CN116016225A - Information processing method, signal location method, device, equipment and medium - Google Patents

Abstract

The present application relates to an information processing method, a signal location method, a device, a device and a medium. The method includes: firstly performing time-domain transformation on a plurality of channel state information of the target channel, correspondingly obtaining a plurality of initial channel impulse response information, then normalizing the influencing parameters of each initial channel impulse response information, and finally normalizing The initial channel impulse response information after the optimization process is denoised, and multiple target channel impulse response information are obtained. Wherein, the influence parameter represents a parameter that affects the stability of the channel state information. By adopting the method to obtain stable and effective signal state information, the position information of the signal can be accurately determined.

Description

Information processing method, signal location method, device, equipment and medium

technical field

The present application relates to the technical field of signal location, and in particular, to an information processing method, a signal location method, a device, a device, and a medium.

Background technique

Channel State Information (CSI) describes the propagation of the signal on each transmission path, including information such as signal scattering, distance attenuation, and environmental attenuation, and is widely used in the field of wireless communication signal positioning technology.

In the related technology, the CSI is combined with the machine learning algorithm, and the features of the CSI data are learned according to the machine learning model, so as to predict the position of the signal. However, the related art cannot obtain stable CSI information when predicting the signal position, and thus cannot accurately determine the position information of the signal.

Contents of the invention

Based on this, it is necessary to provide an information processing method, a signal location method, a device, a device, and a medium for the above-mentioned technical problems, which can obtain stable channel state information, and then accurately determine the location information of the signal.

In a first aspect, the present application provides an information processing method, the method comprising:

performing time-domain transformation on multiple channel state information of the target channel, and correspondingly obtaining multiple initial channel impulse response information;

The influence parameters of each initial channel impulse response information are normalized; the influence parameters represent parameters that affect the stability of the channel state information;

Denoising is performed on the normalized initial channel impulse response information to obtain multiple target channel impulse response information.

In one of the embodiments, the influencing parameters include delay, and normalizing the influencing parameters of each initial channel impulse response information includes:

Acquiring the amplitude of each initial channel impulse response information;

According to the amplitude of each initial channel impulse response information, determine the sampling point corresponding to the maximum amplitude value of each initial channel impulse response information;

According to the sampling point corresponding to the maximum amplitude value of each initial channel impulse response information, the sampling point corresponding to the maximum amplitude value of each initial channel impulse response information is cyclically shifted to the first sampling point, which is used to eliminate the gap between each initial channel impulse response information delay.

In one of the embodiments, the sampling point corresponding to the maximum amplitude value of each initial channel impulse response information is cyclically shifted to before the first sampling point, the method further includes:

Obtain the main path rise information of each initial channel impulse response information after the cyclic displacement;

According to the start sampling point and the end sampling point of the main path rising information, the main path rising information is cyclically shifted to before the maximum amplitude value.

In one of the embodiments, the influencing parameters include amplitude, and normalizing the influencing parameters of each initial channel impulse response information includes:

Determine the maximum amplitude value according to the amplitude of each initial channel impulse response information;

The amplitude of each initial channel impulse response information is divided by the maximum amplitude value, so as to perform normalization processing on the amplitude of each initial channel impulse response information.

In one of the embodiments, denoising processing is performed on the normalized initial channel impulse response information, including:

performing truncation processing on each initial channel impulse response information according to the preset number of sampling points to obtain truncated channel impulse response information of each initial channel impulse response information;

Each truncated channel impulse response information is determined as information after denoising processing of each initial channel impulse response information.

In a second aspect, the present application also provides a signal location method, the method comprising:

Obtain initial channel state information of a transmission channel of the signal according to the received signal;

Using the information processing method in any embodiment of the first aspect to process the initial channel state information to obtain target channel state information;

Input the target channel state information into the machine learning model to obtain the signal location result.

In a third aspect, the present application also provides an information processing device, which includes:

A time-domain transform module, configured to perform time-domain transform on a plurality of channel state information of the target channel, corresponding to obtain a plurality of initial channel impulse response information;

The parameter processing module is used to normalize the influencing parameters of each initial channel impulse response information; the influencing parameters represent parameters affecting the stability of the channel state information;

The denoising processing module is configured to perform denoising processing on the normalized initial channel impulse response information to obtain multiple target channel impulse response information.

In the fourth aspect, the present application also provides a signal locating device, which includes:

An information acquisition module, configured to acquire initial channel state information of the transmission channel of the signal according to the received signal;

An information processing module, configured to use the information processing method in any embodiment of the first aspect to process initial channel state information to obtain target channel state information;

The result acquisition module is used to input the target channel state information into the machine learning model to obtain the positioning result of the signal.

In a fifth aspect, the present application also provides a computer device. The computer device includes a memory and a processor, the memory stores a computer program, and the processor implements the steps of the method in any one of the embodiments of the first aspect and the second aspect when executing the computer program.

In a sixth aspect, the present application further provides a computer-readable storage medium. The computer-readable storage medium has a computer program stored thereon, and when the computer program is executed by a processor, the steps of the method in any one of the embodiments of the first aspect and the second aspect above are realized.

In a seventh aspect, the present application further provides a computer program product. The computer program product includes a computer program, and when the computer program is executed by a processor, the steps of the method in any one of the embodiments of the first aspect and the second aspect above are implemented.

In the above information processing method, signal location method, device, equipment and medium, in the information processing method, firstly, time-domain transformation is performed on multiple channel state information of the target channel, correspondingly obtaining multiple initial channel impulse response information, and then each initial The influencing parameters of the channel impulse response information are normalized, and finally the normalized initial channel impulse response information is denoised to obtain multiple target channel impulse response information. Wherein, the influence parameter represents a parameter that affects the stability of the channel state information. Since the signal processing method is to normalize the influencing parameters on the basis of obtaining the initial channel impulse response information, it is equivalent to eliminating multiple factors that affect the stability of the initial impulse response information when the present application processes the channel information. Furthermore, denoising the acquired initial channel pulse information after normalization processing can eliminate the redundant sampling due to noise in the initial channel pulse information on the basis of retaining the effective signal of the initial channel pulse information point. To sum up, the channel state information obtained by the information processing method of this application takes into account not only the unstable factors of the channel state information, but also the noise information that affects the efficiency of signal positioning, and performs normalization and denoising processing in turn for the above factors, In this way, stable and effective signal state information can be obtained, and the position information of the signal can be accurately determined.

