Information processing system, information processing device, control method, and program

Abstract

An information processing system (100) extracts a pressure signal and a respiration signal from a detection signal output by a sensor (11) that detects vibrations emitted by the torso of a subject, determines the respiration phase of the subject on the basis of variations in the intensity of the pressure signal, and determines whether or not an abnormal sound is included in sounds related to respiration on the basis of the respiration signal. The information processing system (100) estimates whether an abnormal sound is generated in a breathing phase of an expiration interval or an inspiration interval when the abnormal sound is included in the breath-related sound.

Description

Technical Field

[0001] The present invention relates to an information processing system and the like for detecting vibrations emitted by a subject. Background Art

[0002] Various methods have been developed to measure vibrations emitted by a subject (including sounds related to breathing, heartbeat, etc.). For example, Patent Document 1 describes a technique for non-invasively monitoring one or both of at least one breathing pattern and at least one heartbeat pattern of a subject during sleep.

[0003] Prior art literature

[0004] Patent Literature

[0005] Patent Document 1: Japanese Patent Application Publication No. 2009-501557 Summary of the invention

[0006] Technical problem solved by the invention

[0007] Information related to a disease of the subject is obtained based on the type of abnormal sound (including additional sounds such as crepitus and bubbling sound) included in the sound related to the subject's breathing. In order to determine the type of abnormal sound, it may be important whether the abnormal sound is generated in the exhalation interval or the inhalation interval of the subject's breathing.

[0008] Technical means of solving problems

[0009] In order to solve the technical problem, the information processing system of method 1 of the present invention comprises: a sensor, which detects vibrations emitted by the torso of the subject at a position not in contact with the subject or at a position in contact with the torso of the subject; a signal extraction unit, which extracts a pressure signal and a breathing signal from the detection signal output by the sensor, the pressure signal indicating the pressure applied to the sensor, and the breathing signal indicating the sound related to the breathing of the subject; a breathing phase determination unit, which determines the exhalation interval and the inhalation interval of the subject based on the change in the intensity of the pressure signal; an abnormal sound determination unit, which determines whether the sound related to the breathing contains abnormal sound based on the breathing signal; and an estimation unit, which, when the sound related to the breathing contains abnormal sound, estimates whether the abnormal sound is generated in the exhalation interval or the inhalation interval.

[0010] Effects of the Invention

[0011] According to one aspect of the present invention, it is possible to accurately estimate the breathing phase (expiratory interval or inspiratory interval) in which an abnormal sound included in a sound related to the breathing of a subject occurs. BRIEF DESCRIPTION OF THE DRAWINGS

[0012] [ Figure 1] is a conceptual diagram showing an example of the configuration of an information processing system according to one embodiment of the present invention.

[0013] [ Figure 2 ] is a diagram showing an example of the schematic structure of the information processing device of the information processing system.

[0014] [ Figure 3 ] is a diagram of another example of the schematic structure of the information processing device of the information processing system.

[0015] [ Figure 4 ] is a diagram of another example of the schematic structure of the information processing device of the information processing system.

[0016] [ Figure 5 ] is a functional block diagram showing an example of the configuration of the information processing system.

[0017] [ Figure 6 ] is a diagram illustrating various signals included in the detection signal.

[0018] [ Figure 7 ] is a diagram illustrating the classification of additional sounds included in abnormal sounds and representative cases corresponding to each additional sound.

[0019] [ Figure 8 ] is a flowchart showing an example of the process flow of processing performed by the configuration of the information processing system.

[0020] [ Fig. 9 ] is a diagram showing an example of a display screen displayed on the display unit of the communication device of the information processing system.

[0021] [ Fig.10 ] is a functional block diagram showing a modified example of the configuration of an information processing system.

[0022] [ Fig.11 ] is a functional block diagram showing an example of the configuration of an information processing system according to embodiment 2 of the present invention.

[0023] [ Fig.12 ] is a flowchart representing an example of the process of processing performed by the information processing system.

[0024] [ Fig.13 ] is a diagram showing an example of a display screen displayed on the display unit of the communication device of the information processing system.

[0025] [ Fig.14 ] is a functional block diagram showing a modified example of the configuration of the information processing system.

[0026] [ Fig.15] is a functional block diagram showing other variations of the configuration of the information processing system.

[0027] [ Fig.16 ] is a flowchart showing the process of processing performed by the abnormal sound determination unit of the information processing system according to embodiment 3 of the present invention.

[0028] [ Fig.17 ] is a diagram showing a specific example of the processing performed by the abnormal sound determination unit of the information processing system according to embodiment 3 of the present invention.

[0029] [ Fig.18 ] is a chart showing the results of processing performed by the abnormal sound determination unit of the information processing system according to embodiment 3 of the present invention.

[0030] [ Fig.19 ] is a chart showing the results of processing performed by the abnormal sound determination unit of the information processing system according to embodiment 3 of the present invention.

[0031] [ Fig. 20 ] is a diagram showing a specific example of the processing performed by the abnormal sound determination unit of the information processing system according to embodiment 3 of the present invention.

[0032] [ Fig.21 ] is a diagram showing a specific example of the processing performed by the abnormal sound determination unit of the information processing system according to embodiment 3 of the present invention.

[0033] [ Fig. 22 ] is a diagram showing a specific example of the processing performed by the abnormal sound determination unit of the information processing system according to embodiment 3 of the present invention.

[0034] [ Fig.23 ] is a chart showing the results of processing performed by the abnormal sound determination unit of the information processing system according to embodiment 3 of the present invention. DETAILED DESCRIPTION

[0035] [Implementation Method 1]

[0036] In the following, refer to Figures 1 to 10 An implementation mode of the present invention is described in detail.

[0037] (Overview of Information Processing System 100)

[0038] The information processing system 100 of embodiment 1 of the present disclosure is a system for estimating whether an abnormal sound included in a sound related to the breathing of the subject W1 is generated in the breathing phase of the exhalation interval or the inhalation interval based on a detection signal output by a sensor that detects vibrations emitted from the torso of the subject W1 at a position not in contact with the torso of the subject W1 or at a position in contact with the torso of the subject W1.

[0039] In this specification, the "subject" typically refers to a person who needs to be monitored by a medical worker W2 or the like, such as a bedridden patient. The "detection signal" refers to a signal representing the vibration emitted by the subject W1, which is raw data output from a sensor, or data that has been amplified or denoised. The denoising process can be performed, for example, by filtering the region above 2000 Hz of the raw data. A typical example of the "torso" of the subject W1 is at least one of the chest, abdomen and back of the subject W1, and may be other than these.

[0040] (Configuration of Information Processing System 100)

[0041] First, regarding the configuration of the information processing system 100, use Figure 1 Provide explanation. Figure 1 It is a conceptual diagram showing an example of the configuration of the information processing system 100 .

[0042] like Figure 1 As shown, the information processing system 100 may include an information processing device 1 and a communication device 3. The number of the information processing device 1 and the number of the communication device 3 included in the information processing system 100 may be one or more.

[0043] The information processing device 1 analyzes the detection signal of the sensor 11 (see FIG. 1 ) that detects the vibration generated by the torso of the subject person W1 at a position not in contact with the torso of the subject person W1 or at a position in contact with the torso of the subject person W1. Figure 5 ) outputs a detection signal representing the vibration emitted by the trunk of the subject W1. When the sound related to the breathing of the subject W1 contains an abnormal sound, it is estimated that the abnormal sound is generated in the breathing phase of the exhalation interval or the inhalation interval, and the estimation result is output to the outside.

[0044] The information processing device 1 can output information related to the frequency characteristics of the abnormal sound signal representing the abnormal sound contained in the respiratory signal extracted from the detection signal together with the estimation result to the outside. In addition, the information processing device 1 can output the estimation result of what kind of additional sound the abnormal sound is estimated to be to the outside. In addition, the information processing device 1 can output information related to the health status corresponding to the estimated type of additional sound to the outside. The output destination of the estimation result, etc. is typically the communication device 3. The communication device 3 is typically a computer, a smart phone, a tablet terminal, etc. used by medical workers W2, etc., for example, set in a nurse center.

[0045] The information processing device 1 may further estimate the type of additional sound included in the abnormal sound included in the respiratory signal, and output the estimation result of the type of additional sound to the outside (for example, the communication device 3 ).

[0046] The sensor 11 is set at a position that does not contact the subject W1 or at a position that contacts the torso of the subject W1. The sensor 11 can be set on the bed where the subject W1 lies. The setting position of the sensor 11 can be between the bed and the mattress under the mattress, or between the sheets on the mattress and the mattress. In addition, when the subject W1 is wearing clothes, the setting position of the sensor 11 can be the uppermost surface of the bed. When set at these positions, the sensor 11 is typically preferably formed into a thin plate (sheet), thereby allowing the sensor 11 to be installed in various positions.

[0047] As described above, in the information processing system 100 , the sensor 11 provided at a position not in contact with the subject W1 or in contact with the torso of the subject W1 is used, so the subject W1 does not need to be located in a predetermined detection area or take a predetermined detection posture.

[0048] It should be noted that the information processing device 1 and the communication device 3 can be directly connected, such as Figure 1 As shown, the communication connection can be made through a communication network 9. The communication network 9 is not limited in form and can be a local area network (LAN) or the Internet.

[0049] In addition to the information processing device 1 and the communication device 3, the information processing system 100 may further include a server device (not shown) communicatively connected to the information processing device 1 and the communication device 3. For example, the server device may be configured to store and manage the estimation results transmitted by a plurality of information processing devices 1 for each subject W1. The medical worker W2 or the like can access the server device using the communication device 3 and refer to the estimation results of each subject W1.

[0050] (Configuration of Information Processing Device 1)

[0051] Next, for the appearance and schematic structure of the information processing device 1, refer to Figure 2 to Figure 4 and Figure 6 , and use Figure 5 Provide explanation. Figure 5 It is a functional block diagram showing an example of the configuration of the information processing device 1 .

