Information processing apparatus, information processing method, and program

Abstract

To appropriately generate teacher data for supervised machine learning.SOLUTION: A generation unit configured to generate a spectrum image and a spectrogram image on the basis of spectrum data of a received wireless signal, display the spectrum image and the spectrogram image on the same screen, receive designation of a specific range including a specific signal from a user on one of the spectrum image and the spectrogram image, and superimpose and display a first bounding box corresponding to the specific range on the spectrum image; A display unit configured to superimpose and display a second bounding box corresponding to the specific range on the spectrogram image, and an output unit configured to output teacher data in which information indicating the specific range and specification information of the specific signal are set as correct answer data and the spectrum image is set as an explanatory variable.SELECTED DRAWING: Figure 4

Description

[Technical Field]

[0001] The present disclosure relates to an information processing device, an information processing method, and a program. [Background technology]

[0002] Patent Document 1 discloses a technology for generating spectrum data based on a received radio signal, converting the spectrum data into a spectrum image, and inputting the spectrum image into a trained model to detect a signal region. [Prior art documents] [Patent documents]

[0003] [Patent Document 1] Japanese Patent Publication No. 2023-55315 Summary of the Invention [Problem to be solved by the invention]

[0004] However, Patent Document 1 does not consider, for example, the problem of preparing training data for supervised machine learning.

[0005] In view of the above-described problems, an object of the present disclosure is to provide a technology capable of appropriately generating training data for supervised machine learning. [Means for solving the problem]

[0006] In a first aspect of the present disclosure, there is provided an information processing device having: a generation unit that generates a spectrum image and a spectrogram image based on spectrum data of a received radio signal; a display unit that displays the spectrum image and the spectrogram image on the same screen, receives from a user a specification of a specific range on either the spectrum image or the spectrogram image that includes a specific signal, and superimposes a first bounding box corresponding to the specific range on the spectrum image and a second bounding box corresponding to the specific range on the spectrogram image; and an output unit that outputs teacher data using information indicating the specific range and specification information of the specific signal as correct answer data and the spectrum image as an explanatory variable.

[0007] Furthermore, a second aspect of the present disclosure provides an information processing method that generates a spectrum image and a spectrogram image based on spectrum data of a received radio signal, displays the spectrum image and the spectrogram image on the same screen, accepts from a user specification of a specific range that includes a specific signal on either the spectrum image or the spectrogram image, superimposes a first bounding box corresponding to the specific range on the spectrum image, superimposes a second bounding box corresponding to the specific range on the spectrogram image, sets information indicating the specific range and specification information of the specific signal as correct answer data, and outputs training data using the spectrum image as an explanatory variable.

[0008] Furthermore, in a third aspect of the present disclosure, there is provided a program for causing a computer to execute processing to generate a spectrum image and a spectrogram image based on spectrum data of a received radio signal, display the spectrum image and the spectrogram image on the same screen, accept from a user specification of a specific range on either the spectrum image or the spectrogram image that includes a specific signal, superimpose a first bounding box corresponding to the specific range on the spectrum image, superimpose a second bounding box corresponding to the specific range on the spectrogram image, use information indicating the specific range and specification information of the specific signal as correct answer data, and output training data using the spectrum image as an explanatory variable. [Effects of the Invention]

[0009] According to one aspect, training data for supervised machine learning can be appropriately generated. [Brief explanation of the drawings]

