KR102714459B1 - Method and apparatus for generating and transmitting radio spectrum data in radio monitoring system - Google Patents

Abstract

The present invention relates to a method and apparatus for generating and transmitting radio spectrum data in a radio measurement system, wherein the operating method of the radio measurement system may include a step of obtaining real-time spectrum data for a signal received through an antenna, a step of determining whether a signal exists in a target frequency band corresponding to the real-time spectrum data, a step of generating a radio data set based on whether a signal exists in the target frequency band, and a step of transmitting the radio data set to the server.

Description

METHOD AND APPARATUS FOR GENERATING AND TRANSMITTING RADIO SPECTRUM DATA IN RADIO MONITORING SYSTEM

The present invention relates to a radio measurement system, and more particularly, to a method and apparatus for generating and transmitting radio spectrum data in a radio measurement system.

Radio waves, also called radio waves, are a type of electromagnetic wave that is generated by the flow of electric and magnetic fields. Radio waves are widely used as a means of signal transmission in broadcasting systems such as radio and television, radar, navigation, computer networks, communication systems such as mobile phones, medical devices, and industrial control devices. Furthermore, due to the recent rapid development of wireless communication technology, many radio waves are used in real life. For example, cellular communication base stations and wireless LAN APs (access points) that can be easily found around us use radio waves for wireless communication.

As the number of various systems utilizing radio waves increases, the radio environment becomes more complex day by day, and interference problems between systems may occur. To deal with these problems, radio measurement is necessary. For example, when constructing a new wireless network or installing a new base station, the network designer can design cells or set up base stations to minimize interference based on data obtained through radio measurement. In addition, radio measurement can be performed to monitor the usage status of frequency bands even when operating a wireless network.

The present invention provides a method and device for effectively generating and transmitting radio spectrum data in a radio measurement system.

The present invention provides a method and device for effectively measuring a radio spectrum in a radio measurement system.

The present invention provides a method and device for transmitting radio spectrum data based on the presence or absence of a signal in a radio measurement system.

The present invention provides a method and device for transmitting radio spectrum data based on the presence or absence of an abnormal signal in a radio measurement system.

The technical problems to be achieved in the present invention are not limited to the technical problems mentioned above, and other technical problems not mentioned will be clearly understood by a person having ordinary skill in the technical field to which the present invention belongs from the description below.

According to an embodiment of the present invention, a method for generating and transmitting radio spectrum data in a radio measurement system includes the steps of: acquiring real-time spectrum data for a signal received through an antenna; determining whether a signal exists in a target frequency band corresponding to the real-time spectrum data; generating a radio data set based on whether a signal exists in the target frequency band; and transmitting the radio data set to the server, wherein if the signal exists in the target frequency band, the data set includes at least one of statistical spectrum data, instantaneous spectrum data, real-time spectrogram data, and persistence spectrum data based on the real-time spectrum data, and if the signal does not exist in the target frequency band, the data set may include only feature values of the statistical spectrum data.

According to one embodiment of the present invention, the statistical spectrum data includes at least one of a maximum value, an arithmetic mean, a logarithmic mean, a minimum value, and a standard deviation of power on a time axis obtained for each frequency bin of the real-time spectrum data, and a feature value of the statistical spectrum data includes at least one of a representative value of maximum values of power on a time axis obtained for each frequency bin of the real-time spectrum data, a representative value of arithmetic mean values, a representative value of logarithmic means, and a representative value of minimum values, and the representative value may include one of a minimum value, a maximum value, or an average value.

According to one embodiment of the present invention, whether the signal exists in the target frequency band can be determined based on at least one of the statistical spectrum data, the instantaneous spectrum data, the real-time spectrogram data, and the cumulative spectrum data based on the real-time spectrum data.

According to one embodiment of the present invention, the step of determining whether the signal exists may include the step of dividing the target frequency band into a plurality of sub-bands, and the step of determining whether the signal exists in each of the plurality of sub-bands based on statistical spectrum data for each of the plurality of sub-bands.

According to one embodiment of the present invention, the step of determining whether a signal exists in each of the plurality of sub-bands may include the step of comparing at least one of a maximum value, an arithmetic mean value, and a logarithmic mean value of power per frequency bin of each of the plurality of sub-bands with a reference level, and the step of determining whether the signal exists in each of the plurality of sub-bands based on a result of the comparison.

According to one embodiment of the present invention, the step of determining whether a signal exists in each of the plurality of sub-bands may include the step of checking whether a standard deviation per frequency bin of each of the plurality of sub-bands corresponds to a reference standard deviation range, and the step of determining whether the signal exists in each of the plurality of sub-bands based on a result of the checking.

According to one embodiment of the present invention, the step of determining whether a signal exists in each of the plurality of sub-bands may include the step of comparing a difference value of an arithmetic mean and a logarithmic mean of each frequency bin of each of the plurality of sub-bands with a reference difference value, and the step of determining whether the signal exists in each of the plurality of sub-bands based on a result of the comparison.

According to one embodiment of the present invention, the step of generating a radio wave data set to be transmitted to the server includes the step of generating a radio wave data set to be transmitted to the server further based on whether the signal is an abnormal signal or a normal signal when the signal exists in the target frequency band, wherein if the signal is the normal signal, the data set may include at least one of the statistical spectrum data and the instantaneous spectrum data, and if the signal is the abnormal signal, the data set may include at least one of the statistical spectrum data, the instantaneous spectrum data, real-time spectrogram data, and persistence spectrum data.