[0052] like Figure 5 As shown, the information processing device 1 includes a sensor 11 , a control unit 10 , and a storage unit 12 .

[0053] [Sensor 11]

[0054] The sensor 11 is a sensor that can detect vibrations emitted from the torso of the subject person W1 at a position that does not contact the subject person W1 or at a position that contacts the torso of the subject person W1. The type of sensor 11 is not particularly limited. For example, the sensor 11 is a piezoelectric sensor. If a piezoelectric sensor is used as the sensor 11, thinning becomes easy, thereby reducing the possibility of causing discomfort to the subject person. As a piezoelectric sensor, for example, a piezoelectric sensor that generates current for compression deformation, a piezoelectric sensor that generates current for extension deformation, or a piezoelectric sensor that generates current for torsional deformation can be cited. In the case where higher precision detection is desired, as the sensor 11, a piezoelectric sensor that generates current by compression deformation is preferably used. On the other hand, in the case where a low-frequency signal is desired to be detected with higher precision, as the sensor 11, a piezoelectric sensor containing a foam is preferably used.

[0055] The frequency band of the vibration that can be detected by the sensor 11 is preferably wide. This eliminates the need to configure a plurality of sensors having different frequency bands, and makes maintenance and management by the medical worker W2 easier, thereby improving convenience.

[0056] Figure 2 to Figure 4 1 is a diagram showing an example of a schematic configuration of the information processing device 1. Figure 1 As shown in FIG. 1 , the sensor 11 can be set at a position supporting the trunk of the subject W1 lying on the bed. Figure 2 As shown, the sensor 11 is preferably formed into a thin plate (sheet). Figure 3 As shown, the sensor 11 may be provided at a position supporting the trunk of the chair where the subject W1 sits. Thus, the sensor 11 can detect vibrations emitted from the trunk of the subject W1 in a natural posture of lying on a bed or sitting on a chair.

[0057] When the sensor 11 is installed on the bed, the sensor 11 may be installed between the sheet on the mattress and the mattress. In addition, when the subject W1 is wearing clothes, the sensor 11 may be installed on the uppermost surface of the bed.

[0058] In addition, if Figure 4 As shown, the sensor 11 may be provided on clothes worn by the subject W1. Figure 4 5001 represents an example of installing the sensor 11 on clothes. Figure 4 5002 and 5003 of FIG. 1 represent an example of a case where the subject W1 wears clothes provided with the sensor 11. Figure 4 As shown in 5001 of FIG. 5 , the sensor 11 may be provided on the clothes in such a manner that the sensor 11 is located on the chest side of the subject W1 when the subject W1 wears the clothes. Figure 4As shown in 5003 , the sensor 11 may be provided on the clothes so that the sensor 11 is located on the back side of the subject W1 when the subject W1 wears the clothes.

[0059] In addition, when the sensor 11 of the information processing device 1 is provided on the clothes worn by the subject W1, as shown in FIG. Figure 4 As shown in 5003, the sensor 11 can be set on the clothes ( Figure 4 The symbol X1) is composed of the sensor 11 and the trunk ( Figure 4 In this case, the vibration emitted by the subject W1 can be detected without bringing the subject W1 into contact with the sensor 11. In addition, according to the above configuration, even when the subject W1 moves from one place to another, as long as the subject W1 wears clothes equipped with the sensor 11, the vibration emitted by the torso of the subject W1 can be detected.

[0060] The sensor 11 may have one or more detection areas. When the sensor 11 has multiple detection areas, the sensor 11 may output detection signals detected in the multiple detection areas. When the sensor 11 is formed in a thin plate shape, the multiple detection areas may be arranged on the same plane. For example, Figure 2 The information processing device 1 shown in 3001 includes a sensor 11 having a detection area D. Figure 2 The information processing device 1 shown in 3002 includes a sensor 11 having detection areas D1 to D3 arranged in three rows. Figure 2 The information processing device 1 shown in 3003 includes a sensor 11 having detection areas D1a to D3d arranged in four rows and three columns.

[0061] For example, in Figure 2 In the case of the information processing device 1 shown in 3002, the detection signals detected in the detection areas D1 to D3 are output respectively. Figure 3 In the case of the information processing device 1 shown in 3003, the detection signals detected in the detection areas D1a to D3d are outputted respectively. The detection areas D1a to D3d may be, for example, 10 cm square.

[0062] If a configuration including a plurality of detection areas is adopted, the location where the abnormal sound in the breathing signal of the subject W1 is generated can be accurately identified by analyzing the detection signals from the respective detection areas and comparing the analysis results.

[0063] [Control Unit 10 and Storage Unit 12]

[0064] In one example, the control unit 10 may be a CPU (Central Processing Unit). The control unit 10 reads the software stored in the storage unit 12, i.e., the control program, and expands it in a memory such as a RAM (Random Access Memory) to execute various functions. Figure 5 As shown in FIG. 1 , the control unit 10 includes a signal extraction unit 101, a respiratory phase determination unit 102, an abnormal sound determination unit 103, an estimation unit 104, and an output unit 105. Figure 5 In the storage unit 12 shown, illustration of the control program is omitted for simplicity of description.

[0065] The signal extraction unit 101 acquires the detection signal output from the sensor 11 , and extracts a pressure signal indicating the pressure applied to the sensor 11 and a breathing signal indicating the sound related to the breathing of the subject W1 from the acquired detection signal.

[0066] The sensor 11 can detect vibrations in various frequency regions of which the subject W1 is the source. Therefore, the detection signal output from the sensor 11 is a signal in which multiple vibrations with various frequency characteristics overlap with each other. In one example, the sensor 11 can obtain a pressure signal with a frequency of 0.1 Hz to 1 Hz and a breathing signal with a frequency of 20 Hz to 1000 Hz. It should be noted that the pressure signal and the breathing signal can be distinguished based on the frequency component (spectrum).

[0067] In this way, the information processing device 1 can be provided with the sensor 11 having a wide frequency band of detectable vibration. Thus, it is not necessary to configure a plurality of different types of sensors in the information processing device 1, and the maintenance and management of the information processing device 1 by the medical worker W2 or the like using the information processing system 100 becomes easy, thereby improving the convenience of the information processing device 1.

[0068] The signal extraction unit 101 can apply a known method such as frequency separation to the detection signal to extract the pressure signal and the breathing signal from the detection signal. Figure 6 Provide explanation. Figure 6 is a diagram illustrating various signals included in the detection signal. Figure 6 As shown, by frequency separation, a pressure signal and a breathing signal having different frequency characteristics can be extracted from the detection signal.

[0069] The signal extraction unit 101 can extract the breathing signal from the detection signal using a bandpass filter corresponding to each frequency of the additional sound type. As described below, Figure 7 Each frequency of the additional sound type is described in. For example, when extracting bubble sound from the detection signal, it can be extracted using a bandpass filter corresponding to 250 to 500 Hz.

[0070] The signal extraction unit 101 stores the detection signal obtained from the sensor 11 and the pressure signal and the breathing signal extracted from the detection signal in the storage unit 12 (detection signal 121, pressure signal 122 and breathing signal 123). These signals may be stored together with time information indicating the time when the detection signal of the extraction source is detected.

[0071] The respiratory phase determination unit 102 determines the exhalation interval and the inhalation interval of the subject based on the change in the intensity of the pressure signal extracted by the signal extraction unit 101. For example, the respiratory phase can be determined by determining the interval in which the intensity of the pressure signal shows an increasing trend as the inhalation interval and the interval in which the intensity of the pressure signal shows a decreasing trend as the exhalation interval.

[0072] The abnormal sound determination unit 103 determines whether the sound related to breathing includes an abnormal sound based on the breathing signal extracted by the signal extraction unit 101. The abnormal sound determination unit 103 may determine that the sound related to breathing includes an abnormal sound in at least any one of the following (A1) to (A4).

[0073] (A1) The breathing signal has a predetermined frequency characteristic indicating an abnormal sound.

[0074] (A2) Each frequency band of the respiratory signal contains a signal exceeding a predetermined intensity.

[0075] (A3) A signal having an intensity exceeding a predetermined value is included in a frequency band detected during abnormal breathing in the respiratory signal.

[0076] (A4) A ratio of the intensity of a signal in a frequency band detected during normal breathing to the intensity of a signal in a frequency band detected during abnormal breathing in the respiratory signal is equal to or greater than a given threshold.

[0077] The "given frequency characteristics" in (A1) are different frequency characteristics of various additional sounds. Figure 7 As shown, bubbling sound has a frequency characteristic of 250 to 500 Hz, crepitus has a frequency characteristic of 500 to 1000 Hz, wheezing sound has a frequency characteristic of 400 Hz or more, and snoring sound has a frequency characteristic of 200 to 250 Hz. If the respiratory signal has these frequency characteristics, it can be determined that the sound related to breathing contains abnormal sound.

[0078] The "predetermined intensity for each frequency band" in (A2) can be, for example, the signal intensity around 100 Hz in a state where normal breathing sounds of less than 200 Hz are obtained.

[0079] The "frequency band detected during abnormal breathing" in (A3) can be set to, for example, around 200 Hz when normal breathing sounds below 200 Hz are obtained. The "predetermined intensity" can be set to the signal intensity around 100 Hz when normal breathing sounds below 200 Hz are obtained.

[0080] The "given threshold" in (A4) is, for example, the signal strength around 100 Hz when normal breathing sounds of less than 200 Hz are obtained. If a signal strength equal to or greater than the given threshold is detected around 200 Hz, it can be determined that the breathing-related sounds contain abnormal sounds.