[0010] [Figure 1] FIG. 1 is a diagram illustrating an example of a configuration of an information processing apparatus according to an embodiment. [Figure 2] 1 is a diagram illustrating an example of the configuration of an information processing system according to an embodiment. [Figure 3] FIG. 1 is a diagram illustrating an example of a hardware configuration of an information processing apparatus according to an embodiment. [Figure 4] 10 is a flowchart illustrating an example of processing by the information processing apparatus according to the embodiment. [Figure 5] FIG. 2 is a diagram illustrating an example of a display screen that displays a spectrum image and a spectrogram image according to the embodiment. [Figure 6] FIG. 10 is a diagram illustrating an example of an operation when accepting annotation work on a spectrum image according to the embodiment. [Figure 7] FIG. 10 is a diagram illustrating an example of an operation when accepting annotation work on a spectrogram image according to the embodiment. [Figure 8]FIG. 10 is a diagram illustrating an example of a histogram of power values ​​of a received signal according to the embodiment. [Figure 9] 10A and 10B are diagrams illustrating an example of a method for determining a range in which a specific signal exists after determining a power value range in which the specific signal exists according to the embodiment. DETAILED DESCRIPTION OF THE INVENTION

[0011] The principles of the present disclosure will be described with reference to some exemplary embodiments. It should be understood that these embodiments are set forth for illustrative purposes only, to aid those skilled in the art in understanding and practicing the present disclosure, without implying any limitation on the scope of the disclosure. The disclosure described herein may be implemented in various ways other than those described below.

[0012] In the following description and claims, unless defined otherwise, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this disclosure belongs.

[0013] Hereinafter, embodiments of the present disclosure will be described with reference to the drawings. Note that each drawing is merely an example for describing one or more embodiments. Each drawing may not relate to only one particular embodiment, but may also relate to one or more other embodiments. As will be understood by those skilled in the art, various features or steps described with reference to any one drawing can be combined with features or steps shown in one or more other drawings to create, for example, an embodiment not explicitly shown or described. Not all features or steps shown in any one drawing are necessarily required to describe an exemplary embodiment, and some features or steps may be omitted. The order of steps described in any drawing may be changed as appropriate.

[0014] (Embodiment 1) <Configuration> The configuration of an information processing device 10 according to an embodiment will be described with reference to Fig. 1. Fig. 1 is a diagram showing an example of the configuration of an information processing device (teacher data generation device) 10 according to an embodiment. The information processing device 10 has a generation unit 11, a display unit 12, and an output unit 13. Each of these units may be realized by cooperation between one or more programs installed in the information processing device 10 and hardware such as a processor and memory of the information processing device 10.

[0015] The generation unit 11 generates a spectrum image and a spectrogram image based on spectrum data of the received radio signal.

[0016] The display unit 12 displays the spectrum image and the spectrogram image generated by the generation unit 11 on the same screen, and receives from the user a specification of a specific range that includes a specific signal on either the spectrum image or the spectrogram image. The display unit 12 then superimposes a first bounding box corresponding to the specific range on the spectrum image, and superimposes a second bounding box corresponding to the specific range on the spectrogram image.

[0017] The output unit 13 outputs training data that uses the information indicating the specific range and the specification information of the specific signal as correct answer data and the spectrum image as an explanatory variable.

[0018] (Embodiment 2) <System configuration> Next, the configuration of an information processing system 1 according to an embodiment will be described with reference to Fig. 2. Fig. 2 is a diagram showing an example of the configuration of the information processing system 1 according to an embodiment. In the example of Fig. 2, the information processing system 1 has an information processing device 10 and a receiving device 20. In the example of Fig. 2, the information processing device 10 and the receiving device 20 are connected so as to be able to communicate with each other via a network N. Note that the number of information processing devices 10 and the receiving devices 20 is not limited to the example of Fig. 2.

[0019] Examples of the network N include, for example, the Internet, a mobile communication system, a wireless LAN (Local Area Network), a LAN, a bus, etc. Examples of the mobile communication system include, for example, a fifth generation mobile communication system (5G), a sixth generation mobile communication system (6G, Beyond 5G), a fourth generation mobile communication system (4G), a third generation mobile communication system (3G), etc.

[0020] The information processing device 10 is, for example, a device such as a server, a cloud, a personal computer, a smartphone, etc. The information processing device 10 generates training data for supervised machine learning based on, for example, a user's annotation work.