Description of drawings

Fig. 1 is the internal structural diagram of computer equipment in an embodiment;

Fig. 2 is a schematic flow chart of an information processing method in an embodiment;

Fig. 3 is a schematic flow chart of delay normalization processing steps in an embodiment;

Fig. 4 is an information schematic diagram of channel impulse response information in an embodiment;

Fig. 5 is a schematic diagram of displacement of channel impulse response information in an embodiment;

FIG. 6 is a schematic flowchart of delay normalization processing steps in another embodiment;

Fig. 7 is a schematic diagram of main path rise of channel impulse response information in an embodiment;

Fig. 8 is a schematic diagram of principal diameter displacement of channel impulse response information in an embodiment;

Fig. 9 is a schematic flow chart of amplitude normalization processing steps in an embodiment;

FIG. 10 is a schematic flowchart of channel impulse response information denoising processing in an embodiment;

Fig. 11 is a schematic flowchart of an information processing method in another embodiment;

Fig. 12 is a schematic diagram of information collection of channel impulse response information in an embodiment;

Fig. 13 is a schematic diagram of processing information of channel impulse response information in an embodiment;

Fig. 14 is a schematic flowchart of a channel positioning method in an embodiment;

Fig. 15 is a schematic flowchart of a channel positioning method in another embodiment;

Fig. 16 is a structural block diagram of an information processing device in an embodiment;

Fig. 17 is a structural block diagram of a signal locating device in an embodiment.

Detailed ways

In order to make the purpose, technical solution and advantages of the present application clearer, the present application will be further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described here are only used to explain the present application, and are not intended to limit the present application.

The information processing method and the signal location method provided in the embodiments of the present application may be applied to computer equipment. The computer device may be a terminal, and its internal structure may be as shown in FIG. 1 . The computer device includes a processor, a memory, an input/output interface, a communication interface, a display unit and an input device. Wherein, the processor, the memory and the input/output interface are connected through the system bus, and the communication interface, the display unit and the input device are connected to the system bus through the input/output interface. Wherein, the processor of the computer device is used to provide calculation and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system and computer programs. The internal memory provides an environment for the operation of the operating system and computer programs in the non-volatile storage medium. The input/output interface of the computer device is used for exchanging information between the processor and external devices. The communication interface of the computer device is used to communicate with an external terminal in a wired or wireless manner, and the wireless manner can be realized through WIFI, mobile cellular network, NFC (Near Field Communication) or other technologies. When the computer program is executed by a processor, a signal processing method and a signal locating method are realized. The display unit of the computer equipment is used to form a visually visible picture, which may be a display screen, a projection device or a virtual reality imaging device. The display screen may be a liquid crystal display screen or an electronic ink display screen, and the input device of the computer device may be a touch layer covered on the display screen, or a button, a trackball or a touch pad set on the casing of the computer device, or a External keyboard, touchpad or mouse etc.

High-precision location service is a key support service for emerging industries such as the Industrial Internet, the Internet of Things, and the Internet of Vehicles. In the future, there will be a large number of intelligent networked terminals such as industrial robots, driverless cars, and smart sensors that need to provide accurate, real-time, and reliable positioning. Serve. In the field of high-precision location services, using wireless communication signals to accurately locate terminals has become a research hotspot in recent years. However, there are still some problems in this field that are difficult to be effectively solved by traditional signal processing methods, such as non-line-of-sight (NLOS) identification, position estimation under NLOS conditions, and angle-of-arrival ranging in strong multipath environments ( Angle-of-Arrival, AoA) estimation, etc.

In order to solve the above problems, related technologies combine wireless communication signals (such as Channel State Information (CSI)) with the field of artificial intelligence (such as machine learning), and use the feature extraction and nonlinear fitting capabilities of machine learning. Get efficient and accurate location services. However, the measurement error introduced by the non-ideal characteristics of hardware devices, that is, hardware damage, will lead to significant differences between the CSI measured multiple times at the same location, and this mode instability will lead to instability in the output of machine learning. This leads to low positioning accuracy and poor generalization performance.

At present, there are mainly two types of methods for CSI processing in the positioning technology based on the combination of CSI and machine learning. One is that the influence of CSI instability on the output of the machine learning deep network is not considered, and the original CSI is directly input into the machine learning deep network for training. Obviously, due to the unavoidable hardware damage, there will be large differences in amplitude and phase between CSIs measured multiple times at the same location. Directly inputting the original CSI will lead to unstable output results of the machine learning deep network, which will lead to a decrease in positioning accuracy. , Poor generalization performance. Another method is to normalize the amplitude of the CSI, and normalize the amplitude of the Channel Impulse Response (CIR) information (Channel Impulse Response, CIR) obtained by CSI processing based on the total energy of the signal, so as to avoid the impact of the occasional extremely large signal on the machine. Learning the effects of deep network outputs. However, the CSI instability caused by hardware loss is reflected in both amplitude and phase. Only preprocessing the amplitude still cannot completely eliminate the instability of the CSI phase, which will lead to a decrease in the accuracy of the network output.

Based on this, the present application provides an information processing method, a signal location method, a device, a device, and a medium. By performing time-domain transformation on multiple channel state information of the target channel, multiple initial channel impulse response information is correspondingly obtained, and then the The influence parameters of each initial channel impulse response information are normalized to obtain stable CIR information, and the normalized initial channel impulse response information is denoised to obtain multiple stable and effective target channel impulses Response message. The processed target channel state information is used for training in the machine learning model. Due to the stability and effectiveness of the target channel state information, the network training speed is improved and it has better robustness.

In one embodiment, as shown in FIG. 2, an information processing method is provided, including:

S202. Perform time-domain transformation on multiple pieces of channel state information of the target channel to obtain corresponding multiple pieces of initial channel impulse response information.

Channel state information is the channel attribute of the communication link, which describes the attenuation factor of the signal on each transmission path, such as signal scattering (Scattering), environmental fading (fading, multipath fading or shadowing fading), distance attenuation (power decay of distance) and other information. The channel state information can make the communication system adapt to the current channel conditions, and provide guarantee for high-reliability and high-speed communication in the multi-antenna system.