[0081] The estimation unit 104 estimates the type of the additional sound based on the determination result of the respiratory phase determination unit 102 or the determination result of the abnormal sound determination unit 103. In the estimation of the type of the additional sound in the estimation unit 104, the type of the additional sound is estimated based on at least one of whether the abnormal sound is included in the exhalation interval or the inhalation interval; the frequency of the abnormal sound signal indicating the abnormal sound, the sound pressure change of the abnormal sound in the exhalation interval or the inhalation interval; and the time interval when the abnormal sound is generated. These estimates are made with reference to the estimation reference 124 stored in the storage unit 12.

[0082] The estimation reference 124 includes information on the characteristics of various additional sounds (generation interval, frequency characteristics, sound pressure change, time interval, etc.).

[0083] Furthermore, the estimating unit 104 may calculate a smoothing strength obtained by smoothing a temporal variation in the strength of a signal in the same frequency band including the frequency of the abnormal sound signal, and estimate the type of the additional sound based on the smoothing strength.

[0084] As an example of smoothing processing, in this embodiment, cumulative averaging is performed. Cumulative averaging can offset and reduce the noise contained in the signal by accumulating and averaging a plurality of measured data. In this embodiment, as the measurement time passes, the smoothing intensity after the intensity of the signal in the same frequency band containing the frequency of the abnormal sound signal is accumulated and averaged can be obtained. In addition, as other examples of smoothing processing, moving averaging can be cited. Through these processes, the type of additional sound can be estimated with good accuracy and good sensitivity.

[0085] The output unit 105 can output the estimation result of the estimation unit 104 and the information related to the health status based on the estimation result to the communication device 3. The outputted information related to the health status may be information acquired through the communication network 9 or may be information stored in the storage unit 12 in advance.

[0086] (Configuration of Communication Device 3)

[0087] Next, regarding the configuration of the communication device 3, use Figure 5 The communication device 3 includes an input unit 31 , a control unit 30 , a storage unit 32 , and a display unit 33 .

[0088] The input unit 31 may be a keyboard, a touch panel, a mouse, etc. The control unit 30 reads the software stored in the storage unit 32, namely the control program, and expands it in a memory such as a RAM to execute various functions. The control unit 30 includes a display control unit 301 that causes the display unit 33 to display various information.

[0089] (Correspondence between additional sounds included in abnormal sounds and diseases)

[0090] Here, accurately estimating the type of additional sound included in the sound related to the breathing of the subject W1 is important for obtaining accurate information on the health status of the subject W1 , and the reason for this will be described with reference to a specific example. Figure 7 The following are diagrams for explaining the classification of additional sounds and representative cases corresponding to various additional sounds.

[0091] Additional sounds are sounds included in abnormal sounds related to breathing. Additional sounds include "rales" and "pleural friction sounds". "Rales" include intermittent rales and continuous rales. Intermittent rales include bubbling sounds and crepitations, and continuous rales include wheezing, snoring, stridor, and squawking. That is, the additional sounds include at least any one of the bubbling sounds, crepitations, wheezing, snoring, stridor, and squawking of the subject W1 and the pleural friction sounds.

[0092] Both bubbling sounds and crepitus are intermittent and have the characteristic of being produced in the inspiratory interval. Snoring sounds are continuous and have the characteristic of being produced in both the expiratory interval and the inspiratory interval. Wheezing sounds are continuous and have the characteristic of being produced in the expiratory interval.

[0093] If bubbling sounds are mixed in the sounds related to the breathing of the subject W1, the subject W1 may suffer from pneumonia, alveolar hemorrhage, heart failure, emphysema, etc., and if crackles are mixed in, the subject W1 may suffer from pneumonia, etc. If wheezing sounds are mixed in the sounds related to the breathing of the subject W1, the subject may suffer from COPD (chronic obstructive pulmonary disease) and bronchial asthma, etc., and if snoring sounds are mixed in, the subject W1 may suffer from chronic bronchitis, etc.

[0094] In this way, if the type of additional sound can be estimated based on the sound related to the breathing of the subject W1, the disease that the subject W1 may suffer from can be estimated and discovered at an early stage. However, in order to accurately diagnose the health status of the subject W1, it is necessary to first accurately estimate the exhalation interval and the inhalation interval of the subject W1 based on the pressure signal and the respiratory signal, and estimate in which respiratory phase the abnormal sound is generated. If the respiratory phase in which the abnormal sound is generated can be estimated, the type of additional sound contained in the sound related to the breathing of the subject W1 can be estimated with high accuracy. If the information processing system 100 of the present invention is adopted, the exhalation interval and the inhalation interval of the subject W1 can be estimated with high accuracy from the pressure signal and the respiratory signal of the subject W1, and it is estimated with high accuracy what kind of additional sound is the abnormal sound contained in the sound related to the breathing of the subject W1. Therefore, medical workers and the like can diagnose the health status of the subject with high accuracy.

[0095] (Processing by Information Processing System 100)

[0096] Next, the flow of processing performed by the information processing system 100 is described using Figure 8 Provide explanation. Figure 8 This is a flowchart showing an example of the flow of processing performed by the information processing system 100 (for example, the information processing device 1 ).

[0097] First, the signal extraction unit 101 extracts a pressure signal and a breathing signal from the detection signal output from the sensor 11 (step S1 ).

[0098] Next, the abnormal sound determination unit 103 determines whether abnormal sounds are included in the sounds related to breathing based on the breathing signal extracted by the signal extraction unit 101 (step S2). If it is determined that abnormal sounds are not included (No in step S2), the process returns to step S1.

[0099] When it is determined that an abnormal sound is included (YES in step S2 ), the estimating unit 104 estimates whether the abnormal sound is generated in the exhalation interval or the inhalation interval based on the pressure signal (step S3 ).

[0100] The estimating unit 104 further estimates the type of additional sound included in the abnormal sound based on the respiratory phase determining unit 102 , the abnormal sound determining unit 103 , and the estimation reference 124 stored in the storage unit 12 (step S4 ).

[0101] The output unit 105 (health status output unit) outputs the type of additional sound estimated by the estimating unit 104 and information on the health status of the subject determined based on the type of additional sound estimated by the estimating unit 104 (step S5 ).

[0102] It should be noted that the information processing system 100 executes Figure 8The timing of each process shown can be set arbitrarily. For example, the information processing system 100 may execute the process every given period (e.g., 1 hour). Figure 8 Each of the processes shown may be executed every time the sensor 11 determines that the subject has left the bed.

[0103] (Display example)

[0104] When the sound related to the breathing of the subject W1 includes an abnormal sound, the information processing device 1 obtains the following (B1) to (B5) from the information processing device 1, and the screen display on the display unit 33 is displayed using Fig. 9 Provide explanation.

[0105] (B1) The result of estimating whether the abnormal sound is generated in the breathing phase of the exhalation interval or the inhalation interval.

[0106] (B2) Respiration signal extracted from the detection signal.

[0107] (B3) shows the frequency characteristics of the abnormal sound signal of the abnormal sound.

[0108] (B4) Result of estimating the type of the additional sound.

[0109] (B5) Information related to health status.

[0110] Fig. 9 1 is a diagram showing an example of a display screen displayed on the display unit 33 of the communication device 3 of the information processing system 100. Fig. 9 As shown, the display unit 33 can display: region R1, which displays the waveform data of the breathing signal of the subject W1; region R2, which displays the spectrogram of the frequency characteristics and intensity of the abnormal sound signal representing the abnormal sound; and region R3, which displays the estimated results of (B1) and (B4) and the information of (B5). Fig. 9 The region R3 shown shows: "Abnormal sound in the exhalation interval: yes (wheezing)" and "Abnormal sound in the inhalation interval: no" as the estimation results of (B1) and (B4), and "Suspected bronchial asthma" as the information of (B5).

[0111] (Modification of the Configuration of Information Processing System 100)

[0112] Fig.10 It is a functional block diagram showing a modified example of the configuration of the information processing system 100 .

[0113] Fig.10 The information processing system 100A shown is Figure 5Compared with the information processing system 100 shown in FIG. 1 , the difference is that the estimation device 2 as an external device includes the estimation unit 104 as the estimation unit 201, wherein the estimation unit 104 is the estimation unit 104 included in the control unit 10 of the information processing device 1, and the control unit 10A of the information processing device 1A does not include the estimation unit 201. The estimation device 2 includes the control unit 20 and the storage unit 22. In addition, the control unit 20 includes the estimation unit 201 and the output unit 205.

[0114] According to the above-described modification, in the information processing device 1A, the output unit 105 outputs the determination results of the respiratory phase determination unit 102 and the abnormal sound determination unit 103 to the estimation device 2 via the communication network 9 .

[0115] The estimating unit 201 refers to the determination result output by the output unit 105 and the estimation reference 221 stored in the storage unit 22 to estimate the type of additional sound and the information on the health status of the subject W1 .

[0116] The output unit 205 outputs the type of additional sound estimated by the estimating unit 201 and information on the health status of the subject W1 to the communication device 3 via the communication network 9 .

[0117] The configuration of the information processing system 100 is not limited. As described above, each unit included in the information processing device 1 may be newly provided as an external device, or may be integrated into one device.

[0118] [Implementation Method 2]

[0119] It should be noted that, for the sake of convenience, components having the same functions as those described in the above embodiments are denoted by the same reference numerals, and their description will not be repeated.

[0120] (Configuration of Information Processing System 100B)

[0121] The information processing system 100B adopts a configuration in which the sensor 11 has a plurality of detection areas and analyzes detection signals detected in the plurality of detection areas (hereinafter, detection signals by area). Fig.11 Provide explanation. Fig.11 It is a functional block diagram showing an example of the configuration of the information processing system 100B.

[0122] like Fig.11As shown, the information processing system 100B may include an information processing device 1B and a communication device 3. The information processing device 1B includes a sensor 11 having a plurality of detection areas, a control unit 10B, and a storage unit 12. The control unit 10B includes a generation site estimation unit 106 in addition to a signal extraction unit 101, a respiratory phase determination unit 102, an abnormal sound determination unit 103, an estimation unit 104, and an output unit 105.