According to one embodiment of the present invention, whether the signal is an abnormal signal or a normal signal can be determined using at least one of a threshold value, spectral masking, and an artificial intelligence model.

According to one embodiment of the present invention, the artificial intelligence model may be a neural network-based model that outputs a replica signal for an input signal.

According to one embodiment of the present invention, the artificial intelligence model can be trained to output a replica signal for a normal signal for each band.

In a radio wave measurement system according to one embodiment of the present invention, a measuring device includes a transceiver, and a processor connected to the transceiver, wherein the processor controls the transceiver to obtain real-time spectrum data for a signal received from an antenna, determine whether a signal exists in a target frequency band corresponding to the real-time spectrum data, generate the data radio wave data set based on whether a signal exists in the target frequency band, and transmit the radio wave data set to a data server, wherein if the signal exists in the target frequency band, the data set includes at least one of statistical spectrum data, instantaneous spectrum data, real-time spectrogram data, and persistence spectrum data based on the real-time spectrum data, and if the signal does not exist in the target frequency band, the data set may include only feature values of the statistical spectrum data.

According to one embodiment of the present invention, a radio wave measuring system comprises: an antenna; a measuring device which processes a signal received through the antenna; and a data server which analyzes data provided from the measuring device and provides the analyzed data, wherein the measuring device obtains real-time spectrum data for a signal received through the antenna, determines whether a signal exists in a target frequency band corresponding to the real-time spectrum data, generates the data radio wave data set based on whether a signal exists in the target frequency band, and transmits the radio wave data set to the data server, and if the signal exists in the target frequency band, the data set may include statistical spectrum data based on the real-time spectrum data, and if the signal does not exist in the target frequency band, the data set may include feature values of the statistical spectrum data.

According to the present invention, radio spectrum data can be transmitted more effectively in a radio measurement system.

The effects obtainable from the present invention are not limited to the effects mentioned above, and other effects not mentioned will be clearly understood by those skilled in the art to which the present invention belongs from the description below.

FIG. 1a illustrates an example of a real-time spectrogram according to one embodiment of the present invention.
FIG. 1b illustrates an example of a cumulative spectrum according to one embodiment of the present invention.
Figure 2 illustrates an example of a statistical spectrum according to one embodiment of the present invention.
FIG. 3 illustrates an example of the structure of a radio wave measurement system according to one embodiment of the present invention.
FIG. 4 illustrates an example of a procedure for transmitting radio spectrum data according to one embodiment of the present invention.
FIG. 5 illustrates an example of a procedure for determining the presence or absence of a signal in a partial band according to one embodiment of the present invention.
FIG. 6 illustrates a division example for a target frequency band according to one embodiment of the present invention.
Figure 7 illustrates an example of a procedure for determining an abnormal signal according to one embodiment of the present invention.
Figure 8 illustrates an example of abnormal signal detection according to one embodiment of the present invention.

The following merely illustrates the principles of the invention. Therefore, those skilled in the art can invent various devices that implement the principles of the invention and are included in the concept and scope of the invention, even though they are not explicitly described or illustrated in this specification. In addition, it should be understood that all conditional terms and embodiments listed in this specification are, in principle, expressly intended only for the purpose of making the concept of the invention understood, and are not limited to the embodiments and conditions specifically listed in this way.

The above-described objects, features and advantages will become more apparent through the following detailed description with reference to the attached drawings, whereby a person having ordinary skill in the art to which the invention pertains will be able to easily practice the technical idea of the invention.

The terms “first,” “second,” “third,” and “fourth,” etc., in the specification and claims, are used to distinguish between similar elements, if any, and to describe a particular sequence or order of occurrence, although not necessarily. It will be understood that the terms so used are interchangeable, under appropriate circumstances, so that the embodiments of the invention described herein can be operated in other sequences than those illustrated or described herein. Likewise, where a method is described herein as comprising a series of steps, the order of those steps presented herein is not necessarily the order in which those steps can be performed, and any of the described steps may be omitted and/or any other steps not described herein may be added to the method.

Also, the terms “left,” “right,” “front,” “back,” “top,” “bottom,” “above,” “below,” and the like in the specification and claims are used for the purpose of description and are not necessarily intended to describe invariant relative positions. It will be understood that the terms used herein are interchangeable so that the embodiments of the invention described herein can be operated in other orientations than those illustrated or described herein, for example. The term “connected,” as used herein, is defined as being directly or indirectly connected, whether electrically or non-electrically. Objects described herein as being “adjacent” to one another can be in physical contact with one another, in close proximity to one another, or in the same general range or area as one another, as appropriate to the context in which the phrase is used. The appearance of the phrase “in one embodiment” herein means the same embodiment, although not necessarily so.

Also, in the specification and claims, the terms “connected,” “connecting,” “fastened,” “fastening,” “coupled,” “coupled,” and various variations of such expressions are used to mean connected directly with another component or indirectly through another component.

In addition, the suffixes “module” and “part” used for components in this specification are given or used interchangeably only for the convenience of writing the specification, and do not have distinct meanings or roles in themselves.

Also, the terms used in this specification are for the purpose of describing embodiments only and are not intended to limit the present invention. In this specification, the singular also includes the plural unless specifically stated otherwise. The words 'comprise' and/or 'comprising' as used in the specification do not exclude the presence or addition of one or more other components, steps, operations and/or elements mentioned.

