Communication method, environment perception method, device, machine, medium and product

Abstract

Embodiments of the present application provide a communication method, a communication environment sensing method, a communication device, a network device, a computer-readable storage medium, and a computer program product. By analyzing wireless communication signals, communication environment sensing information is obtained, and furthermore, sensing of the wireless communication environment is relatively well realized.

Description

Technical Field

[0001] This application is proposed based on a Chinese patent application with an application number of 202210982215.2 and an application date of August 16, 2022, claims the priority of this Chinese patent application, and all the contents of this Chinese patent application are incorporated herein by reference into this application.

[0002] Embodiments of this application relate to the field of communication technologies, and in particular to communication methods, communication environment sensing methods, communication devices, network devices, media, and products.

Background Art

[0003] The integration of communication and sensing (abbreviated as the integration of communication and sensing) is an important technology in future communication networks, such as 6G, etc. Communication is the transmission of information, and sensing is the detection and information acquisition of the environment, such as the communication environment. The integration technology of communication and sensing has characteristics such as high spectral efficiency and relatively small interference between communication and sensing compared to the technology that separates communication and sensing. Therefore, in some technologies, it is desired to select a receiver that matches the communication environment based on the sensing result by sensing the communication environment.

[0004] In related technologies, communication physical layer receivers generally adopt a unified receiver processing framework and unified configuration parameters, and it is difficult for the receiver to match the sensing environment relatively well. How to match the receiver according to different communication environments has become an urgent problem to be studied and solved currently.

Summary of the Invention

Problems to be Solved by the Invention

[0005] Embodiments of this application provide a communication method, a communication environment sensing method, a communication device, a network device, a computer-readable storage medium, and a computer program product, which aim to sense a communication environment and match a receiver according to the sensed communication environment.

Means for Solving the Problem

[0006] According to a first aspect, an embodiment of the present application provides a communication method, the method including receiving an orthogonal frequency division multiplexing (OFDM) signal including at least a received pilot signal and a received data signal; performing channel estimation based on the received pilot signal to obtain channel characteristics; obtaining first environmental information based on the channel characteristics; obtaining interference characteristic data based on the OFDM signal, and obtaining second environmental information based on the interference characteristic data; obtaining communication environment perception information based on the first environmental information and the second environmental information; and matching a receiver based on the communication environment perception information.

[0007] According to a second aspect, an embodiment of the present application provides a communication environment perception method, the method including receiving an orthogonal frequency division multiplexing (OFDM) signal including at least a pilot signal and a data signal; performing channel estimation based on pilot symbols included in the pilot signal to obtain channel characteristics; obtaining first environmental information based on the channel characteristics; obtaining corresponding interference characteristic data based on the OFDM signal, and obtaining second environmental information based on the interference characteristic data; and obtaining communication environment perception information based on the first environmental information and the second environmental information.

[0008] According to a third aspect, an embodiment of the present application provides a communication device, which includes a receiving unit configured to receive an orthogonal frequency division multiplexing (OFDM) signal including at least a received pilot signal and a received data signal, a first analysis unit configured to perform channel estimation based on the received pilot signal to obtain channel characteristics and obtain first environmental information based on the channel characteristics, a second analysis unit configured to obtain interference characteristic data based on the OFDM signal and obtain second environmental information based on the interference characteristic data, and a processing unit configured to obtain communication environment sensing information based on the first environmental information and the second environmental information.

[0009] According to a fourth aspect, an embodiment of the present application provides a network device, which includes a memory configured to store a computer program, and a processor configured to execute the computer program to perform the communication method described in the first aspect or the communication environment sensing method described in the second aspect.

[0010] According to a fifth aspect, an embodiment of the present application provides a computer-readable storage medium, on which computer-executable instructions are stored, and the computer-executable instructions are used to perform the communication method described in the first aspect or the communication environment sensing method described in the second aspect.

[0011] According to a sixth aspect, an embodiment of the present application provides a computer program product, which includes a computer program or computer instructions, the computer program or the computer instructions are stored in a computer-readable storage medium, a processor of a computer device reads the computer program or the computer instructions from the computer-readable storage medium, the processor executes the computer program or the computer instructions, and causes the computer device to perform the communication method described in the first aspect or the communication environment sensing method described in the second aspect.

Brief Description of the Drawings

[0012]

Figure 1

Figure 2

Figure 3

Figure 4

Figure 5

Figure 6

Figure 7

Figure 8

Figure 9

Figure 10

Figure 11

Figure 12

Figure 13

Figure 14

Figure 15

Figure 16

Figure 17

Figure 18

Figure 19

Embodiments for Carrying Out the Invention

[0013] In order to make the object, technical solution and advantages of the present application clearer, the present application will be described in more detail below with reference to the drawings and embodiments. The specific embodiments described herein are only used for interpreting the present application and are not intended to limit the present application.