[0123] The generation site estimation unit 106 estimates the generation site of the abnormal sound in the body of the subject W1 based on the breathing signal extracted from each of the detection signals for each region.

[0124] Here, the configuration in which the information processing device 1B includes the generation location estimation unit 106 is described as an example, but the present invention is not limited to this. For example, the communication device 3 or a server device (not shown) may include the generation location estimation unit 106.

[0125] (Processing by Information Processing System 100B)

[0126] Next, the flow of processing performed by the information processing system 100B is described using Fig.12 Provide explanation. Fig.12 This is a flowchart showing an example of the flow of processing performed by the information processing system 100B.

[0127] The signal extraction unit 101 obtains the signal from the detection area (for example, Figure 3 The detection signals for each region are outputted from the detection regions D1 to D4 as shown, and the pressure signal and the breathing signal are extracted from each of the detection signals for each region (step S1a).

[0128] Next, the generation part estimation unit 106 estimates the generation part of the abnormal sound in the body of the subject W1 based on the breathing signal extracted from each of the detection signals for each region (step S6). For example, the generation part estimation unit 106 may determine the position of the detection region that outputs the detection signal for each region from which the breathing signal containing the most abnormal sound is extracted, and estimate the part of the subject's body estimated to be close to the determined position as the abnormal sound generation part.

[0129] Next, the output unit 105 outputs abnormal location information indicating the estimated abnormal sound generation location (step S7).

[0130] With this configuration, the information processing system 100B can measure the breathing signal of the subject W1 with high accuracy and identify the abnormal sound generating part related to the disease of the subject W1. For example, if the output breathing signal and abnormal sound generating part information are provided to medical personnel, the medical personnel can diagnose with high accuracy which part of the body of the subject W1 is likely to have an abnormality in addition to the health status of the subject W1.

[0131] (Display example)

[0132] When the sound related to the breathing of the subject W1 includes an abnormal sound, the information processing device 1B obtains the following (B1) to (B6) from the information processing device 1B, and uses the screen display on the display unit 33 to display the abnormal sound. Fig.13 Provide explanation.

[0133] (B1) The result of estimating whether the abnormal sound is generated in the breathing phase of the exhalation interval or the inhalation interval.

[0134] (B2) Respiration signal extracted from the detection signal.

[0135] (B3) shows the frequency characteristics of the abnormal sound signal of the abnormal sound.

[0136] (B4) Result of estimating the type of the additional sound.

[0137] (B5) Information related to health status.

[0138] (B6) Abnormal site information.

[0139] Fig.13 FIG. 1 is a diagram showing an example of a display screen displayed on the display unit 33 of the communication device 3 of the information processing system 100B. Fig.13 As shown, in the display unit 33, in addition to Fig. 9 In addition to the regions R1 to R3 shown, a region R4 capable of displaying abnormal part information related to the subject in (B6) described above may be displayed. Fig.13 In the example shown, the abnormal sound generation location is indicated by an oval mark M in the figure simulating the front and back of the subject's body in the region R4.

[0140] For example, medical workers can refer to the display on the communication device 3 to make appropriate judgments on the health status of the subject, the type and location of the disease affecting the subject, and the necessity of medical intervention for the subject.

[0141] (Modification of the Configuration of Information Processing System 100B)

[0142] use Fig.14 , Fig.15 A modified example of the configuration of the information processing system 100B will be described.

[0143] Fig.14 This is a functional block diagram showing a modified example of the configuration of the information processing system. Fig.14 The information processing system 100C shown is Fig.11 Compared with the information processing system 100B shown in FIG. 1 , the difference is that the estimation device 2A as an external device has the estimation unit 104 and the generation part estimation unit 106 as the estimation unit 201 and the generation part estimation unit 202, respectively, wherein the estimation unit 104 and the generation part estimation unit 106 are the estimation units 104 and the generation part estimation unit 106 that the control unit 10B of the information processing device 1B has, but the control unit 10C of the information processing device 1C does not have these. The estimation device 2A has the control unit 20A and the storage unit 22. In addition, the control unit 20A has the estimation unit 201 and the output unit 205.

[0144] According to the above-described modification, the output unit 105 in the information processing device 1C outputs the determination results from the respiratory phase determination unit 102 and the abnormal sound determination unit 103 and the respiratory signals extracted from the detection signals for each region to the estimation device 2A via the communication network 9 .

[0145] The output unit 205 in the estimation device 2A outputs the estimation result of the estimation unit 201 , the information on the health status of the subject W1 , and the estimation result of the generation site estimation unit 202 to the communication device 3 via the communication network 9 .

[0146] Fig.15 This is a functional block diagram showing another modified example of the configuration of the information processing system. Fig.15 The information processing system 100D shown in the figure includes an information processing device 1D having a configuration Fig.11 The information processing system 100B shown and Fig.14 The information processing system 100C shown in the figure has all the components. In addition to the sensor 11 , the control unit 10D and the storage unit 12 , the information processing device 1D further includes a display unit 13 .

[0147] The control unit 10D includes a display control unit 107 that causes the display unit 13 to display various information, in addition to the signal extraction unit 101, the respiratory phase determination unit 102, the abnormal sound determination unit 103, the estimation unit 104, the output unit 105, and the generation site estimation unit 106. As an example, the display unit 13 displays Fig.13 The display screen shown.

[0148] The information processing device 1D can communicate with at least one communication device 3 via the communication network 9. For example, the information displayed on the display unit 13 can be displayed on the communication devices 3 such as smartphones and tablet terminals owned by a plurality of medical workers W2.

[0149] Fig.14 The information processing system 100C shown and Fig.15 The configuration of the information processing system 100D shown is an example, and the information processing system is not limited to this configuration. Each unit constituting the information processing system can be arbitrarily provided as an external device.

[0150] [Implementation method 3]

[0151] Hereinafter, another embodiment (Embodiment 3) of the present invention will be described. It should be noted that, for the sake of convenience, components having the same functions as those described in the above embodiment are denoted by the same reference numerals, and their description will not be repeated.

[0152] (Overview of Information Processing System 100E)

[0153] The information processing system 100E according to the third embodiment of the present invention is a system including an abnormal sound determination unit 103A that determines whether or not abnormal sounds are included in sounds related to breathing based on the result of averaging processing of a breathing signal representing sounds related to breathing of the subject W1.

[0154] (Configuration of Information Processing System 100E)

[0155] The information processing system 100E is a system in which the information processing systems 100 to 100D include an abnormal sound determination unit 103A instead of the abnormal sound determination unit 103 of each of the information processing devices 1 to 1D. Hereinafter, the information processing system 100E is described by taking as an example a system in which the information processing device 1 of the information processing system 100 includes the abnormal sound determination unit 103A instead of the abnormal sound determination unit 103.

[0156] (Processing by Abnormal Sound Determination Unit 103A)

[0157] The flow of the processing performed by the abnormal sound determination unit 103A is as follows: Fig.16 Provide explanation. Fig.16 103A is a flowchart showing an example of the flow of processing performed by the abnormal sound determination unit 103A.

[0158] First, the abnormal sound determination unit 103A extracts a first respiratory signal above the first frequency and a second respiratory signal below the second frequency from the detection signal output by the sensor (step S10). Here, the first respiratory signal and the second respiratory signal can be respiratory signals that do not include a frequency band representing the heartbeat of the subject W1. That is, the first frequency can exceed the upper limit value of the frequency representing the heartbeat of the subject W1, and the second frequency can be lower than the lower limit value of the frequency representing the heartbeat of the subject W1. In general, the frequency representing the heartbeat varies according to age, living habits, etc. Therefore, the first frequency and the second frequency can be arbitrarily set according to the age and living habits of the subject W1. For example, with respect to the first frequency, the first frequency can be set to be 3 Hz or more when the subject W1 is a child, 1.5 Hz or more when the subject W1 is an athlete, and 2.0 Hz or more when the subject W1 is an average adult. Regardless of the age and living habits of the subject W1, the second frequency can be set to be 1 Hz or less. This makes it possible to remove the signal indicating the heartbeat frequency from the breathing signal indicating the sound related to the breathing of the subject W1, and to determine the presence or absence of abnormal sound with higher accuracy.

[0159] In addition, in order to remove signals such as vibrations other than sound, the first frequency is preferably 20 Hz or more, and further preferably 60 Hz or more in order to remove signals representing hum. The method of extracting the first respiratory signal and the second respiratory signal is not particularly limited, but in this embodiment, a bandpass filter, a low-pass filter, etc. are used to extract the first respiratory signal and the second respiratory signal. In order to extract the first respiratory signal, a high-pass filter can be used instead of a bandpass filter. In order to prevent aliasing generated in digital processing, a bandpass filter is used in this embodiment.

[0160] It should be noted that the first respiratory signal and the second respiratory signal may correspond to the respiratory signal and the pressure signal extracted in the signal extraction unit 101 .

[0161] Next, the abnormal sound determination unit 103A divides the first respiratory signal extracted in step S10 at given time intervals, and calculates power spectra for each of them (step S11). As an example, the abnormal sound determination unit 103A can divide the first respiratory signal into unit intervals corresponding to the exhalation interval and the inhalation interval determined by the respiratory phase determination unit 102, or unit intervals corresponding to the respiratory intervals combining the exhalation interval and the inhalation interval, and calculate the power spectrum in each of the unit intervals. Therefore, the given time interval for dividing the first respiratory signal can be the time interval of each unit interval, and can be an arbitrarily set time interval. The arbitrarily set time interval is preferably greater than 0.1 seconds and less than 0.8 seconds, and more preferably 0.1 seconds. That is, multiple power spectra can be calculated for one unit interval. It should be noted that the following description takes the case of calculating the power spectrum of the first respiratory signal for each unit interval as an example.