In addition, when describing the invention, if it is judged that a detailed description of a known technology related to the invention may unnecessarily obscure the gist of the invention, the detailed description will be omitted. Hereinafter, a preferred embodiment of the present invention will be described in detail with reference to the attached drawings.

The present invention proposes a technology for generating and transmitting radio spectrum data in a radio measurement system. In particular, the present invention proposes a technology for generating radio spectrum data and effectively transmitting the generated radio spectrum data. Specifically, the present invention proposes a method and device for monitoring a full-band radio spectrum at regular intervals in terms of time and frequency, and transmitting radio big data generated thereby, that is, full-band radio spectrum data, to a server.

Real-time spectrum data is spectrum data measured without signal interruption for a certain period of time, and includes information on the frequency spectrum over time. Real-time spectrum data can be expressed or reproduced as instantaneous spectrum data, statistical spectrum data, real-time spectrogram data, and/or real-time persistence spectrum data. Instantaneous spectrum data indicates amplitude data per frequency bin for a very short period of time, i.e., instantaneous amplitude data per frequency bin.

FIG. 1A illustrates an example of a real-time spectrogram according to one embodiment of the present invention. The real-time spectrogram data indicates changes in amplitude per frequency bin over time, as illustrated in FIG. 1A. According to one embodiment, the real-time spectrogram data can represent data indicating changes in amplitude per frequency bin over time as an image.

Figure 1b illustrates an example of a cumulative spectrum according to one embodiment of the present invention. The cumulative spectrum data indicates the time ratio during which a frequency bin-specific signal exists, as illustrated in Figure 1b. That is, the cumulative spectrum data indicates a histogram in frequency and power space that indicates, as a percentage, how often a frequency appears in a signal.

FIG. 2 illustrates an example of a statistical spectrum according to an embodiment of the present invention. As illustrated in FIG. 2, the statistical spectrum data includes at least one of a maximum (max) value, an arithmetic mean (mean (linear)) value, a logarithmic mean (mean (dB)) value, a minimum value, and a standard deviation (STD) of power on a time axis obtained for each frequency bin of a real-time spectrum. That is, the statistical spectrum data is generated by calculating statistical values for real-time spectrum data measured for a certain period of time (e.g., for a period of time of several hundred milliseconds (ms) or less). In other words, one measurement of the statistical spectrum data can be primarily obtained using a real-time spectrum measured for a certain period of time.

For various purposes, single or multiple sensors need to measure and generate radio spectrum data and transmit the generated radio spectrum data to the server. However, the amount of measured and generated radio spectrum data is usually very large. Therefore, if all radio spectrum data is transmitted to the server, a traffic load may occur and the server needs a very large storage.

Accordingly, the present invention proposes a method and device for transmitting radio spectrum data to reduce network traffic and the size of required storage. Specifically, the present invention proposes a method and device for determining radio spectrum data to be transmitted based on whether a signal in a target frequency band corresponding to the radio spectrum data exists and/or whether a signal in the target frequency band is an abnormal signal.

That is, a radio measurement system according to one embodiment of the present invention determines whether a signal containing meaningful information exists in a corresponding band based on measured radio spectrum data, and transmits all or part of the radio spectrum data based on whether a signal exists.

FIG. 3 illustrates an example of the structure of a radio wave measurement system according to one embodiment of the present invention.

Referring to FIG. 3, the radio measurement system includes an antenna device (310), a measurement device (320), a data server (330), and a management device (340).

The antenna device (310) is installed at a designated site for radio wave measurement and detects radio signals. The antenna device (310) may be placed at a location where radio wave reception is easy. For example, the antenna device (310) may be installed outdoors.

The measuring device (320) generates measurement data by converting radio waves detected by the antenna device (310) into data, and provides the measurement data to the data server (330). Here, the measurement data includes real-time spectrum data, which is radio spectrum data. The measuring device (320) includes a signal detection unit (322) that processes a signal provided from the antenna device (310), a communication unit (324) that generates and interprets a signal for communication, and a processor (326) that performs overall control of the measuring device (320). The signal detection unit (322) can process an RF (radio frequency) signal. The communication unit (324) provides a wired or wireless interface, and performs a function for transmitting and receiving data according to a corresponding communication protocol. The communication unit (324) may be referred to as a transceiver.

The processor (326) of the measuring device (320) analyzes the measurement data provided from the signal detection unit (322) to check the presence or absence of a signal and/or the presence or absence of an abnormal signal for each band, and generates a radio wave data set to be transmitted to the data server (330). The presence or absence of a signal and/or the presence or absence of an abnormal signal for each band can be checked through signal processing or an artificial intelligence-based model for real-time spectrum data. Specifically, the processor (326) sets a frequency band of a real-time spectrum measured for a certain period of time as a target frequency band, and checks whether a signal containing meaningful information exists in the target frequency band. That is, the processor (326) can check whether the real-time spectrum data measured for a certain period of time contains meaningful information. Whether the real-time spectrum data contains meaningful information can be checked based on at least one of statistical spectrum data, instantaneous spectrum data, real-time spectrogram data, and cumulative spectrum data generated based on the real-time spectrum data. When it is determined that a signal exists in the target frequency band, the processor (326) generates a radio data set including statistical spectrum data, and when it is determined that no signal exists in the target frequency band, it determines that only noise exists in the target frequency band and generates a radio data set including characteristic values of statistical spectrum data. Here, the characteristic values of the statistical spectrum data may be values representing that only noise exists in the corresponding band.

