CN116016225A

CN116016225A - Information processing method, signal positioning method, device, equipment and medium

Info

Publication number: CN116016225A
Application number: CN202211702952.9A
Authority: CN
Inventors: 李雨晴; 刘鹏; 齐望东; 尤肖虎; 黄永明; 刘升恒
Original assignee: Network Communication and Security Zijinshan Laboratory
Current assignee: Network Communication and Security Zijinshan Laboratory
Priority date: 2022-12-29
Filing date: 2022-12-29
Publication date: 2023-04-25
Also published as: WO2024140593A1

Abstract

The application relates to an information processing method, a signal positioning method, a device, equipment and a medium. The method comprises the following steps: firstly, performing time domain transformation on a plurality of channel state information of a target channel to correspondingly obtain a plurality of initial channel impulse response information, then performing normalization processing on influence parameters of the initial channel impulse response information, and finally performing denoising processing on the initial channel impulse response information after the normalization processing to obtain a plurality of target channel impulse response information. Wherein the influencing parameter represents a parameter influencing the stability of the channel state information. By adopting the method, stable and effective signal state information is obtained, and the position information of the signal can be accurately determined.

Description

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

Technical Field

The present disclosure relates to the field of signal positioning technologies, and in particular, to an information processing method, a signal positioning method, an apparatus, a device, and a medium.

Background

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

In the related art, CSI data features are learned according to a machine learning model by combining CSI with a machine learning algorithm to predict a position of a signal. However, in the related art, when signal position prediction is performed, stable CSI information cannot be obtained, and thus the position information of the signal cannot be accurately determined.

Disclosure of Invention

In view of the foregoing, it is desirable to provide an information processing method, a signal positioning method, a device, an apparatus, and a medium, which can acquire stable channel state information, and further accurately determine position information of a signal.

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

performing time domain transformation on a plurality of channel state information of a target channel to correspondingly obtain a plurality of initial channel impulse response information;

normalizing the influence parameters of the impulse response information of each initial channel; the influencing parameter represents a parameter influencing the stability of the channel state information;

denoising the initial channel impulse response information after normalization processing to obtain a plurality of target channel impulse response information.

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

Acquiring the amplitude of impulse response information of each initial channel;

determining sampling points corresponding to maximum amplitude values of the initial channel impulse response information according to the amplitude of the initial channel impulse response information;

and circularly shifting the sampling point corresponding to the maximum amplitude value of each initial channel impulse response information to the first sampling point according to the sampling point corresponding to the maximum amplitude value of each initial channel impulse response information, so as to eliminate the time delay between the initial channel impulse response information.

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

acquiring main path rising information of each initial channel impulse response information after cyclic displacement;

and circularly shifting the main path rising information to the front of the maximum amplitude value according to the starting sampling point and the ending sampling point of the main path rising information.

In one embodiment, the influencing parameter includes amplitude, and normalizing the influencing parameter of each initial channel impulse response information includes:

determining a maximum amplitude value according to the amplitude of each initial channel impulse response message;

the amplitude of each initial channel impulse response information is divided by the maximum amplitude value to normalize the amplitude of each initial channel impulse response information.

In one embodiment, denoising each initial channel impulse response information after normalization processing includes:

according to the preset sampling points, carrying out truncation processing on each initial channel impulse response message to obtain truncated channel impulse response messages of each initial channel impulse response message;

and determining the impulse response information of each truncated channel as the information after denoising processing of the impulse response information of each initial channel.

In a second aspect, the present application further provides a signal positioning method, including:

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

processing the initial channel state information by adopting the information processing method of any embodiment of the first aspect to obtain target channel state information;

and inputting the target channel state information into a machine learning model to obtain a positioning result of the signal.

In a third aspect, the present application also provides an information processing apparatus, including:

the time domain transformation module is used for performing time domain transformation on the multiple channel state information of the target channel to correspondingly obtain multiple initial channel impulse response information;

the parameter processing module is used for carrying out normalization processing on the influence parameters of the impulse response information of each initial channel; the influencing parameter represents a parameter influencing the stability of the channel state information;

The denoising processing module is used for denoising the normalized initial channel impulse response information to obtain a plurality of target channel impulse response information.

In a fourth aspect, the present application also provides a signal positioning device, including:

the information acquisition module is used for acquiring initial channel state information of a 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 according to any one of the embodiments of the first aspect, to obtain target channel state information;

and the result acquisition module is used for inputting the target channel state information into the machine learning model to obtain a positioning result of the signal.

In a fifth aspect, the present application also provides a computer device. The computer device comprises a memory storing a computer program and a processor implementing the steps of the method in any one of the embodiments of the first and second aspects described above when the computer program is executed.

In a sixth aspect, the present application also provides a computer-readable storage medium. The computer readable storage medium having stored thereon a computer program which, when executed by a processor, implements the steps of the method in any of the embodiments of the first and second aspects described above.

In a seventh aspect, the present application also provides a computer program product. The computer program product comprising a computer program which, when executed by a processor, implements the steps of the method in any of the embodiments of the first and second aspects described above.

