows a schematic diagram of the convolutional neural network according to an embodiment of the present application. As shown in fig. 6, the convolutional neural network constitutes an AI receiver. The convolutional neural network is composed of M layers of convolutional layers 602, the number of convolutional kernels of the M-th layer is Km, the dimension of the convolutional kernel of the M-th layer is Pm, and the size of the convolutional kernel is Dm= [ D_1 (M), D_2 (M) and … D_Pm (M) ]. The AI receiver configured by the convolutional neural network may also be used to process the received information 601 into the first information 603, thereby realizing all or part of the functions of the receiver.
The above designs of the fully-connected network-based neural network and the convolutional-based neural network can be used singly or jointly, and can also be added with an activation layer, a normalization layer, a quantization layer and other independent network layers.
In one possible implementation, the receiver model includes a first fully-connected layer, a second fully-connected layer, a common layers, a first convolutional layer, and a second convolutional layer; each public layer comprises a third convolution layer, a normalization layer and an activation layer which are sequentially connected; the A public layers are connected in sequence; a is more than or equal to 1, and A is an integer;
Processing the received information according to the first full connection layer to obtain first characteristic information; processing the first characteristic information according to the A public layers, the first convolution layer and the second convolution layer to obtain second characteristic information; obtaining third characteristic information according to the first characteristic information and the second characteristic information; and processing the third characteristic information according to the second full connection layer to obtain the first information.
The first full-connection layer includes a single full-connection layer, or is formed by sequentially connecting at least two full-connection layers, that is, the number of layers of the first full-connection layer may be 1, or may be 2 or more than 2.
Similarly, the first convolution layer comprises a single convolution layer, or is formed by sequentially connecting at least two convolution layers; the second convolution layer comprises a single convolution layer, or is formed by sequentially connecting at least two convolution layers; the third convolution layer comprises a single convolution layer, or is formed by sequentially connecting at least two convolution layers; the second full-connection layer comprises a single full-connection layer or is formed by sequentially connecting at least one full-connection layer.
In one possible implementation manner, the received information is input into the first full connection layer to obtain first feature extraction information; and carrying out dimension adjustment on the first feature extraction information to obtain the first feature information.
The received information is continuous data in the time domain, so that longer vector data is obtained after full-connection interlayer characteristic extraction, and the vector data is unfavorable to be processed through a neural network model, so that the vector data can be dimensionally adjusted to be matrix data, and the neural network model is convenient to process the data.
In a possible implementation manner, the third characteristic information is subjected to dimension adjustment to obtain dimension adjustment information; and processing the dimension adjustment information according to the second full connection layer to obtain the first information.
After the one-dimensional vector data is converted into matrix data through dimension transformation and the second characteristic information is processed through a convolution layer and a public layer, two-dimensional matrix data are still obtained, and in the process of processing the data by a receiver, finally one-dimensional data which are continuous in time domain are needed to be obtained, so that dimension adjustment is needed to be carried out on the third characteristic information in the form of the matrix, and the one-dimensional vector data which are continuous in time domain are obtained.
In one possible implementation manner, the first feature information is sampled to obtain first feature sampling information; and obtaining the third characteristic information according to the first characteristic sampling information and the second characteristic information.
After the first characteristic information is processed according to the convolution layer and the public layer, more original information may be lost, in order to ensure the authenticity of the data, the first characteristic information needs to be sampled, the first characteristic sampled information is obtained, and the first characteristic sampled information and the second characteristic information are overlapped (namely, jump link in neural network training) to form a depth residual network (Deep residual network, resNet), so that the accuracy of decoding of the neural network model is ensured. Where depth residual network res net is a residual block consisting of a series of residual blocks, one can be expressed as:
x l+1 ＝x l +f(x l ,w l )
the residual block is divided into two parts, a direct mapped part and a residual part. X is x l Is a direct mapped part, f (x l ,w l ) The residual part is generally formed by two or three convolution operations, and the forward transmission of the neural network is realized through the residual block, so that the network of the first layer (1) is ensured to contain more image information than the network of the first layer (1), and the gradient vanishing problem when the level of the neural network is larger is solved.
As shown in fig. 7, which illustrates a receiver neural network model according to an embodiment of the present application. As shown in fig. 7, the received signal 701 is firstly subjected to feature extraction through the full connection layer 702, then subjected to dimension adjustment through the dimension adjustment module 703, the feature after dimension adjustment is sampled to obtain a sampled feature, the feature after dimension adjustment synchronously enters the convolution layer 704 to perform feature extraction, then enters the a serial connected common layer modules 705, is subjected to superposition of the sampled feature after passing through the convolution layer 706 and the sampled feature after sampling, is subjected to dimension adjustment through the dimension adjustment module 707, and is processed through the full connection layer 708, and finally, the first information 709 is obtained as output. Each common layer module 705 in fig. 7 is formed by concatenating a convolution layer, a normalization layer, and an activation function.
As shown in fig. 8, a receiver neural network model is shown, to which embodiments of the present application relate. As shown in fig. 8, the received signal 801 is first subjected to feature extraction through a fully connected layer of 1024 neurons. Wherein the received signal 801 may be 512 modulation symbols modulated by means of QPSK (Quadrature Phase Shift Keying ). The 1024 neurons in the fully connected layer 802 perform feature extraction on the 512 modulation symbols in a fully connected manner, and the obtained dimension is 1024×1 features.