In addition, the processor (326) additionally checks whether the signal is a normal signal or an abnormal signal when a signal exists in the target frequency band. The abnormal signal may include at least one of a signal suspected of crosstalk and/or interference, and a signal having a singularity. When the signal existing in the target frequency band is confirmed to be an abnormal signal, the processor (326) generates a radio data set including at least one of instantaneous spectrum data, real-time spectrogram data, and cumulative spectrum data in addition to statistical spectrum data. At this time, the radio data set may further include an abnormal signal flag for indicating that the radio data set is for an abnormal signal. This is for precise analysis and management of the abnormal signal in the server at a later time. The processor (326) transmits the generated radio data set to the data server (330) through the communication unit (324). In addition, the processor (326) may control various functions of the measuring device (320).

The data server (330) stores and analyzes the radio data set provided from the measuring device (320). The data server (330) can store and accumulate the radio data set provided from the measuring device (320) in the storage. In addition, the data server (330) performs preprocessing, such as frequency band-by-frequency usage measurement or channel-by-channel power measurement, based on the radio data set provided from the measuring device (320), and stores the preprocessing performance result in the storage together with the corresponding radio data set. In addition, the data server (330) can search for data stored in the storage according to a request from the management device (340), and convert the searched data into visual data and transmit it to the management device (340). Additionally, if the radio data set provided from the measuring device (320) is a radio data set for an abnormal signal, the data server (330) precisely analyzes the radio data set for the abnormal signal and immediately transmits information related to the occurrence of the abnormal signal including the precise analysis result to the management device (340), thereby enabling the manager to take measures for the abnormal signal.

In the embodiment of FIG. 3, one antenna device (310) and one measuring device (320) are described. However, a radio measurement system according to an embodiment of the present invention may include multiple antenna devices and multiple measuring devices. According to an embodiment, the antenna device (310) and the measuring device (320) may be configured as one sensor, and the radio measurement system may include multiple spatially distributed sensors.

FIG. 4 illustrates an example of a procedure for transmitting radio spectrum data according to one embodiment of the present invention. The procedure of FIG. 4 may be performed by a measuring device (e.g., the measuring device (320) of FIG. 3). Hereinafter, for convenience of explanation, the operating entity of each step is expressed as a 'device', but the executing entity of each step may be understood as the measuring device (320) of FIG. 3.

Referring to FIG. 4, at step S401, the device generates real-time spectrum data. That is, the device generates real-time spectrum data by datafiguring radio waves detected from at least one antenna.

In step S403, the device determines whether a signal exists. That is, the device can determine whether a signal exists in a target frequency band corresponding to the real-time spectrum data by performing signal processing on real-time spectrum data measured for a certain period of time. Whether a signal exists in a target frequency band corresponding to the real-time spectrum data can be determined based on at least one of statistical spectrum data, instantaneous spectrum data, real-time spectrogram data, and cumulative spectrum data generated based on the real-time spectrum data. Specifically, the device can obtain statistical spectrum data based on the real-time spectrum data, and determine whether a signal exists in the target frequency band using the statistical spectrum data. The statistical spectrum data can include at least one of a maximum value, an arithmetic mean value, a logarithmic mean value, a minimum value, or a standard deviation value of power of a bin-wise time axis of the real-time spectrum.

If there is no signal in the target frequency band, in step S405, the device transmits the feature value. That is, if the target frequency band corresponding to the real-time spectrum data does not include a signal, the device determines that only noise exists in the target frequency band and transmits only the feature value of the statistical spectrum data to the server. At this time, the feature value of the statistical spectrum data is a value expressing noise in the target frequency band and may include at least one of the representative value of the arithmetic mean values of the power by frequency bin and the representative value of the maximum values of the power by frequency bin. Here, the representative value may include at least one of the minimum value, the maximum value, or the average value. If there is no signal, transmitting only the feature value of the statistical spectrum data is the minimum information required for the server to confirm the radio data of the corresponding band later. That is, this is to enable the server to restore and/or generate a statistical spectrum representing noise based on the feature value of the statistical spectrum data.

If a signal exists in the target frequency band, in step S407, the device determines whether the signal is an abnormal signal. That is, if a signal exists in the target frequency band corresponding to the real-time spectrum data, the device determines whether the signal is an abnormal signal. The abnormal signal may include at least one of a signal suspected of crosstalk and/or interference, and a signal having singularity. According to one embodiment, the device may determine whether the signal in the target frequency band is an abnormal signal based on an artificial intelligence model. The artificial intelligence model may be a model that copies an input signal and outputs it. For example, the artificial intelligence model may include an autoencoder.

If the signal of the target frequency band is not an abnormal signal, in step S409, the device transmits statistical spectrum data. That is, if the signal of the target frequency band is a normal signal and not an abnormal signal, the device transmits statistical spectrum data corresponding to the real-time spectrum data to the server.

If the signal of the target frequency band is an abnormal signal, in step S411, the device transmits statistical spectrum data and real-time spectrogram data. The real-time spectrogram data is acquired based on the real-time spectrum data. At this time, the device may additionally transmit at least one of the instantaneous spectrum data and the cumulative spectrum data, or transmit at least one of the instantaneous spectrum data and the cumulative spectrum data instead of the real-time spectrogram data. That is, the device may transmit at least one of the instantaneous spectrum data, the real-time spectrogram data, and the cumulative spectrum data and the statistical spectrum data to the server. According to one embodiment, the real-time spectrogram data may be converted to a specific size and transmitted. For example, the real-time spectrogram data may be converted to have a size of 800×800 or 400×400. This is for the ease of analysis and search based on an artificial intelligence model, and for reducing the amount of data transmitted. However, the embodiment of the present disclosure is not limited thereto. According to one embodiment, the device may additionally transmit an abnormal signal flag for subsequent precise analysis and management of the abnormal signal.