In the information processing method, time domain transformation is firstly carried out on a plurality of channel state information of a target channel to correspondingly obtain a plurality of initial channel impulse response information, then normalization processing is carried out on influencing parameters of the initial channel impulse response information, and finally denoising processing is carried out on the initial channel impulse response information after normalization processing to obtain a plurality of target channel impulse response information. Wherein the influencing parameter represents a parameter influencing the stability of the channel state information. The signal processing method is characterized in that normalization processing is carried out on the influence parameters on the basis of acquiring the initial channel impulse response information, which is equivalent to the fact that a plurality of factors influencing the stability of the initial impulse response information are eliminated when the channel information is processed, and further, denoising processing is carried out on the acquired initial channel impulse information after normalization processing, so that redundant sampling points generated due to noise in the initial channel impulse information can be eliminated on the basis of keeping the effective signal of the initial channel impulse information. In summary, the channel state information acquired by the information processing method considers not only the unstable factor of the channel state information, but also the noise point information influencing the signal positioning efficiency, and performs normalization and denoising processing sequentially aiming at the factors, so that stable and effective signal state information is acquired, and the position information of the signal can be accurately determined.

Drawings

FIG. 1 is an internal block diagram of a computer device in one embodiment;

FIG. 2 is a flow chart of a method of processing information in one embodiment;

FIG. 3 is a flow chart of a delay normalization process step in one embodiment;

FIG. 4 is a schematic diagram of the channel impulse response information in one embodiment;

FIG. 5 is a schematic diagram of the displacement of the channel impulse response information in one embodiment;

FIG. 6 is a flowchart illustrating a delay normalization process step in another embodiment;

FIG. 7 is a diagram illustrating the primary path rise of the channel impulse response information in one embodiment;

FIG. 8 is a schematic diagram of the primary path shift of the channel impulse response information in one embodiment;

FIG. 9 is a flow chart of the steps of the amplitude normalization process in one embodiment;

FIG. 10 is a flow diagram of a channel impulse response information denoising process in one embodiment;

FIG. 11 is a flow chart of a method of processing information according to another embodiment;

FIG. 12 is a diagram of information collected from channel impulse response information in one embodiment;

FIG. 13 is a diagram of processing information of channel impulse response information in one embodiment;

FIG. 14 is a flow chart of a channel locating method in one embodiment;

FIG. 15 is a flow chart of a channel locating method according to another embodiment;

FIG. 16 is a block diagram showing the structure of an information processing apparatus in one embodiment;

fig. 17 is a block diagram of a signal positioning device in one embodiment.

Detailed Description

In order to make the objects, technical solutions and advantages of the present application more apparent, the present application will be further described in detail with reference to the accompanying drawings and examples. It should be understood that the specific embodiments described herein are for purposes of illustration only and are not intended to limit the present application.

The information processing method and the signal positioning method provided by the embodiment of the application can 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 means. The processor, the memory and the input/output interface are connected through a 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 configured to provide computing 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 a computer program. The internal memory provides an environment for the operation of the operating system and computer programs in the non-volatile storage media. The input/output interface of the computer device is used to exchange information between the processor and the external device. The communication interface of the computer device is used for carrying out wired or wireless communication with an external terminal, and the wireless mode can be realized through WIFI, a mobile cellular network, NFC (near field communication) or other technologies. The computer program is executed by a processor to implement a signal processing method and a signal positioning method. The display unit of the computer device is used for forming a visual picture, and can be a display screen, a projection device or a virtual reality imaging device. The display screen can be a liquid crystal display screen or an electronic ink display screen, and the input device of the computer equipment can be a touch layer covered on the display screen, can also be a key, a track ball or a touch pad arranged on the shell of the computer equipment, and can also be an external keyboard, a touch pad or a mouse and the like.

The high-precision location service is a key support service of the emerging industries such as the industrial Internet, the Internet of things, the Internet of vehicles and the like, and in the future, mass intelligent networking terminals such as industrial robots, unmanned vehicles, intelligent sensors and the like need to provide accurate, real-time and reliable location services. In the field of high-precision location services, a technique of precisely positioning a terminal using a wireless communication signal has become a research hot spot in recent years. However, there are still some problems in this field that are difficult to be effectively solved by conventional signal processing methods, such as Non-Line of Sight (NLOS) recognition, position estimation under NLOS conditions, angle-of-Arrival (AoA) estimation under strong multipath environments, and the like.

To solve the above problems, the related art combines wireless communication signals (such as channel state information (Channel State Information, CSI)) with artificial intelligence fields (such as machine learning), and utilizes the feature extraction capability and nonlinear fitting capability of the machine learning to obtain efficient and accurate location services. However, measurement errors, i.e., hardware damage, introduced by non-ideal characteristics of hardware devices may cause significant differences between CSI measured multiple times at the same location, and this mode instability may cause unstable output results of machine learning, thereby causing low positioning accuracy, poor generalization performance, and the like.