[0162] Next, the abnormal sound determination unit 103A determines a time point as a starting point in the averaging process of the power spectrum of the first respiratory signal described below (step S12). As an example, the abnormal sound determination unit 103A determines a time point as a starting point for each unit interval in the averaging process of the power spectrum of the first respiratory signal based on the second respiratory signal extracted in step S10. At this time, the abnormal sound determination unit 103A can remove a large-amplitude signal having an amplitude greater than a predetermined standard amplitude from the second respiratory signal extracted in step S10. For example, the time point as a starting point can be determined based on changing the large-amplitude signal to the second respiratory signal of the standard amplitude, and the time point as a starting point can be determined based on the second respiratory signal from which the large-amplitude signal has been removed.

[0163] Next, the abnormal sound determination unit 103A performs averaging processing on the power spectrum calculated in step S11 (step S13). As an example, the abnormal sound determination unit 103A matches the time point as the starting point of each unit interval determined in step S12, and performs averaging processing on the power spectrum of the first respiratory signal of each unit interval. At this time, the abnormal sound determination unit 103A can perform processing to remove a large-amplitude signal having an amplitude larger than a predetermined standard amplitude from the first respiratory signal. For example, averaging processing can be performed on the power spectrum of the first respiratory signal in which the large-amplitude signal is changed to the standard amplitude, and averaging processing can be performed on the power spectrum of the first respiratory signal in which the large-amplitude signal is removed. It should be noted that in this averaging processing, the method of averaging the power spectrum of the first respiratory signal is not particularly limited and can be determined arbitrarily. Specific examples of the method of averaging the power spectrum of the first respiratory signal include averaging the power of each frequency on the vertical axis (frequency axis) of the power spectrum, moving average of the power spectrum, or a method using a low-pass filter (low-pass IIR filter).

[0164] Finally, the abnormal sound determination unit 103A determines whether the sound related to the breathing of the subject W1 includes an abnormal sound based on the result of the averaging process of the power spectrum of the first breathing signal (step S14). As an example, the abnormal sound determination unit 103A determines that the sound related to the breathing of the subject W1 includes an abnormal sound when the ratio of the dispersion of the power spectrum to the square of the power average of the first breathing signal is greater than a given threshold.

[0165] In addition to the above-mentioned processing, the abnormal sound determination unit 103A can also perform frequency-based correction processing. Frequency-based correction processing refers to the processing of reducing the time offset in each frequency of the spectrogram that expresses the power spectrum three-dimensionally (frequency × amplitude × time). Specifically, it includes processing of reducing the value after time averaging at each frequency in the display interval of the spectrogram, and processing of removing the offset by applying a high-pass filter on the time axis at each frequency. By performing frequency-based correction processing, noise concentrated on specific frequencies such as AC noise and motor noise can be removed. As a result, changes based on breathing can be made significant in the spectrogram, so it is easy to visually determine whether abnormal sounds are included in the sounds related to breathing.

[0166] In this embodiment, the case where the abnormal sound determination unit 103A of the information processing device 10E performs the above-mentioned processing (steps S10 to S14) is taken as an example, and the subject that performs the above-mentioned processing is not limited to the abnormal sound determination unit 103A. For example, an averaging processing unit may be newly provided, step S10 is performed by the signal extraction unit 101, step S12 is performed by the respiratory phase determination unit 102, steps S11 and S13 are performed by the averaging processing unit, and step S14 is performed by the abnormal sound determination unit 103A.

[0167] Hereinafter, each process of the abnormal sound determination unit 103A will be described in more detail.

[0168] (Calculation of Power Spectrum (Step S11))

[0169] The process of calculating the power spectrum of the first respiratory signal will be described. The power spectrum of the first respiratory signal is calculated by executing the following process.

[0170] (C1) Convert the first respiratory signal into a number series.

[0171] (C2) is made into a signal set.

[0172] (C3) Weighting each element of the signal set by means of a window function.

[0173] (C4) Perform Fourier transform on each element of the signal set.

[0174] (C5) Calculate the power spectrum of each element of the signal set.

[0175] (C6) Remove singular values.

[0176] For each of the processes (C1) to (C6), the first respiratory signal sampled at 44.1 kHz is taken as an example. Fig.17 Provide explanation. Fig.17 This is a diagram for explaining the processing performed to calculate the power spectrum of the first respiratory signal.

[0177] First, the abnormal sound determination unit 103A converts the first respiratory signal sampled at 44.1 kHz into a sequence y(n) (process (C1)).

[0178] Next, a signal set is created from the sequence representing the first respiratory signal (process (C2)). As an example, the signal set created here is a signal set in which the starting point of the sequence y(n) is shifted by a given number. For example, a signal set Y having 8192 elements (about 186 msec) is created, each of which is shifted by 2048 (about 46 msec) from the starting point of the sequence y(n). 8192 .

[0179] Next, each element of the signal set is weighted by a window function (process (C3)). As an example, a signal set WY is obtained after 8192 elements are weighted by a Hanning window function. 8192 . Schematically represents the processing (3), such as Fig.17 The graph showing the first respiratory signal shown in "a" is as follows Fig.17 The value changes as shown in the graph of "b".

[0180] Next, the elements weighted by the window function are subjected to Fourier transform (process (C4)). As an example, the signal set WY is obtained. 8192 CY after Fourier transformation 8192 CY 8192 It is complex data.

[0181] Next, the power spectrum of each element after Fourier transformation is calculated (process (C5)). As an example, CY 8192 The power spectrum P = pow(CY 8192 (n)). Fig.17 The "c" represents the power spectrum of the first respiratory signal P = pow(CY 8192 (n)).

[0182] Finally, a process of removing singular values ​​from the power spectrum of the first respiratory signal may be performed (process (6)). As an example, the singular value is impulsive noise.

[0183] The abnormal sound determination unit 103A can calculate the power spectrum of the first respiratory signal from which the impulse noise has been removed by executing the processes (C1) to (C6).

[0184] (Calculation of the time point as the starting point (step S12))

[0185] The following describes a process for determining a time point that serves as a starting point in the averaging process of the power spectrum of the first respiratory signal based on the second respiratory signal. The time point that serves as a starting point is determined by executing the following process.

[0186] (D1) Convert the second respiratory signal into a number sequence.

[0187] (D2) Downsampling.

[0188] (D3) Apply a digital filter.

[0189] (D4) produces a filter waveform after delay correction.

[0190] (D5) Calculate the time point as the starting point.

[0191] Each of the processes (D1) to (D5) will be described by taking the second respiratory signal sampled at 44.1 kHz as an example.

[0192] First, the abnormal sound determination unit 103A converts the second respiratory signal sampled at 44.1 kHz into a sequence x(n) (processing (D1)).

[0193] Next, the abnormal sound determination unit 103A performs downsampling to reduce the amount of data (processing (D2)). As an example, the sampling interval N 2048 (about 46 msec) The second respiratory signal is resampled.

[0194] Next, a digital filter is applied to the sequence x(n) representing the second respiratory signal after downsampling (processing (D3)). As an example, an IIR filter is applied to the sequence x(n).

[0195] Next, a filter waveform is created that corrects the delay of the sequence x(n) representing the second breathing signal to which the digital filter is applied (processing (D4)). Usually, when a signal is filtered, a delay occurs. With respect to the sequence x(n) representing the second breathing signal, a deviation occurs from the sound representing the actual breathing of the subject W1 by applying the digital filter of the processing (D3). In this processing, a filter waveform is created that corrects this deviation.

[0196] Next, based on the delay-corrected filtered waveform, a time point is determined as the starting point in the averaging process of the power spectrum of the first respiratory signal (processing (D5)). Here, the time point as the starting point can be any point in the respiratory phase in the filtered waveform representing the second respiratory signal, and must be a moment of the same phase in the respiratory phase. Therefore, in the present embodiment, the delay correction of the filtered waveform after applying IIR filtering to the second respiratory signal is performed, and the moment corresponding to the extreme value in the waveform after the delay correction is determined as the starting point. It should be noted that in processing D3, when applying FIR filtering to the second respiratory signal and using an asymmetric waveform, the moment corresponding to the amplitude value of 0 can be used as the starting point. However, it is necessary to select either the point where the amplitude changes from negative to positive or the point where the amplitude changes from positive to negative.

[0197] (specific example)

[0198] In the following, a specific example of the power spectrum of the first respiratory signal output by the abnormal sound determination unit 103A and the power spectrum of the first respiratory signal after the averaging process is performed is described using Fig.18 and Fig.19 Provide explanation.

[0199] Fig.18 is the power spectrum P=pow(CY 8192 (n)) is a spectrum (spectrogram) of the 100th to 350th data. In this spectrum, the vertical axis represents the density of the power spectrum, the horizontal axis represents the frequency, and the lightness and darkness represent the amplitude. Fig.18 As shown in FIG. 1 , when the power spectrum of the first respiratory signal is averaged and then corrected based on the frequency (see FIG. 1 ), Fig.18 ), a band-shaped signal synchronized with the breathing of the subject W1 can be confirmed.

[0200] Fig.19 A spectrum diagram showing a case where an averaging process is performed on the power spectrum of the first respiratory signal. Fig.19 In the example, the averaging process is performed using a first-order low-pass IIR filter designed with different averaging parameters α. Here, the averaging parameter α refers to the pole of the first-order low-pass IIR filter. In other words, it represents the cutoff frequency of the first-order low-pass IIR filter, that is, the point where the transfer function becomes ∞. When the value of such averaging parameter α is 0, it means no averaging, and when the value of averaging parameter α is 1, it means that everything is averaged. Fig.19 As shown, the closer the value of the averaging parameter α is to 1, the more a band-shaped signal synchronized with the breathing of the subject W1 can be confirmed.