The target channel contains multiple channel state information, and the multiple channel state information is represented by the function of frequency. In order to facilitate the processing of each channel state information, the Inverse Fast Fourier Transform (Inverse Fast Fourier Transform) is performed on each channel state information respectively. Transform, IFFT), which converts each channel state information from a frequency domain signal to a time domain signal, that is, each channel state information corresponds to each initial channel impulse response information. It should be noted that both channel state information and channel impulse response information are representation forms of channel signal information, and the information provided by both is the same.

S204. Perform normalization processing on the influencing parameters of each initial channel impulse response information; the influencing parameters represent parameters affecting the stability of the channel state information.

Due to the non-ideal characteristics of hardware devices, such as the loss of the receiving source, etc., measurement errors, that is, hardware damage, will be introduced in the process of obtaining channel state information. Hardware damage will lead to differences between the channel state information measured multiple times at the same location, which is reflected in the instability of the channel state information measured multiple times. Then, after obtaining the initial channel impulse response information corresponding to the channel state information, taking into account the factors that affect the instability of the channel state information, the influencing parameters of the initial channel impulse response information are obtained, and the influencing parameters of each initial channel impulse response information Normalization is performed to eliminate the influence of unstable factors, so as to obtain stable channel impulse response information.

S206. Perform denoising processing on the normalized initial channel impulse response information to obtain multiple target channel impulse response information.

After the initial channel impulse response information is normalized, the influence of unstable factors is eliminated, and then according to the acquired normalized initial channel impulse response information, combined with machine learning and other algorithms for signal positioning. In the process of signal location, since each initial channel impulse response sequence itself has random noise, it means that the input data of signal location cannot effectively represent the channel state information, which will lead to a decrease in the accuracy of signal location results, and the random noise reflects For multiple redundant sampling points, this will lengthen the signal localization process. That is to say, the noise of the normalized initial channel impulse response information will affect the efficiency of signal location. Therefore, it is necessary to further process the normalized initial channel impulse response information to eliminate the noise of the initial channel impulse response information.

In the embodiment of the present application, firstly, time-domain transformation is performed on multiple channel state information of the target channel to obtain corresponding multiple initial channel impulse response information, and then normalization is performed on the influencing parameters of each initial channel impulse response information, and finally the normalized The initial channel impulse response information after the optimization process is denoised, and multiple target channel impulse response information are obtained. Wherein, the influence parameter represents a parameter that affects the stability of the channel state information. Since the signal processing method is to normalize the influencing parameters on the basis of obtaining the initial channel impulse response information, it is equivalent to eliminating multiple factors that affect the stability of the initial impulse response information when the present application processes the channel information. Furthermore, denoising the acquired initial channel pulse information after normalization processing can eliminate the redundant sampling due to noise in the initial channel pulse information on the basis of retaining the effective signal of the initial channel pulse information point. To sum up, the channel state information obtained by the information processing method of this application takes into account not only the unstable factors of the channel state information, but also the noise information that affects the efficiency of signal positioning, and performs normalization and denoising processing in turn for the above factors, In this way, stable and effective signal state information can be obtained, and the position information of the signal can be accurately determined.

When normalizing the influencing parameters of each initial channel impulse response information, it is necessary to consider multiple parameters affecting the stability of the channel state information, such as delay instability, amplitude instability and other influencing parameters, in order to obtain Stable channel impulse response information. Based on this, an embodiment is used below to describe the normalization processing steps of the initial channel impulse response information for the instability of the time delay.

In one embodiment, as shown in FIG. 3, the influencing parameters include time delay, and normalizing the influencing parameters of each initial channel impulse response information includes:

S302. Acquire the amplitude of each initial channel impulse response information.

The initial channel impulse response information corresponds to a group of sampling points, and the amplitude of all sampling points in the initial channel impulse response information is used as the amplitude of the channel impulse response information. That is to say, each piece of initial channel impulse response information corresponds to a set of amplitudes, and the number of amplitudes of each piece of initial channel impulse response information is consistent with the number of corresponding sampling points.

S304. According to the magnitude of each initial channel impulse response information, determine a sampling point corresponding to the maximum magnitude value of each initial channel impulse response information.

Select the maximum amplitude from the amplitudes corresponding to the multiple sampling points of the initial channel impulse response information, and determine the sampling point corresponding to the maximum amplitude as the sampling point corresponding to the maximum amplitude value of the initial channel impulse response information. The process of determining the sampling point n _max corresponding to the maximum amplitude value is characterized by the following expression:

n _max ＝argmax(CIR ^amp ) Formula 1

In Equation 1, CIR ^amp represents the initial channel impulse response information, and argmax( ) represents the position of the sampling point corresponding to the maximum amplitude value of CIR ^amp .

Taking an initial channel impulse response information as an example, as shown in FIG. 4, FIG. 4 is a schematic diagram of an initial channel impulse response information, the horizontal axis represents sampling points, and the vertical axis represents the magnitude of the initial channel impulse response information. It can be seen from FIG. 4 that the amplitude of the initial channel impulse response information corresponding to the dotted line is the maximum amplitude value CIR ^amp , and the intersection point n _max of the dotted line and the horizontal axis is the sampling point corresponding to the maximum amplitude value of the initial channel impulse response information.

S306. According to the sampling point corresponding to the maximum amplitude value of each initial channel impulse response information, cyclically shift the sampling point corresponding to the maximum amplitude value of each initial channel impulse response information to the first sampling point, so as to eliminate each initial channel impulse response information time delay between.

Take the sampling point corresponding to the maximum amplitude value of each initial channel impulse response information as the displacement amount, take one sampling point as a unit, and circularly shift the waveform of each initial channel impulse response information. After the cyclic displacement, each initial channel impulse response information is the largest The sampling points corresponding to the amplitude value are all moved to the first sampling point. The operation of the above cyclic shift can be expressed as:

CIR ^amp ＝cirshift(CIR ^amp ,-n _max +1) Formula 2

In formula 2, cirshift(x(n),n ₀ ) means to cyclically shift the sequence x(n) to the right by n ₀ points.