[0014] In the schematic diagram of the device, the functional modules are divided, and the logical order is shown in the flowchart. However, in some cases, the module division in the device may be different, or the steps shown or described may be executed in an order different from that in the flowchart. Terms such as "first" and "second" in the specification, claims and the above drawings are used to distinguish similar objects and are not necessarily for describing a specific order or sequence.

[0015] In the description of the embodiments of the present application, unless otherwise clearly defined, terms such as installation, attachment, connection, etc. should be understood in a broad sense, and those skilled in the art may reasonably determine the specific meaning of the above terms in the embodiments of the present application with reference to the specific content of the technical solution. In the embodiments of the present application, terms such as "further", "exemplarily" or "optionally" are used for illustration, exemplification or explanation, and should not be construed as being more preferred or having more advantages than other embodiments or design solutions. The use of terms such as "further", "exemplarily" or "optionally" is intended to present related concepts in a specific manner.

[0016] Embodiments of the present application may be used in various wireless communication systems, such as Global System of Mobile communication (GSM (registered trademark)) systems, Code Division Multiple Access (CDMA) systems, Wideband Code Division Multiple Access (WCDMA (registered trademark)) systems, General Packet Radio Service (GPRS), Long Term Evolution (LTE) systems, LTE-A (Advanced long term evolution) systems, Universal Mobile Telecommunication System (UMTS), 5G, Beyond Fifth Generation (B5G), 6th Generation (6G) systems, and the like.

[0017] Embodiments of the present application relate to a fusion matching receiver technology for communication and sensing. The fusion technology of communication and sensing realizes the fusion and symbiosis of communication functions and sensing functions by using the same spectrum resources through the co-design of air interfaces and protocols and the sharing of software and hardware devices. In this way, the wireless network can analyze the characteristic data of wireless communication signals while performing data communication, so as to obtain the sensing of target objects or environmental information. By adopting the fusion technology of communication and sensing, not only the spectrum utilization rate and device multiplexing rate can be increased, but also the application scenarios of the communication network can be expanded. For example, it can be used in adaptive matching receivers or smart matching receivers. Receivers, such as link-level receivers, adopt a unified processing framework and parameter configuration, and it is difficult to perform adaptive processing according to different communication scenarios, such as different communication environments, different noise interferences, different user characteristics, and thus different users, and it is difficult to obtain excellent working performance thereby.

[0018] To describe the present technical solution in detail, taking the application scenario related to the receiver in the OFDM system as an example, the application scenario of the embodiments of the present application will be further described.

[0019] FIG. 1 is a schematic diagram of a receiver and its related devices in an OFDM system. As shown in FIG. 1, after the signal undergoes CP removal and FFT (Fast Fourier Transform) processing, it is received by a symbol-level receiver (i.e., input into the symbol-level processing module), and after further processing by the symbol-level receiver, it is input into the demodulation and decoding module. The implementation of the present application may be used in various receivers, such as conventional receivers, new smart receivers, receivers with adaptation capabilities, receivers with neural network prediction models, etc.

[0020] In the OFDM system shown in FIG. 1, assuming that the received frequency-domain signal is represented by Y,

Equation

[0021] In some technologies, the communication physical layer receiver adopts a unified receiver processing framework and unified configuration parameters, making it difficult to sense complex communication environments, such as wireless communication environments, and furthermore, it is impossible to dynamically control the optimal receiving algorithm according to different wireless communication environments. In some other technologies, there are also physical layer OFDM receivers based on artificial intelligence (AI), such as model-driven OFDM receivers, data-driven OFDM receivers, or data model dual-driven OFDM receivers. However, due to the lack of sensing ability for complex communication environments, such as wireless communication, in the above technologies, it is difficult for the OFDM receiver to obtain excellent performance matching the wireless communication environment.

[0022] Hereinafter, embodiments of the present application will be described by taking a wireless communication environment as an example.

[0023] Embodiments of the present application provide a wireless communication method, a wireless communication environment sensing method, a wireless communication device, a network device, a computer-readable storage medium, and a computer program product. By analyzing wireless communication signals, communication environment sensing information is obtained, and moreover, sensing of the wireless communication environment is relatively well realized. Another embodiment of the present application further realizes selecting different receivers under different wireless communication environments based on the sensing of the wireless communication environment, thereby realizing smart and dynamic control of the receiver, for example, a link-level receiver, and improving system performance.

[0024] Hereinafter, embodiments of the present application will be further described with reference to the drawings.

[0025] FIG. 2 is a flowchart of a communication environment sensing method according to an embodiment of the present application. As shown in FIG. 2, this communication environment sensing method may be applied to an OFDM communication system. In the embodiment of FIG. 2, this communication environment sensing method may include, but is not limited to, steps S100, S200, S300, S400, and S500.

[0026] Step S100: Receive an OFDM signal.