Currently, there are two main types of methods for CSI processing in a positioning technology based on a combination of CSI and machine learning. One is to directly input the original CSI into the machine learning depth network for training without considering the influence of the instability of the CSI on the output of the machine learning depth network. Obviously, because hardware damage is difficult to avoid, large difference exists between the CSI measured for many times at the same position in amplitude and phase, and direct input of the original CSI leads to unstable output results of a machine learning depth network, so that positioning accuracy is reduced, and generalization performance is poor. Another type of method is to normalize the CSI amplitude, normalize the amplitude of the channel impulse response information (Channel Impulse Response, CIR) obtained from the CSI processing based on the total energy of the signal, so as to avoid the influence of occasional occurrence of a very large signal on the machine learning depth network output. However, CSI instability caused by hardware loss is reflected in both amplitude and phase, and only the amplitude is preprocessed, CSI phase instability cannot be completely eliminated, so that network output accuracy is reduced.

Based on the above, the application provides an information processing method, a signal positioning method, a device, equipment and a medium, which are used for obtaining a plurality of initial channel impulse response information through performing time domain transformation on a plurality of channel state information of a target channel, then performing normalization processing on influencing parameters of each initial channel impulse response information to obtain stable CIR information, and performing denoising processing on each initial channel impulse response information after normalization processing to obtain a plurality of stable and effective target channel impulse response information. The processed target channel state information is used for training in a machine learning model, and the stability and the effectiveness of the target channel state information enable the network training speed to be improved, so that the method has good robustness.

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

s202, performing time domain transformation on a plurality of channel state information of a target channel to correspondingly obtain a plurality of initial channel impulse response information.

The channel state information is the channel properties of the communication link and describes the attenuation factors of the signal on each transmission path, such as signal Scattering (Scattering), environmental attenuation (fading, multipath fading or shadowing fading), distance attenuation (power decay of distance), etc. The channel state information can adapt the communication system to the current channel condition, and guarantees are provided for high-reliability and high-speed communication in the multi-antenna system.

The target channel contains a plurality of channel state information, and the plurality of channel state information is characterized by a function of frequency, in order to facilitate processing of each channel state information, each channel state information is subjected to inverse fast fourier transform (Inverse Fast Fourier Transform, IFFT) respectively, and each channel state information is converted from a frequency domain signal to a time domain signal, that is, each channel state information corresponds to each initial channel impulse response information respectively. It should be noted that, both the channel state information and the channel impulse response information are a representation form of the channel signal information, and the information provided by both are the same.

S204, normalizing the influence parameters of the impulse response information of each initial channel; the influencing parameter means a parameter influencing stability of channel state information.

Due to non-ideal characteristics of hardware devices, such as loss of a receiving source, measurement errors, i.e., hardware damage, are introduced in the process of obtaining channel state information. The hardware damage can cause the difference between the channel state information measured for a plurality of times at the same position, which is reflected by the unstable channel state information measured for a plurality of times. Then, after the initial channel impulse response information corresponding to the channel state information is obtained, taking factors influencing the instability of the channel state information into consideration, obtaining influence parameters of the initial channel impulse response information, and carrying out normalization processing on the influence parameters of the initial channel impulse response information to eliminate the influence of the instability factors, thereby obtaining stable channel impulse response information.

S206, denoising the initial channel impulse response information after normalization processing to obtain a plurality of target channel impulse response information.

After normalization processing is carried out on each initial channel impulse response information, the influence of unstable factors is eliminated, and then signal positioning is carried out according to the acquired normalization processed initial channel impulse response information and by combining algorithms such as machine learning. In the signal positioning process, since each initial channel impulse response sequence is random noise, it means that the input data of signal positioning can not effectively represent channel state information, which can result in the reduction of the accuracy of the signal positioning result, and the random noise is embodied as a plurality of redundant sampling points, which can prolong the signal positioning process. That is, noise of the normalized initial channel impulse response information affects the efficiency of signal localization. Therefore, it is necessary to further process each initial channel impulse response information after normalization processing, and to cancel noise of the initial channel impulse response information.

According to the method, time domain transformation is firstly carried out on a plurality of pieces of channel state information of a target channel, a plurality of pieces of initial channel impulse response information are correspondingly obtained, then normalization processing is carried out on influence parameters of the initial channel impulse response information, and finally denoising processing is carried out on the initial channel impulse response information after normalization processing, so that a plurality of pieces of target channel impulse response information are obtained. Wherein the influencing parameter represents a parameter influencing the stability of the channel state information. The signal processing method is characterized in that normalization processing is carried out on the influence parameters on the basis of acquiring the initial channel impulse response information, which is equivalent to the fact that a plurality of factors influencing the stability of the initial impulse response information are eliminated when the channel information is processed, and further, denoising processing is carried out on the acquired initial channel impulse information after normalization processing, so that redundant sampling points generated due to noise in the initial channel impulse information can be eliminated on the basis of keeping the effective signal of the initial channel impulse information. In summary, the channel state information acquired by the information processing method considers not only the unstable factor of the channel state information, but also the noise point information influencing the signal positioning efficiency, and performs normalization and denoising processing sequentially aiming at the factors, so that stable and effective signal state information is acquired, and the position information of the signal can be accurately determined.