Still taking the channel impulse response information shown in Figure 4 as an example, taking one sampling point as the unit, if the initial channel impulse response information is cyclically shifted to the first sampling point, it needs to move -n _max +1 units, and the corresponding The displacement process is shown in Figure 5. In Fig. 5, S1 is the initial channel impulse response information, S2 is the channel impulse response information of the initial channel impulse response information shifted by one unit, and S3 is the channel impulse response information of the initial channel impulse response information shifted by n _max units.

In the embodiment of the present application, by obtaining the amplitude of each initial channel impulse response information, according to the maximum amplitude of each initial channel impulse response information, determine the sampling point corresponding to the maximum amplitude of each initial channel impulse response information, and according to each initial channel impulse response information The sampling point of each initial channel impulse response information is shifted as a whole until the sampling point corresponding to the maximum amplitude of each initial channel impulse response information is displaced to the first sampling point, which is equivalent to unifying the maximum amplitude of each initial channel impulse information into one sampling point point, in order to achieve the purpose of eliminating the delay jitter between the initial channel pulse information.

In the foregoing embodiments, during the cyclic shifting process of the initial channel impulse response information, complete information of each initial channel impulse response needs to be preserved. In the process of cyclic displacement, the main path information of each initial channel impulse response information will be lost. Based on this, the main path information compensating step of the information processing method will be described below through an embodiment.

In one embodiment, as shown in FIG. 6, the sampling point corresponding to the maximum amplitude value of each initial channel impulse response information is cyclically shifted to before the first sampling point, and the method further includes:

S602. Obtain main path rise information of each initial channel impulse response information after cyclic displacement.

The main path of each initial channel impulse response information refers to a piece of continuous channel impulse response information including the maximum magnitude of each initial channel impulse response information. The main path rise information of each channel impulse response information is determined according to the magnitude of the initial impulse response information of each channel. The main path rise information includes the main path rise time, the start sampling point and the end sampling point of the main path rise information, etc.

Among them, the rise time of the main path is to first obtain the maximum amplitude value of each channel impulse response information according to the amplitude of each initial channel impulse response information, and then compare the amplitude of each initial channel impulse response information with the corresponding maximum amplitude value, according to the comparison As a result, determine the start time and end time of the rise of the main path, and finally use the difference between the end time and the start time of the rise of the main path as the rise time of the main path.

Exemplarily, if the magnitude of the initial channel impulse response information is expressed as CIR ^amp (n), n represents a sampling point, and the maximum amplitude value is expressed as max(CIR ^amp (n)), then the main path rise time of the channel impulse response information n _rise is shown in Figure 7, and the corresponding expression is:

In Equation 3, max( ) represents the operation of taking the maximum value, n _start represents the start time of the main diameter rise, and n _stop represents the end time of the main diameter rise.

S604. According to the start sampling point and the end sampling point of the main path rising information, cyclically shift the main path rising information to before the maximum amplitude value.

In the ascent information of the main path, the sampling point corresponding to the starting time of the main path ascent is determined as the starting sampling point, and the sampling point corresponding to the end time of the main path is determined as the ending sampling point, and then determined according to the starting sampling point and the ending sampling point The displacement amount of the initial channel impulse response information, and then take one sampling point as a unit, and cyclically shift the rising information of the main path to before the maximum amplitude value.

As shown in Figure 8, the channel impulse response information S3 of the initial channel impulse response information in Figure 5 displaced by n _max units is used as the original waveform, S4 represents the waveform of the original waveform displaced by one unit, and S5 represents the original waveform displaced by n _rise units waveform. It can be seen from Figure 8 that the original waveform S3 loses coherent information, and when it is shifted by n _rise units, it can display the complete main diameter information. The process corresponding to the cyclic shift from S3 to S5 can be expressed as: CIR ^amp =cirshift(CIR ^amp ,n _rise ).

In the embodiment of the present application, the initial channel impulse response information is cyclically shifted through the main path rising information of each initial channel impulse response information, so that each initial channel impulse response information can be completely preserved and the corresponding main path information can be displayed.

When normalizing the influencing parameters of each initial channel impulse response information, it is necessary to consider multiple parameters affecting the stability of the channel state information, such as delay instability, amplitude instability and other influencing parameters, in order to obtain Stable channel impulse response information. The above-mentioned embodiment eliminates the instability of the delay through the normalization of the delay. The following describes the normalization processing steps of the initial channel impulse response information in view of the instability of the amplitude through an embodiment.

In one embodiment, as shown in FIG. 9 , the influencing parameters include amplitude, and normalizing the influencing parameters of each initial channel impulse response information includes:

S902. Determine the maximum amplitude value according to the amplitude of each initial channel impulse response information.

According to the amplitude of each initial channel impulse response information, the maximum amplitude value of each initial channel impulse response information is obtained, which is denoted as CIR ^amp =abs(CIR), where abs(·) represents the maximum amplitude operation.

S904. Divide the amplitude of each initial channel impulse response information by the maximum amplitude value, so as to perform normalization processing on the amplitude of each initial channel impulse response information.

After obtaining the amplitude of each initial channel impulse response information and the maximum amplitude value of each initial channel impulse response information, divide the amplitude of each initial channel impulse response information by the maximum amplitude value to obtain the amplitude normalization process of each initial channel impulse response result.

Taking a channel impulse response information as an example, normalize it according to the following formula:

CIR ^amp_norm = CIR ^amp /max(CIR ^amp ) Formula 4

In Equation 4, max(CIR ^amp ) represents the maximum amplitude value of the initial channel impulse response information, and CIR ^amp_n o ^rm represents the amplitude normalization result of the initial channel impulse response information.

In the embodiment of the present application, by dividing the amplitude of each initial channel impulse response information by the maximum amplitude value and performing normalization processing, it is possible to avoid instability of the channel impulse response information obtained at the same measurement position caused by hardware damage.

It should be known that, during the processing of the above initial channel impulse response information, the present application does not limit the processing sequence of the parameter normalization processing affected by delay and the parameter normalization processing affected by amplitude.

The normalized initial channel impulse response information contains noise, and when the normalized initial channel impulse response information is combined with other signal location algorithms, it will affect the accuracy of signal location. Based on this, the denoising processing steps of the normalized initial channel impulse response information will be described below through an embodiment.