[0027]

Number

[0028]

Number

[0029]

Number

[0030]

Number

[0031]

Number

[0032] In one embodiment, the channel estimation may employ an estimation algorithm based on a training sequence or a blind estimation algorithm. The estimation algorithm based on a training sequence may include methods such as a least squares channel estimation algorithm (LS channel estimation), a minimum mean square error channel estimation method (MMSE channel estimation), and a low-order minimum mean square error channel estimation method (LMMSE channel estimation). The embodiments of the present application are not limited thereto. For the convenience of describing the present technical solution, the following will describe LS channel estimation as an example.

[0033] In one embodiment, the channel characteristics may include one or more of a frequency domain fading coefficient, a time correlation coefficient, an energy distribution of a time domain channel estimation value, and a Rice coefficient, and the channel characteristics may further include other parameters, data, or content that can be used to characterize the channel characteristics.

[0034] Step S300: Obtain first environmental information based on the channel characteristics.

[0035] In one embodiment, the first environmental information may include one or more of communication environment speed information, information within the communication line of sight, and communication environment multipath delay information, and the first environmental information may further include other information that can be used to characterize the communication environment situation.

[0036] In another embodiment, the first environmental information may include one or more of terminal characteristic information and user characteristic information. Here, the terminal characteristic information is parameter information for characterizing terminal characteristics, and the user characteristic information is parameter information for characterizing user characteristics.

[0037] In another embodiment, the communication environment speed information may include one or more of high speed, medium speed, and low speed. The communication visibility information may include one or more of within visibility and outside visibility. The communication multipath delay information may include one or more of high multipath delay and low multipath delay.

[0038] In another embodiment, obtaining the first environmental information based on the channel characteristics may obtain the first environmental information by comparing the channel characteristics with a preset threshold value, or may obtain the first environmental information by inputting the channel characteristics into a neural network.

[0039] Step S400: Obtain interference feature data based on the OFDM signal, and obtain second environmental information based on the interference feature data.

[0040] In one embodiment, the interference feature data may include one or more of noise interference, received signal strength indication, and covariance matrix of the signal, and the interference feature data may further include other data available for characterizing the communication interference situation characteristics.

[0041] In another embodiment, the noise interference may include one or more of total bandwidth noise interference power, spatial frequency domain dimensional noise interference, and resource block RB granularity noise interference power, and the noise interference may further include other parameters, data, or content available for characterizing the communication noise interference characteristics.

[0042] In one embodiment, the second environmental information may include communication interference information.

[0043] In another embodiment, the communication interference information may include one or more of presence of interference, absence of interference, interference intensity information, and interference position information. The communication interference information may further include other information available for characterizing the communication interference characteristics.

[0044] In another embodiment, obtaining interference feature data based on the OFDM signal and obtaining second environmental information based on the interference feature data may include obtaining the second environmental information by comparing the interference feature data with a communication interference threshold value, obtaining the second environmental information by inputting the interference feature data into a second neural network, or obtaining the second environmental information by applying a clustering algorithm, such as a K-means based algorithm, to the interference feature data.

[0045] Step S500: Obtain communication environment perception information based on the first environmental information and the second environmental information.

[0046] The embodiments of the present application provide a communication environment perception method, which can realize obtaining communication environment perception information through extraction and analysis of communication environment characteristics, and further relatively well perceive the wireless communication environment. In a communication scenario, it can not only enhance the perception ability of the environment, but also better utilize wireless signals to obtain surrounding physical environment information, explore communication capabilities, and improve the user experience.

[0047] FIG. 3 is a flowchart of a communication method according to an embodiment of the present application. As shown in FIG. 3, this communication method may include, but is not limited to, steps S100, S200, S300, S400, S500, and S600.

[0048] Step S100: Receive an OFDM signal.

[0049]

Number

[0050] Step S300: Obtain first environmental information based on channel characteristics.

[0051] Step S400: Obtain interference feature data based on the OFDM signal and obtain second environmental information based on the interference feature data.

[0052] Step S500: Obtain communication environment perception information based on the first environmental information and the second environmental information.

[0053] Step S600: Match the receiver based on the communication environment perception information.

[0054] The embodiments of the present application provide a communication method. By extracting and analyzing the characteristics of the communication environment, communication environment perception information is obtained, and by using the communication environment perception information to select different receivers in different wireless communication environments, it is possible to realize smart and dynamic control of receivers, such as link-level receivers, and improve the system performance. The content described in the foregoing communication environment perception method is also applicable to this embodiment.

[0055] FIG. 4 is a flowchart of a communication method according to an embodiment of the present application. As shown in FIG. 4, this communication method may further include step S700.

[0056]

Number

[0057] The embodiments of the present application provide a communication method, which not only realizes smart and dynamic control of the receiver by perceiving the communication environment, obtaining communication environment perception information, and matching different receivers, but also improves the system performance.