The feature with dimension 1024×1 is input into the releasrel layer 803, that is, the non-linear conversion is realized through the releasrel activation function, then the samples are sampled after dimension adjustment (2-dimensional data adjusted to 32×32), then the samples enter the convolution layer 804 formed by 256 convolution kernels, then the features are extracted by entering the 18 serial connected common layer modules 805, each common module is formed by a 256-kernel convolution layer, a normalization layer and an activation function releasrel layer, the samples are superimposed with the original samples after passing through the convolution layer 806 formed by 1 convolution kernel, the vectors with length 1024×1 are obtained after dimension adjustment, and finally the first information 809 is obtained as output through the full connection layer 807 formed by 1024 neurons and the sigmoid activation function layer 808.
In one possible implementation, a training sample set is obtained; the training sample set comprises the received information samples and information processing samples; the receiver model is trained based on the training sample set.
The received information sample and the received information are the same type of information, and the information processing sample and the first information are the same type of information. Training the receiver model according to the training sample set can enable the receiver model to process input received information to obtain first information corresponding to the received information.
In one possible implementation manner, the first information is information source information corresponding to the received information; the information processing sample is information source information corresponding to the received information sample.
When the information processing sample is the information source information corresponding to the received information sample, the received information can be processed according to the received information sample and the receiver model trained by the information processing sample to obtain first information, and the first information is the information source information corresponding to the received information. That is, when the information processing sample is the source information corresponding to the received information sample, the receiver model obtained according to the received information sample and the information processing sample may have all functions of a receiver, so as to implement direct processing and restoration of the received information into the source information corresponding to the received information.
In another possible implementation manner, the first information is used for obtaining information source information corresponding to the received information after the first processing, and the information processing sample is obtained after the second processing of the information source information corresponding to the received information sample.
Wherein the first processing includes at least one of a decryption operation, a decoding operation, a demodulation operation; the second process includes at least one of an encryption operation, a coding operation, and a modulation operation.
In one possible implementation, the first process is an inverse process operation corresponding to the second process.
For example, when the first process is a decryption operation, the second process is an inverse process operation corresponding to the decryption operation, i.e., an encryption operation; alternatively, when the first process includes a decoding operation and a demodulation operation, the second process is an inverse process operation of the first process, i.e., the second process includes an encoding operation and a modulation operation.
When the information processing sample is an encrypted information processing sample obtained after the information source information corresponding to the received information sample is subjected to a second process (taking the second process as an encryption operation as an example), the information processing sample also needs to form sending information corresponding to the information processing sample through operations such as coding, modulation and the like, and the sending information forms a received information sample after channel interference and is received by a receiver. In this case, the training target of the receiver model is to process the received information sample into a corresponding information processing sample, so the first information obtained by processing the received information sample and the receiver model where the information processing sample is trained should also be encrypted source information, and therefore the first information needs to be subjected to a first process (i.e. a decoding operation corresponding to a second process) to obtain the source information.
In another possible implementation, the receiver model may only choose to train the receiver model to a model that implements part of the receiver functionality when processing based on the received information samples and the information processing samples (i.e., the source information corresponding to the receiver samples). For example, when the receiver model is trained, a data processing model (for example, the data processing model implements the function of the decryption module) may be added after the receiver model, and at this time, the data input by the receiver model after inputting the received information sample needs to be input to the decryption module for decryption processing, so as to obtain the prediction information corresponding to the information processing sample, and at this time, the receiver model may implement updating of the receiver model according to the prediction information and the information processing sample by using a back propagation algorithm. After the receiver model is processed by a large number of received information samples and information processing samples, the receiver model can process the received information into encrypted information source information, and the encrypted information source information can obtain the information source information corresponding to the received information after passing through a decryption module.
The decryption module in the above scheme may be replaced by another functional module, that is, by the received information sample and the information processing sample (the source information corresponding to the received information sample), the training of the receiver model into a machine learning model capable of implementing data processing of all or part of functions on the received information sample may be implemented.
In another possible implementation manner, when the information processing sample is recovery information for recovering source information, the received information may be processed according to the received information sample and a receiver model trained by the information processing sample, so as to obtain the first information for recovering the source information.
In one possible implementation, the training sample set further includes at least one of sample transmission mode information and sample transmission feature information; the sample transmission characteristic information includes at least one of data characteristic information and channel characteristic information.
Determining a receiver model corresponding to the training sample set according to at least one of the sample transmission characteristic information and the sample transmission mode information; based on the training sample set, the receiver model corresponding to the training sample set is trained.
