JP2022131286A - Abnormality detection device, abnormality detection system, and abnormality detection method - Google Patents

Abstract

To provide an abnormality detection device, an abnormality detection system and an abnormality detection method which detect an abnormality of an object person such that the abnormality is distinguished from daily behaviors.SOLUTION: In a system in which a measuring instrument attached to an object person is communicably connected with an abnormality detection device which analyzes information acquired by the measuring instrument via a network, the abnormality detection device 40 comprises a detection unit 43 which detects an abnormality of the object person on the basis of comparison of frequency components of time series data targeting different periods. The time series data is the time series data of a measurement value of a sensor which measures information of a state of the object person. The abnormality detection device further comprises a conversion unit 42 which converts the time series data into a frequency component distribution for every period of the time series data. The comparison of the frequency components of the time series data targeting the different periods includes comparison of peak patterns appearing in the frequency component distribution of the time series data targeting the different periods.SELECTED DRAWING: Figure 3

Description

The present disclosure relates to an anomaly detection device, an anomaly detection system, and an anomaly detection method.

BACKGROUND ART In recent years, attempts to prevent serious accidents from occurring by monitoring the behavior of subjects and detecting abnormalities or their signs at an early stage have been extensively studied. A technique related to monitoring the behavior of a subject is described in Non-Patent Document 1, for example.

In the above research, in addition to detecting the subject's daily behavior such as walking, running, and climbing from the measured values of the sensor attached to the subject, the subject unintentionally or intentionally It is important to detect the contrary behavior (that is, the subject's abnormal behavior, hereinafter simply referred to as the subject's abnormality).

A typical example of a subject's anomaly is a subject's motion that occurs with a so-called near miss, and specifically includes, for example, stumbling, slipping, falling, contact, collision, and falling. Here, a near miss generally refers to an incident that does not lead to a serious accident but may cause a serious accident (incident), or the recognition of such a case.

Yoshimitsu Shinagawa et al., "Detection of Human Walking and Falling Using an Acceleration Sensor," Kawasaki Medical Welfare Society Journal, 1999, vol. 9 no. 2 243-250

Non-Patent Document 1 discusses a method for detecting walking (routine behavior) and falling (abnormal behavior) of a subject using an acceleration sensor, and describes the results of the examination. However, as concluded in Non-Patent Document 1, it is not easy to detect a subject's abnormality such as a fall only from the measurement result of the acceleration sensor. In particular, it is difficult with conventional technology to detect an abnormality of a subject by distinguishing it from the subject's daily behavior, and new ideas are expected to further improve the technology.

Based on the actual situation as described above, it is an object of one aspect of the present invention to provide a technique for detecting an abnormality of a subject by distinguishing it from daily behavior.

An anomaly detection device according to an aspect of the present invention is time-series data of measured values of a sensor that measures information on the state of a subject, and is based on comparison of frequency components of the time-series data for different periods. and a detection unit for detecting an abnormality of the subject.

According to the above aspect, an abnormality of the subject can be detected by distinguishing it from daily behavior.

It is a figure which illustrated the structure of the system which concerns on one Embodiment. It is the figure which illustrated the hardware constitutions of the measuring device in one embodiment. It is the figure which illustrated the functional structure of the abnormality detection apparatus in one Embodiment. 1 is an example sequence diagram illustrating interaction between components of a system according to one embodiment; FIG. 4 is an example of a flow chart showing processing performed by a system according to an embodiment; It is an example of data measured by the measuring device according to one embodiment. It is an example of the data which shows the frequency distribution of the data measured with the measuring device which concerns on one Embodiment. It is a figure explaining the time frequency analysis performed with the abnormality detection apparatus which concerns on one Embodiment. It is a figure which shows an example of classification standard information. 4 is a flow chart showing a specific example of processing performed by the system according to one embodiment; It is a figure which shows the relationship between the function structure of the system and apparatus structure which concern on one Embodiment. It is a figure which shows the relationship of the functional structure of the system and apparatus structure which concern on another embodiment. FIG. 10 is a diagram showing the relationship between the functional configuration of a system and the device configuration according to still another embodiment; FIG. 10 is a diagram showing the relationship between the functional configuration of a system and the device configuration according to still another embodiment; FIG. 10 is a diagram showing the relationship between the functional configuration of a system and the device configuration according to still another embodiment; It is the figure which illustrated the hardware constitutions of the computer for implement|achieving the abnormality detection apparatus which concerns on embodiment mentioned above.