[0058] FIG. 5 is a flowchart of a communication method according to an embodiment of the present application. As shown in FIG. 5, this communication method may further include step S800.

[0059] Step S800: Perform demodulation based on the transmitted signal to obtain demodulated data.

[0060] FIG. 6 is a flowchart of a communication method according to an embodiment of the present application and is also a further explanation of step S600. As shown in FIG. 6, step S600 may include, but is not limited to, steps S610 and S620.

[0061] Step S610: Obtain a communication scenario type based on the communication environment perception information.

[0062] In one embodiment, the communication scenario type may be comprehensively determined based on one or more of the communication environment speed information, the information within the communication line of sight, the communication multipath delay information, the terminal feature information, the user feature information, and the communication interference information. Different communication scenario types may be constructed based on different combinations, and the embodiments of the present application are not limited thereto.

[0063] To facilitate a further description of the communication scenario type in the embodiments of the present application, the following will exemplarily describe the communication scenario type in combination with the communication environment speed information, the information within the communication line of sight, the communication multipath delay information, and the communication interference information.

[0064] Table 1 is a communication type list according to an embodiment of the present application, including nine different communication scenario types.

[0065]

Table 1

[0066] Table 2 is a communication type list according to another embodiment of the present application, including eighteen different communication scenario types.

[0067]

Table 2

[0068] Step S620: Match a receiver based on the communication scenario type.

[0069] In one embodiment, the receiver may be a conventional receiver, a smart receiver, a neural network receiver, or any other type of receiver.

[0070] In another embodiment, the neural network receiver may be a receiver having a neural network detector, and this neural network detector may be pre-trained.

[0071] FIG. 7 is a flowchart of a communication method according to an embodiment of the present application, and is also a further explanation of step S700. As shown in FIG. 7, step S700 may include, but is not limited to, steps S710 and S720.

[0072]

Number

[0073]

Number

[0074]

Number

[0075] FIG. 8 is a flowchart of a communication method according to an embodiment of the present application, and is also a further explanation of step S710. As shown in FIG. 8, step S710 may include, but is not limited to, steps S711 and S712.

[0076]

Number

[0077]

Number

[0078] FIG. 9 is a flowchart of a communication method according to an embodiment of the present application, and is also a further explanation of step S800. As shown in FIG. 9, step S800 may include, but is not limited to, steps S810 and S820.

[0079]

Number

[0080]

Number

[0081] FIG. 10 is a schematic diagram of a communication device according to an embodiment of the present application. As shown in FIG. 10, the communication device includes a receiving unit, a first analysis unit, a second analysis unit, and a processing unit.

[0082] The receiving unit is configured to receive an orthogonal frequency division multiplexing (OFDM) signal including at least a received pilot signal and a received data signal. The first analysis unit is configured to perform channel estimation based on the received pilot signal to obtain channel characteristics, and obtain first environmental information based on the channel characteristics, where the first environmental information includes at least one of communication environment speed information, in-communication visibility information, and communication multipath delay information. The second analysis unit is configured to obtain interference characteristic data based on the OFDM signal, and obtain second environmental information including at least communication interference information based on the interference characteristic data. The processing unit is configured to obtain communication environment perception information based on the first environmental information and the second environmental information.

[0083] The embodiments of the present application provide a communication device that can obtain communication environment perception information through extraction and analysis of communication environment characteristics, and can further relatively well perceive the wireless communication environment. In a communication scenario, it can not only enhance the perception ability of the environment, but also better utilize wireless signals to obtain surrounding physical environment information, explore communication capabilities, and improve user experience.

[0084] As shown in FIG. 11, the communication device may further include a matching unit.

[0085] The matching unit is configured to match a receiver based on communication environment perception information.

[0086] The embodiments of the present application provide another communication device. This communication device can obtain communication environment perception information through extraction and analysis of communication environment characteristics, and use the communication environment perception information to select different receivers in different wireless communication environments, thereby realizing smart and dynamic control of receivers, such as link-level receivers, and improving system performance.

[0087] The communication and perception fusion adaptive receiver according to the embodiments of the present application can better detect the transmission signal X from the received signal Y in different communication environments, such as wireless transmission environments. This includes, but is not limited to, the following steps.

[0088] Step 1: Perform smart perception and recognition, that is, use an OFDM signal, such as an OFDM frequency domain signal, to perform perception and recognition on the wireless transmission environment and the interference existing in the environment. An exemplary method is as follows.

[0089] ● Use the OFDM frequency domain signal to sense the wireless transmission environment and recognize the wireless channel scenario where the current terminal or user is located. Use the OFDM pilot signal to perform wireless channel scenario recognition. The perception and recognition algorithm includes, but is not limited to, an algorithm that extracts channel characteristics based on the experience of conventional experts and performs threshold determination, or an algorithm that extracts channel characteristics based on the experience of experts and combines them with a neural network.