The sample transmission mode information is the same type of information as the transmission mode information, and the sample transmission characteristic information is the same type of information as the sample transmission characteristic information. When the receiver model is trained through the training sample set, different receiver models can be determined through sample transmission mode information and sample transmission characteristic information, and after the receiver model is determined according to at least one of the sample transmission mode information and the sample transmission characteristic information, the receiver model is trained according to the training sample set. That is, different receiver models can be determined according to the sample transmission mode information and the sample transmission characteristic information, different transmission mode information and different transmission characteristic information are corresponding to each receiver model after training according to different training sample sets, and the trained receiver model is selected according to the transmission mode information and the transmission characteristic information, so that the data processing effect of the receiver can be improved under the transmission mode corresponding to the transmission mode information and the transmission characteristic information.
In one possible implementation, the training process of the receiver model is trained in the receiver device, and the trained receiver model is directly stored in the memory of the receiver device.
In one possible implementation, a receiver model issued by a sender device is received.
The training process of the receiver model can also be training in the transmitting end equipment, the transmitting end equipment can firstly issue the receiver model to the transmitting end equipment before the receiving end equipment communicates, and the transmitting end equipment processes the received information corresponding to the transmitting end equipment according to the receiver model, so that only the equipment receiving the receiver model can normally process the information, and the confidentiality of the information is improved.
In one possible implementation, the training process of the receiver model is as follows:
1) Initializing a receiver model
And the training equipment corresponding to the receiver model initializes the weight parameters corresponding to the receiver model according to the set model structure of the receiver model so as to obtain an initial untrained receiver model. The initialization process may be to perform random assignment on each weight parameter of the receiver model, or input a preset initial value into the receiver model.
2) Inputting received information samples into a receiver model
Acquiring a training sample set corresponding to the receiver model, wherein a receiving information sample corresponding to the receiver model exists in the training sample set, and inputting the receiving information sample into the receiver model to obtain a predicted sample value corresponding to the receiving information sample output by the receiver model; and inputting the predicted sample value and the information processing sample corresponding to the received information sample into a loss function to obtain a loss function value corresponding to the received information sample.
3) Updating weight parameters of a receiver model
After the loss function value corresponding to the received information sample is obtained according to the loss function, gradient updating can be carried out on the receiver model according to the loss function value through a back propagation algorithm. The receiver model may be gradient updated by a back-propagation algorithm based on one loss function value, or gradient updated by a back-propagation algorithm based on multiple loss function values (e.g., by a sum of multiple loss function values or a mean of multiple loss function values). The loss function may be an appropriate loss function according to the type of signal and the structure of the model, for example, a cross entropy loss function, etc., and is not limited herein.
4) Obtaining a trained receiver model
Repeating the above process until the training meets the specified condition, and acquiring the trained model as a trained receiver model to realize the processing of the received information. The specified condition may be that the training number reaches a training threshold, or the specified condition may be that the accuracy of the receiver model when verified by the verification set is greater than a verification threshold.
The model training process can be applied to models with different structures. For example, the fully connected neural network model, the convolutional neural network model, the depth residual network, and the like can be used for training the network model weights through the model training process.
In summary, in the scheme shown in the embodiment of the present application, the receiving end device uses the machine learning model trained by the training sample as the receiver model, and processes the received information according to the receiver model, so as to obtain the first information. By the scheme, the neural network model is applied to the processing mode of the received information, and the receiver model for processing the received information is different according to the different transmission mode information, namely, for different received information, different receiver models can be used for data processing according to the different transmission modes of the received information, so that the accuracy of data processing is improved.
Fig. 9 is a flowchart illustrating a method for processing received information implemented by a receiving end device according to an exemplary embodiment of the present application. The receiving end device is a terminal, and the receiving information received by the terminal is issued from a network side device, as shown in fig. 9:
s901, the terminal receives transmission mode information issued by network side equipment.
When the terminal communicates with the network side device by receiving the information, the terminal needs to receive the transmission mode information issued by the network side device first so as to determine the processing mode of the terminal for the information issued by the network side device.
S902, the terminal acquires the received information.
The receiving information is a transmitting information obtained by encoding, modulating and encrypting the information source information by the network side equipment, and is formed by interference of channels and the like in a free space.
S903, the terminal determines the receiver model according to the transmission mode information issued by the network side equipment.
In one possible implementation, the receiver model may be pre-trained by the terminal and stored in the memory of the terminal.
In another possible implementation, the receiver model may be well trained by the network-side device to be delivered to the terminal and stored in the terminal-side memory.
In another possible implementation manner, the receiver model may also be that the network side device responds to the sending information corresponding to the sending source information and issues the sending information to the terminal according to the downlink signaling.
And S904, the terminal processes the received information according to the receiver model corresponding to the transmission mode information to obtain first information.
The first information may be information source information corresponding to the received information, or recovery information of the information source information that needs to be obtained after processing.
Fig. 10 is a flowchart illustrating a method for processing received information implemented by a receiving end device according to an exemplary embodiment of the present application. The receiving end device is a network side device, and the receiving information received by the network side device is sent by the terminal. As shown in fig. 10:
s1001, the network side device determines a transmission mode.
That is, when the terminal transmits the transmission information corresponding to the source information to the free space, the terminal needs to acquire the indication information of the network side device first so as to determine the transmission mode of the source information.