[0201] (Modification of Abnormal Sound Determination Unit 103A)

[0202] The abnormal sound determination unit 103A may perform a linear combination process of the power spectrum of the first respiratory signal subjected to n-th power averaging (n is a natural number greater than 2) in addition to averaging the power spectrum of the first respiratory signal in the averaging process S12. As an example, the abnormal sound determination unit 103A calculates the power spectrum of the first respiratory signal subjected to n-th power averaging (n is a natural number greater than 2) for each unit interval. <pow(w) 2 >-<pow(w)> 2 The dispersion of the power spectrum of the first respiratory signal represented by <pow(w) 2 >-2<pow(w)> 2 .

[0203] (Calculation method)

[0204] for <pow(w) 2 >-<pow(w)> 2 or <pow(w) 2 >-2<pow(w)> 2 The value of is calculated using Figure 20 to Figure 22 Provide explanation. Figure 20 to Figure 22 The calculation method is shown assuming that the first respiratory signal is a pulse sequence, which generates multiple pulses Af(t) with the same waveform and pulse width Δt only during the time Te in the period Tr. Here, A is the amplitude of the pulse. The timing of generation is random during the period Te, and is generated at an average density of n (pulse / sec). In addition, the start time of Te is set to τ m .

[0205] Assume that the first respiratory signal is at time t n (n=1,2·) observed pulse f(tt n ). In this case, if Figure 20 to Figure 22 As shown, the calculation is performed according to the following process <pow(w) 2 >-<pow(w)> 2 or <p ow(w) 2 >-2<pow(w)> 2 The value of .

[0206] (E1) Perform Fourier transform on the pulse sequence representing the first respiratory signal (Equation 1).

[0207] (E2) Calculate the energy in the Fourier interval (Equation 2 to Equation 3).

[0208] (E3) Calculate the average energy and the square average energy in the Fourier interval (Formula 4 to Formula 8).

[0209] (E4) Based on the energy in the Fourier interval, the power average and the square average of the power of the power spectrum are calculated (Formula 9 to Formula 10').

[0210] (E5) Calculation <pow(w) 2 >-<pow(w)> 2 or <pow(w) 2 >-2<pow(w)> 2 The value of (Equation 11 to Equation 15).

[0211] The power spectrum of the breathing signal representing the crepitus and the normal sound is calculated using the above calculation method. <pow(w) 2 >-<pow(w)> 2 That is, the value of V(pow(w)) and <pow(w) 2 >-2<pow(w)> 2 That is, the value of U(pow(w)) is obtained by using Fig.23 Provide explanation. Fig.23 is a diagram showing the results of applying the above calculation method to the models of crepitus and normal sound. Fig.23 In the figure, case 1 shows a case where a respiratory signal including a small number of pulses with large amplitude represents a crepitus sound, and case 2 shows a case where a respiratory signal including a large number of pulses with small amplitude represents a normal sound.

[0212] like Fig.23 As shown, it represents the average square of the power spectrum of case1 and case2<pow(w)> 2 The value of is the same value. That is, in the averaging of the power spectrum of the respiratory signal, it is difficult to distinguish between the crepitus and the normal sound. However, when the values ​​of V(pow(w)) and U(pow(w)) of case 1 and case 2 are compared, V(p ow(w)) is 10 times, and U(pow(w)) is about 100 times, which are different values. Therefore, the crepitus and the normal sound can be distinguished by comparing the values ​​of V(p ow(w)) or U(pow(w)).

[0213] Therefore, the abnormal sound determination unit 103A can calculate the power spectrum of the first respiratory signal by <pow(w) 2 >-<pow(w)> 2 The value and <pow(w) 2 >-2<pow(w)> 2 The values ​​of are respectively calculated from the power spectrum of the breathing signal representing normal sound <pow(w) 2 >-<pow(w)> 2 The value and <pow(w) 2 >-2<pow(w)> 2By comparing the values, it is possible to more accurately determine whether the sound related to the breathing of the subject W1 contains abnormal sounds.

[0214] [Variation of the Information Processing System]

[0215] The execution subject of each process described in each embodiment is arbitrary and is not limited to the examples described. For example, Figure 8 and Fig.12 Each step (control method) shown can be executed by one or more information processing devices. Figure 8 and Fig.12 The steps (control methods) shown may be entirely executed by one information processing device, or may be executed in a shared manner by a plurality of information processing devices.

[0216] [Software-based implementation example]

[0217] As for the functions of the information processing system 100, 100A~100D (hereinafter referred to as the "system"), the information processing device 1, 1A~1D and the inference device 2, 2A (hereinafter referred to as the "device"), it is a program for enabling the computer to function as the system and the device, which can be achieved by a program for enabling the computer to function as the system and the various control blocks of the information processing device 1 (especially the various parts included in the control part).

[0218] In this case, the system and the device include a computer as hardware for executing the program, and the computer has at least one control device (e.g., a processor) and at least one storage device (e.g., a memory). The program is executed by the control device and the storage device, thereby realizing each function described in each embodiment.

[0219] The program may be non-temporary and recorded in one or more computer-readable recording media. The recording medium may or may not be provided by the device. In the latter case, the program may be provided to the device via any transmission medium, whether wired or wireless.

[0220] In addition, part or all of the functions of each control block can be implemented by a logic circuit. For example, an integrated circuit having a logic circuit that functions as each control block is also included in the scope of the present invention. In addition, the functions of each control block can also be implemented by, for example, a quantum computer.

[0221] In addition, each process described in each embodiment may be executed by AI (Artificial Intelligence). In this case, AI may be executed in the control device or in another device (for example, an edge computer or a cloud server).

[0222] [Additional Notes]

[0223] The present invention is not limited to the above-described embodiments, and various modifications can be made within the scope of the claims. Embodiments obtained by appropriately combining technical means disclosed in different embodiments are also included in the technical scope of the present invention.

[0224] [Summarize]

[0225] As described above, the information processing system of mode 1 of the present invention comprises: a sensor, which detects vibrations emitted from the torso of the subject at a position not in contact with the subject or at a position in contact with the torso of the subject; a signal extraction unit, which extracts a pressure signal and a breathing signal from the detection signal output by the sensor, the pressure signal indicating the pressure applied to the sensor, and the breathing signal indicating the sound related to the breathing of the subject; a breathing phase determination unit, which determines the exhalation interval and the inhalation interval of the subject based on the change in the intensity of the pressure signal; an abnormal sound determination unit, which determines whether the sound related to the breathing contains abnormal sound based on the breathing signal; and an estimation unit, which estimates whether the abnormal sound is generated in the exhalation interval or the inhalation interval when the sound related to the breathing contains abnormal sound.

[0226] When a subject's body has some abnormality, the sound related to the subject's breathing may contain abnormal sound. It is known that there are multiple types of abnormal sound that may be contained in the sound related to breathing, and the type of abnormality in the subject's body can sometimes be determined based on the type of abnormal sound.

[0227] Breathing has breathing phases such as an inhalation interval in which air is taken into the lungs and an exhalation interval in which air is expelled from the lungs. If the breathing phase in which an abnormal sound is generated can be identified, the type of the abnormal sound can be accurately identified.

[0228] According to the above configuration, the information processing system extracts a pressure signal and a breathing signal from a detection signal output by a sensor that detects vibrations emitted from the subject's trunk. The information processing system determines the subject's breathing phase (expiratory interval and inspiratory interval) based on the change in the intensity of the pressure signal, and determines whether the sound related to breathing includes an abnormal sound based on the breathing signal. If the sound related to breathing includes an abnormal sound, the information processing system estimates whether the abnormal sound is generated in the exhalation interval or the inhalation interval.

[0229] Thus, the information processing system can accurately estimate the breathing phase that produces the abnormal sound included in the sound related to the breathing of the subject based on the detection signal output from the sensor that detects the vibration emitted from the torso of the subject. For example, a medical worker can determine the type of abnormal sound included in the sound related to the breathing of the subject based on the estimation result of the information processing system, and judge the type of abnormality produced in the body of the subject.

[0230] In the information processing system of mode 2 of the present invention, in mode 1, the abnormal sound determination unit determines that the sound related to the breathing contains the abnormal sound in at least any one of the following cases: a case where each frequency band of the breathing signal contains a signal exceeding a predetermined intensity; a case where a predetermined frequency band in the breathing signal contains a signal exceeding a predetermined intensity; and a case where the ratio of the intensity of the signal in the frequency band detected during normal breathing in the breathing signal to the intensity of the signal in the predetermined frequency band is above a given threshold.

[0231] According to the above configuration, the information processing system uses at least one of the frequency characteristics of the subject's breathing signal, the strength of the breathing signal, and the ratio of the breathing signal during normal breathing to the signal in a predetermined frequency band to determine the presence or absence of abnormal sounds. Thus, the information processing system can correctly determine the abnormal sounds included in the sounds related to breathing.

[0232] In the information processing system of aspect 3 of the present invention, in aspect 1 or 2, the abnormal sound may include an additional sound, and the estimating unit may estimate the type of the additional sound based on whether the abnormal sound is included in the exhalation interval or the inhalation interval.

[0233] According to the above configuration, the type of additional sound is estimated based on whether the abnormal sound is included in the exhalation interval or the inhalation interval. In addition to the sound related to breathing, the type of additional sound can be estimated with high accuracy by considering whether it is generated in the exhalation interval or the inhalation interval.

[0234] In the information processing system according to aspect 4 of the present invention, in aspect 3, the estimating unit may estimate the type of the additional sound based on the frequency of an abnormal sound signal indicating the abnormal sound.

[0235] The additional sound has different frequency characteristics depending on the type. According to the above configuration, the type of the additional sound can be estimated with higher reliability based on the frequency of the abnormal sound signal indicating the abnormal sound.

[0236] In the information processing system of mode 5 of the present invention, in any one of modes 1 to 4, the estimation unit calculates a smoothing strength obtained by smoothing the time variation of the strength of a signal in the same frequency band including the frequency of the abnormal sound signal, and estimates the type of the additional sound based on the smoothing strength.