[0090] ● Adopt OFDM frequency domain signals to sense whether there is interference in the environment, or the interference intensity, whether there is interference in the current three-dimensional resources of time, space, and frequency, what type of interference exists, or the recognized interference intensity. Here, methods such as the total bandwidth noise interference power, received signal strength indicator (RSSI), noise interference in the spatial frequency domain dimension, or the covariance matrix of the signal may be adopted to sense and recognize interference. The sensing and recognition algorithm may include, but is not limited to, an algorithm that extracts interference features based on the experience of conventional experts for threshold determination, or an algorithm that extracts interference features based on the experience of experts and combines them with a neural network.

[0091] ● Comprehensive determination: Based on the wireless transmission environment and the sensing and recognition results of interference in the environment, perform a comprehensive determination to obtain which scenario in the scenario set the current user is located in. The scenario type set is exemplified as wireless channel scenarios 1, 2,..., N without interference, and scenarios 1, 2,..., N with interference.

[0092] Step 2: Match the receiver, that is, adaptively select a receiver that matches the wireless transmission environment based on the recognition result to perform OFDM signal detection.

[0093]

Number

[0094]

Number

[0095] Here, the receivers in different scenarios may be conventional receivers, and there are different algorithm flow processes according to different scenarios. For different multipath delay spreads, the channel estimation module may adopt filters with different window lengths to remove noise and interference, and may also adopt different pilot configurations and different frequency offset estimation and compensation algorithms at different speeds. Alternatively, the receiver may be a smart adaptive receiver. Each scenario corresponds to a neural network signal detector, and these neural network signal detectors are pre-trained offline to form a model set in order to facilitate online detection. Here, the structure of the neural network includes, but is not limited to, a deep neural network, a convolutional neural network, a residual neural network, or a residual neural network with an attention mechanism.

[0096]

Number

[0097] To further describe the communication environment perception method, communication device, network device, computer-readable storage medium, and computer program product according to the embodiments of the present application, different examples are combined and described below.

[0098]

Number

[0099] Step 1: Perform smart perception and recognition, that is, adopt the OFDM frequency domain signal to perform perception and recognition on the wireless transmission environment and the interference existing in the environment.

[0100]

Number

[0101] Adopt the noise interference power at the granularity of the OFDM frequency domain resource block (Resource Block, RB) to sense the interference existing in the environment, and recognize whether there is interference in the current frequency domain resource, the interference source, and the intensity of the interference. Collect the noise interference power at the RB level across the entire frequency domain bandwidth, and then adopt the K-means clustering algorithm to recognize which RBs across the entire bandwidth have interference and the intensity of the interference.

[0102] Comprehensive determination: Based on the wireless transmission environment and the sensing and recognition results of the interference in the environment, perform a comprehensive determination to obtain which scenario in the scenario set the current terminal's all scheduling RBs are located in. Here, the scenario set may be six types: low speed, medium speed, and high speed without interference, and low speed, medium speed, and high speed with interference. The recognition of the wireless channel scenario is such that all RB results are the same, but the interference recognition result is at the RB level. In this example, each RB of the UE is determined one by one, and finally the recognition result at the RB level is obtained.

[0103] Step 2: Determine the adaptive receiver, that is, adaptively select a receiver that matches the wireless transmission environment based on the scenario recognition result at the RB level in Step 1, and perform OFDM signal detection. As shown in FIG. 12, the processing in the figure is the processing flow of each RB. Based on the channel scenario recognition result and the interference recognition result obtained in Step 1, select the receiver that best matches the current propagation environment from the receiver sets of different scenarios.

[0104]

Number

[0105]

Number

[0106] Example 2: Figure 14 is a schematic diagram of an adaptive receiver according to an embodiment of the present application. The adaptive receiver in step 2 of Embodiment 1 may be the smart adaptive receiver shown in Figure 14. The smart adaptive receiver includes a least squares (LS) channel estimation submodule and a scenario adaptive OFDM signal detector submodule.

[0107]

Number

[0108]

Number

[0109] 2. Scenario Adaptive OFDM Signal Detector: The set of neural network signal detectors in this example may include six types, namely, low-speed, medium-speed, and high-speed neural network signal detectors without interference, and low-speed, medium-speed, and high-speed neural network signal detectors with interference. These six types of neural network signal detectors are pre-trained offline to facilitate online detection. Based on the channel scenario recognition result and interference recognition result obtained in step 1, a neural network model that best matches the current propagation environment is selected from the set of neural network signal detector models.