[0021] The receiving device 20 includes a radio wave sensor that receives various types of radio signals. The receiving device 20 performs a short-time Fourier transform (STFT) on the received radio signal data to generate spectrum data, and transmits the generated spectrum data to the information processing device 10.

[0022] <Hardware configuration> Fig. 3 is a diagram showing an example of the hardware configuration of an information processing device 10 according to an embodiment. In the example of Fig. 3, the information processing device 10 (computer 100) includes a processor 101, a memory 102, and a communication interface 103. These components may be connected via a bus or the like. The memory 102 stores at least a part of a program 104. The communication interface 103 includes an interface required for communication with other network elements.

[0023] When the program 104 is executed by the processor 101, memory 102, and the like in cooperation with each other, the computer 100 performs at least some of the processing of the embodiments of the present disclosure. The memory 102 may be of any type. As a non-limiting example, the memory 102 may be a non-transitory computer-readable storage medium. The memory 102 may also be implemented using any suitable data storage technology, such as semiconductor-based memory devices, magnetic memory devices and systems, optical memory devices and systems, fixed memory, and removable memory. Although only one memory 102 is shown in the computer 100, several physically different memory modules may exist in the computer 100. The processor 101 may be of any type. The processor 101 may include one or more of a general-purpose computer, a special-purpose computer, a microprocessor, a digital signal processor (DSP), and a processor based on a multi-core processor architecture, as a non-limiting example. The computer 100 may have multiple processors, such as application-specific integrated circuit chips that are time-slaved to a clock that synchronizes the main processor.

[0024] Embodiments of the present disclosure may be implemented in hardware or special purpose circuits, software, logic, or any combination thereof. Some aspects may be implemented in hardware, while other aspects may be implemented in firmware or software that may be executed by a controller, microprocessor, or other computing device.

[0025] The present disclosure also provides at least one computer program product tangibly stored on a non-transitory computer-readable storage medium. The computer program product includes computer-executable instructions, such as instructions included in program modules, that execute on a target real or virtual processor or device to perform the processes or methods of the present disclosure. Program modules include routines, programs, libraries, objects, classes, components, data structures, etc. that perform particular tasks or implement particular abstract data types. The functionality of the program modules may be combined or divided among program modules as desired in various embodiments. The machine-executable instructions of the program modules may be executed in local or distributed devices. In a distributed device, the program modules may be located in both local and remote storage media.

[0026] The program code for executing the methods of the present disclosure may be written in any combination of one or more programming languages. The program code may be provided to a processor or controller of a general-purpose computer, a special-purpose computer, or other programmable data processing apparatus. When the program code is executed by the processor or controller, the functions / acts in the flowcharts and / or implementing block diagrams are performed. The program code may be executed entirely on the machine, partly on the machine, as a standalone software package, partly on the machine and partly on a remote machine, or entirely on a remote machine or server.

[0027] The program can be stored and provided to a computer using various types of non-transitory computer-readable media. Non-transitory computer-readable media include various types of tangible recording media. Examples of non-transitory computer-readable media include magnetic recording media, magneto-optical recording media, optical disk media, and semiconductor memory. Magnetic recording media include, for example, flexible disks, magnetic tapes, and hard disk drives. Magneto-optical recording media include, for example, magneto-optical disks. Optical disk media include, for example, Blu-ray discs, CD (Compact Disc)-ROMs (Read Only Memory), CD-Rs (Recordable), and CD-RWs (Rewritable). Semiconductor memory includes, for example, solid-state drives, mask ROMs, PROMs (Programmable ROMs), EPROMs (Erasable PROMs), flash ROMs, and RAMs (Random Access Memory). The program may also be provided to a computer by various types of temporary computer-readable media. Examples of temporary computer-readable media include electrical signals, optical signals, and electromagnetic waves. The temporary computer-readable medium can supply the program to the computer via a wired communication path such as an electric wire or an optical fiber, or via a wireless communication path.