In the description referring to FIG. 4, the device used an artificial intelligence model to determine whether the corresponding signal is an abnormal signal. However, the embodiments of the present invention are not limited thereto. That is, whether the corresponding signal is an abnormal signal or a normal signal can be determined based on the characteristics of statistical spectrum data. For example, the device can determine whether the corresponding signal is an abnormal signal or a normal signal by using at least one threshold value set in advance based on statistical spectrum data of normal signals for each frequency band. At this time, at least one threshold value can be set differently for each frequency through spectrum masking. Spectrum masking refers to a filter or masking technique for evaluating the occupied bandwidth of radio spectrum data. The at least one threshold value can include at least one of a threshold value for a maximum value for each frequency bin, a threshold value for an arithmetic mean value, a threshold value for a logarithmic mean value, a threshold value for a minimum value, and a threshold value for a standard deviation.

In addition, in the description referring to FIG. 4, it was described that the feature value of the statistical spectrum data includes at least one of the representative value of maximum values and the representative value of the arithmetic mean values, but the embodiments of the present invention are not limited thereto. For example, the feature value of the statistical spectrum data may include at least one of the representative value of maximum values, the representative value of minimum values, the representative value of the arithmetic mean values, and the representative value of the logarithmic mean values. Here, the feature value is not a value that represents the data of each bin, but a value that represents the data of the entire interval without a signal or at least some interval larger than the bin among the entire interval without a signal.

As described above, the device sets the frequency band of real-time spectrum data measured for a certain period of time as the target frequency band, and determines whether there is a signal in the target frequency band using statistical spectrum data generated based on the real-time spectrum data. However, according to one embodiment of the present disclosure, the target frequency band may be divided into several sub-bands, and the presence or absence of a signal may be determined for each of the divided sub-bands. This is because, as a result of analyzing the spectrum of the full band, there are bands that include signals for each measured instantaneous band, but there are also many bands in which signals are included only in narrow bands. For example, when a plurality of spectrum bins are assumed to be one band, a signal may exist only in some of these bands, and no signal may exist in the remaining bands. Therefore, the measuring device according to one embodiment of the present invention may divide the target frequency band into several sub-bands, and determine whether there is a signal for each of the divided sub-bands.

FIG. 5 illustrates an example of a procedure for determining the presence or absence of a signal in a partial band according to one embodiment of the present invention. The procedure of FIG. 5 may be performed by a measuring device (e.g., the measuring device (320) of FIG. 3). Hereinafter, for convenience of explanation, the operating entity of each step is expressed as a 'device', but the executing entity of each step may be understood as the measuring device (320) of FIG. 3. According to one embodiment, the procedure of FIG. 5 may be understood as a detailed procedure of step S403 of FIG. 4.

Referring to FIG. 5, in step S501, the device divides the target frequency band into sub-bands. The target frequency band may be a frequency band corresponding to the generated real-time spectrum data. That is, the device may divide the target frequency band corresponding to the measured real-time spectrum data into a plurality of sub-bands. According to one embodiment, the target frequency band may be divided based on the number of frequency bins of the target frequency band. For example, when the number of frequency bins of the target frequency band is 3200, the device may divide the target frequency band into four sub-bands such that each sub-band includes 800 bins.

In step S503, the device analyzes the statistical spectrum data for each subband. That is, the device acquires the statistical spectrum data for each subband from the real-time spectrum data, and analyzes the statistical spectrum data for each subband. The statistical spectrum data includes at least one of the maximum value, the arithmetic mean value, the logarithmic mean value, the minimum value, and the standard deviation of the power of the time axis acquired for each frequency bin of the real-time spectrum data. Specifically, the device can compare the maximum value, the arithmetic mean value, and the logarithmic mean value of the power for each frequency bin of each subband with reference levels. At this time, the reference levels can include a reference level for the maximum value, a reference level for the arithmetic mean value, and a reference level for the logarithmic mean value. In addition, the device can compare the standard deviations of the power for each frequency bin of each subband with a reference standard deviation range. In addition, the device can compare the differences between the arithmetic mean and the logarithmic mean of the power for each frequency bin of each subband with a reference difference value.

In step S505, the device determines whether or not a signal exists for each sub-band based on the analysis result. That is, the device determines whether or not a signal exists for each sub-band based on the result of comparing at least one of the maximum value, the arithmetic mean, the logarithmic mean, the standard deviation, and the difference between the arithmetic mean and the logarithmic mean of the power for each frequency bin of each sub-band with a corresponding reference value. Specifically, the device determines that a signal does not exist in the sub-band when all of the maximum value, the arithmetic mean, and the logarithmic mean of the power for each frequency bin of a specific sub-band are smaller than the reference levels, and can determine that a signal exists in the sub-band when the maximum value, the arithmetic mean, and the logarithmic mean of the power for at least one frequency bin of the specific sub-band are greater than or equal to the reference levels. In addition, the device may determine that no signal exists in the sub-band if all standard deviations of the power of each frequency bin of a specific sub-band are included in a reference standard deviation range, and may determine that a signal exists in the sub-band if the standard deviation of the power of at least one frequency bin of the specific sub-band is not included in the reference standard deviation range. In addition, the device may determine that no signal exists in the sub-band if both the arithmetic mean and the logarithmic mean of the power of each frequency bin of the specific sub-band are smaller than a reference difference value, and may determine that a signal exists in the sub-band if the difference value of the arithmetic mean and the logarithmic mean of the power of at least one frequency bin of the specific sub-band is greater than or equal to the reference difference value.