FIG. 1 is a diagram illustrating the configuration of a system according to one embodiment. A system 100 shown in FIG. 1 is an example of an anomaly detection system that detects an anomaly of a subject 1 . First, the configuration of system 100 will be described with reference to FIG.

In the following, a case where the target person 1 is, for example, a worker who works at a factory or a construction site, for example, will be described as an example where an abnormality is likely to lead to a serious accident. However, the target person 1 is not limited to the above workers. The target person 1 may be, for example, an inpatient in a hospital, a person requiring nursing care in a nursing home, or an elderly person who needs to be watched over. That is, the system 100 may be constructed for any person for whom early detection of abnormality and alerting are effective in preventing aggravation of abnormality and occurrence of a serious accident. Further, by analyzing under what operating environment the abnormality of the subject 1 occurred, it may be useful for improving the environment such as working environment and living environment.

In this specification, the subject's abnormality mainly means an abnormal behavior of the subject, such as stumbling, slipping, falling, contact, collision, falling, etc., unintentionally by the subject or means to act against one's intentions. However, the subject's abnormality may include, for example, the subject's physical changes represented by fever, cold sweat, palpitations, shortness of breath, and shivering. That is, the subject's abnormality may broadly include an abnormal state of the subject.

The system 100 includes a measurement device 10 attached to the subject 1 and an abnormality detection device 40 that analyzes information acquired by the measurement device 10 . The system 100 may further include a notification device 20 that the subject 1 possesses.

Each device constituting the system 100 is communicably connected via a network 30 . Communication between each device may be performed via another device (not shown). Communication between each device may also take place directly in an ad-hoc communication mode. Here, the communication may be wireless communication or wired communication. Alternatively, a combination of wireless communication and wired communication may be used.

In the system 100 , the abnormality detection device 40 detects abnormality of the subject 1 based on the information acquired by the measurement device 10 . The abnormality detection device 40 may further analyze the detected abnormality and classify it into several categories. Further, the abnormality detection device 40 may record the detected abnormality in association with other information of the subject 1 such as position information. Further, the abnormality detection device 40 may notify the notification device 20 of the detected abnormality, and the notification device 20 may notify the subject 1 of information according to the classification of the abnormality.

In FIG. 1, only one subject 1 is illustrated as a subject wearing the measuring device 10, but the system 100 may include a plurality of measuring devices 10 worn by a plurality of subjects 1. Well, the anomaly detection device 40 may process information from a plurality of measurement devices 10 . Moreover, one subject 1 may be equipped with a plurality of measuring devices 10 .

FIG. 2 is a diagram illustrating the hardware configuration of the measuring device in one embodiment. FIG. 3 is a diagram illustrating the functional configuration of the abnormality detection device in one embodiment. The configuration of the system 100 will be described in more detail with reference to FIGS. 2 and 3. FIG.

The measuring device 10 includes a sensor 11 for measuring information on the condition of the subject 1, as shown in FIG. The measurement device 10 may be, for example, an inertial measurement unit (IMU), and the sensor 11 may include an inertial sensor (acceleration sensor, gyro sensor) for measuring acceleration, angular velocity, and the like. The sensor 11 further includes an inclination sensor that measures the angle of inclination, a GPS (Global Positioning System) that measures position, an indoor positioning sensor, a pressure sensor that measures pressure, a biosensor that measures vital signs and other biological information, and the like. may include

In addition to the sensor 11, the measuring device 10 includes a microprocessor 12 that controls the operation of the measuring device 10, a memory 13 that stores measurement value data measured by the sensor 11, and external devices (abnormality detection device 40, notification It comprises a communication circuit 14 for communicating with the device 20, etc.) and a battery 15 for supplying power.

In the measuring device 10 , the sensor 11 measures information on the condition of the subject 1 under the control of the microprocessor 12 , and the memory 13 stores the measured values of the sensor 11 . Furthermore, the communication circuit 14 transmits the time-series data of the measured values stored in the memory 13 to the abnormality detection device 40 .

For example, as shown in FIG. 1 , the measuring device 10 is attached to the waist of the subject 1 by fixing it to a belt or the like worn by the subject 1 . By attaching the measuring device 10 to the waist position near the center of the body, it is possible to measure the movement of the entire body while suppressing the effects of local movements of body parts such as arms and legs. Therefore, it is suitable as a mounting position of the measuring device 10 as an inertial measuring device.