[0028] <Processing> Next, an example of processing by the information processing device 10 according to the embodiment will be described with reference to FIGS. 4 to 9. FIG. 4 is a flowchart showing an example of processing by the information processing device 10 according to the embodiment. FIG. 5 is a diagram showing an example of a display screen displaying a spectrum image and a spectrogram image according to the embodiment. FIG. 6 is a diagram showing an example of an operation when accepting annotation work on a spectrum image according to the embodiment. FIG. 7 is a diagram showing an example of an operation when accepting annotation work on a spectrogram image according to the embodiment. FIG. 8 is a diagram showing an example of a histogram of power values ​​of a received signal according to the embodiment. FIG. 9 is a diagram showing an example of a method for determining a range in which a specific signal exists after determining a power value region in which a specific signal exists according to the embodiment. Note that the processing in FIG. 4 may be executed when a predetermined operation is performed by a user, for example.

[0029] In step S101, the generation unit 11 generates a spectrum image and a spectrogram image based on spectrum data of a radio signal received and recorded by the receiving device 20. Here, the spectrum data may be generated by performing a short-time Fourier transform on the radio signal data received by the receiving device 20.

[0030] A spectrum image is, for example, a visualization of a radio signal as a two-dimensional image of frequency and signal strength. In area 511 of FIG. 5, a spectrum image is displayed with the horizontal axis representing frequency and the vertical axis representing signal strength (power). A spectrum image may be generated by performing a short-time Fourier transform shown in (Equation 1) on a signal received by a radio wave sensor and arranging the results in the time direction. Here, x(t) is the received signal, and w(t) is a window function. In (Equation 1), a coefficient of 1 / (2π) is used in addition to the integral symbol. 1 / 2 may be multiplied.

number

[0031] A spectrogram image is, for example, a visualization of a wireless signal using time, frequency, and signal strength. Area 512 in Fig. 5 displays a spectrogram image with frequency on the horizontal axis, time on the vertical axis, and signal strength on color or brightness. A spectrogram image with time on the vertical axis is also called a "waterfall" because it resembles a waterfall.

[0032] Next, the display unit 12 displays the spectrum image and the spectrogram image generated by the generation unit 11 on the same screen as shown in Fig. 5 (step S102). In the example of Fig. 5, on the display screen 501, the spectrum image is displayed in an area 511, and the spectrogram image is displayed in an area 512.

[0033] The spectrogram image in region 512 visualizes the situation in which signals A1 to A3 are continuously received during a specific time in the time direction. Furthermore, the spectrum image in region 511 shows the situation in which signals A1 to A3, each with a different bandwidth, are received at a specific time T specified by the user on the spectrogram image in region 512. Horizontal lines A4 below each signal simulate the noise floor. Note that noise is known to have randomness, and therefore does not actually form a straight line segment like A4.

[0034] The display unit 12 may allow a cross-shaped cursor (crosshair cursor) to be operated using a pointing device such as a mouse. In the example of Fig. 5, the display unit 12 displays a display area 513 superimposed on the spectrum image of the area 511. The display unit 12 may display, in the display area 513, the coordinates of the pixel pointed to by the crosshair cursor, the corresponding frequency, the received power level of the signal, etc.

[0035] Next, the display unit 12 receives from the user an operation (annotation operation) of designating a specific range on the spectrum image or the spectrogram image that includes a specific signal (step S103). Here, the display unit 12 may receive an operation to select each specific range that is thought to include one or more specific signals, using an input device such as a mouse. The display unit 12 may also receive an operation to input specification information for each of one or more specific signals, using an input device such as a keyboard. The specification information may include, for example, individual information (e.g., transmitter name) or model information of the transmitter that transmitted the specific signal. The specification information may also include, for example, attribute information such as the modulation method of the specific signal, digital communication wave, analog communication wave, non-communication wave, or impulse noise. The specification information may also include, for example, a class number used for deep learning.