[0110]

Number

[0111] Here, the neural network signal detector is composed of two sub-networks: an extended channel estimation sub-network and a channel equalization sub-network. Here, the extended channel estimation sub-network plays a role in removing noise and interference, improving the quality of the channel estimation value, performing the function of channel interpolation, obtaining the channel estimation value of the data symbol, and the channel equalization sub-network is used for the detection of OFDM signals as an alternative to the conventional channel equalization function. Both of the two sub-networks adopt a residual neural network with a channel attention mechanism. The two sub-networks are trained together, and the mean square error (MSE) between the transmitted data and its estimated value is adopted as the loss function, for example, as shown in the following formula (3).

[0112]

Number

[0113]

Number

[0114] Step 1: Perform smart sensing and recognition, that is, adopt the OFDM frequency-domain signal to perform sensing and recognition on the wireless transmission environment and the interference existing in the environment.

[0115]

Number

[0116]

Number

[0117] Comprehensive determination: Based on the wireless transmission environment and the perception and recognition results of interference in the environment, a comprehensive determination is made to obtain which scenario in the scenario set the current user is located in. Here, there are a total of 18 types of scenarios in the scenario set, with 9 types each for the presence and absence of interference, as shown in Table 2. The recognition of the wireless channel scenario is such that all RB results are the same, but the interference recognition result is at the RB level. Here, if all RBs of the UE are grouped such that 4 RBs form one RB group (if less than 4, they are processed in one RB group), if there is one determination result of interference on an RB within one RB group, this RB group is recognized as having interference, and finally the recognition result at the RB group level is obtained.

[0118] Step 2: Determine the smart adaptive receiver, that is, as shown in FIG. 14, based on the scenario recognition result at the RB group level in Step 1, adaptively select a smart receiver that matches the wireless transmission environment to perform OFDM signal detection. The processing in FIG. 14 is the processing flow for each RB group, and the smart adaptive receiver includes an LS channel estimation sub-module and a scenario adaptive OFDM signal detector sub-module.

[0119] 1. Select an appropriate neural network OFDM signal detector. Based on the channel scenario recognition result and interference recognition result obtained in Step 1, select the neural network model that most matches the current propagation environment from the set of neural network signal detector models (a total of 18 types, as shown in Table 2). All models in this set of neural network signal detectors are pre-trained offline in advance to facilitate online detection.

[0120] 2. Perform OFDM signal detection.

[0121] Figure 16 is a schematic diagram of the structure of a neural network signal detector according to an embodiment of the present application. As shown in Figure 16, the structure of the neural network signal detector in each scenario of this example performs the detection of a plurality of OFDM signals according to the streaming structure.

[0122]

Number

[0123]

Number

[0124]

Number

[0125] The processing flow of the subsequent pilot and data symbols is the same as above until the demodulation result of the last data symbol is obtained.

[0126] Here, the neural network signal detector in each scenario all adopts a convolutional neural network with residual connections. During offline training, the mean square error (MSE) between the transmitted data and its estimated value is adopted as the loss function, and referring to Equation (3), the Adam optimizer is used for training. When the loss function converges to a certain extent, the network training is completed, and the model parameters are saved for subsequent online signal detection.

[0127]

Number

[0128] Example 4: FIG. 17 is a schematic diagram of a conventional receiver according to an embodiment of the present application. As shown in FIG. 17, the difference between this example and Example 3 is that the conventional receiver in Scenario n replaces the neural network signal detector in Scenario n.

[0129]

Number

[0130] FIG. 19 is a schematic structural diagram of a communication device according to an embodiment of the present application. As shown in FIG. 19, this communication device 1000 includes a memory 1100 and a processor 1200. The number of the memory 1100 and the processor 1200 may be one or more. In FIG. 19, taking one memory 1101 and one processor 1201 as an example, the memory 1101 and the processor 1201 in the communication device may be connected via a bus or other means. In FIG. 19, the connection via the bus is taken as an example.

[0131] The memory 1101 may be used as a computer-readable storage medium to store software programs, computer-executable programs, and modules, for example, program instructions / modules corresponding to the method according to any one of the embodiments of the present application. The processor 1201 realizes the above method by executing the software programs, instructions, and modules stored in the memory 1101.

[0132] Memory 1101 may mainly include a program storage area and a data storage area. Here, the program storage area may store an operating system and application programs necessary for at least one function. Note that memory 1101 may include a high-speed random access memory and may also include a non-volatile memory, for example, at least one magnetic disk memory device, a flash memory device, or other non-volatile solid-state memory devices. In some examples, memory 1101 may further include a memory installed remotely with respect to processor 1201, and these remote memories may be connected to the device via a network. Examples of the above network include, but are not limited to, the Internet, an intranet, a local area network, a mobile communication network, and combinations thereof.

[0133] An embodiment of the present application further provides a computer-readable storage medium, in which computer-executable instructions are stored, and these computer-executable instructions are used to execute the communication method or the communication environment sensing method according to any one of the embodiments of the present application.

