High-level semantic information acquisition method for cognitive radio

Abstract

The invention discloses a cognitive radio-oriented high-level semantic information acquisition method, which comprises the following steps of: performing spectrum situation sensing based on a received original electromagnetic signal, judging whether an idle authorized spectrum exists or not, and acquiring frequency equipment information in a current network; performing high-level semantic information reasoning based on the frequency spectrum situation sensing information to obtain a topological structure of a current network and service type information transmitted between nodes; performing interference estimation on the filtered original electromagnetic signal, performing interference cognition based on an interference estimation result, and extracting interference type information; and performing interference suppression on the filtered original electromagnetic signal based on an interference estimation result, performing channel estimation on an interference suppression result, performing channel cognition based on a channel estimation result, and extracting channel type information. According to the method, the multi-domain cognitive ability of the cognitive radio station is enhanced, and more decision information is provided for the cognitive radio station to adaptively adjust the internal state and the transmitting parameters according to the external environment change.

Description

Technical Field

[0001] The present invention relates to the field of wireless communication technology, and more particularly to a method for acquiring high-level semantic information oriented to cognitive radio. Background Art

[0002] The high-level semantic information acquisition method for cognitive radio is a method to extract multi-dimensional high-level semantic information such as electromagnetic network domain from the wireless network environment, aiming to improve the cognitive ability of radio by enhancing the perception ability of electromagnetic network domain. At present, cognitive radio has the problem of single perception information dimension. Deep learning neural network and other methods can be used to mine deeper and more dimensional semantic information in electromagnetic signals. There are many frequency-using devices in the communication environment. By analyzing the received electromagnetic signals, high-level semantic information implied by the spectrum information, such as the network topology of the frequency-using nodes and the type of transmission services between nodes, can be obtained.

[0003] What distinguishes cognitive radio from traditional radio is that cognitive radio adds data processing and semantic extraction of received electromagnetic signals, as well as decision-making on key parameters of the transmitting waveform. On the one hand, the multi-dimensional perception information of cognitive radio is integrated into the traditional signal processing process, participating in the decision-making and optimization of key parameters of the transmitting waveform; on the other hand, it is presented to radio users through the visualization panel through semantic information extraction, so that users have an intuitive and quantitative understanding of the current communication environment. The essence of cognitive radio is to understand the environmental status through the strength of the electric field, and then optimize the communication to meet the needs and adapt to the environment.

[0004] Therefore, how to obtain as much information as possible in different dimensions from the electric field strength to provide more decision-making conditions for optimizing communication performance is a problem that technical personnel in this field need to solve urgently. Summary of the invention

[0005] In view of the above problems, the present invention provides a method for acquiring high-level semantic information for cognitive radio, so as to at least solve some of the technical problems mentioned in the above background technology.

[0006] In order to achieve the above object, the present invention adopts the following technical solution:

[0007] The present invention provides a method for acquiring high-level semantic information for cognitive radio, comprising:

[0008] Perform spectrum situation awareness based on the received original electromagnetic signals, determine whether there is idle authorized spectrum based on the spectrum situation awareness information, and obtain information about frequency-using devices in the current network;

[0009] Based on spectrum situational awareness information, high-level semantic information reasoning is performed to obtain the current network topology and service type information transmitted between nodes;

[0010] Perform interference estimation on the original electromagnetic signal after filtering, and perform interference recognition based on the interference estimation result to extract interference type information;

[0011] Based on the interference estimation result, interference suppression is performed on the original electromagnetic signal after filtering, channel estimation is performed on the interference suppression result, and channel recognition is performed based on the channel estimation result to extract channel type information.

[0012] Furthermore, the spectrum situation awareness is performed based on the received original electromagnetic signal, and whether there is an idle authorized spectrum is determined according to the spectrum situation awareness information, and the frequency-using device information in the current network is obtained; specifically, it includes:

[0013] Extracting statistical features from raw electromagnetic signals received within a target communication area;

[0014] Analyzing the correlation between every two different original electromagnetic signals using the statistical characteristics;

[0015] Based on the correlation between different original electromagnetic signals, a spectrum situation map is constructed to present spectrum situation awareness information;

[0016] It is determined whether there is idle authorized spectrum in the electromagnetic space according to the spectrum situation awareness information, and the frequency-using equipment information in the current network is obtained.