[0036] The display unit 12 may superimpose the specific range specified by the user and the specification information of the specific signal included in the specific range on the spectrum image and the spectrogram image, respectively. Note that, when an annotation operation is performed on the spectrogram image, the display unit 12 may superimpose on the spectrum image the range information only for the time selected by the user on the spectrogram image.

[0037] (Example of accepting annotations on a spectrum image) An example of a user operation when accepting annotation work on a spectrum image will be described with reference to FIG. 6. For example, the user operates the crosshair cursor (e.g., drags it as shown by the arrow 611) on the area 511 (spectrum view) where the spectrum image is displayed, and specifies a range (first bounding box) 612 that can surround the signal A1 as a specific signal. Then, the user inputs specification information of the specific signal using an input device (e.g., a keyboard or a touch display). At this time, the display unit 12 may, for example, pop up a specification information input screen on the screen.

[0038] The display unit 12 may then superimpose the first bounding box 612 specified by the user and the specification information 631 on the spectrum view. The display unit 12 may then superimpose a second bounding box 622 surrounding the signal A1, which is the specific signal specified by the user, in the area 512 (spectrogram view) where the spectrogram image is displayed. In this case, the display unit 12 may change the color of the border of the second bounding box 622 or color the inside of the second bounding box based on the specification information (for example, a class number, etc.). Displaying the second bounding box 622 according to the first bounding box 612 specified by the user not only on the spectrum view but also on the spectrogram view facilitates annotation work.

[0039] (Example of accepting annotations on a spectrogram image) An example of a user operation when accepting annotation work on a spectrogram image will be described with reference to Fig. 7. In this case, the user operates the crosshair cursor (e.g., drags it as indicated by arrow 711) on spectrogram view 512, for example, to specify a range (second bounding box) 622 that can enclose signal A1 as a specific signal. In this case, in the example of Fig. 5, only the area corresponding to specific time T is enclosed, but if the specific signal is transmitted continuously in the time direction, such as a communication wave, an operation to select the entire signal may be performed.

[0040] Then, the user inputs the specification information of the specific signal using an input device (for example, a keyboard or a touch display). At this time, the display unit 12 may, for example, pop up a specification information input screen on the screen.

[0041] Then, the display unit 12 may superimpose the second bounding box 622 specified by the user and the specification information 731 on the spectrogram view 512. In this case, the display unit 12 may change the color of the border of the second bounding box 622 or may color the inside of the second bounding box 622 based on the specification information (for example, a class number, etc.).

[0042] The display unit 12 may then superimpose a first bounding box 612 surrounding the signal A1, which is the specific signal designated by the user, on the spectrum view 511. Note that since a spectrum corresponds to a spectrogram cut out at a certain time, a spectrogram image corresponding to a specific time T in the spectrogram view is displayed on the spectrum view. In this way, annotation work on the spectrum view involves annotation of only one shot at a certain time. This reduces the burden of annotation work, as annotation work on the spectrogram view is also reflected on the spectrogram side.

[0043] Next, the output unit 13 outputs data of a combination of the spectrum image and the correct answer data as training data (step S104). Here, the output unit 13 may set information indicating a specific range specified by a user and specification information of the specific signal as the correct answer data. This makes it possible to generate a trained model that infers a range including a specific signal and specification information of the specific signal based on the spectrum image through machine learning using the training data.

[0044] 7, the display unit 12 may accept, from the user, an operation to expand the second bounding box 622 surrounding the specific signal at the specific time T displayed on the spectrogram view 512 in the time direction of the spectrogram image. In this case, the display unit 12 may accept, from the user, an operation to expand the range in the time direction by, for example, dragging an upper line segment of the second bounding box 622 upward or dragging a lower line segment thereof downward. In this case, in the process of step S104, the output unit 13 may output, as training data, each data set consisting of a combination of a spectrum image for each time bin (specific time unit) included in the expanded time range and the supervised data. In this case, the output unit 13 may output, for example, first training data including a first spectrum image corresponding to a first time point included in the second bounding box expanded in the time direction and the supervised data. Then, the output unit 13 may output, for example, a second spectrum image corresponding to a second time point included in the second bounding box expanded in the time direction, and second teacher data including the supervised answer data.