[0134] An embodiment of the present application further provides a computer program product, including a computer program or computer instructions, which are stored in a computer-readable storage medium. The processor of the computer device reads the computer program or computer instructions from the computer-readable storage medium and executes the computer program or computer instructions, so that the computer device executes the communication method or the communication environment sensing method according to any one of the embodiments of the present application.

[0135] All or some of the steps in the method disclosed above, and the functional modules / units in the system and device, may be implemented as software, firmware, hardware, and appropriate combinations thereof.

[0136] In the hardware embodiment, the division between the functional modules / units mentioned above does not necessarily correspond to the division of physical assemblies. For example, one physical assembly may have multiple functions, or one function or step may be executed in cooperation by several physical assemblies. Some physical assemblies or all physical assemblies may be implemented as software executed by a processor, such as a central processor, a digital signal processor, or a microprocessor, or as hardware, or as an integrated circuit, such as an application-specific integrated circuit. Such software may be distributed on a computer-readable medium, and the computer-readable medium may include a computer storage medium (or non-transitory medium) and a communication medium (or transitory medium). As is known to those skilled in the art, the term computer storage medium includes volatile and non-volatile, removable and non-removable media implemented in any method or technology for storing information (such as computer-readable instructions, data structures, program modules, or other data). The computer storage medium includes RAM, ROM, EEPROM, flash memory or other memory technologies, CD-ROM, digital versatile disk (DVD) or other optical disk storage, magnetic cartridges, magnetic tapes, magnetic disk storage or other magnetic storage devices, or any other medium that can be used to store desired information and can be accessed by a computer, but is not limited thereto. Note that, as is known to those skilled in the art, the communication medium generally includes computer-readable instructions, data structures, program modules, or other data in a modulated data signal such as a carrier or other transmission mechanism, and may include any information transmission medium.

[0137] As used herein, terms such as "member", "module", "system", etc. are used to represent computer-related entities, hardware, firmware, combinations of hardware and software, software, or software in execution. For example, a member may be, but is not limited to, a process running on a processor, a processor, an object, an executable file, an execution thread, a program, or a computer. By way of illustration, both an application running on a computing device and the computing device may each be a member. One or more members may reside within a process or execution thread, and a member may be located on one computer or distributed between two or more computers. Additionally, these members may be executed from various computer-readable media storing various data structures. A member may communicate, for example, via a local or remote process based on signals having one or more data packets (e.g., data from two members interacting with another member in a local system, a distributed system, or across a network, such as the Internet that interacts with other systems via signals).

[0138] As described above, some embodiments of the present application have been described with reference to the drawings, but this does not limit the scope of the present application. Any modifications, equivalent replacements, and improvements made by those skilled in the art without departing from the scope and essence of the present invention should all be within the scope of the present application.

Claims

1. A communication method, comprising: receiving an orthogonal frequency division multiplexing (OFDM) signal including at least a received pilot signal and a received data signal; performing channel estimation based on the received pilot signal to obtain channel characteristics; obtaining first environmental information based on the channel characteristics, the first environmental information including at least one of communication environment speed information, in-communication visibility information, and communication multipath delay information; obtaining interference characteristic data based on the OFDM signal, and obtaining second environmental information including at least communication interference information based on the interference characteristic data; obtaining communication environment perception information based on the first environmental information and the second environmental information; and matching a receiver based on the communication environment perception information.

2. The method according to claim 1, wherein the matching of the receiver based on the communication environment perception information includes: obtaining a communication scenario type based on the communication environment perception information, and matching the receiver based on the communication scenario type.

3. The method according to claim 1, further comprising performing signal detection based on the received pilot signal, the received data signal, and a preset local pilot signal to obtain a transmitted signal.

4. The method according to claim 3, wherein the performing of signal detection based on the received pilot signal, the received data signal, and a preset local pilot signal to obtain a transmitted signal includes: performing channel estimation based on the received pilot signal and the preset local pilot signal to obtain a channel estimation value; and performing channel equalization based on the channel estimation value and the received data signal to obtain a transmitted signal.

5. The method according to claim 3 or 4, further comprising demodulating based on the transmission signal to obtain demodulated data.

6. The received pilot signal includes at least a first received pilot symbol, The received data signal includes at least a first received data symbol and a second received data symbol, Performing signal detection based on the received pilot signal, the received data signal, and a preset local pilot signal to obtain a transmission signal includes: Performing channel estimation based on the first received pilot symbol and the local pilot signal to obtain a first channel estimation value; Performing channel equalization based on the first channel estimation value and the first received data signal to obtain a first transmitted data estimation value; Performing hard decision based on the first transmitted data estimation value to obtain hard decision data; Performing channel estimation based on the hard decision data and the first received data symbol to obtain a second channel estimation value; The method according to claim 3, further comprising performing channel equalization based on the second channel estimation value and the second received data symbol to obtain a second transmitted data estimation value.