In the description referring to Fig. 5, the presence or absence of a signal for each divided partial band was determined based on statistical spectrum data, but the present invention is not limited thereto. For example, the presence or absence of a signal for each divided partial band may be determined based on at least one of instantaneous spectrum data based on real-time spectrum data, real-time spectrogram data, and cumulative spectrum data.

FIG. 6 illustrates an example of division of a target frequency band according to an embodiment of the present invention. Referring to FIG. 6, a target frequency band corresponding to a spectrum of a plurality of frequency bins may be divided into N sub-bands (611, 612, 613, 614). For example, if the number of frequency bins corresponding to the target frequency band is 3200, the 3200 frequency bins may be divided into four, and each of the four sub-bands may be composed of 800 frequency bins. In this case, since signals exist only in the first sub-band (611) and the second sub-band (612) among the four sub-bands (611, 612, 613, 614), statistical spectrum data of the first sub-band (611) and the second sub-band (612) are transmitted to the server. On the other hand, since there is no signal in the third sub-band (613) and the fourth sub-band (614) and only noise exists, the statistical spectrum data of the third sub-band (613) and the fourth sub-band (614) are not transmitted to the server, and only the characteristic values are transmitted to the server. On the other hand, if the target frequency band is not divided, the statistical spectrum data of the entire target frequency band should be transmitted to the server by the signal included in the front part of the target frequency band. That is, if the target frequency band is divided into multiple sub-bands and the presence or absence of a signal in each divided sub-band is determined, the amount of data transmitted can be reduced compared to the case where the target frequency band is not divided. Therefore, in order to reduce network traffic, it is important to divide the target frequency band into multiple sub-bands. However, as the number of divided sub-bands increases, the amount of calculation and the number of bands to be managed also increase, so the number of divisions for the target frequency band should be appropriately set in consideration of the amount of calculation and the number of bands to be managed.

For radio management, it is important to measure and analyze the entire band, but it is also very important to focus on analyzing bands where service disruption is likely to occur when radio interference occurs. For example, it is very important to detect abnormal signals caused by interference or jammers for key infrastructure and disaster networks of a country, such as GNSS (Global Navigation Satellite System), LTE (Long Term Evolution), 5G (5th Generation), or PS-LTE (Public Safety LTE) bands. Therefore, the present invention sets the bands for the key infrastructure and/or disaster networks of a country as priority monitoring bands, and can detect the occurrence of abnormal signals in the priority monitoring bands. A device according to an embodiment of the present invention (e.g., a measuring device (320) of FIG. 3) detects an abnormal signal within a key surveillance band through an artificial intelligence model or a signal processing technique, and when an abnormal signal is detected, transmits at least one of instantaneous spectrum data, real-time spectrogram data, and cumulative spectrum data together with statistical spectrum data of the corresponding key surveillance band to a server (e.g., a data server (330) of FIG. 3) for precise analysis and data management. However, it is generally very difficult to collect abnormal signal data due to interference or jammers. Therefore, according to an embodiment of the present invention, a measuring device determines data generally detected in a key surveillance band as a normal signal and trains an artificial intelligence model, and detects an abnormal signal using the artificial intelligence model trained by the normal signal. The artificial intelligence model may be a neural network-based model that replicates (or copies) an input signal and outputs it. According to an embodiment, the artificial intelligence model may include an autoencoder that copies input data into output data by encoding input data and decoding the encoding result. According to one embodiment of the present invention, the artificial intelligence model can be trained based on real-time spectrogram data of a normal signal acquired in the corresponding band.

FIG. 7 illustrates an example of a procedure for determining an abnormal signal according to one embodiment of the present invention. The procedure of FIG. 7 can be performed by a measuring device (e.g., the measuring device (320) of FIG. 3). Hereinafter, for convenience of explanation, the operating entity of each step is expressed as a 'device', but the executing entity of each step can be understood as the measuring device (320) of FIG. 3. According to one embodiment, the procedure of FIG. 7 can be understood as a detailed procedure of step S407 of FIG. 4.

Referring to FIG. 7, in step S701, the device replicates a signal. That is, the device obtains a replicated signal for a signal detected in the corresponding band, that is, an original signal, by using an artificial intelligence model. Specifically, the device may obtain a replicated signal for the original signal by encoding the original signal into a low-dimensional vector using an artificial intelligence model including an autoencoder and then decoding the original signal into a high-dimensional vector again. According to one embodiment, the device may obtain replicated real-time spectrogram data from the artificial intelligence model by inputting real-time spectrogram data based on real-time spectrum data of the corresponding band in which the original signal exists into the artificial intelligence model. The corresponding band may be any one of a band set as a focus monitoring band, a target frequency band determined to have a signal in step S403 of FIG. 4, or a partial band determined to have a signal in step S505 of FIG. 5.

In step S703, the device determines whether the original signal and the replicated signal match. For example, the device determines whether the original signal and the replicated signal match based on the MSE (Mean Squared Error) loss values for the original signal and the replicated signal. Specifically, the device may calculate the MSE loss for the original signal and the replicated signal, and compare the calculated MSE loss value with a reference value of the corresponding band. If the calculated MSE loss value is less than or equal to the reference value of the corresponding band, the device determines that the original signal and the replicated signal match. On the other hand, if the calculated MSE loss value is greater than the reference value of the corresponding band, the device determines that the original signal and the replicated signal do not match. The reference value may be set differently for each band. This is because the characteristics of a normal signal may be different for each band.