S1002, the terminal receives a transmission mode issued by the network side device.
S1003, the terminal sends sending information corresponding to the information source information to the space according to the transmission mode, and the network side equipment receives receiving information corresponding to the information source information.
The received information is obtained by the transmission information after the interference of a channel and the like.
S1004, the network side equipment determines the transmission mode information corresponding to the received information according to the transmission mode issued to the terminal.
The transmission mode information may be an ID identifier corresponding to the transmission mode.
S1005, the network side equipment determines the receiver model according to the transmission mode information.
The receiver model is trained in advance by the network side device, and the network side device can determine the receiver model corresponding to the transmission mode information according to the transmission mode information (ID identification).
S1006, the network side equipment processes the received information through the receiver model to obtain first information.
The first information may be information source information corresponding to the received information, or recovery information of the information source information that needs to be obtained after processing.
The following are device embodiments of the present application, which may be used to perform method embodiments of the present application. For details not disclosed in the device embodiments of the present application, please refer to the method embodiments of the present application.
Referring to fig. 11, a block diagram of a received information processing apparatus according to an embodiment of the present application is shown. The device is used for receiving end equipment and has the function of realizing the received information processing method. As shown in fig. 11, the apparatus may include:
A wireless signal receiving module 1101 for performing wireless signal reception to obtain reception information;
a transmission mode information obtaining module 1102, configured to obtain transmission mode information corresponding to the received information;
a model determining module 1103, configured to determine a receiver model according to the transmission mode information;
a first information obtaining module 1104, configured to process the received information through the receiver model to obtain first information; the receiver model takes a received information sample as input, and takes an information processing sample as a label to train so as to obtain a machine learning model.
In a possible implementation manner, the first information is information source information corresponding to the received information; the information processing sample is information source information corresponding to the received information sample.
In a possible implementation manner, the first information is used for obtaining information source information corresponding to the received information after first processing; the information processing sample is obtained by performing second processing on information source information corresponding to the received information sample.
In one possible implementation, the first process is an inverse process operation corresponding to the second process.
In one possible implementation manner, when the receiving end device is a network side device, the apparatus further includes:
the transmission mode determining module is used for determining a transmission mode corresponding to the received information; the transmission mode is a transmission mode used by the terminal for transmitting the sending information corresponding to the receiving information;
a transmission mode issuing module, configured to issue the transmission mode to a terminal;
the transmission mode information obtaining module 1102 is configured to,
and acquiring the transmission mode information corresponding to the received information according to the transmission mode.
In one possible implementation manner, when the receiving end device is a terminal, the transmission manner information obtaining module 1102 is configured to,
and receiving the transmission mode information issued by the network side equipment.
In one possible implementation, the transmission mode information includes at least one of a modulation mode and MIMO configuration information.
In one possible implementation, the module determines a first module for determining, for each of the first and second modules,
determining a model structure and/or model parameters of the receiver model according to the transmission mode information;
in one possible implementation, the apparatus further includes:
The transmission characteristic information acquisition module is used for acquiring transmission characteristic information corresponding to the received information;
the model determination module 1103 is further configured to, in use,
and determining the receiver model according to the transmission mode information and the transmission characteristic information.
In a possible implementation manner, the transmission characteristic information includes at least one of data characteristic information of the received information and channel information corresponding to the received information;
the data characteristic information is used for indicating the data type of the received information; the channel information is used to indicate channel conditions of a channel used to transmit the received information.
In one possible implementation, the receiver model is a fully connected neural network model consisting of N fully connected layers, N is greater than or equal to 1, and N is an integer.
In one possible implementation, the receiver model is a convolutional neural network model consisting of M layers of convolutional layers, M is greater than or equal to 1, and M is an integer.
In one possible implementation, the receiver model includes a first fully-connected layer, a second fully-connected layer, a common layers, a first convolutional layer, and a second convolutional layer; each public layer comprises a third convolution layer, a normalization layer and an activation layer which are sequentially connected; the A public layers are connected in sequence; a is more than or equal to 1, and A is an integer;
The first information acquisition module 1104 includes:
the first characteristic information acquisition unit is used for processing the received information according to the first full-connection layer to acquire first characteristic information;
the second characteristic information acquisition unit is used for processing the first characteristic information according to the A public layers, the first convolution layer and the second convolution layer to obtain second characteristic information;
the third characteristic information acquisition unit is used for acquiring third characteristic information according to the first characteristic information and the second characteristic information;
and the first information acquisition unit is used for processing the third characteristic information according to the second full-connection layer to acquire the first information.
In one possible implementation manner, the first feature information obtaining unit includes:
the first feature extraction subunit is used for inputting the received information into the first full-connection layer to obtain first feature extraction information;
the first dimension adjusting unit is used for dimension adjusting the first feature extraction information to obtain the first feature information;