In one embodiment, as shown in FIG. 10 , performing denoising processing on the normalized impulse response information of each channel includes:

S1002. Perform truncation processing on each initial channel impulse response information according to a preset number of sampling points, to obtain truncated channel impulse response information of each initial channel impulse response information.

After obtaining the impulse response information of each initial signal after normalization processing, in order to eliminate the noise part of the impulse response information of each channel, it is necessary to determine the number of sampling points of each initial signal impulse response signal according to the preset sampling points. Perform truncation to obtain truncated channel impulse response information. It should be noted that the value of the sampling point needs to be determined according to the actual use environment. The basic principle is to remove the noise sampling point to the greatest extent on the basis of retaining the signal.

Still taking a channel impulse response information as an example, if the preset number of sampling points is N _cut , then the truncated channel impulse response information CIR ^amp_norm_cut corresponding to the channel impulse response information is:

CIR ^amp_norm_cut ＝CIR ^amp_norm (1:N _cut ) Formula 5

CIR ^amp_norm in Formula 5 represents a normalized initial channel impulse response information.

S1004. Determine each truncated channel impulse response information as information after denoising processing of each initial channel impulse response information.

In the embodiment of the present application, the initial channel impulse response information is truncated according to the preset number of sampling points, which not only ensures the validity of each initial channel response information, but also eliminates the redundant data of each initial channel response information, effectively reducing the The amount of training data is reduced to prevent over-fitting when the impulse response data is combined with the deep network.

In one embodiment, as shown in FIG. 11 , an information processing method is provided, including:

S1101. Perform an inverse fast Fourier transform on the CSI to obtain a CIR. Time-domain transformation is performed on multiple channel state information of the target channel to obtain multiple initial channel impulse response information correspondingly,

S1102. Normalize the CIR delay. Obtain the amplitude of each initial channel impulse response information, and then determine the sampling point corresponding to the maximum amplitude value of each initial channel impulse response information according to the amplitude of each initial channel impulse response information, and finally according to the maximum amplitude value of each initial channel impulse response information. The sampling point corresponding to the maximum amplitude value of each initial channel impulse response information is cyclically shifted to the first sampling point, which is used to eliminate the time delay between each initial channel impulse response information.

S1103, CIR main diameter cyclic displacement. The main path rise information after the cyclic shift of each initial channel impulse response information is obtained, and according to the start sampling point and the end sampling point of the main path rise information, the main path rise information is cyclically shifted to before the maximum amplitude value.

S1104. Normalize the CIR amplitude. Determine the maximum amplitude value according to the amplitude of each initial channel impulse response information, and divide the amplitude of each channel impulse response information obtained in S1103 by the maximum amplitude value, so as to normalize the amplitude of each initial channel impulse response information.

S1105, truncation and denoising processing. According to the preset number of sampling points, the channel impulse response information obtained in S1104 is truncated to obtain the truncated channel impulse response information corresponding to each initial channel impulse response information, and each truncated channel impulse response information is determined as each initial channel impulse response information denoising processed information.

In the embodiment of the present application, firstly, time-domain transformation is performed on multiple channel state information of the target channel to obtain corresponding multiple initial channel impulse response information, and then the influence parameters of each initial channel impulse response information are normalized, and finally the The normalized initial channel impulse response information is subjected to denoising processing to obtain a plurality of target channel impulse response information. Wherein, the influence parameter represents a parameter that affects the stability of the channel state information. Since the signal processing method is to normalize the influencing parameters on the basis of obtaining the initial channel impulse response information, it is equivalent to eliminating multiple factors that affect the stability of the initial impulse response information when the present application processes the channel information. Furthermore, denoising the acquired initial channel pulse information after normalization processing can eliminate the redundant sampling due to noise in the initial channel pulse information on the basis of retaining the effective signal of the initial channel pulse information point. To sum up, the channel state information obtained by the information processing method of this application takes into account not only the unstable factors of the channel state information, but also the noise information that affects the efficiency of signal positioning, and performs normalization and denoising processing in turn for the above factors, In this way, stable and effective signal state information can be obtained, and the position information of the signal can be accurately determined.

The effectiveness of the information processing method provided by this application is described below: Taking the indoor NLOS recognition experiment based on the sub6G frequency band 5G system as an example, the neural network is used to judge whether the CIR information is correct. Figure 12 shows the CIR data under 1200 groups of Line of Sight (LOS) conditions collected at a fixed point and in a uniform time interval for 72 hours under the condition of constant environment, that is, the effective CIR information is 1200. It can be seen that both the CIR amplitude and the delay are offset due to hardware damage. After inputting the collected data into the neural network, the judgment results obtained are shown in Table 1, and Table 1 is the statistical table of the output results of the neural network based on the original CIR data.

Table 1

LOS CIR data volume 1200 Neural network judges the correct amount of CIR data 996

From Table 1, it can be seen that 996 sets of data are correctly judged by the network, and 204 sets of wrong data are judged. It can be seen that the instability of the original CIR data due to hardware damage will lead to extremely unstable network judgment results.

Fig. 13 is the CIR data obtained through the information processing method provided in this application. It can be seen that the CIR after information processing can effectively guarantee the stability of signal amplitude and time delay while retaining the original characteristics of the signal. After inputting the information-processed CIR into the neural network, the judgment results obtained are shown in Table 2. Table 2 is a statistical table of the output results of the neural network based on the information-processed CIR data.

Table 2

LOS CIR data volume 1200 Neural network judges the correct amount of CIR data 1200

It can be seen from Table 2 that all the data are judged to be correct. It can be seen that the proposed information processing method can effectively reduce the deviation of channel state information amplitude and delay caused by hardware damage, and obtain a relatively stable network input mode, thereby further ensuring the stability of network output.

With the in-depth study of machine learning theory, machine learning has been widely used in the field of high-precision positioning with its strong feature extraction ability and strong nonlinear fitting ability. Through the combination of channel state information and machine learning technology, it is possible to obtain Efficient and accurate location services. Based on this, an embodiment is used below to describe a signal location method combining an information processing method and machine learning.