When the normalization processing is performed on the influence parameters of each initial channel impulse response information, a plurality of parameters which influence the stability of the channel state information, such as the influence parameters of time delay instability, amplitude instability and the like, need to be considered so as to obtain stable channel impulse response information. Based on this, the following describes the normalization processing step of the initial channel impulse response information with respect to the instability of the delay by an embodiment.

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

s302, the amplitude of each initial channel impulse response information is acquired.

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, each initial channel impulse response information corresponds to a set of amplitudes, and the number of amplitudes of each initial channel impulse response information is identical to the corresponding number of sampling points.

S304, according to the amplitude of each initial channel impulse response information, determining the sampling point corresponding to the maximum amplitude value of each initial channel impulse response information.

And selecting the maximum amplitude from the amplitudes corresponding to the plurality of sampling points of the initial channel impulse response information, and determining 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 sampling point n corresponding to the maximum amplitude value is determined _max Characterized by the following expression:

n _max ＝argmax(CIR ^amp ) 1 (1)

CIR in 1 ^amp Representing initial channel impulse response information, argmax (·) represents taking the CIR ^amp Sampling point positions corresponding to the maximum amplitude values.

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, where the horizontal axis represents sampling points and the vertical axis represents the amplitude of the initial channel impulse response information. As can be seen from fig. 4, the amplitude of the initial channel impulse response information corresponding to the dotted line is the maximum amplitude value CIR ^amp Intersection point n of broken line and horizontal axis _max The sampling point corresponding to the maximum amplitude value of the initial channel impulse response information is obtained.

S306, according to the sampling point corresponding to the maximum amplitude value of each initial channel impulse response information, circularly shifting the sampling point corresponding to the maximum amplitude value of each initial channel impulse response information to the first sampling point for eliminating time delay between the initial channel impulse response information.

And taking the sampling point corresponding to the maximum amplitude value of each initial channel impulse response information as a displacement, circularly displacing the waveform of each initial channel impulse response information by taking one sampling point as a unit, and after the cyclic displacement, moving the sampling point corresponding to the maximum amplitude value of each initial channel impulse response information to the first sampling point. The above cyclic shift operation can be expressed as:

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

Cirshift (x (n), n) in formula 2 ₀ ) Representing a cyclic right shift of the sequence x (n) by n ₀ A point.

Taking the channel impulse response information shown in fig. 4 as an example, taking one sample point as a unit, if the initial channel impulse response information is cyclically shifted to the first sample point, it is necessary to shift-n _max +1 units, the corresponding displacement process is shown in fig. 5. In fig. 5, S1 is initial channel impulse response information, S2 is channel impulse response information shifted by one unit from the initial channel impulse response information, and S3 is an initial channelImpulse response information displacement n _max Channel impulse response information of a unit.

In the embodiment of the application, the amplitude of each initial channel impulse response message is obtained, the sampling point corresponding to the maximum amplitude of each initial channel impulse response message is determined according to the maximum amplitude of each initial channel impulse response message, and the whole of each initial channel impulse response message is shifted according to the sampling point of each initial channel impulse response message until the sampling point corresponding to the maximum amplitude of each initial channel impulse response message is shifted to the first sampling point, which is equivalent to unifying the maximum amplitude of each initial channel impulse message to one sampling point, so as to achieve the purpose of eliminating delay jitter among the initial channel impulse messages.

The above embodiment needs to keep the complete information of each initial channel impulse response in the cyclic shift process of each initial channel impulse response information. And in the cyclic shift process, the main path information of the impulse response information of each initial channel is lost. Based on this, the main path information compensation step of the information processing method will be described below by way of one embodiment.

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

s602, acquiring main path rising information of each initial channel impulse response information after cyclic shift.

The main path of each initial channel impulse response information refers to a continuous channel impulse response information segment including the maximum amplitude of each initial channel impulse response information. And determining main path rising information of each channel impulse response information according to the amplitude of the initial each channel impulse response information, wherein the main path rising information comprises main path rising time, a starting sampling point, an ending sampling point and the like of the main path rising information.

The main path rising time is that firstly, the maximum amplitude value of each channel impulse response information is obtained according to the amplitude of each initial channel impulse response information, then the amplitude of each initial channel impulse response information is compared with the corresponding maximum amplitude value, the starting time and the ending time of the main path rising are determined according to the comparison result, and finally, the difference result between the ending time and the starting time of the main path rising is used as the main path rising time.

Exemplary if the amplitude of the initial channel impulse response information is expressed as CIR ^amp (n), n represents the sampling point, and the maximum amplitude value is represented as max (CIR ^amp (n)), the main path rise time n of the channel impulse response information _rise As shown in fig. 7, the corresponding expression is:

in formula 3, max (. Cndot.) represents a maximum value taking operation, n _start Indicating the starting time of lifting the main path, n _stop Indicating the main diameter rise end time.