the first information acquisition unit includes:
the second dimension adjustment subunit is used for carrying out dimension adjustment on the third characteristic information to obtain dimension adjustment information;
And the first information acquisition subunit is used for processing the dimension adjustment information according to the second full-connection layer to acquire the first information.
In a possible implementation manner, the third feature information obtaining unit is further configured to,
sampling the first characteristic information to obtain first characteristic sampling information;
and obtaining the third characteristic information according to the first characteristic sampling information and the second characteristic information.
In one possible implementation, the apparatus further includes:
the training sample set acquisition module is used for acquiring a training sample set; the training sample set comprises the received information samples and the information processing samples;
and the receiver training module is used for training the receiver model according to the training sample set.
In one possible implementation manner, the training sample set further includes at least one of sample transmission mode information and sample transmission characteristic information; the sample transmission characteristic information includes at least one of data characteristic information and channel characteristic information;
the receiver training module comprises:
a receiver model determining unit, configured to determine a receiver model corresponding to the training sample set according to at least one of the sample transmission characteristic information and the sample transmission mode information;
And the receiver training submodule is used for training the receiver model corresponding to the training sample set based on the training sample set.
In one possible implementation, the apparatus further includes:
and the module receiving module is used for receiving the receiver model issued by the transmitting end equipment.
In summary, according to the scheme shown in the embodiment of the present application, the receiving end device uses the machine learning model trained by the training sample as the receiver model, and processes the received information according to the receiver model, so as to obtain the first information. By the scheme, the neural network model is applied to the processing mode of the received information, and the receiver model for processing the received information is different according to the different transmission mode information, namely, for different received information, different receiver models can be used for data processing according to the different transmission modes of the received information, so that the accuracy of data processing is improved.
It should be noted that, when the apparatus provided in the foregoing embodiment performs the functions thereof, only the division of the respective functional modules is used as an example, in practical application, the foregoing functional allocation may be performed by different functional modules according to actual needs, that is, the content structure of the device is divided into different functional modules, so as to perform all or part of the functions described above.
The specific manner in which the various modules perform the operations in the apparatus of the above embodiments have been described in detail in connection with the embodiments of the method, and will not be described in detail herein.
Referring to fig. 12, a schematic structural diagram of a computer device 1200 according to an embodiment of the present application is shown. The computer device 1200 may include: a processor 1201, a receiver 1202, a transmitter 1203, a memory 1204, and a bus 1205.
The processor 1201 includes one or more processing cores, and the processor 1201 executes various functional applications and information processing by running software programs and modules.
The receiver 1202 and the transmitter 1203 may be implemented as one communication component, which may be a communication chip. The communication chip may also be referred to as a transceiver.
The memory 1204 is connected to the processor 1201 by a bus 1205.
The memory 1204 may be used for storing a computer program, and the processor 1201 is configured to execute the computer program to implement the steps performed by the server device, the configuration device, the cloud platform, or the account server in the above method embodiment.
Further, the memory 1204 may be implemented by any type or combination of volatile or nonvolatile memory devices including, but not limited to: magnetic or optical disks, electrically erasable programmable read-only memory, static random access memory, read-only memory, magnetic memory, flash memory, programmable read-only memory.
In an exemplary embodiment, the computer device includes a processor, a memory, and a transceiver (which may include a receiver for receiving information and a transmitter for transmitting information);
in one possible implementation, when the computer device is implemented as a receiving end device, the terminal includes a processor, a memory, and a transceiver;
the receiver is used for performing wireless signal reception to obtain reception information;
the processor is used for acquiring the transmission mode information corresponding to the received information;
the processor is used for determining a receiver model according to the transmission mode information;
the processor is used for processing the received information through the receiver model to obtain first information; the receiver model is a machine learning model obtained after training according to the received information samples and the information processing samples.
The processor and the transceiver in the receiving end device according to the embodiments of the present application may execute the steps executed by the receiving end device in the method for processing the received information shown in fig. 3 or fig. 4, which are not described herein again.
The embodiment of the present application also provides a computer readable storage medium having a computer program stored therein, the computer program being loaded and executed by a processor to implement each step in the received information processing method shown in any one of fig. 3 or fig. 4.
The present application also provides a computer program product or computer program comprising computer instructions stored in a computer readable storage medium. The processor of the computer device reads the computer instructions from the computer-readable storage medium, and the processor executes the computer instructions so that the computer device performs the steps in the received information processing method shown in fig. 3 or fig. 4 described above.
Those skilled in the art will appreciate that in one or more of the examples described above, the functions described in the embodiments of the present application may be implemented in hardware, software, firmware, or any combination thereof. When implemented in software, these functions may be stored on or transmitted over as one or more instructions or code on a computer-readable medium. Computer-readable media includes both computer storage media and communication media including any medium that facilitates transfer of a computer program from one place to another. A storage media may be any available media that can be accessed by a general purpose or special purpose computer.
The foregoing description of the exemplary embodiments of the present application is not intended to limit the invention to the particular embodiments disclosed, but on the contrary, the intention is to cover all modifications, equivalents, alternatives, and alternatives falling within the spirit and scope of the invention.