[0017] Furthermore, the high-level semantic information reasoning based on the spectrum situational awareness information to obtain the topological structure of the current network specifically includes:

[0018] Each signal source in the spectrum situation diagram is regarded as a device node; edges are constructed between device nodes according to the correlation between different original electromagnetic signals to represent the communication relationship network between device nodes;

[0019] Based on the communication relationship network, redundant edges and redundant nodes are removed, and the topological structure of the current network in the target communication area is output.

[0020] Furthermore, the high-level semantic information reasoning is performed based on the spectrum situation awareness information to obtain the service type information currently transmitted between network nodes; specifically including:

[0021] Extract time domain features from the spectrum situation map, and analyze the spectrum data dimension of the original electromagnetic signal in the time dimension based on the time domain features;

[0022] Extract frequency domain features from the spectrum situation map and analyze the spectrum characteristics of the original electromagnetic signal based on the frequency domain features;

[0023] Associating the modulation mode of the original electromagnetic signal with a preset communication service type;

[0024] The current transmission service type information is determined based on the spectrum data dimension, spectrum characteristics and preset communication service type.

[0025] Furthermore, the interference estimation is performed on the original electromagnetic signal after filtering, and interference recognition is performed based on the interference estimation result to extract interference type information, which specifically includes:

[0026] For the original electromagnetic signal after filtering, by comparing the difference between the actual spectrum and the expected spectrum, it is possible to identify whether there is an interference signal in the spectrum;

[0027] The interference type information is identified based on the spectrum characteristics and time domain characteristics of the interference signal.

[0028] Further, the identifying interference type information according to the spectrum characteristics and time domain characteristics of the interference signal specifically includes:

[0029] Use deep learning neural networks to construct a mapping between interference feature parameters and interference type information;

[0030] The extracted spectral characteristics and time domain characteristics of the interference signal are input into the neural network to obtain the interference type information.

[0031] Further, the performing interference suppression on the original electromagnetic signal after filtering based on the interference estimation result, performing channel estimation on the interference suppression result, and performing channel recognition based on the channel estimation result to extract channel type information specifically includes:

[0032] Remove interference signals from original electromagnetic signals to achieve interference suppression;

[0033] The original electromagnetic signal after interference suppression is processed based on the least squares channel estimation method to obtain complex exponential type channel gain data information;

[0034] Channel characteristic parameters are extracted based on the channel gain data information, and channel type information is obtained according to the mapping relationship between the channel characteristic parameters and the channel type.

[0035] Further, the acquiring the channel type information according to the mapping relationship between the channel characteristic parameter and the channel type specifically includes:

[0036] The channel gain is converted into a time-domain channel impulse response using Fourier transform;

[0037] The power delay spectrum is obtained by taking the modulus and squaring the time domain channel impulse response;

[0038] Extract the power and delay information of each multipath based on the power delay spectrum;

[0039] Calculate and obtain the root mean square delay spread characteristic parameter according to the multipath power and delay information;

[0040] A mapping between the root mean square delay spread characteristic parameters and the channel type is constructed based on a neural network to identify the channel type information.

[0041] Furthermore, the method also includes: using a minimum mean square error equalizer to eliminate the influence of the channel type information on the original electromagnetic signal to achieve channel equalization.

[0042] Furthermore, it also includes: demodulating and decoding the original electromagnetic signal after channel equalization to complete signal reception.

[0043] Furthermore, the spectrum situation awareness information includes basic spectrum information and geographic location information; wherein, the basic spectrum information includes spectrum energy, spectrum bandwidth and incoming wave direction of the frequency-using node; and the geographic location information includes the latitude, longitude and altitude of the equipment.

[0044] Furthermore, the filtering process specifically includes filtering out electromagnetic components and ineffective electromagnetic components in the original electromagnetic signal whose frequencies are higher than a preset value.