S604, circularly shifting the main path rising information to the front of the maximum amplitude value according to the initial sampling point and the end sampling point of the main path rising information.

In the main path rising information, a sampling point corresponding to the main path rising start time is determined as a starting sampling point, a sampling point corresponding to the main path ending time is determined as an ending sampling point, then the displacement of the initial channel impulse response information is determined according to the starting sampling point and the ending sampling point, and then the main path rising information is circularly displaced to the position before the maximum amplitude value by taking one sampling point as a unit.

As shown in fig. 8, the initial channel impulse response information in fig. 5 is shifted by n _max Channel impulse response information S3 of one unit is taken as an original waveform, S4 represents a waveform of which the original waveform is shifted by one unit, and S5 represents an original waveform shift n _rise Waveforms of units. As can be seen from fig. 8, the original waveform S3 loses the coherence information, when the displacement n _rise After a unit, the complete main path information can be displayed. The process of cyclic shift from S3 to S5 can be expressed as: CIR (common information and Rate) ^amp ＝cirshift(CIR ^amp ,n _rise )。

According to the method and the device, the initial channel impulse response information is circularly shifted through the main path ascending information of the initial channel impulse response information, so that the initial channel impulse response information can be completely reserved and the corresponding main path information is displayed.

When the normalization processing is performed on the influence parameters of each initial channel impulse response information, a plurality of parameters which influence the stability of the channel state information, such as the influence parameters of time delay instability, amplitude instability and the like, need to be considered so as to obtain stable channel impulse response information. The above embodiment eliminates the instability of the delay through delay normalization, and the following describes the normalization processing steps of the initial channel impulse response information with respect to the instability of the amplitude through one embodiment.

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

s902, determining 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, obtaining the maximum amplitude value of each initial channel impulse response information, and marking the maximum amplitude value as CIR ^amp =abs (CIR), where abs (·) represents the maximum magnitude operation.

S904, dividing the amplitude of each initial channel impulse response information by the maximum amplitude value so as to normalize the amplitude of each initial channel impulse response information.

After the amplitude of each initial channel impulse response information and the maximum amplitude value of each initial channel impulse response information are obtained, dividing the amplitude of each initial channel impulse response information by the maximum amplitude value to obtain the amplitude normalization processing result of each initial channel impulse response.

Taking a channel impulse response information as an example, normalization is performed according to the following formula:

CIR ^amp_norm ＝CIR ^amp /max(CIR ^amp ) 4. The method is to

Max (CIR) in 4 ^amp ) Maximum amplitude value representing initial channel impulse response information, CIR ^amp_n o ^rm Representing an initial channelAmplitude normalization of the impulse response information.

In the embodiment of the application, the amplitude of each initial channel impulse response information divided by the maximum amplitude value is normalized, so that the unstable channel impulse response information obtained at the same measurement position due to hardware damage can be avoided.

It should be noted that, in the processing procedure of the above-mentioned initial channel impulse response information, the processing order of the parameter normalization processing of the delay effect and the parameter normalization processing of the amplitude effect in the present application is not limited.

The normalized initial channel impulse response information contains noise, and when the normalized initial channel impulse response information is combined with other signal positioning algorithms, the signal positioning accuracy is affected. Based on this, the denoising processing step of the initial channel impulse response information after normalization processing is described below by way of one embodiment.

In one embodiment, as shown in fig. 10, denoising the normalized channel impulse response information includes:

s1002, cutting off the impulse response information of each initial channel according to the preset sampling points to obtain the cut-off impulse response information of each initial channel.

After the initial signal impulse response information after normalization processing is obtained, in order to eliminate the noise part of the channel impulse response information, the number of sampling points of the initial signal impulse response signals is determined according to preset sampling points, the signal impulse response information is truncated, and truncated channel impulse response information is obtained. It should be noted that, the value of the sampling point needs to be determined according to the actual use environment, and the basic principle is to remove the noise sampling point to the maximum extent on the basis of the reserved signal.

Taking a channel impulse response information as an example, if the preset sampling point number is N _cut Truncated channel impulse response information CIR corresponding to the channel impulse response information ^amp_norm_cut The method comprises the following steps:

CIR ^amp_norm_cut ＝CIR ^amp_norm (1:N _cut ) 5. The method is to

CIR in 5 ^amp_norm Representing an initial channel impulse response information after normalization.

S1004, determining each piece of truncated channel impulse response information as information after denoising processing of each piece of initial channel impulse response information.

In the embodiment of the application, the impulse response information of each initial channel is truncated according to the preset sampling points, so that the validity of the impulse response information of each initial channel is guaranteed, redundant data of the response information of each initial channel is eliminated, the data quantity of training data is effectively reduced, and the phenomenon of fitting is prevented when the impulse response data are combined with a deep network.

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

s1101, performing inverse fast Fourier transform on the CSI to obtain the CIR. Performing time domain transformation on the multiple channel state information of the target channel to correspondingly obtain multiple initial channel impulse response information,

s1102, CIR time delay normalization. And finally, circularly shifting the sampling point corresponding to the maximum amplitude value of each initial channel impulse response information to the first sampling point according to the sampling point corresponding to the maximum amplitude value of each initial channel impulse response information, so as to eliminate time delay among the initial channel impulse response information.