[0237] By performing a smoothing process on the intensity of a signal in a given frequency band including the frequency of the abnormal sound signal, noise included in the signal can be offset and reduced. According to the above configuration, the information processing system can estimate the type of additional sound with high accuracy and high sensitivity.

[0238] In the information processing system of aspect 6 of the present invention, in any of aspects 3 to 5, the estimating unit estimates the type of the additional sound based on a change in sound pressure of the abnormal sound in the exhalation interval or the inhalation interval and a time interval at which the abnormal sound is generated.

[0239] For example, bubbling sounds are low-pitched sounds such as "gurgle gurgle" and "buzzbuzz", and crepitus sounds are high-pitched sounds such as "barblick creak". Both bubbling sounds and crepitus sounds are intermittent and have the characteristic of being produced in the inspiratory interval. Snoring sounds are low-pitched sounds such as "buzzle buzzle", which are continuous and have the characteristic of being produced in both the expiratory interval and the inspiratory interval. Wheezing sounds are high-pitched sounds such as "beep", which are continuous and have the characteristic of being produced in the expiratory interval. That is, depending on the type of additional sound, (1) whether it is produced in the expiratory interval or the inspiratory interval is different, and (2) the time interval of production (i.e., continuity or intermittency) is different.

[0240] According to the above configuration, the information processing system estimates the type of the additional sound based on the change in sound pressure of the abnormal sound in the exhalation interval or the inhalation interval and the time interval at which the abnormal sound is generated. Thus, the information processing system can estimate the type of the additional sound with high accuracy.

[0241] The information processing system of mode 7 of the present invention may further include, in any of modes 3 to 6, a health status output unit that outputs information related to the health status of the subject, wherein the health status of the subject is determined based on the estimated type of the additional sound.

[0242] According to the above configuration, the information processing system can output information about the health status related to the generation of additional sounds (for example, information about diseases or lesions) to the subject. For example, a medical worker who refers to the output health information can start medical intervention for the subject as soon as possible.

[0243] In the information processing system according to aspect 8 of the present invention, in any one of aspects 1 to 7, a frequency of the pressure signal may be greater than or equal to 0.1 Hz and less than or equal to 1 Hz.

[0244] According to the above configuration, the pressure signal can be extracted from the detection signal based on the frequency characteristics.

[0245] In the information processing system according to aspect 9 of the present invention, in any one of aspects 1 to 8, the frequency of the respiratory signal may be greater than or equal to 20 Hz and less than or equal to 1000 Hz.

[0246] According to the above configuration, the breathing signal can be extracted from the detection signal based on the frequency characteristics.

[0247] The information processing system of mode 10 of the present invention can be in any of the modes 1 to 9, wherein the sensor for detecting the vibration at a position not in contact with the subject person is arranged at: a position in the clothes worn by the subject person where the clothes are clamped by the sensor and the torso; or a position on the bed where the subject person is lying or on the chair where the subject person is sitting, where the torso is supported.

[0248] According to the above configuration, the sensor can detect vibrations emitted from the torso of the subject at a position not in contact with the subject or at a position in contact with the torso of the subject. That is, the subject does not need to be located in a given detection area and does not need to take a given detection posture. For example, when the subject is leaning on a chair or lying on a bed while wearing clothes, the subject is naturally close to the sensor, so the vibrations emitted from the torso of the subject can be detected with good accuracy.

[0249] The information processing system according to aspect 11 of the present invention may be configured as any one of aspects 1 to 10, wherein the trunk includes at least a chest of the subject.

[0250] According to the above configuration, vibrations generated from the respirator of the subject person can be detected with higher accuracy.

[0251] The information processing system according to aspect 12 of the present invention may be any one of aspects 1 to 11, wherein the sensor is in the form of a thin plate.

[0252] According to the above configuration, the sensor can be attached to various positions, for example, the sensor can be attached to clothes worn by the subject.

[0253] The information processing system according to aspect 13 of the present invention may be any one of aspects 1 to 12, wherein the sensor includes a piezoelectric sensor.

[0254] According to the above configuration, the sensor can be easily thinned, so the possibility of causing discomfort to the subject can be reduced.

[0255] The information processing system of mode 14 of the present invention may be in any one of modes 1 to 13, wherein the sensor has a plurality of detection areas for outputting the detection signal, and the signal extraction unit extracts the pressure signal and the breathing signal from the detection signals output by each detection area of ​​the plurality of detection areas.

[0256] According to the above configuration, the information processing system extracts the pressure signal and the breathing signal from the detection signals outputted by each detection area of ​​the plurality of detection areas. Thus, the information processing system can detect the vibration emitted from the trunk of the subject in the detection area near the place where the vibration is generated. Therefore, the information processing system can detect the vibration emitted from the trunk of the subject with better accuracy.

[0257] The information processing system of aspect 15 of the present invention may further include, in aspect 14, a site estimation unit that estimates a site where the abnormal sound is generated in the body of the subject based on the breathing signal extracted from each of the detection signals for each region.

[0258] According to the above configuration, the information processing system estimates the abnormal sound generating part in the subject's body based on the breathing signal extracted from the detection signals for each region, thereby being able to estimate which part of the subject's body is likely to have an abnormality (eg, inflammation).

[0259] In the information processing system of aspect 16 of the present invention, in any one of aspects 3 to 7, the signal extraction unit may extract the breathing signal from the detection signal using a bandpass filter corresponding to each frequency of the type of the additional sound.

[0260] Since the additional sound has a unique frequency characteristic depending on the type, the breathing signal can be extracted from the detection signal by using a bandpass filter corresponding to each frequency of the type of additional sound.

[0261] The information processing device of the embodiment 17 of the present invention comprises: a signal extraction unit, which extracts a pressure signal and a breathing signal from a detection signal output by a sensor, wherein the sensor detects vibrations emitted from the trunk of the subject at a position not in contact with the subject or at a position in contact with the trunk of the subject, the pressure signal represents the pressure applied to the sensor, and the breathing signal represents the sound related to the breathing of the subject; a breathing phase determination unit, which determines the exhalation interval and the inhalation interval of the subject based on the change in the intensity of the pressure signal; an abnormal sound determination unit, which determines whether the sound related to the breathing includes an abnormal sound based on the breathing signal; and an estimation unit, which estimates whether the abnormal sound is generated in the exhalation interval or the inhalation interval when the sound related to the breathing includes an abnormal sound. According to this configuration, the same effect as the information processing system of the embodiment 1 is exerted.

[0262] The information processing device of mode 18 of the present invention comprises: a signal extraction unit, which extracts a pressure signal and a breathing signal from a detection signal output by a sensor, wherein the sensor detects vibrations emitted from the trunk of a subject at a position not in contact with the subject or at a position in contact with the trunk of the subject, wherein the pressure signal represents pressure applied to the sensor, and the breathing signal represents sound related to the breathing of the subject; a breathing phase determination unit, which determines an exhalation interval and an inhalation interval of the subject based on changes in the intensity of the pressure signal; and an abnormal sound determination unit, which determines whether the sound related to the breathing includes an abnormal sound based on the breathing signal, and the information processing device further comprises:

[0263] The output unit outputs a determination result based on the breathing phase determination unit and a determination result based on the abnormal sound determination unit to an external device having an estimation unit, wherein the estimation unit estimates whether the abnormal sound is generated in the exhalation interval or the inhalation interval when the sound related to the breathing includes the abnormal sound. According to this configuration, the same effect as the information processing system of the embodiment 1 is achieved.

[0264] The control method of mode 19 of the present invention is a control method executed by one or more information processing devices, and includes: a signal extraction step, which extracts a pressure signal and a breathing signal from a detection signal output by a sensor, wherein the sensor detects vibrations emitted by the trunk of the subject at a position not in contact with the subject or at a position in contact with the trunk of the subject, the pressure signal represents the pressure applied to the sensor, and the breathing signal represents the sound related to the breathing of the subject; a breathing phase determination step, which determines the exhalation interval and the inhalation interval of the subject based on the change in the intensity of the pressure signal; an abnormal sound determination step, which determines whether the sound related to the breathing includes an abnormal sound based on the breathing signal; and an estimation step, which estimates whether the abnormal sound is generated in the exhalation interval or the inhalation interval when the sound related to the breathing includes an abnormal sound. According to this configuration, the same effect as the information processing system of mode 1 is exerted.

[0265] The program of aspect 20 of the present invention is a program for controlling a computer as the information processing system of aspect 1, wherein the program is used to make the computer function as the signal extraction unit, the respiratory phase determination unit, the abnormal sound determination unit, and the estimation unit. According to this configuration, the same effect as the information processing system of aspect 1 is achieved.

[0266] In the information processing system of mode 21 of the present invention, in any one of modes 1 to 18, the abnormal sound determination unit calculates the power spectrum of the first breathing signal above the first frequency contained in the detection signal for the unit intervals corresponding to the exhalation interval and the inhalation interval respectively, or the unit intervals corresponding to the breathing intervals formed by merging the exhalation interval and the inhalation interval, and the abnormal sound determination unit determines, for each unit interval, a time point as a starting point in the averaging processing of the power spectrum based on the second breathing signal below the second frequency contained in the breathing signal, and the abnormal sound determination unit determines whether the sound related to the breathing contains abnormal sound based on the result of the averaging processing, and the result of the averaging processing is obtained by performing the averaging processing on each of the unit intervals in a manner matching the starting point in the power spectrum.

[0267] According to the above configuration, since the signal of an unnecessary frequency band is removed from the breathing signal and the averaging process is performed, it is possible to determine with higher accuracy whether or not the sound related to the breathing of the subject includes an abnormal sound.

[0268] In the information processing system of mode 22 of the present invention, in mode 21, the judgment processing, in the averaging processing, determines that the sound related to the breathing contains abnormal sound when the ratio of the dispersion of the power spectrum to the square of the power average value of the first respiratory signal is greater than a given threshold.

[0269] According to the above configuration, it is possible to determine with high accuracy whether an abnormal sound is included, and to distinguish between similar abnormal sounds.