[0045] It can be seen from the above technical solutions that, compared with the prior art, the present invention discloses a method for acquiring high-level semantic information for cognitive radio, which has the following beneficial effects:

[0046] The present invention can more accurately identify spectrum holes and intuitively understand the electromagnetic situation information such as the location, radiation range, and intensity of the radiation source by extracting high-level semantic information of the electromagnetic network domain such as spectrum situation, network topology, service type, channel type, and interference type from the original electromagnetic signal, thereby realizing better network planning and spectrum access and other spectrum management solutions; it can adjust waveform transmission parameters according to real-time perception information of the external environment to ensure communication quality; it can identify various types of interference and take targeted countermeasures such as switching signals, adjusting power, and using anti-interference coding; it can adjust transmission strategies according to different service types (such as voice, data, video, etc.) to meet the requirements of different services for bandwidth, delay, reliability, etc.; it can dynamically adjust the topology structure according to network requirements. Subsequent cognitive radio stations can optimize transmission strategies from the aspects of modulation mode, transmission power, coding mode, and other key parameters of the transmitting waveform according to high-level semantic information.

[0047] Other features and advantages of the present invention will be set forth in the description which follows.

[0048] The technical solution of the present invention is further described in detail below through the accompanying drawings and embodiments. BRIEF DESCRIPTION OF THE DRAWINGS

[0049] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on the provided drawings without paying creative work.

[0050] Figure 1 A system diagram of a method for acquiring high-level semantic information for cognitive radio provided by an embodiment of the present invention.

[0051] Figure 2 A schematic flow chart of a method for acquiring high-level semantic information for cognitive radio provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0052] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0053] The terms "including" and "having" and any variations thereof in the embodiments of the present invention are intended to cover non-exclusive inclusions. For example, a process, method, system, product or device comprising a series of steps or modules is not necessarily limited to those steps or modules explicitly listed, but may include other steps or modules not explicitly listed or inherent to these processes, methods, products or devices.

[0054] See also Figure 1 and Figure 2 As shown, Figure 1 A system schematic diagram of a high-level semantic information acquisition method for cognitive radio disclosed in an embodiment of the present invention. The high-level semantic information acquisition method for cognitive radio can be applied in different communication scenarios and device types. The embodiment of the present invention does not limit the usage scenarios and device types of the method. Figure 2 The flowchart of a method for acquiring high-level semantic information for cognitive radio disclosed in an embodiment of the present invention is shown in Figure 2. For the convenience of description, each step is marked with numbers 201 to 205 in the embodiment of the present invention. It should be noted that the numbers are only for the convenience of description and do not limit the execution order of each step. The flowchart of the method for acquiring high-level semantic information for cognitive radio includes the following steps:

[0055] 201. Perform spectrum situation awareness based on the received original electromagnetic signal, determine whether there is idle authorized spectrum according to the spectrum situation awareness information, and obtain frequency-using device information in the current network;

[0056] 202. Perform high-level semantic information reasoning based on spectrum situational awareness information to obtain the current network topology and service type information transmitted between nodes;

[0057] 203. Perform interference estimation on the original electromagnetic signal after filtering, and perform interference recognition based on the interference estimation result to extract interference type information;

[0058] 204. Perform interference suppression on the original electromagnetic signal after filtering based on the interference estimation result, perform channel estimation on the interference suppression result, perform channel recognition based on the channel estimation result, and extract channel type information.

[0059] This method obtains a series of higher-level semantic reasoning information, such as external channel type, malicious interference information from non-cooperative parties, topological structure of frequency-using equipment, and node transmission service type, through perception of spectrum situation and processing of received signals. It can provide more decision-making information for the radio station to adaptively adjust internal status and transmission parameters, and help achieve robust communication in complex unknown environments.

[0060] The main purpose of the present invention is to extract multi-dimensional information of the electromagnetic network domain from the received original electromagnetic signal. Next, the steps indicated by the above numbers are described in detail.

[0061] In the step 201, spectrum situation awareness is performed based on the received original electromagnetic signal, and whether there is an idle authorized spectrum is determined according to the spectrum situation awareness information, and information on frequency-using devices in the current network is obtained; specifically, the following contents are included:

[0062] (1) Receive the original electromagnetic signal from the target communication area through the receiving antenna, and extract statistical features from the original electromagnetic signal; the statistical features include the duration, carrier frequency, power change and other features that can reflect the correlation between signals and communication behavior;

[0063] (2) Analyze the correlation between each two different original electromagnetic signals using the statistical characteristics of the original electromagnetic signals; if two original electromagnetic signals overlap or appear alternately in time, and parameters such as power match each other, it indicates that there is a possibility of a communication relationship between the two original electromagnetic signals;