However, the mounting position of the measuring device 10 is not limited to the above example. For example, the measurement device 10 may be fixed to a helmet and attached to the head position. Moreover, the measuring device 10 may be attached to an appropriate position according to the type of the sensor 11 .

Furthermore, the measurement device 10 may be incorporated into wearable devices such as smart watches and smart glasses. Moreover, the measuring device 10 may be held by the subject 1, and may be incorporated in a mobile terminal such as a smartphone or a tablet held by the subject 1, for example. Moreover, the measuring device 10 may be embedded in the subject 1 .

The notification device 20 is a device that notifies the subject 1 of information. The information notified by the notification device 20 may be presented to the subject 1 visually, audibly, or tactilely. The notification device 20 may be, for example, a display device having a display, and may notify the subject 1 of information by displaying the information. The notification device 20 may be, for example, a light-emitting device having an LED or the like, and may notify the subject 1 of information by lighting or blinking the light. The notification device 20 may be, for example, an audio output device having a speaker, and may notify the subject 1 of information by outputting audio, warning sound, or the like. The notification device 20 may be, for example, a vibrator or the like, and may notify the subject 1 of information by vibration.

When receiving the notification of abnormality detection from the abnormality detection device 40, the notification device 20 notifies the subject 1 of different information according to the classification of the abnormality included in the notification, for example.

The notification device 20 does not necessarily have to be fixed to the subject 1, and may be held in the hand of the subject 1, for example, as shown in FIG. Also, the subject 1 may carry the notification device 20 in a pocket, bag, or the like. Alternatively, the notification device 20 may be fixed to a belt or the like, similar to the measurement device 10 . Further, the notification device 20 may be incorporated in a mobile terminal such as a smartphone or a tablet held by the subject 1, or may be incorporated in a wearable device worn by the subject 1.

The abnormality detection device 40 is a device that detects an abnormality of the subject 1 . The abnormality detection device 40 is not particularly limited, but may be, for example, a server computer (tower server, rack mount server, blade server), personal computer (desktop computer, laptop computer, tablet computer). good. Further, the abnormality detection device 40 may be a smart phone, a mobile phone, or other computer as long as it has sufficient processing power for abnormality detection.

The abnormality detection device 40 includes a control section 41, a communication section 45, and a recording section 46, as shown in FIG. The control unit 41 includes a conversion unit 42, a detection unit 43, a classification unit 44, and may further include other functional units.

The control unit 41 performs time-frequency analysis on the time-series data of the measured values of the sensor 11 output from the measuring device 10, and detects abnormality of the subject 1 based on the analysis result. The conversion unit 42 converts the time-series data of the measured values of the sensor 11 into a frequency component distribution for each period of the time-series data. The detection unit 43 detects an abnormality of the subject 1 based on a comparison of frequency component distributions of the time-series data for different periods generated by the conversion unit 42 . The classification unit 44 classifies the detection results of the detection unit 43 . The communication unit 45 communicates with other devices such as the measurement device 10 and the notification device 20 according to instructions from the control unit 41 . The recording unit 46 stores the abnormality of the subject 1 detected by the detection unit 43 . The recording unit 46 may also store information that the classifying unit 44 refers to when classifying the detection results.

The abnormality detection processing performed by the system 100 will be described below.

FIG. 4 is an example sequence diagram illustrating interaction between system components according to one embodiment. For example, as shown in FIG. and a process to be performed (notification process).

First, the measurement device 10 starts measurement processing. In the measurement process, time-series data (measurement data in FIG. 4) of measurement values measured by the measurement device 10 is periodically transmitted from the measurement device 10 to the abnormality detection device 40, for example. The abnormality detection device 40 starts detection processing upon receiving the measurement data. In the detection process, measurement data is analyzed. When an abnormality of the subject 1 is detected, the abnormality detection device 40 notifies the notification device 20 of the abnormality detection. The notification device 20 starts notification processing upon receiving the notification of the abnormality detection. In the notification process, the target person 1 is notified of information according to the received notification.

FIG. 5 is an example of a flowchart illustrating processing performed by a system according to one embodiment. FIG. 6 is an example of data measured by the measuring device according to one embodiment. FIG. 7 is an example of data showing the frequency distribution of data measured by the measuring device according to one embodiment. FIG. 8 is a diagram explaining the time-frequency analysis performed by the abnormality detection device according to the embodiment. FIG. 9 is a diagram showing an example of classification criterion information. The anomaly detection processing performed by the system 100 will be described in more detail with reference to FIGS. 5 to 9. FIG.