In one embodiment, as shown in FIG. 14 , a signal location method is provided, including:

S1402. According to the received signal, acquire the initial channel state information of the transmission channel of the signal.

S1404. Use the information processing method in any embodiment of the information processing method to process the initial channel state information to obtain target channel state information.

Perform information processing on the acquired initial channel state information, the information processing method may be the information processing method in any of the above embodiments, and acquire target channel state information.

Optionally, the target channel state information may be time-domain information, that is, the truncated channel impulse response information obtained by any of the above information processing methods, or frequency domain information, that is, the truncated channel impulse response information is Fourier Channel state information obtained after transformation.

S1406. Input the target channel state information into the machine learning model to obtain a signal location result.

The target channel state information is input into the machine learning model, and the machine learning model predicts and outputs the corresponding positioning parameters by learning the input data, and uses the positioning parameters as the positioning result of the signal.

It should be known that the machine learning model corresponds to the application field. As shown in Figure 15, the signal processing method is used as a preprocessing method, and the preprocessed channel state information is input into the machine learning model, and the machine learning output and channel state The positioning parameter corresponding to the information may be an NLOS indication, may also be an AOA, or may be a terminal coordinate.

In the embodiment of the present application, according to the received signal, the initial channel state information of the transmission channel of the signal is obtained, and then the information processing method is used to process the channel state information to obtain the target channel state information, and finally the target channel state information is input into the machine learning In the model, the positioning result of the signal is obtained. It is equivalent to, when this application performs signal location, the channel state processing information used is obtained by the above information processing method, then when the channel state information is stable and effective, the corresponding machine learning input is also stable and effective, and the machine learning obtained The positioning result of the signal is also accurate.

It should be understood that although the steps in the flow charts involved in the above embodiments are shown sequentially as indicated by the arrows, these steps are not necessarily executed sequentially in the order indicated by the arrows. Unless otherwise specified herein, there is no strict order restriction on the execution of these steps, and these steps can be executed in other orders. Moreover, at least some of the steps in the flow charts involved in the above-mentioned embodiments may include multiple steps or stages, and these steps or stages are not necessarily executed at the same time, but may be performed at different times For execution, the execution order of these steps or stages is not necessarily performed sequentially, but may be executed in turn or alternately with other steps or at least a part of steps or stages in other steps.

Based on the same inventive concept, an embodiment of the present application further provides an information processing device for implementing the information processing method involved above. The solution to the problem provided by the device is similar to the implementation described in the above method, so for the specific limitations in one or more embodiments of the information processing device provided below, please refer to the definition of the information processing method above, I won't repeat them here.

In one embodiment, as shown in FIG. 16 , an information processing device 1600 is provided, including: a time domain transformation module 1620, a parameter processing module 1640, and a denoising processing module 1660, wherein:

A time-domain transformation module 1620, configured to perform time-domain transformation on multiple channel state information of the target channel, corresponding to obtain multiple initial channel impulse response information;

The parameter processing module 1640 is used to normalize the influencing parameters of each initial channel impulse response information; the influencing parameters represent parameters that affect the stability of the channel state information;

The denoising processing module 1660 is configured to perform denoising processing on the normalized initial channel impulse response information to obtain multiple target channel impulse response information.

In one embodiment, the parameter processing module 840 includes: a first acquisition unit, a first determination unit and a first displacement unit, wherein:

A first acquisition unit, configured to acquire the amplitude of each initial channel impulse response information;

The first determination unit is configured to determine the sampling point corresponding to the maximum amplitude value of each initial channel impulse response information according to the amplitude of each initial channel impulse response information;

The first displacement unit is used to cyclically shift the sampling points corresponding to the maximum amplitude values of each initial channel impulse response information to the first sampling point according to the sampling points corresponding to the maximum amplitude values of each initial channel impulse response information, so as to eliminate each Delay between initial channel impulse response messages.

In one embodiment, the information processing device 1600 further includes: a main diameter acquisition module and a main diameter displacement module, wherein:

The main path acquisition module is used to obtain the main path rise information of each initial channel impulse response information after the cyclic displacement;

The main diameter displacement module is used for cyclically shifting the main diameter ascending information to before the maximum amplitude value according to the start sampling point and the ending sampling point of the main diameter ascending information.

In one embodiment, the parameter processing module 1640 includes: a second determination unit and a first processing unit, wherein:

The second determination unit is configured to determine the maximum amplitude value according to the amplitude of each initial channel impulse response information;

The first processing unit is configured to divide the amplitude of each initial channel impulse response information by the maximum amplitude value, so as to perform normalization processing on the amplitude of each initial channel impulse response information.

In one embodiment, the denoising processing module 1660 includes: a second acquiring unit and a second processing unit, wherein:

The second acquisition unit is configured to truncate each initial channel impulse response information according to a preset number of sampling points to obtain truncated channel impulse response information of each initial channel impulse response information;

The second processing unit is configured to determine each truncated channel impulse response information as information after denoising processing of each initial channel impulse response information.

Each module in the above-mentioned signal processing device can be fully or partially realized by software, hardware and a combination thereof. The above-mentioned modules can be embedded in or independent of the processor in the computer device in the form of hardware, and can also be stored in the memory of the computer device in the form of software, so that the processor can invoke and execute the corresponding operations of the above-mentioned modules.

Based on the same inventive concept, an embodiment of the present application further provides a signal locating device for implementing the above-mentioned signal locating method. The solution to the problem provided by the device is similar to the implementation described in the above method, so the specific limitations in one or more embodiments of the signal locating device provided below can be referred to above for the definition of the signal locating method, I won't repeat them here.

In one embodiment, as shown in FIG. 17 , a signal locating device 1700 is provided, further comprising: an information acquisition module 1720, an information processing module 1740 and a result acquisition module 1760, wherein:

An information acquisition module 1720, configured to acquire initial channel state information of the transmission channel of the signal according to the received signal;

The information processing module 1740 is configured to use the information processing method in any embodiment of the information processing method to process the channel state information to obtain target channel state information;

The result obtaining module 1760 is configured to input the target channel state information into the machine learning model to obtain a signal positioning result.