If the original signal and the replicated signal do not match, the device determines the signal as an abnormal signal in step S705. That is, since the AI model is trained to output a replicated signal for a normal signal, if the input original signal is not a normal signal, the device cannot output a replicated signal that is substantially identical to the original signal. Accordingly, if the original signal and the replicated signal do not match, the device can determine the signal in the corresponding band as an abnormal signal. The abnormal signal may include a signal suspected of crosstalk and/or interference, and/or a signal having a singularity.

If the original signal and the replicated signal match, the device determines the signal as a normal signal at step S707. That is, as described above, since the artificial intelligence model is trained to output a replicated signal for a normal signal, if the input original signal is a normal signal, it can output a replicated signal that is substantially identical to the original signal. Therefore, if the original signal and the replicated signal match, the device determines the signal in the corresponding band as a normal signal.

Figure 8 illustrates an example of abnormal signal detection according to one embodiment of the present invention.

Referring to FIG. 8, when a normal signal is input to the artificial intelligence model, it can be seen that the MSE loss values for the input signal (e.g., the original signal) and the output signal (e.g., the duplicate signal) have relatively small values. On the other hand, when an abnormal signal is input to the artificial intelligence model, it can be seen that the MSE loss values for the input signal and the output signal increase significantly. This is because the artificial intelligence model is trained to receive a normal signal for each band and output a duplicate signal for the normal signal. Therefore, the device according to the embodiment of the present invention can detect the appearance of an abnormal signal based on the difference between the signal input to the artificial intelligence model and the signal output from the artificial intelligence model. The difference between the signal input to the artificial intelligence model and the signal output from the artificial intelligence model can be determined based on the MSE loss value.

In the embodiments of the present invention described above, the radio data set to be transmitted to the server (e.g., the data server (330) of FIG. 3) is configured differently depending on the presence or absence of a signal and/or the presence or absence of an abnormal signal. That is, the radio data set to be transmitted is configured to include only the characteristic values of statistical spectrum data when no signal exists, to include statistical spectrum data when a normal signal exists, and to include at least one of instantaneous spectrum data, real-time spectrogram data, and cumulative spectrum data in addition to the statistical spectrum when an abnormal signal exists. However, the present invention is not limited thereto. According to one embodiment, when a normal signal exists, the radio data set to be transmitted may be configured to include at least one of statistical spectrum data and instantaneous spectrum data, and when an abnormal signal exists, the radio data set to be transmitted may be configured to include at least one of statistical spectrum data, instantaneous spectrum data, real-time spectrogram data, and cumulative spectrum data. In this case, the radio data set in the case of the presence of an abnormal signal may be configured to include more types of data and/or a larger amount of data than the radio data set in the case of the presence of a normal signal. This is for precise analysis and management of abnormal signals on the server in the future.

The method for generating and transmitting a radio spectrum according to an embodiment described above may be implemented in the form of program commands that can be executed through various computer means and recorded on a computer-readable medium. The computer-readable medium may include program commands, data files, data structures, etc., alone or in combination. The program commands recorded on the medium may be those specially designed and configured according to the embodiment or may be those known to and available to those skilled in the art of computer software. Examples of the computer-readable recording medium include magnetic media such as hard disks, floppy disks, and magnetic tapes, optical media such as CD-ROMs and DVDs, magneto-optical media such as floptical disks, and hardware devices specially configured to store and execute program commands such as ROMs, RAMs, and flash memories. Examples of the program commands include not only machine language codes generated by a compiler, but also high-level language codes that can be executed by a computer using an interpreter, etc.

Each of the drawings referenced in the description of the preceding embodiments is merely an example illustrated for convenience of description, and the items, contents and images of the information displayed on each screen may be transformed and displayed in various forms.

Although the present invention has been described with reference to one embodiment shown in the drawings, this is merely exemplary, and those skilled in the art will understand that various modifications and equivalent other embodiments are possible therefrom. Accordingly, the true technical protection scope of the present invention should be determined by the technical idea of the appended claims.

Claims (13)