Claims (38)

  1. A method of processing received information, the method being for a receiving-end device, the method comprising:
    performing wireless signal reception to obtain reception information;
    acquiring transmission mode information corresponding to the received information;
    determining a receiver model according to the transmission mode information;
    processing the received information through the receiver model to obtain first information; the receiver model is a machine learning model obtained after training according to the received information samples and the information processing samples.
  2. The method of claim 1, wherein the first information is source information corresponding to the received information; the information processing sample is information source information corresponding to the received information sample.
  3. The method of claim 1, wherein the first information is used for obtaining source information corresponding to the received information after a first process; the information processing sample is obtained by performing second processing on information source information corresponding to the received information sample.
  4. A method according to claim 3, wherein the first process is an inverse process operation corresponding to the second process.
  5. The method of claim 1, wherein when the receiving end device is a network side device, before the obtaining the transmission mode information corresponding to the receiving information, the method further comprises:
    determining a transmission mode corresponding to the received information; the transmission mode is a transmission mode used by the terminal for transmitting the sending information corresponding to the receiving information;
    the transmission mode is issued to the terminal;
    the obtaining the transmission mode information corresponding to the received information includes:
    and acquiring the transmission mode information corresponding to the received information according to the transmission mode.
  6. The method of claim 5, wherein when the receiving end device is a terminal, the obtaining the transmission mode information corresponding to the receiving information includes:
    and receiving the transmission mode information issued by the network side equipment.
  7. The method according to any one of claims 1 to 6, wherein the transmission mode information includes at least one of modulation mode and MIMO configuration information.
  8. The method according to any one of claims 1 to 6, wherein said determining said receiver model from said transmission mode information comprises:
    And determining a model structure and/or model parameters of the receiver model according to the transmission mode information.
  9. The method according to any one of claims 1 to 6, wherein before determining the receiver model according to the transmission scheme, further comprising:
    acquiring transmission characteristic information corresponding to the received information;
    the determining the receiver model according to the transmission mode information comprises the following steps:
    and determining the receiver model according to the transmission mode information and the transmission characteristic information.
  10. The method of claim 9, wherein the transmission characteristic information includes at least one of data characteristic information of the received information and channel information corresponding to the received information;
    the data characteristic information is used for indicating the data type of the received information; the channel information is used to indicate channel conditions of a channel used to transmit the received information.
  11. The method of any one of claims 1 to 6, wherein the receiver model is a fully connected neural network model consisting of N fully connected layers, N is greater than or equal to 1, and N is an integer.
  12. The method of any one of claims 1 to 6, wherein the receiver model is a convolutional neural network model consisting of M convolutional layers, M is ≡1, and M is an integer.
  13. The method of any of claims 1 to 6, wherein the receiver model comprises a first fully connected layer, a second fully connected layer, a common layers, a first convolutional layer, and a second convolutional layer; each public layer comprises a third convolution layer, a normalization layer and an activation layer which are sequentially connected; the A public layers are connected in sequence; a is more than or equal to 1, and A is an integer;
    processing the received information according to the receiver model to obtain first information, including:
    processing the received information according to a first full connection layer to obtain first characteristic information;
    processing the first characteristic information according to the A public layers, the first convolution layer and the second convolution layer to obtain second characteristic information;
    obtaining third characteristic information according to the first characteristic information and the second characteristic information;
    and processing the third characteristic information according to the second full connection layer to obtain the first information.
  14. The method of claim 13, wherein the processing the received information according to the first full connection layer to obtain first feature information comprises:
    inputting the received information into the first full-connection layer to obtain first feature extraction information;
    Performing dimension adjustment on the first feature extraction information to obtain first feature information;
    and processing the third feature information according to the second full connection layer to obtain the first information, where the processing includes:
    performing dimension adjustment on the third characteristic information to obtain dimension adjustment information;
    and processing the dimension adjustment information according to the second full connection layer to obtain the first information.
  15. The method of claim 13, wherein the obtaining third feature information from the first feature information and the second feature information comprises:
    sampling the first characteristic information to obtain first characteristic sampling information;
    and obtaining the third characteristic information according to the first characteristic sampling information and the second characteristic information.
  16. The method according to any one of claims 1 to 6, further comprising:
    acquiring a training sample set; the training sample set comprises the received information samples and the information processing samples;
    and training the receiver model according to the training sample set.
  17. The method of claim 16, wherein the training sample set further comprises at least one of sample transmission mode information and sample transmission characteristic information; the sample transmission characteristic information includes at least one of data characteristic information and channel characteristic information;
    The training the receiver model according to the training sample set further includes:
    determining a receiver model corresponding to the training sample set according to at least one of the sample transmission characteristic information and the sample transmission mode information;
    and training the receiver model corresponding to the training sample set based on the training sample set.
  18. The method according to any one of claims 1 to 6, wherein before determining a receiver model based on the transmission mode information, further comprising:
    and receiving a receiver model issued by the transmitting end equipment.
  19. A reception information processing apparatus for a reception-side device, the apparatus comprising:
    the wireless signal receiving module is used for executing wireless signal receiving to obtain receiving information;
    the transmission mode information acquisition module is used for acquiring transmission mode information corresponding to the received information;
    the model determining module is used for determining a receiver model according to the transmission mode information;
    the first information acquisition module is used for processing the received information through the receiver model to acquire first information; the receiver model takes a received information sample as input, and takes an information processing sample as a label to train so as to obtain a machine learning model.