[0045] This reduces the annotation workload when signals are transmitted continuously in the time direction, such as communication waves. Also, for example, annotation work in the spectrum view 511 is reflected in the spectrogram view 512, and annotation work for multiple pieces of training data can be performed collectively by expanding the range in the time direction in the spectrogram view 512.

[0046] (Example of estimating a specific range containing a specific signal) In the above example, the user specifies a specific range in which a specific signal is included. Alternatively, or in addition, the display unit 12 may estimate the specific range in which the specific signal is included. In this case, the display unit 12 may estimate the specific range based on spectrum data and superimpose a first bounding box corresponding to the estimated specific range on the spectrum image. Then, the display unit 12 may superimpose a second bounding box corresponding to the estimated specific range on the spectrogram image. The received signal may contain many signals to be detected. In this case, manually annotating all the specific signals increases the workload. Therefore, estimating the specific range in which the specific signal is included can reduce the workload on the user.

[0047] In this case, the display unit 12 may first calculate a power value for each frequency bin based on spectrum data of the radio signal received and recorded by the receiving device 20. If the spectrum data indicates that the i-th frequency bin at time t is X i (t), it is assumed that the received power value P i (t) may be calculated using equation (3).

number

number

[0048] The display unit 12 may then generate a histogram of the power values. Fig. 8 shows an example of a histogram of the power values ​​of a received signal according to this embodiment. When the band of the received signal is not congested, the frequency (reception frequency) of power values ​​corresponding to background noise near the noise floor increases. In this case, as shown in Fig. 8, the power level of the specific signal to be detected and the power level of noise are separated on the histogram. The power value at which the frequency value is maximum is set to N0, and a value to which a predetermined value D (margin) is added is set to N. T Then, the power value is N TThe above area is the power value area where a specific signal exists, and the power value is N T The area below this can be considered as an area where background noise exists.

[0049] Therefore, the display unit 12 displays the power value of the bin as N on the spectrum image. T The range in which the specific signal exists may be estimated as the range in which the specific signal exists.

[0050] 9 shows an example of a method for determining the range in which a specific signal exists after determining the power value range in which the specific signal exists according to the embodiment. As shown in FIG. 9, when the power value of each bin is N T Each of the regions 911 to 913 including not only the region exceeding the predetermined number of bins but also the margins of a predetermined number of bins on both sides may be determined as the range in which the specific signal exists.

[0051] The display unit 12 may automatically set and display bounding boxes (frames) on the spectrum image for each of one or more ranges where a specific signal is estimated to exist. The user then checks each estimated bounding box. The user may then fine-tune or delete each bounding box as appropriate. Furthermore, if the user finds a specific signal that has been omitted from the automatic estimation, the user may set (add) a bounding box that includes the omitted specific signal.

[0052] (Example of using machine learning to estimate a specific range containing a specific signal) The display unit 12 may estimate a specific range containing a specific signal by machine learning based on the spectrum image and a trained model. In this case, the display unit 12 may detect a specific signal on the spectrum image using a trained model generated by machine learning using a set of training data created based on previously received wireless signals. In this case, the display unit 12 may use semi-supervised learning, particularly utilizing the idea of ​​the bootstrap method, for example. Note that in this case, it is assumed that a training data set, albeit small in size, has been constructed at least once.

[0053] (others) To perform signal detection using deep learning, it is necessary to prepare training data for generating a learning model. Conventionally, training data is created by, for example, annotation work in which a person manually specifies positions (i.e., coordinates) using application software. Deep learning is generally known to require a large amount of training data, and it is desirable to be able to reduce the effort (load) required to create training data.

[0054] According to the present disclosure, for example, in order to reduce the burden of annotation work for generating teacher data for wireless signal detection, the results of annotation work on either a spectrum image or a spectrogram image can be reflected on the other, thereby reducing the burden of annotation work on spectrum images of wireless signals for generating teacher data.