[0064] (3) Based on the correlation between different original electromagnetic signals, a spectrum situation map is constructed; the spectrum situation map can visualize the spectrum situation awareness information extracted from the original electromagnetic signals in the form of a tensor;

[0065] Specifically, the spectrum situation awareness information includes spectrum basic information and geographic location information; wherein the spectrum basic information includes spectrum energy, spectrum bandwidth and wave direction of the frequency node; the geographic location information includes the latitude and longitude and altitude of the equipment;

[0066] Since the above spectrum situation map can characterize the spatial distribution of radio parameters such as the received signal strength and the used frequency band of the communication nodes in the target communication area; therefore, based on the spectrum situation map, the distribution and communication behavior of the original electromagnetic signal in the target communication area can be intuitively displayed;

[0067] (4) Based on the above spectrum situation awareness information, determine whether there is idle authorized spectrum in the electromagnetic space; based on this, the spectrum utilization efficiency can be improved; in addition, based on the above spectrum situation awareness information, the number of frequency-using nodes and frequency-using equipment information in the current network in the target communication area can also be obtained, thereby achieving a comprehensive grasp of the electromagnetic spectrum space.

[0068] In the step 202, high-level semantic information reasoning is performed based on the spectrum situation awareness information to obtain the topology of the current network and the service type information transmitted between nodes; specifically, the following contents are included:

[0069] (1) Obtain the topology of the current network:

[0070] Each signal source in the spectrum situation diagram is regarded as a device node, and edges are constructed between the device nodes according to the correlation between different original electromagnetic signals to represent the communication relationship network or potential communication contact network between the device nodes;

[0071] Graph theory and network optimization algorithms are used to optimize the initially constructed communication relationship network, remove redundant edges and redundant nodes, and output the topological structure of the frequency node network in the target communication area; this topological structure can be presented in two-dimensional structures such as star network topology, ring network topology, and distributed topology, and can also be presented in the form of a three-dimensional topological structure in combination with the equipment altitude information.

[0072] (2) Obtain information about the type of service currently transmitted between network nodes:

[0073] Extract time domain features from the spectrum situation diagram, analyze the spectrum data dimension of the original electromagnetic signal in the time dimension based on the time domain features, such as the periodicity and burstiness of the signal, and count the occupancy of different frequency bands in different time periods. This can obtain information such as the active time and duration of the communication service, which is convenient for users to analyze the communication behavior of the frequency-using nodes.

[0074] Extract frequency domain features from the spectrum situation diagram and analyze the spectrum characteristics of the signal, such as bandwidth, center frequency, spectrum shape, etc., based on the frequency domain features;

[0075] Through demodulation analysis, the modulation type of the signal, such as AM, FM, PSK, etc., is identified, and the modulation mode of the original electromagnetic signal is associated with the preset communication service type.

[0076] The current transmission service type information is determined based on the spectrum data dimension, spectrum characteristics and preset communication service type. For example, voice data is one-dimensional spectrum data and image data is two-dimensional spectrum data.

[0077] In the step 203, interference estimation is performed on the original electromagnetic signal after filtering, and interference recognition is performed based on the interference estimation result to extract interference type information; specifically, the following contents are included:

[0078] (1) filtering the received original electromagnetic signal to remove electromagnetic components with frequencies higher than a preset value and ineffective electromagnetic components in the original electromagnetic signal;

[0079] (2) For the original electromagnetic signal after filtering, by comparing the difference between the actual spectrum and the expected spectrum, identify whether there is an interference signal in the spectrum;

[0080] (3) Identify interference type information based on the spectral characteristics (such as frequency range, bandwidth, spectral shape, center frequency, etc.) and time domain characteristics (such as duration, periodicity, burstiness, etc.) of the interference signal;

[0081] Specifically, a deep learning neural network can be used to construct a mapping between interference feature parameters (spectral characteristics and time domain characteristics of interference signals) and interference type information, and the extracted spectral characteristics and time domain characteristics of interference signals are input into the neural network to obtain interference type information, thereby realizing the extraction of high-level semantic information of interference.