[0270] The information processing system of mode 23 of the present invention, in mode 21, when at least either one of the first respiratory signal and the second respiratory signal includes a large-amplitude signal having an amplitude greater than a predetermined standard amplitude, changes the amplitude of the large-amplitude signal to the standard amplitude and performs the averaging processing.

[0271] According to the above configuration, complicated processing can be simplified. Thus, it is possible to determine with high accuracy whether or not the sound related to the subject's breathing includes an abnormal sound, and the determination can be performed efficiently.

[0272] The information processing system of mode 24 of the present invention, in mode 21, removes the large amplitude signal from the unit section and performs the averaging process when at least either the first respiratory signal or the second respiratory signal includes a large amplitude signal having an amplitude greater than a predetermined standard amplitude.

[0273] According to the above configuration, complicated processing can be simplified. Thus, it is possible to determine with high accuracy whether or not the sound related to the subject's breathing includes an abnormal sound, and the determination can be performed efficiently.

[0274] The information processing system of mode 25 of the present invention determines in mode 21 whether the sound related to the breathing includes abnormal sound based on the value calculated by the linear combination of the power spectrum subjected to n-th power averaging operation, where n is a natural number greater than 2.

[0275] According to the above configuration, even a breathing signal that cannot be distinguished from a normal sound by averaging processing can be determined with high accuracy.

[0276] Explanation of symbols

[0277] 1, 1A, 1B, 1C, 1D Information processing device

[0278] 2.2A Presumption Device

[0279] 3 communication device

[0280] 11 Sensors

[0281] 100, 100A, 100B, 100C, 100D Information Processing System

[0282] 101 Signal Extraction Unit

[0283] 102 Respiratory phase determination unit

[0284] 103 Abnormal sound determination unit

[0285] 104, 201 Presumption Department

[0286] 105, 205 Output unit (health status output unit)

[0287] 106, 202 Producing site estimation unit

Claims

1. An information processing system comprising: a sensor that detects vibrations emitted by a torso of a subject person at a position not in contact with the torso of the subject person or at a position in contact with the torso of the subject person; a signal extraction unit that extracts a pressure signal and a breathing signal from the detection signal output by the sensor, the pressure signal indicating the pressure applied to the sensor and the breathing signal indicating a sound related to the breathing of the subject; a respiratory phase determination unit that determines an exhalation interval and an inhalation interval of the subject based on a change in the intensity of the pressure signal; an abnormal sound determination unit that determines whether the sound related to the breathing includes an abnormal sound based on the breathing signal; and The estimating unit estimates, when the sound related to the breathing includes an abnormal sound, whether the abnormal sound is generated in the exhalation interval or the inhalation interval.

2. The information processing system according to claim 1, wherein: The abnormal sound determination unit determines that the abnormal sound is included in the breathing-related sound in at least any one of the following cases: The breathing signal has a predetermined frequency characteristic; A situation in which each frequency band of the respiratory signal contains a signal exceeding a predetermined strength; A situation in which a predetermined frequency band in the respiratory signal contains a signal exceeding a predetermined intensity; and When the ratio of the intensity of the signal in the frequency band detected during normal breathing in the respiratory signal to the intensity of the signal in the predetermined frequency band is greater than or equal to a predetermined threshold value.

3. The information processing system according to claim 1, wherein: The abnormal sound includes additional sound. The estimating unit estimates the type of the additional sound based on whether the abnormal sound is included in the exhalation interval or the inhalation interval.

4. The information processing system according to claim 3, wherein: The estimating unit estimates the type of the additional sound based on the frequency of the abnormal sound signal indicating the abnormal sound.

5. The information processing system according to claim 4, wherein: The estimating unit calculates a smoothing strength obtained by smoothing a temporal variation in the strength of a signal in a same frequency band including a frequency of the abnormal sound signal. The estimating unit estimates the type of the additional sound based on the smoothing intensity.

6. The information processing system according to claim 3, wherein: The estimating unit estimates the type of the additional sound based on a change in sound pressure of the abnormal sound in the exhalation interval or the inhalation interval and a time interval at which the abnormal sound is generated.

7. The information processing system according to claim 3, further comprising: A health status output unit outputs information on the health status of the subject, the health status of the subject being determined based on the estimated type of the additional sound.

8. The information processing system according to claim 1, wherein: The frequency of the pressure signal is greater than or equal to 0.1 Hz and less than or equal to 1 Hz.

9. The information processing system according to claim 1, wherein: The frequency of the breathing signal is greater than or equal to 20 Hz and less than or equal to 1000 Hz.

10. The information processing system according to claim 1, wherein: The sensor for detecting the vibration at a position not in contact with the subject is disposed at: A position in the clothing worn by the subject at which the clothing is sandwiched between the sensor and the torso; or A position on a bed where the subject lies or a chair where the subject sits, supporting the trunk.

11. The information processing system according to claim 1, wherein: The torso includes at least a chest of the subject.

12. The information processing system according to claim 1, wherein: The sensor is in the shape of a thin plate.

13. The information processing system according to claim 1, wherein: The sensor comprises a piezoelectric sensor.

14. The information processing system according to claim 1, wherein: The sensor includes a plurality of detection areas for outputting the detection signal. The signal extraction unit extracts the pressure signal and the breathing signal from each of the detection signals for each region output from each of the plurality of detection regions.

15. The information processing system according to claim 14, further comprising: A generation site estimation unit estimates an abnormal sound generation site in the body of the subject based on the breathing signal extracted from each of the region-by-region detection signals.

16. The information processing system according to claim 3, wherein: The signal extraction unit extracts the breathing signal from the detection signal using a bandpass filter corresponding to each frequency of the type of additional sound.

17. An information processing device comprising: a signal extraction unit that extracts a pressure signal and a breathing signal from a detection signal output by a sensor that detects vibrations emitted from a torso of a subject person at a position that does not contact the subject person or at a position that contacts the subject person's torso, the pressure signal indicating pressure applied to the sensor, and the breathing signal indicating sound related to the subject person's breathing; a respiratory phase determination unit that determines an exhalation interval and an inhalation interval of the subject based on a change in the intensity of the pressure signal; an abnormal sound determination unit that determines whether the sound related to the breathing includes an abnormal sound based on the breathing signal; and The estimating unit estimates, when the related sound includes an abnormal sound, whether the abnormal sound is generated in the exhalation interval or the inhalation interval.

18. An information processing device comprising: a signal extraction unit that extracts a pressure signal and a breathing signal from a detection signal output by a sensor that detects vibrations emitted from a torso of a subject person at a position that does not contact the subject person or at a position that contacts the subject person's torso, the pressure signal indicating pressure applied to the sensor, and the breathing signal indicating sound related to the subject person's breathing; a respiratory phase determination unit that determines an exhalation interval and an inhalation interval of the subject based on a change in the intensity of the pressure signal; and an abnormal sound determination unit that determines whether the sound related to the breathing includes an abnormal sound based on the breathing signal, The information processing device further comprises: An output unit outputs a determination result based on the respiratory phase determination unit and a determination result based on the abnormal sound determination unit to an external device having an estimation unit, wherein the estimation unit estimates whether the abnormal sound is generated in the exhalation interval or the inhalation interval when the sound related to the breathing includes an abnormal sound.

19. A control method performed by one or more information processing devices, comprising: a signal extraction step of extracting a pressure signal and a breathing signal from a detection signal output by a sensor, wherein the sensor detects vibrations emitted by a torso of the subject at a position not in contact with the subject or at a position in contact with the torso of the subject, the pressure signal indicating pressure applied to the sensor, and the breathing signal indicating sound related to breathing of the subject; a respiratory phase determination step of determining an exhalation interval and an inhalation interval of the subject based on a change in the intensity of the pressure signal; an abnormal sound determination step, which determines whether the sound related to the breathing includes an abnormal sound based on the breathing signal; and and an estimating step of estimating whether the abnormal sound is generated in the exhalation interval or the inhalation interval when the sound related to the breathing includes an abnormal sound.

20. A program for controlling a computer as the information processing system according to claim 1, wherein: The program is for causing a computer to function as the signal extraction unit, the respiratory phase determination unit, the abnormal sound determination unit, and the estimation unit.

21. The information processing system according to claim 1, wherein: The abnormal sound determination unit calculates a power spectrum of a first respiratory signal having a first frequency or higher contained in the detection signal for unit intervals corresponding to the exhalation interval and the inhalation interval, respectively, or for a unit interval corresponding to a respiratory interval formed by combining the exhalation interval and the inhalation interval. The abnormal sound determination unit determines a time point as a starting point in the averaging process of the power spectrum for each unit section based on a second respiratory signal having a second frequency or less included in the respiratory signal, The abnormal sound determination unit determines whether the sound related to the breathing includes an abnormal sound based on a result of an averaging process obtained by performing the averaging process on each of the unit sections in accordance with the starting point in the power spectrum.

22. The information processing system according to claim 21, wherein: The abnormal sound determination unit determines that the sound related to breathing includes an abnormal sound when a ratio of a dispersion of a power spectrum to a square of a power average value of the first breathing signal is equal to or larger than a predetermined threshold value in the averaging process.

23. The information processing system according to claim 21, wherein when at least any one of the first respiratory signal and the second respiratory signal includes a large-amplitude signal having an amplitude greater than a predetermined standard amplitude, the amplitude of the large-amplitude signal is changed to the standard amplitude to perform the averaging process.

24. The information processing system according to claim 21, wherein when at least one of the first respiratory signal and the second respiratory signal includes a large-amplitude signal having an amplitude greater than a predetermined standard amplitude, the large-amplitude signal is removed and the averaging process is performed.

25. The information processing system according to claim 21, which determines whether the sound related to the breathing includes abnormal sound based on the value calculated by linear combination of the power spectrum subjected to n-th power averaging operation, wherein n is a natural number greater than 2.

Images