[0055] <Modification> The information processing device 10 may be a device contained in a single housing, but the information processing device 10 of the present disclosure is not limited to this. Each unit of the information processing device 10 may be realized, for example, by cloud computing configured with one or more computers. Furthermore, the information processing device 10 and the receiving device 20 may be housed in the same housing and configured as an integrated information processing device. Furthermore, at least a portion of the processing of each functional unit of the information processing device 10 may be performed by the receiving device 20. Such information processing devices 10 are also included in examples of the "information processing device" of the present disclosure.

[0056] Although the present disclosure has been described above with reference to the embodiments, the present disclosure is not limited to the above-described embodiments. Various modifications that can be understood by those skilled in the art can be made to the configuration and details of the present disclosure within the scope of the present disclosure. Furthermore, each embodiment can be combined with other embodiments as appropriate.

[0057] Some or all of the above embodiments may also be described as, but are not limited to, the following appendices. Note that some or all of the elements (e.g., configurations and functions) described in each appendix dependent on appendix 1 may also be dependent on independent appendices in other categories in a similar dependency relationship. Some or all of the elements described in any appendix may be applied to various hardware, software, recording means for recording software, systems, and methods. (Appendix 1) a generation unit that generates a spectrum image and a spectrogram image based on spectrum data of the received radio signal; a display unit that displays the spectrum image and the spectrogram image on the same screen, receives from a user a specification of a specific range on either the spectrum image or the spectrogram image that includes a specific signal, and superimposes a first bounding box corresponding to the specific range on the spectrum image and a second bounding box corresponding to the specific range on the spectrogram image; an output unit that outputs teacher data using the information indicating the specific range and the specification information of the specific signal as correct answer data and the spectrum image as an explanatory variable; An information processing device having the above. (Appendix 2) The display unit When the designation of the specific range on the spectrum image is accepted, the second bounding box corresponding to the specific range is superimposed and displayed on the spectrogram image; when the designation of the specific range on the spectrogram image is accepted, a first bounding box corresponding to the specific range is superimposed on the spectrum image. 10. The information processing device according to claim 1. (Appendix 3) the display unit accepts, from the user, an operation to expand the second bounding box in the time direction of the spectrogram image. 3. The information processing device according to claim 1 or 2. (Appendix 4) the output unit outputs first teacher data including a first spectrum image corresponding to a first time point included in the second bounding box expanded in the time direction and the supervised answer data, and outputs second teacher data including a second spectrum image corresponding to a second time point included in the second bounding box expanded in the time direction and the supervised answer data. 4. The information processing device according to claim 3. (Appendix 5) the display unit estimates the specific range based on the spectrum data, superimposes and displays the first bounding box corresponding to the estimated specific range on the spectrum image, and superimposes and displays the second bounding box corresponding to the estimated specific range on the spectrogram image. 3. The information processing device according to claim 1 or 2. (Appendix 6) the display unit estimates the specific range based on the reception power and reception frequency of the received wireless signal. 6. The information processing device according to claim 5. (Appendix 7) The display unit estimates the specific range based on the spectrum image and a trained model. 6. The information processing device according to claim 5. (Appendix 8) The specification information includes at least one of individual information or model information of a transmitter that transmitted the specific signal, attribute information of the specific signal, and a class number to be used for deep learning. 3. The information processing device according to claim 1 or 2. (Appendix 9) generating a spectrum image and a spectrogram image based on spectrum data of the received wireless signal; displaying the spectrum image and the spectrogram image on the same screen; receiving, from a user, designation of a specific range including a specific signal on either the spectrum image or the spectrogram image; superimposing a first bounding box corresponding to the specific range on the spectrum image, and superimposing a second bounding box corresponding to the specific range on the spectrogram image; outputting training data in which the information indicating the specific range and the specification information of the specific signal are used as correct answer data and the spectrum image is used as an explanatory variable; Information processing methods. (Appendix 10) generating a spectrum image and a spectrogram image based on spectrum data of the received wireless signal; displaying the spectrum image and the spectrogram image on the same screen; receiving, from a user, designation of a specific range including a specific signal on either the spectrum image or the spectrogram image; superimposing a first bounding box corresponding to the specific range on the spectrum image, and superimposing a second bounding box corresponding to the specific range on the spectrogram image; outputting training data in which the information indicating the specific range and the specification information of the specific signal are used as correct answer data and the spectrum image is used as an explanatory variable; A program that causes a computer to perform a process. [Explanation of symbols]