7. Performing demodulation based on the first transmitted data estimation value to obtain first demodulated data; The method according to claim 6, further comprising performing demodulation based on the second transmitted data estimation value to obtain second demodulated data.

8. The channel characteristics include: At least one of a frequency domain fading coefficient, a time correlation coefficient, an energy distribution of a time domain channel estimation value, and a Rice coefficient. The method according to any one of claims 1 to 3 is characterized by this.

9. The communication environment speed information includes at least one of high speed, medium speed, and low speed. The information within the communication visibility includes at least one of within visibility and outside visibility. The communication multipath delay information includes at least one of high multipath delay and low multipath delay. The method according to any one of claims 1 to 4, 6 to 7.

10. Obtaining the first environmental information based on the channel characteristics includes: Comparing the channel characteristics with a preset threshold to obtain the first environmental information; Inputting the channel characteristics into a first neural network to obtain the first environmental information. The method according to claim 1 or 2 includes at least one of the above.

11. The interference characteristic data includes: At least one of noise interference, received signal strength indication, and signal covariance matrix. The method according to any one of claims 1 to 3.

12. The noise interference includes: At least one of total bandwidth noise interference power, spatial frequency domain dimension noise interference, and resource block RB granularity noise interference power. The method according to claim 11.

13. The communication interference information includes: At least one of presence of interference, absence of interference, interference intensity information, and interference position information. Here, the interference intensity includes at least one of high interference, medium interference, and low interference. The method according to any one of claims 1 to 3 is characterized by this.

14. Obtaining the second environmental information based on the interference characteristic data corresponding to the OFDM signal includes: Comparing the interference characteristic data with a communication interference threshold to obtain the second environmental information; Inputting the interference feature data into a second neural network to obtain the second environmental information; The method according to any one of claims 1 to 3, comprising at least one of obtaining the second environmental information by a clustering algorithm based on the interference feature data.

15. The first environmental information The method according to any one of claims 1 to 3 and 6 to 7, further comprising at least one of terminal feature information which is parameter information for characterizing terminal features.

16. Performing channel estimation based on the received pilot signal and a preset local pilot signal to obtain a channel estimation value, which Performing channel estimation based on the received pilot signal and a preset local pilot signal to obtain a first channel estimation value; The method according to claim 4, comprising performing time-frequency offset estimation and compensation, channel estimation noise reduction, and channel interpolation processing on the first channel estimation value to obtain a second channel estimation value.

17. A communication environment sensing method, comprising: Receiving an orthogonal frequency division multiplexing (OFDM) signal including at least a pilot signal and a data signal; Performing channel estimation based on pilot symbols included in the pilot signal to obtain channel features; Obtaining first environmental information based on the channel features, wherein the first environmental information includes at least communication environment speed information, communication visibility information, communication multipath delay information, terminal feature information, and user feature information; Obtaining interference feature data based on the OFDM signal, and obtaining second environmental information including at least communication interference information based on the interference feature data; Obtaining communication environment sensing information based on the first environmental information and the second environmental information.

18. Further comprising obtaining a communication scenario type based on the communication environment perception information, wherein the communication scenario type is comprehensively determined based on at least one of communication environment speed information, in-communication visibility information, communication multipath delay information, terminal characteristic information, and communication interference information. The method according to claim 17.

19. A communication device, A receiving unit configured to receive an orthogonal frequency division multiplexing (OFDM) signal including at least a received pilot signal and a received data signal; A first analysis unit configured to perform channel estimation based on the received pilot signal to obtain channel characteristics, and obtain first environment information based on the channel characteristics, wherein the first environment information includes at least one of communication environment speed information, in-communication visibility information, and communication multipath delay information. The first analysis unit; A second analysis unit configured to obtain interference characteristic data based on the OFDM signal and obtain second environment information including at least communication interference information based on the interference characteristic data; And a processing unit configured to obtain communication environment perception information based on the first environment information and the second environment information. The communication device.

20. The communication device according to claim 19, further comprising a matching unit configured to match a receiver based on the communication environment perception information.

21. A communication device, A memory configured to store a computer program; A processor configured to execute the computer program to execute the communication method according to any one of claims 1 to 16, or the communication environment perception method according to claim 17 or 18. The communication device.

22. A computer-readable storage medium storing computer-executable instructions, wherein the computer-executable instructions are used to execute the communication method according to any one of claims 1 to 16 or the communication environment sensing method according to claim 17 or 18, the computer-readable storage medium.

23. A computer program product including a computer program or computer instructions, wherein the computer program or the computer instructions are stored in a computer-readable storage medium, a processor of a computer device reads the computer program or the computer instructions from the computer-readable storage medium, the processor executes the computer program or the computer instructions, and causes the computer device to execute the communication method according to any one of claims 1 to 16 or the communication environment sensing method according to claim 17 or 18, the computer program product.

Images