Each module in the above-mentioned signal positioning device can be fully or partially realized by software, hardware and a combination thereof. The above-mentioned modules can be embedded in or independent of the processor in the computer device in the form of hardware, and can also be stored in the memory of the computer device in the form of software, so that the processor can invoke and execute the corresponding operations of the above-mentioned modules.

In one embodiment, a computer device is provided, including a memory and a processor, a computer program is stored in the memory, and the processor implements the following steps when executing the computer program:

performing time-domain transformation on multiple channel state information of the target channel, and correspondingly obtaining multiple initial channel impulse response information;

The influence parameters of each initial channel impulse response information are normalized; the influence parameters represent parameters that affect the stability of the channel state information;

Denoising is performed on the normalized initial channel impulse response information to obtain multiple target channel impulse response information.

In one embodiment, the following steps are also implemented when the processor executes the computer program:

Acquiring the amplitude of each initial channel impulse response information;

According to the amplitude of each initial channel impulse response information, determine the sampling point corresponding to the maximum amplitude value of each initial channel impulse response information;

According to the sampling point corresponding to the maximum amplitude value of each initial channel impulse response information, the sampling point corresponding to the maximum amplitude value of each initial channel impulse response information is cyclically shifted to the first sampling point, which is used to eliminate the gap between each initial channel impulse response information delay.

In one embodiment, the following steps are also implemented when the processor executes the computer program:

Obtain the main path rise information of each initial channel impulse response information after the cyclic displacement;

According to the start sampling point and the end sampling point of the main path rising information, the main path rising information is cyclically shifted to before the maximum amplitude value.

In one embodiment, the following steps are also implemented when the processor executes the computer program:

Determine the maximum amplitude value according to the amplitude of each initial channel impulse response information;

The amplitude of each initial channel impulse response information is divided by the maximum amplitude value, so as to perform normalization processing on the amplitude of each initial channel impulse response information.

In one embodiment, the following steps are also implemented when the processor executes the computer program:

performing truncation processing on each initial channel impulse response information according to the preset number of sampling points to obtain truncated channel impulse response information of each initial channel impulse response information;

Each truncated channel impulse response information is determined as information after denoising processing of each initial channel impulse response information.

In one embodiment, the following steps are also implemented when the processor executes the computer program:

Obtain initial channel state information of a transmission channel of the signal according to the received signal;

Using the information processing method of any embodiment of the information processing method to process the initial channel state information to obtain the target channel state information;

Input the target channel state information into the machine learning model to obtain the signal location result.

In one embodiment, a computer-readable storage medium is provided, on which a computer program is stored, and when the computer program is executed by a processor, the following steps are implemented:

performing time-domain transformation on multiple channel state information of the target channel, and correspondingly obtaining multiple initial channel impulse response information;

The influence parameters of each initial channel impulse response information are normalized; the influence parameters represent parameters that affect the stability of the channel state information;

Denoising is performed on the normalized initial channel impulse response information to obtain multiple target channel impulse response information.

In one embodiment, when the computer program is executed by the processor, the following steps are also implemented:

Acquiring the amplitude of each initial channel impulse response information;

According to the amplitude of each initial channel impulse response information, determine the sampling point corresponding to the maximum amplitude value of each initial channel impulse response information;

According to the sampling point corresponding to the maximum amplitude value of each initial channel impulse response information, the sampling point corresponding to the maximum amplitude value of each initial channel impulse response information is cyclically shifted to the first sampling point, which is used to eliminate the gap between each initial channel impulse response information delay.

In one embodiment, when the computer program is executed by the processor, the following steps are also implemented:

Obtain the main path rise information of each initial channel impulse response information after the cyclic displacement;

According to the start sampling point and the end sampling point of the main path rising information, the main path rising information is cyclically shifted to before the maximum amplitude value.

In one embodiment, when the computer program is executed by the processor, the following steps are also implemented:

Determine the maximum amplitude value according to the amplitude of each initial channel impulse response information;

The amplitude of each initial channel impulse response information is divided by the maximum amplitude value, so as to perform normalization processing on the amplitude of each initial channel impulse response information.

In one embodiment, when the computer program is executed by the processor, the following steps are also implemented:

performing truncation processing on each initial channel impulse response information according to the preset number of sampling points to obtain truncated channel impulse response information of each initial channel impulse response information;

Each truncated channel impulse response information is determined as information after denoising processing of each initial channel impulse response information.

In one embodiment, when the computer program is executed by the processor, the following steps are also implemented:

Obtain initial channel state information of a transmission channel of the signal according to the received signal;

Using the information processing method of any embodiment of the information processing method to process the initial channel state information to obtain the target channel state information;

Input the target channel state information into the machine learning model to obtain the signal location result.

In one embodiment, a computer program product is provided, comprising a computer program, which, when executed by a processor, implements the following steps:

performing time-domain transformation on multiple channel state information of the target channel, and correspondingly obtaining multiple initial channel impulse response information;

The influence parameters of each initial channel impulse response information are normalized; the influence parameters represent parameters that affect the stability of the channel state information;

Denoising is performed on the normalized initial channel impulse response information to obtain multiple target channel impulse response information.

In one embodiment, when the computer program is executed by the processor, the following steps are also implemented:

Acquiring the amplitude of each initial channel impulse response information;

According to the amplitude of each initial channel impulse response information, determine the sampling point corresponding to the maximum amplitude value of each initial channel impulse response information;

According to the sampling point corresponding to the maximum amplitude value of each initial channel impulse response information, the sampling point corresponding to the maximum amplitude value of each initial channel impulse response information is cyclically shifted to the first sampling point, which is used to eliminate the gap between each initial channel impulse response information delay.

In one embodiment, when the computer program is executed by the processor, the following steps are also implemented:

Obtain the main path rise information of each initial channel impulse response information after the cyclic displacement;

According to the start sampling point and the end sampling point of the main path rising information, the main path rising information is cyclically shifted to before the maximum amplitude value.

In one embodiment, when the computer program is executed by the processor, the following steps are also implemented:

Determine the maximum amplitude value according to the amplitude of each initial channel impulse response information;

The amplitude of each initial channel impulse response information is divided by the maximum amplitude value, so as to perform normalization processing on the amplitude of each initial channel impulse response information.