[0058] 1. Information Processing Systems 10. Information processing equipment 11 Generation part 12 Display section 13 Output section 20 Receiving device

Claims

1. a generation unit that generates a spectrum image and a spectrogram image based on spectrum data of the received radio signal; a display unit that displays the spectrum image and the spectrogram image on the same screen, receives from a user a specification of a specific range on either the spectrum image or the spectrogram image that includes a specific signal, and superimposes a first bounding box corresponding to the specific range on the spectrum image and a second bounding box corresponding to the specific range on the spectrogram image; an output unit that outputs teacher data using the information indicating the specific range and the specification information of the specific signal as correct answer data and the spectrum image as an explanatory variable; An information processing device having the above.

2. The display unit When the designation of the specific range on the spectrum image is accepted, the second bounding box corresponding to the specific range is superimposed and displayed on the spectrogram image; when the designation of the specific range on the spectrogram image is accepted, a first bounding box corresponding to the specific range is superimposed and displayed on the spectrum image; The information processing device according to claim 1 .

3. the display unit accepts, from the user, an operation to expand the second bounding box in the time direction of the spectrogram image.

3. The information processing device according to claim 1.

4. the output unit outputs first teacher data including a first spectrum image corresponding to a first time point included in the second bounding box expanded in the time direction and the supervised answer data, and outputs second teacher data including a second spectrum image corresponding to a second time point included in the second bounding box expanded in the time direction and the supervised answer data. The information processing device according to claim 3 .

5. the display unit estimates the specific range based on the spectrum data, superimposes and displays the first bounding box corresponding to the estimated specific range on the spectrum image, and superimposes and displays the second bounding box corresponding to the estimated specific range on the spectrogram image.

3. The information processing device according to claim 1.

6. the display unit estimates the specific range based on the reception power and reception frequency of the received wireless signal. The information processing device according to claim 5 .

7. The display unit estimates the specific range based on the spectrum image and a trained model. The information processing device according to claim 5 .

8. The specification information includes at least one of individual information or model information of a transmitter that transmitted the specific signal, attribute information of the specific signal, and a class number to be used for deep learning.

3. The information processing device according to claim 1.

9. generating a spectrum image and a spectrogram image based on spectrum data of the received wireless signal; displaying the spectrum image and the spectrogram image on the same screen; receiving, from a user, designation of a specific range including a specific signal on either the spectrum image or the spectrogram image; superimposing a first bounding box corresponding to the specific range on the spectrum image, and superimposing a second bounding box corresponding to the specific range on the spectrogram image; outputting training data in which the information indicating the specific range and the specification information of the specific signal are used as correct answer data and the spectrum image is used as an explanatory variable; Information processing methods.

10. generating a spectrum image and a spectrogram image based on spectrum data of the received wireless signal; displaying the spectrum image and the spectrogram image on the same screen; receiving, from a user, designation of a specific range including a specific signal on either the spectrum image or the spectrogram image; superimposing a first bounding box corresponding to the specific range on the spectrum image, and superimposing a second bounding box corresponding to the specific range on the spectrogram image; outputting training data in which the information indicating the specific range and the specification information of the specific signal are used as correct answer data and the spectrum image is used as an explanatory variable; A program that causes a computer to perform a process.

Images