S1103, cyclic displacement of the CIR main path. And acquiring main path rising information of each initial channel impulse response information after cyclic displacement, and cyclically displacing the main path rising information to the front of the maximum amplitude value according to the initial sampling point and the end sampling point of the main path rising information.

S1104, CIR amplitude normalization. And determining a maximum amplitude value according to the amplitude of each initial channel impulse response information, dividing the amplitude of each channel impulse response information obtained in the step S1103 by the maximum amplitude value, and carrying out normalization processing on the amplitude of each initial channel impulse response information.

S1105, cutting off denoising processing. And (3) carrying out truncation processing on the channel impulse response information acquired in the step (1104) according to the preset sampling points to obtain truncated channel impulse response information corresponding to each piece of initial channel impulse response information, and determining each piece of truncated channel impulse response information as information after denoising processing of each piece of initial channel impulse response information.

In the embodiment of the application, time domain transformation is firstly performed on a plurality of channel state information of a target channel, a plurality of initial channel impulse response information is correspondingly obtained, then normalization processing is performed on influence parameters of the initial channel impulse response information, and finally denoising processing is performed on the initial channel impulse response information after normalization processing, so that a plurality of target channel impulse response information is obtained. Wherein the influencing parameter represents a parameter influencing the stability of the channel state information. The signal processing method is characterized in that normalization processing is carried out on the influence parameters on the basis of acquiring the initial channel impulse response information, which is equivalent to the fact that a plurality of factors influencing the stability of the initial impulse response information are eliminated when the channel information is processed, and further, denoising processing is carried out on the acquired initial channel impulse information after normalization processing, so that redundant sampling points generated due to noise in the initial channel impulse information can be eliminated on the basis of keeping the effective signal of the initial channel impulse information. In summary, the channel state information acquired by the information processing method considers not only the unstable factor of the channel state information, but also the noise point information influencing the signal positioning efficiency, and performs normalization and denoising processing sequentially aiming at the factors, so that stable and effective signal state information is acquired, and the position information of the signal can be accurately determined.

The validity of the information processing method provided in the present application is described below: taking an indoor NLOS identification experiment based on a sub6G frequency band 5G system as an example, whether CIR information is correct or not is judged through a neural network. Fig. 12 is a diagram showing CIR data under a Line of Sight (LOS) condition of 1200 sets collected at a fixed point location for 72 hours continuously at uniform time intervals under an environment-unchanged condition, that is, effective CIR information is 1200. It can be seen that both CIR amplitude and delay shift due to hardware impairments. After the acquired data is input into the neural network, the obtained judgment result is shown in table 1, and table 1 is a neural network output result statistical table based on the original CIR data.

TABLE 1

LOS CIR data volume	1200
		Neural network for judging correct CIR data volume	996

From table 1, it can be seen that the network judges that the correct data is 996 groups and the erroneous data is 204 groups, and that the instability of the original CIR data caused by the hardware damage will cause the network judgment result to be extremely unstable.

Fig. 13 is CIR data obtained by the information processing method provided in the present application. The CIR after information processing can be seen, and meanwhile, the stability of signal amplitude and time delay can be effectively ensured while the original characteristics of the signal are maintained. After the CIR after the information processing is input into the neural network, the obtained judgment result is shown in table 2, and table 2 is a neural network output result statistical table based on the CIR data after the information processing.

TABLE 2

LOS CIR data volume	1200
		Neural network for judging correct CIR data volume	1200

All the data in table 2 are judged to be correct. Therefore, the information processing method can effectively reduce the deviation of the channel state information amplitude and the time delay caused by hardware damage, and obtain a relatively stable network input mode, thereby further ensuring the stability of network output.

Along with the deep research of machine learning theory, the machine learning is widely applied to the field of high-precision positioning by the strong feature extraction capability and the strong nonlinear fitting capability, and the high-efficiency and accurate position service can be obtained by combining channel state information with the machine learning technology. Based on this, a signal positioning method combining the information processing method and the machine learning is explained below by way of one embodiment.

In one embodiment, as shown in fig. 14, there is provided a signal positioning method, including:

s1402 obtains initial channel state information of a transmission channel of the signal according to the received signal.

S1404, the information processing method of any embodiment of the information processing method is adopted to process the initial channel state information to obtain the target channel state information.

And performing information processing on the obtained initial channel state information, wherein the information processing method can be the information processing method in any embodiment, and the target channel state information is obtained.

Alternatively, the target channel state information may be time domain information, that is, truncated channel impulse response information obtained by any embodiment of the above information processing method, or may be frequency domain information, that is, channel state information obtained after fourier transforming the truncated channel impulse response information.

S1406, inputting the target channel state information into a machine learning model to obtain a positioning result of the signal.