[0082] The interference type information refers to radio signals that disrupt normal communication order and affect the normal transmission of information; specifically, it includes interference between signals emitted by different signal sources in the same channel, interference between adjacent channels, and suppressive interference that overlaps or semi-overlaps with signal frequencies. Targeted anti-interference measures can be taken based on the identified interference type information.

[0083] In the step 204, interference suppression is performed on the original electromagnetic signal after filtering based on the interference estimation result, channel estimation is performed on the interference suppression result, and channel recognition is performed based on the channel estimation result to extract channel type information; specifically, the following contents are included:

[0084] (1) Remove interference signals from the original electromagnetic signals to achieve interference suppression;

[0085] (2) Processing the original electromagnetic signal after interference suppression based on the least squares channel estimation method to obtain complex exponential type channel gain data information;

[0086] (3) extracting channel characteristic parameters based on the channel gain data information, and obtaining channel type information according to the mapping relationship between the channel characteristic parameters and the channel type;

[0087] Specifically, the channel gain (i.e., channel frequency domain response data) obtained by channel estimation is input into the channel recognition module, and the channel gain is converted into a time domain channel impulse response using Fourier transform; the power delay spectrum is obtained by taking the modulus and squaring the time domain channel impulse response; the power and delay information of each multipath is extracted based on the power delay spectrum; the root mean square delay spread characteristic parameters that can reflect the multipath richness in the current channel are calculated based on the multipath power and delay information; then, a mapping between the root mean square delay spread characteristic parameters and the channel type is constructed based on a neural network (i.e., the current propagation scenario is divided into a specific channel according to the characteristic parameter value), the channel type information is identified, and the extraction of high-level semantic information of the channel is realized;

[0088] The channel type information includes the Ricean channel with line-of-sight transmission path and the Rayleigh channel with pure non-line-of-sight path; the estimated parameters of the channel state information include: the transfer function of the transmission system, multipath delay, Doppler frequency shift, signal-to-noise ratio, channel noise power, availability of authorized frequency band, etc.

[0089] In another embodiment, the method further includes: using a minimum mean square error equalizer to eliminate the influence of the channel type information on the original electromagnetic signal to achieve channel equalization.

[0090] In another embodiment, the method further includes: demodulating and decoding the original electromagnetic signal after channel equalization to complete signal reception.

[0091] In another embodiment, it also includes: based on the acquired spectrum situation, topology structure, service type information, interference type information and channel type information, deciding waveform parameters suitable for the current communication scenario.

[0092] In summary, the high-level semantic information acquisition method for cognitive radio provided by the embodiment of the present invention can effectively guide the communication nodes in the network to flexibly access authorized or idle spectrum in a timely manner through the perception of spectrum situation, which can effectively alleviate the problem of spectrum resource shortage; the perception and identification of wireless channels, malicious interference, network topology and service types can enhance the multi-domain cognitive ability of cognitive radio stations, provide more decision-making information for cognitive radio stations to adaptively adjust internal states and transmission parameters according to changes in the external environment, and help to achieve robust communication in complex and unknown environments.

[0093] The various embodiments in this specification are described in a progressive manner, and each embodiment focuses on the differences from other embodiments. The same or similar parts between the various embodiments can be referenced to each other.

[0094] The above description of the disclosed embodiments enables one skilled in the art to implement or use the present invention. Various modifications to these embodiments will be apparent to one skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of the present invention. Therefore, the present invention will not be limited to the embodiments shown herein, but rather to the widest scope consistent with the principles and novel features disclosed herein.

Claims

1. A high-level semantic information acquisition method for cognitive radio. It is characterized in that include: Perform spectrum situation awareness based on the received original electromagnetic signals, determine whether there is idle authorized spectrum based on the spectrum situation awareness information, and obtain information about frequency-using devices in the current network; Based on spectrum situational awareness information, high-level semantic information reasoning is performed to obtain the current network topology and service type information transmitted between nodes; Perform interference estimation on the original electromagnetic signal after filtering, and perform interference recognition based on the interference estimation result to extract interference type information; Based on the interference estimation result, interference suppression is performed on the original electromagnetic signal after filtering, channel estimation is performed on the interference suppression result, and channel recognition is performed based on the channel estimation result to extract channel type information.