  20. The apparatus of claim 19, wherein the first information is source information corresponding to the received information; the information processing sample is information source information corresponding to the received information sample.
  21. The apparatus of claim 19, wherein the first information is used to obtain source information corresponding to the received information after a first process; the information processing sample is obtained by performing second processing on information source information corresponding to the received information sample.
  22. The apparatus of claim 21, wherein the first process is an inverse process operation corresponding to the second process.
  23. The apparatus of claim 19, wherein when the receiving end device is a network side device, the apparatus further comprises:
    the transmission mode determining module is used for determining a transmission mode corresponding to the received information; the transmission mode is a transmission mode used by the terminal for transmitting the sending information corresponding to the receiving information;
    a transmission mode issuing module, configured to issue the transmission mode to a terminal;
    the transmission mode information acquisition module is used for acquiring the transmission mode information of the mobile terminal,
    and acquiring the transmission mode information corresponding to the received information according to the transmission mode.
  24. The apparatus of claim 19, wherein the transmission mode information obtaining module is configured to,
    and receiving the transmission mode information issued by the network side equipment.
  25. The apparatus according to any one of claims 19 to 24, wherein the transmission mode information includes at least one of modulation mode and MIMO configuration information.
  26. The apparatus according to any one of claims 19 to 24, wherein the module determining module is configured to,
    and determining a model structure and/or model parameters of the receiver model according to the transmission mode information.
  27. The apparatus according to any one of claims 19 to 24, further comprising:
    the transmission characteristic information acquisition module is used for acquiring transmission characteristic information corresponding to the received information;
    the model determination module is further configured to determine, based on the model information,
    and determining the receiver model according to the transmission mode information and the transmission characteristic information.
  28. The apparatus of claim 27, wherein the transmission characteristic information comprises at least one of data characteristic information of the received information and channel information corresponding to the received information;
    The data characteristic information is used for indicating the data type of the received information; the channel information is used to indicate channel conditions of a channel used to transmit the received information.
  29. The apparatus of any one of claims 19 to 24, wherein the receiver model is a fully connected neural network model consisting of N fully connected layers, N being greater than or equal to 1, and N being an integer.
  30. The apparatus of any one of claims 19 to 24, wherein the receiver model is a convolutional neural network model consisting of M convolutional layers, M is ≡1, and M is an integer.
  31. The apparatus of any of claims 19 to 24, wherein the receiver model comprises a first fully-connected layer, a second fully-connected layer, a common layers, a first convolutional layer, and a second convolutional layer; each public layer comprises a third convolution layer, a normalization layer and an activation layer which are sequentially connected; the A public layers are connected in sequence; a is more than or equal to 1, and A is an integer;
    the first information acquisition module includes:
    the first characteristic information acquisition unit is used for processing the received information according to the first full-connection layer to acquire first characteristic information;
    the second characteristic information acquisition unit is used for processing the first characteristic information according to the A public layers, the first convolution layer and the second convolution layer to obtain second characteristic information;
    The third characteristic information acquisition unit is used for acquiring third characteristic information according to the first characteristic information and the second characteristic information;
    and the first information acquisition unit is used for processing the third characteristic information according to the second full-connection layer to acquire the first information.
  32. The apparatus according to claim 31, wherein the first characteristic information acquiring unit includes:
    the first feature extraction subunit is used for inputting the received information into the first full-connection layer to obtain first feature extraction information;
    the first dimension adjusting unit is used for dimension adjusting the first feature extraction information to obtain the first feature information;
    the first information acquisition unit includes:
    the second dimension adjustment subunit is used for carrying out dimension adjustment on the third characteristic information to obtain dimension adjustment information;
    and the first information acquisition subunit is used for processing the dimension adjustment information according to the second full-connection layer to acquire the first information.
  33. The apparatus of claim 31, wherein the third feature information obtaining unit is further configured to sample the first feature information to obtain first feature sampling information;
    And obtaining the third characteristic information according to the first characteristic sampling information and the second characteristic information.
  34. The apparatus according to any one of claims 19 to 24, further comprising:
    the training sample set acquisition module is used for acquiring a training sample set; the training sample set comprises the received information samples and the information processing samples;
    and the receiver training module is used for training the receiver model according to the training sample set.
  35. The apparatus of claim 34, wherein the training sample set further comprises at least one of sample transmission mode information and sample transmission characteristic information; the sample transmission characteristic information includes at least one of data characteristic information and channel characteristic information;
    the receiver training module comprises:
    a receiver model determining unit, configured to determine a receiver model corresponding to the training sample set according to at least one of the sample transmission characteristic information and the sample transmission mode information;
    and the receiver training submodule is used for training the receiver model corresponding to the training sample set based on the training sample set.
  36. The method of any one of claims 19 to 24, wherein the apparatus further comprises:
    and the module receiving module is used for receiving the receiver model issued by the transmitting end equipment.
  37. A computer device, wherein the computer device is a receiving end device, the receiving end device comprising a processor, a memory, and a transceiver;
    the receiver is used for performing wireless signal reception to obtain reception information;
    the processor is used for acquiring the transmission mode information corresponding to the received information;
    the processor is used for determining a receiver model according to the transmission mode information;
    the processor is used for processing the received information through the receiver model to obtain first information; the receiver model is a machine learning model obtained after training according to the received information samples and the information processing samples.
  38. A computer-readable storage medium, in which a computer program for execution by a processor to implement the received information processing method according to any one of claims 1 to 18 is stored.
CN202180075039.8A 2021-01-13 2021-01-13 Received information processing method, device, computer equipment and storage medium Pending CN116458094A (en)