And inputting the target channel state information into a machine learning model, wherein the machine learning model predicts and outputs corresponding positioning parameters through learning input data, and takes the positioning parameters as a positioning result of the signal.

It should be noted that the machine learning model corresponds to the application field, and as shown in fig. 15, the signal processing method is used as a preprocessing method, the channel state information after preprocessing is input into the machine learning model, and the machine learning outputs positioning parameters corresponding to the channel state information, which may be NLOS instruction, AOA, or terminal coordinates.

According to the method, initial channel state information of a transmission channel of a signal is obtained according to the received signal, then the channel state information is processed by an information processing method to obtain target channel state information, and finally the target channel state information is input into a machine learning model to obtain a positioning result of the signal. When the signal positioning is performed, the channel state processing information is obtained by the information processing method, so that when the channel state information is stable and effective, the corresponding input of machine learning is stable and effective, and the positioning result of the signal acquired by the machine learning is accurate.

It should be understood that, although the steps in the flowcharts related to the above embodiments are sequentially shown as indicated by arrows, these steps are not necessarily sequentially performed in the order indicated by the arrows. The steps are not strictly limited to the order of execution unless explicitly recited herein, and the steps may be executed in other orders. Moreover, at least some of the steps in the flowcharts described in the above embodiments may include a plurality of steps or a plurality of stages, which are not necessarily performed at the same time, but may be performed at different times, and the order of the steps or stages is not necessarily performed sequentially, but may be performed alternately or alternately with at least some of the other steps or stages.

Based on the same inventive concept, the embodiments of the present application also provide an information processing apparatus for implementing the above-mentioned related information processing method. The implementation of the solution provided by the device is similar to the implementation described in the above method, so the specific limitation of one or more embodiments of the information processing device provided below may refer to the limitation of the information processing method hereinabove, and will not be repeated herein.

In one embodiment, as shown in fig. 16, there is provided an information processing apparatus 1600 comprising: time domain transform module 1620, parameter processing module 1640, and denoising processing module 1660, wherein:

the time domain transformation module 1620 is configured to perform time domain transformation on the multiple channel state information of the target channel, so as to correspondingly obtain multiple initial channel impulse response information;

a parameter processing module 1640, configured to normalize the influencing parameters of the impulse response information of each initial channel; the influencing parameter represents a parameter influencing the stability of the channel state information;

and the denoising processing module 1660 is used for denoising the normalized initial channel impulse response information to obtain a plurality of 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 for acquiring the amplitude of each initial channel impulse response information;

the first determining unit is used for determining sampling points corresponding to the maximum amplitude values of the initial channel impulse response information according to the amplitude of the initial channel impulse response information;

the first displacement unit is used for circularly displacing the sampling point corresponding to the maximum amplitude value of each initial channel impulse response information to the first sampling point according to the sampling point corresponding to the maximum amplitude value of each initial channel impulse response information, and is used for eliminating time delay among the initial channel impulse response information.

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

the main path acquisition module is used for acquiring main path rising information of each initial channel impulse response information after cyclic displacement;

and the main path displacement module is used for circularly displacing the main path ascending information to the front of the maximum amplitude value according to the initial sampling point and the end sampling point of the main path ascending information.

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

A second determining unit, configured to determine a maximum amplitude value according to the amplitude of each initial channel impulse response information;

and the first processing unit is used for dividing the amplitude of each initial channel impulse response information by the maximum amplitude value so as to normalize the amplitude of each initial channel impulse response information.

In one embodiment, the denoising processing module 1660 comprises: a second acquisition unit and a second processing unit, wherein:

the second acquisition unit is used for carrying out truncation processing on the impulse response information of each initial channel according to the preset sampling points to obtain truncated impulse response information of each initial channel;

and the second processing unit is used for determining the impulse response information of each truncated channel as the denoising processed information of the impulse response information of each initial channel.

Each of the modules in the above-described signal processing apparatus may be implemented in whole or in part by software, hardware, and combinations thereof. The above modules may be embedded in hardware or may be independent of a processor in the computer device, or may be stored in software in a memory in the computer device, so that the processor may call and execute operations corresponding to the above modules.

Based on the same inventive concept, the embodiment of the application also provides a signal positioning device for realizing the above related signal positioning method. The implementation of the solution provided by the device is similar to the implementation described in the above method, so the specific limitation in the embodiments of the signal positioning device or devices provided below may be referred to the limitation of the signal positioning method hereinabove, and will not be repeated here.

In one embodiment, as shown in fig. 17, there is provided a signal positioning apparatus 1700, 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 a transmission channel of a signal according to the received signal;

an information processing module 1740 for processing the channel state information by using any one of the information processing methods 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, and obtain a positioning result of the signal.

The various modules in the signal locating apparatus described above may be implemented in whole or in part by software, hardware, and combinations thereof. The above modules may be embedded in hardware or may be independent of a processor in the computer device, or may be stored in software in a memory in the computer device, so that the processor may call and execute operations corresponding to the above modules.