2. The method for acquiring high-level semantic information for cognitive radio according to claim 1, It is characterized in that The spectrum situation awareness is performed based on the received original electromagnetic signal, and whether there is an idle authorized spectrum is determined according to the spectrum situation awareness information, and the frequency-using device information in the current network is obtained; specifically, it includes: Extracting statistical features from raw electromagnetic signals received within a target communication area; Analyzing the correlation between every two different original electromagnetic signals using the statistical characteristics; Based on the correlation between different original electromagnetic signals, a spectrum situation map is constructed to present spectrum situation awareness information; It is determined whether there is idle authorized spectrum in the electromagnetic space according to the spectrum situation awareness information, and the frequency-using equipment information in the current network is obtained.

3. The method for acquiring high-level semantic information for cognitive radio according to claim 2, It is characterized in that The high-level semantic information reasoning based on the spectrum situation awareness information to obtain the topological structure of the current network specifically includes: Each signal source in the spectrum situation diagram is regarded as a device node; edges are constructed between device nodes according to the correlation between different original electromagnetic signals to represent the communication relationship network between device nodes; Based on the communication relationship network, redundant edges and redundant nodes are removed, and the topological structure of the current network in the target communication area is output.

4. The method for acquiring high-level semantic information for cognitive radio according to claim 2, It is characterized in that The high-level semantic information reasoning based on the spectrum situation awareness information to obtain the service type information currently transmitted between network nodes specifically includes: Extract time domain features from the spectrum situation map, and analyze the spectrum data dimension of the original electromagnetic signal in the time dimension based on the time domain features; Extract frequency domain features from the spectrum situation map and analyze the spectrum characteristics of the original electromagnetic signal based on the frequency domain features; Associating the modulation mode of the original electromagnetic signal with a preset communication service type; The current transmission service type information is determined based on the spectrum data dimension, spectrum characteristics and preset communication service type.

5. The method for acquiring high-level semantic information for cognitive radio according to claim 1, It is characterized in that The interference estimation is performed on the original electromagnetic signal after filtering, and interference recognition is performed based on the interference estimation result to extract interference type information, which specifically includes: For the original electromagnetic signal after filtering, by comparing the difference between the actual spectrum and the expected spectrum, it is possible to identify whether there is an interference signal in the spectrum; The interference type information is identified based on the spectrum characteristics and time domain characteristics of the interference signal.

6. The method for acquiring high-level semantic information for cognitive radio according to claim 5, It is characterized in that The identifying interference type information according to the spectrum characteristics and time domain characteristics of the interference signal specifically includes: Use deep learning neural networks to construct a mapping between interference feature parameters and interference type information; The extracted spectral characteristics and time domain characteristics of the interference signal are input into the neural network to obtain the interference type information.

7. The method for acquiring high-level semantic information for cognitive radio according to claim 1, It is characterized in that The method of performing interference suppression on the filtered original electromagnetic signal based on the interference estimation result, performing channel estimation on the interference suppression result, and performing channel recognition based on the channel estimation result to extract channel type information specifically includes: Remove interference signals from original electromagnetic signals to achieve interference suppression; The original electromagnetic signal after interference suppression is processed based on the least squares channel estimation method to obtain complex exponential type channel gain data information; Channel characteristic parameters are extracted based on the channel gain data information, and channel type information is obtained according to the mapping relationship between the channel characteristic parameters and the channel type.

8. The method for acquiring high-level semantic information for cognitive radio according to claim 7, It is characterized in that The acquiring the channel type information according to the mapping relationship between the channel characteristic parameter and the channel type specifically includes: The channel gain is converted into a time-domain channel impulse response using Fourier transform; The power delay spectrum is obtained by taking the modulus and squaring the time domain channel impulse response; Extract the power and delay information of each multipath based on the power delay spectrum; Calculate and obtain the root mean square delay spread characteristic parameter according to the multipath power and delay information; A mapping between the root mean square delay spread characteristic parameters and the channel type is constructed based on a neural network to identify the channel type information.

9. The method for acquiring high-level semantic information for cognitive radio according to claim 1, It is characterized in that Also includes: The minimum mean square error equalizer is used to eliminate the influence of channel type information on the original electromagnetic signal and achieve channel equalization.

10. The method for acquiring high-level semantic information for cognitive radio according to claim 9, It is characterized in that Also includes: The original electromagnetic signal after channel equalization is demodulated and decoded to complete signal reception.

Images