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
PCT/CN2021/071547 WO2022151069A1 (en) 2021-01-13 2021-01-13 Method and apparatus for processing received information, computer device, and storage medium

Publications (1)

Publication Number Publication Date
CN116458094A true CN116458094A (en) 2023-07-18

Family

ID=82446645

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202180075039.8A Pending CN116458094A (en) 2021-01-13 2021-01-13 Received information processing method, device, computer equipment and storage medium

Country Status (2)

Country Link
CN (1) CN116458094A (en)
WO (1) WO2022151069A1 (en)

Family Cites Families (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US10637544B1 (en) * 2018-04-24 2020-04-28 Genghiscomm Holdings, LLC Distributed radio system
CN111181612B (en) * 2019-12-31 2021-03-30 内蒙古大学 Cooperative beamforming method of large-scale MIMO system
CN111614398B (en) * 2020-05-12 2021-06-11 北京邮电大学 Method and device for identifying modulation format and signal-to-noise ratio based on XOR neural network
CN111614587B (en) * 2020-05-25 2021-04-06 齐鲁工业大学 SC-FDE system signal detection method based on self-adaptive integrated deep learning model
CN112118066A (en) * 2020-11-23 2020-12-22 西南交通大学 FBMC-PON demodulation method based on improved convolutional neural network

Also Published As

Publication number Publication date
WO2022151069A1 (en) 2022-07-21

Similar Documents

Publication Publication Date Title
CN109391304B (en) Data transmission method, base station, terminal and storage medium
EP3852326A1 (en) Transmitter
CN106982086B (en) Spatial modulation method based on receiving and transmitting antenna selection
EP3418821A1 (en) Method and device for configuring a data transmission system
CN116034381A (en) Communication method and communication device
CN109565360B (en) Information transmitting method, receiving method, device and storage medium
CN116458094A (en) Received information processing method, device, computer equipment and storage medium
CN107078992B (en) Information transmission method, equipment and system
CN107431564B (en) Communication system, relay device, reception device, relay method, reception method, relay program, and reception program
CN110971276B (en) Communication method and device
CN115668218A (en) Communication system
WO2022151067A1 (en) Wireless signal noise reduction method and apparatus, device, and storage medium
WO2023283785A1 (en) Method for processing signal, and receiver
WO2023060503A1 (en) Information processing method and apparatus, device, medium, chip, product, and program
CN116828486A (en) Communication method and related device
US20240048207A1 (en) Method and apparatus for transmitting and receiving feedback information based on artificial neural network
WO2024011554A1 (en) Techniques for joint probabilistic shaping of multiple bits per modulation constellation
WO2024008065A1 (en) Method and apparatus used in wireless communication node
WO2023115254A1 (en) Data processing method and device
CN117200935A (en) Signal processing method and device
EP4336408A1 (en) Signal processing method, communication device, and communication system
WO2023274046A1 (en) Method and apparatus used in node for wireless communication
EP4318964A1 (en) Method for transmitting compressed codebook, and method for obtaining channel state information matrix
CN117395115A (en) Communication method and device
CN117203898A (en) Channel information feedback method, transmitting device and receiving device

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