In a method of generating and transmitting radio spectrum data in a radio measurement system,
A step of acquiring real-time spectrum data for a target frequency band using an antenna;
A step of determining whether a signal that does not correspond to noise exists in the target frequency band based on the power of frequency bins of the real-time spectrum data;
A step of generating a radio data set based on whether a signal that does not correspond to the noise exists in the target frequency band; and
A step of transmitting the above radio wave data set to a server,
If a signal that does not correspond to the noise exists in the target frequency band, the data set includes at least one of statistical spectrum data indicating statistical values for the real-time spectrum data, instantaneous spectrum data indicating amplitude data of instantaneous frequency bins, real-time spectrogram data indicating changes in amplitude of frequency bins over time, and cumulative spectrum data indicating a time ratio in which a signal exists in frequency bins.
If only the noise exists in the target frequency band, the data set includes only feature values representing the noise existing in the target frequency band among the statistical values of the statistical spectrum data.
A method wherein the statistical spectrum data, the instantaneous spectrum data, the real-time spectrogram data, and the cumulative spectrum data are obtained based on the real-time spectrum data.
In claim 1,
The above statistical spectrum data includes at least one of a maximum value, an arithmetic mean value, a logarithmic mean value, a minimum value, and a standard deviation of power on a time axis for each frequency bin of the real-time spectrum data,
Among the statistical values of the statistical spectrum data, a feature value representing noise existing in the frequency band includes at least one of a representative value of maximum values of power on the time axis for each frequency bin of the real-time spectrum data, a representative value of arithmetic mean values, a representative value of logarithmic means, and a representative value of minimum values.
A method wherein the representative value comprises one of a minimum value, a maximum value, or an average value.
In claim 2,
A method in which whether a signal that does not correspond to the noise exists in the target frequency band is determined based on at least one of the statistical spectrum data, the continuous instantaneous spectrum data, the real-time spectrogram data, and the accumulated spectrum data.
In claim 2,
The step of determining whether there is a signal that does not correspond to the above noise is:
A step of dividing the target frequency band into a plurality of sub-bands; and
A method comprising the step of determining whether a signal that does not correspond to noise exists in each of the plurality of sub-bands based on statistical spectral data for each of the plurality of sub-bands.
In claim 4,
The step of determining whether there is a signal that does not correspond to noise in each of the above multiple sub-bands is:
A step of comparing at least one of the maximum value, the arithmetic mean value, and the logarithmic mean value of the power of the frequency bins of the statistical spectrum data for each of the plurality of sub-bands with a reference level; and
A method comprising a step of determining whether a signal that does not correspond to the noise exists in each of the plurality of partial bands based on the comparison result.
In claim 4,
The step of determining whether there is a signal that does not correspond to noise in each of the above multiple sub-bands is:
A step of checking whether the standard deviation of the frequency bins of the statistical spectrum data for each of the above multiple partial bands corresponds to a reference standard deviation range; and
A method comprising a step of determining whether a signal that does not correspond to the noise exists in each of the plurality of partial bands based on the above verification results.
In claim 4,
The step of determining whether there is a signal that does not correspond to noise in each of the above multiple sub-bands is:
A step of comparing the difference value of the arithmetic mean and the logarithmic mean of the frequency bins of the statistical spectrum data for each of the above multiple partial bands with the reference difference value; and
A method comprising a step of determining whether a signal that does not correspond to the noise exists in each of the plurality of partial bands based on the comparison result.
In claim 1,
The step of generating a set of radio data to be transmitted to the above server is:
If a signal that does not correspond to the noise exists in the target frequency band,
A step of generating a radio data set to be transmitted to the server further based on whether the signal is an abnormal signal or a normal signal,
If the signal is the normal signal, the data set includes at least one of the statistical spectrum data and the instantaneous spectrum data,
A method wherein, when the signal is the abnormal signal, the data set includes at least one of the statistical spectrum data, the instantaneous spectrum data, the real-time spectrogram data, and the cumulative spectrum data.
In claim 8,
A method in which it is determined whether the above signal is an abnormal signal or a normal signal by using at least one of a threshold value, spectral masking, and an artificial intelligence model.
In claim 9,
The above artificial intelligence model is a neural network-based model that outputs a replica signal for an input signal.
In claim 10,
The above artificial intelligence model is a method learned to output a replica signal for a normal signal for each band.
In a measuring device in a radio measurement system,
Transmitter and receiver; and
A processor connected to the transceiver, the processor comprising:
Obtain real-time spectrum data for the target frequency band using an antenna,
Based on the power of the frequency bins of the above real-time spectrum data, it is determined whether a signal that does not correspond to noise exists in the target frequency band,
Generate the data propagation data set based on whether a signal that does not correspond to the noise exists in the target frequency band,
Controlling the transceiver to transmit the above radio wave data set to the data server;
If a signal that does not correspond to the noise exists in the target frequency band, the data set includes at least one of statistical spectrum data indicating statistical values for the real-time spectrum data, instantaneous spectrum data indicating amplitude data of instantaneous frequency bins, real-time spectrogram data indicating changes in amplitude of frequency bins over time, and cumulative spectrum data indicating a time ratio in which a signal exists in frequency bins.
If only noise exists in the target frequency band, the data set includes a feature value representing the noise existing in the target frequency band among the statistical values of the statistical spectrum data.
A measuring device wherein at least one of the statistical spectrum data, the instantaneous spectrum data, the real-time spectrogram data, and the cumulative spectrum data is acquired based on the real-time spectrum data.
In a radio measurement system,
antenna;
A measuring device for processing a signal received through the antenna; and
A data server that analyzes data provided from the above measuring device and provides analysis data,
The above measuring device obtains real-time spectrum data for a target frequency band through the antenna, determines whether a signal that does not correspond to noise exists in the target frequency band based on the power of frequency bins of the real-time spectrum data, generates the data propagation data set based on whether a signal that does not correspond to noise exists in the target frequency band, and transmits the propagation data set to the data server.
If a signal that does not correspond to the noise exists in the target frequency band, the data set includes at least one of statistical spectrum data indicating statistical values for the real-time spectrum data, instantaneous spectrum data indicating amplitude data of instantaneous frequency bins, real-time spectrogram data indicating changes in amplitude of frequency bins over time, and cumulative spectrum data indicating a time ratio in which a signal exists in frequency bins.
If only noise exists in the target frequency band, the data set includes a feature value representing the noise existing in the target frequency band among the statistical values of the statistical spectrum data,
A radio measurement system, wherein at least one of the statistical spectrum data, the instantaneous spectrum data, the real-time spectrogram data, and the cumulative spectrum data is acquired based on the real-time spectrum data.

Images