In one embodiment, when the computer program is executed by the processor, the following steps are also implemented:

performing truncation processing on each initial channel impulse response information according to the preset number of sampling points to obtain truncated channel impulse response information of each initial channel impulse response information;

Each truncated channel impulse response information is determined as information after denoising processing of each initial channel impulse response information.

In one embodiment, when the computer program is executed by the processor, the following steps are also implemented:

Obtain initial channel state information of a transmission channel of the signal according to the received signal;

Using the information processing method of any embodiment of the information processing method to process the initial channel state information to obtain the target channel state information;

Input the target channel state information into the machine learning model to obtain the signal location result.

Those of ordinary skill in the art can understand that all or part of the processes in the methods of the above embodiments can be implemented through computer programs to instruct related hardware, and the computer programs can be stored in a non-volatile computer-readable memory In the medium, when the computer program is executed, it may include the processes of the embodiments of the above-mentioned methods. Wherein, any reference to storage, database or other media used in the various embodiments provided in the present application may include at least one of non-volatile and volatile storage. Non-volatile memory can include read-only memory (Read-Only Memory, ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive variable memory (ReRAM), magnetic variable memory (Magnetoresistive Random Access Memory, MRAM), Ferroelectric Random Access Memory (FRAM), Phase Change Memory (Phase Change Memory, PCM), graphene memory, etc. The volatile memory may include random access memory (Random Access Memory, RAM) or external cache memory, etc. By way of illustration and not limitation, RAM can be in various forms such as Static Random Access Memory (SRAM) or Dynamic Random Access Memory (DRAM). The databases involved in the various embodiments provided in this application may include at least one of a relational database and a non-relational database. The non-relational database may include a blockchain-based distributed database, etc., but is not limited thereto. The processors involved in the various embodiments provided by this application can be general-purpose processors, central processing units, graphics processors, digital signal processors, programmable logic devices, data processing logic devices based on quantum computing, etc., and are not limited to this.

The technical features of the above embodiments can be combined arbitrarily. To make the description concise, all possible combinations of the technical features in the above embodiments are not described. However, as long as there is no contradiction in the combination of these technical features, they should be It is considered to be within the range described in this specification.

The above-mentioned embodiments only express several implementation modes of the present application, and the description thereof is relatively specific and detailed, but should not be construed as limiting the patent scope of the present application. It should be noted that those skilled in the art can make several modifications and improvements without departing from the concept of the present application, and these all belong to the protection scope of the present application. Therefore, the protection scope of the present application should be determined by the appended claims.

Claims (10)

1. An information processing method, characterized in that the method comprises: performing time-domain transformation on multiple channel state information of the target channel, and correspondingly obtaining multiple initial channel impulse response information; Perform normalization processing on the influence parameters of each of the initial channel impulse response information; the influence parameters represent parameters that affect the stability of the channel state information; Denoising processing is performed on each of the normalized initial channel impulse response information to obtain a plurality of target channel impulse response information. 2. The method according to claim 1, wherein the influencing parameters include time delay, and the normalizing the influencing parameters of each of the initial channel impulse response information includes: Acquiring the magnitude of each initial channel impulse response information; Determine the sampling point corresponding to the maximum amplitude value of each initial channel impulse response information according to the magnitude of each initial channel impulse response information; According to the sampling points corresponding to the maximum amplitude values of each of the initial channel impulse response information, the sampling points corresponding to the maximum amplitude values of each of the initial channel impulse response information are cyclically shifted to the first sampling point, so as to eliminate each of the initial channel impulse response information. The delay between channel impulse response messages. 3. The method according to claim 2, wherein, before said sampling point cyclically shifted to the first sampling point corresponding to each said initial channel impulse response information maximum amplitude value, said method also includes: Obtain the main path rise information of each of the initial channel impulse response information after the cyclic displacement; According to the start sampling point and the end sampling point of the main path rising information, the main path rising information is cyclically shifted to before the maximum amplitude value. 4. according to the method described in any one of claim 1-3, it is characterized in that, described influence parameter comprises amplitude, described each described influence parameter of initial channel impulse response information is carried out normalization process, comprises: determining a maximum amplitude value according to the amplitude of each initial channel impulse response information; Divide the amplitude of each of the initial channel impulse response information by the maximum amplitude value, so as to perform normalization processing on the amplitude of each of the initial channel impulse response information. 5. The method according to any one of claims 1-3, wherein the denoising processing of each of the initial channel impulse response information after normalization processing includes: performing truncation processing on each of the initial channel impulse response information according to a preset number of sampling points, to obtain truncated channel impulse response information of each of the initial channel impulse response information; Each of the truncated channel impulse response information is determined as information after denoising processing of each of the initial channel impulse response information. 6. A signal location method, characterized in that said method comprises: Acquiring initial channel state information of a transmission channel of the signal according to the received signal; Process the initial channel state information by using the information processing method described in any one of claims 1-5 to obtain target channel state information; The target channel state information is input into a machine learning model to obtain a positioning result of the signal. 7. An information processing device, characterized in that the device comprises: A time-domain transform module, configured to perform time-domain transform on a plurality of channel state information of the target channel, corresponding to obtain a plurality of initial channel impulse response information; A parameter processing module, configured to normalize the influencing parameters of each of the initial channel impulse response information; the influencing parameters represent parameters affecting the stability of the channel state information; The denoising processing module is configured to perform denoising processing on each of the normalized initial channel impulse response information to obtain a plurality of target channel impulse response information. 8. A signal location device, characterized in that said device comprises: An information acquisition module, configured to acquire initial channel state information of the transmission channel of the signal according to the received signal; An information processing module, configured to process the initial channel state information by using the information processing method described in any one of claims 1-5 to obtain target channel state information; The result acquisition module is configured to input the target channel state information into the machine learning model to obtain the positioning result of the signal. 9. A computer device, comprising a memory and a processor, the memory stores a computer program, wherein the processor implements the information processing method of claims 1-5 and the information processing method of claim 6 when executing the computer program The steps of any one of the signal location methods. 10. A computer-readable storage medium, on which a computer program is stored, characterized in that, when the computer program is executed by a processor, any of the information processing method of claims 1-5 and the signal location method of claim 6 is implemented. A step of the described method.

Images