In one embodiment, a computer device is provided comprising a memory and a processor, the memory having stored therein a computer program, the processor when executing the computer program performing the steps of:

In one embodiment, the processor when executing the computer program further performs the steps of:

Processing the initial channel state information by adopting the information processing method of any embodiment of the information processing methods to obtain target channel state information;

In one embodiment, a computer readable storage medium is provided having a computer program stored thereon, which when executed by a processor, performs the steps of:

In one embodiment, the computer program when executed by the processor further performs the steps of:

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

Those skilled in the art will appreciate that implementing all or part of the above described methods may be accomplished by way of a computer program stored on a non-transitory computer readable storage medium, which when executed, may comprise the steps of the embodiments of the methods described above. Any reference to memory, database, or other medium used in the various embodiments provided herein may include at least one of non-volatile and volatile memory. The nonvolatile Memory may include Read-Only Memory (ROM), magnetic tape, floppy disk, flash Memory, optical Memory, high density embedded nonvolatile Memory, resistive random access Memory (ReRAM), magnetic random access Memory (Magnetoresistive Random Access Memory, MRAM), ferroelectric Memory (Ferroelectric Random Access Memory, FRAM), phase change Memory (Phase Change Memory, PCM), graphene Memory, and the like. Volatile memory can include random access memory (Random Access Memory, RAM) or external cache memory, and the like. By way of illustration, and not limitation, RAM can be in the form of a variety of forms, such as static random access memory (Static Random Access Memory, SRAM) or dynamic random access memory (Dynamic Random Access Memory, DRAM), and the like. The databases referred to in the various embodiments provided herein may include at least one of relational databases and non-relational databases. The non-relational database may include, but is not limited to, a blockchain-based distributed database, and the like. The processors referred to in the embodiments provided herein may be general purpose processors, central processing units, graphics processors, digital signal processors, programmable logic units, quantum computing-based data processing logic units, etc., without being limited thereto.

The technical features of the above embodiments may be arbitrarily combined, and all possible combinations of the technical features in the above embodiments are not described for brevity of description, however, as long as there is no contradiction between the combinations of the technical features, they should be considered as the scope of the description.

The above examples only represent a few embodiments of the present application, which are described in more detail and are not to be construed as limiting the scope of the present application. It should be noted that it would be apparent to those skilled in the art that various modifications and improvements could be made without departing from the spirit of the present application, which would be within the scope of the present application. Accordingly, the scope of protection of the present application shall be subject to the appended claims.

Claims

1. An information processing method, characterized in that the method comprises:

2. The method of claim 1 wherein said influencing parameters comprise time delays and said normalizing the influencing parameters for each of said initial channel impulse response information comprises:

acquiring the amplitude of each initial channel impulse response message;

determining a 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 circularly shifting the sampling point corresponding to the maximum amplitude value of each initial channel impulse response information to the first sampling point according to the sampling point corresponding to the maximum amplitude value of each initial channel impulse response information, so as to eliminate time delay between the initial channel impulse response information.

3. The method of claim 2, wherein prior to cyclically shifting the sample point corresponding to the maximum amplitude value of each of the initial channel impulse response information to the first sample point, the method further comprises:

And circularly shifting the main path rising information to the front of the maximum amplitude value according to the initial sampling point and the end sampling point of the main path rising information.

4. A method according to any one of claims 1-3, wherein said influencing parameter comprises an amplitude, and said normalizing the influencing parameter for each of said initial channel impulse response information comprises:

dividing the amplitude of each initial channel impulse response information by the maximum amplitude value to normalize the amplitude of each initial channel impulse response information.

5. A method according to any one of claims 1 to 3, wherein said denoising each of said initial channel impulse response information after normalization processing comprises:

performing truncation processing on each piece of initial channel impulse response information according to a preset sampling point number to obtain truncated channel impulse response information of each piece of initial channel impulse response information;

and determining each piece of truncated channel impulse response information as information after denoising processing of each piece of initial channel impulse response information.

6. A signal positioning method, the method comprising:

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

processing the initial channel state information by the information processing method according to any one of claims 1 to 5 to obtain target channel state information;

7. An information processing apparatus, characterized in that the apparatus comprises:

the parameter processing module is used for carrying out normalization processing on the influence parameters of the initial channel impulse response information; the influencing parameter represents a parameter influencing the stability of the channel state information;

the denoising processing module is used for denoising the initial channel impulse response information after normalization processing to obtain a plurality of target channel impulse response information.

8. A signal positioning device, the device comprising:

An information processing module, configured to process the initial channel state information by using the information processing method according to any one of claims 1 to 5, to obtain target channel state information;

and the result acquisition module is used for inputting the target channel state information into a machine learning model to obtain a positioning result of the signal.

9. A computer device comprising a memory and a processor, the memory storing a computer program, characterized in that the processor, when executing the computer program, implements the steps of the method of any one of the information processing methods of claims 1-5 and the signal localization method of claim 6.

10. A computer-readable storage medium, on which a computer program is stored, characterized in that the computer program, when being executed by a processor, implements the steps of the method of any one of the information processing methods of claims 1-5 and the signal localization method of claim 6.