The abnormality detection process performed by the system 100 may include, for example, six processes (measurement process, conversion process, comparison/detection process, classification process, recording process, and notification process) as shown in FIG. The abnormality detection process shown in FIG. 5 may be started by the system 100 when the measuring device 10 is activated, for example.

When the abnormality detection process is started, the measuring device 10 performs the measurement process (step S1). In step S1, the sensor 11 measures information on the state of the subject 1. FIG. The information on the state of the subject 1 measured by the sensor 11 is sampled, for example, at regular intervals, and the memory 13 stores the data obtained by sampling.

Data 1000 shown in FIG. 6 is time-series data of the measured values of the sensor 11 obtained by sampling the measured values of the sensor 11 during the walking period of the subject 1 when the sensor 11 is an acceleration sensor. An example. The time-series data stored in the memory 13 is transmitted from the measurement device 10 to the abnormality detection device 40 using the communication circuit 14 at predetermined timings under the control of the microprocessor 12 . Note that the measurement process is repeated, for example, after the measuring device 10 is activated until the measuring device 10 is stopped.

Upon receiving the time-series data of the measured values, the abnormality detection device 40 performs time-frequency analysis on the time-series data of the measured values to detect an abnormality of the subject 1 (steps S2 to S4). That is, the abnormality detection device 40 analyzes how the frequency component included in the time-series data changes depending on the target period of the time-series data of the measured values, and detects an abnormality of the subject 1 based on the analysis result. .

The abnormality detection device 40 first converts the time-series data of the measured values (step S2). Here, the control unit 41 operates as the conversion unit 42 . The control unit 41 performs, for example, a Fourier transform on the time-series data of the measured values to generate data by extracting frequency components included in the time-series data. Data 2000 shown in FIG. 7 is an example of frequency distribution obtained by Fourier transforming data 1000 shown in FIG.

More specifically, in step S2, the conversion unit 42 repeatedly converts the time-series data while gradually shifting the target period of the time-series data of the measurement values. The transformation unit 42 may, for example, cut out the time-series data using a window function of a certain size, and perform Fourier transform on the cut out data. In FIG. 8, time-series data of different target periods (data 1001, data 1002, data 1003, and data 1004) are cut out from the time-series data of the measured values, Fourier transform is performed on each, and time series data is obtained for each target period. An example of generating frequency component distributions of series data (data 2001, data 2002, data 2003, and data 2004) is shown.

When the frequency component distribution is generated, the abnormality detection device 40 compares the generated frequency component distributions to detect abnormality of the subject 1 (step S3). Here, the controller 41 operates as the detector 43 . The control unit 41 detects abnormality of the subject 1 based on comparison of frequency components of time-series data for different periods. The control unit 41 may detect an abnormality of the subject 1, for example, based on comparison of peak patterns appearing in frequency component distributions of time-series data for different periods.

In general, abnormal human movements represented by stumbling, slipping, falling, contacting, colliding, falling, etc. are movements that occur momentarily. is different from In other words, normal behavior differs from abnormal behavior in terms of whether or not there is continuity in the frequency component distribution.

The control unit 41 may detect abnormality of the subject 1 by paying attention to the presence or absence of continuity of the frequency component distribution. Specifically, for example, the control unit 41 compares the peak patterns of the frequency components of the time-series data for different periods, and based on the peak pattern transience identified by the comparison of the peak patterns, the target Abnormality of the person 1 may be detected separately from daily behavior. Further, the control unit 41 may detect the daily behavior of the subject 1 in addition to the abnormality of the subject 1. For example, based on the continuity of the peak pattern identified by comparing the peak patterns, The behavior of the subject 1 may be detected.

Everyday behavior contains various frequency components depending on the type of behavior. Thus, everyday activities can include a wide range of frequency components, from relatively low frequency components (eg walking) to relatively high frequency components (eg running). On the other hand, an abnormal motion is a motion that accompanies a momentary large change in acceleration, and is dominated by high frequency components. In other words, abnormal behavior can be distinguished from at least part of everyday behavior also by the frequency of peaks contained in the frequency component distribution.

The control unit 41 may detect the abnormality of the subject 1 with higher accuracy by focusing on the frequency range of this peak. Specifically, the control unit 41 compares, for example, peak patterns of frequency components of time-series data for different periods, and detects abnormalities of the subject 1 based on the frequency of the temporarily occurring peaks. may In this case, the control unit 41 detects abnormality of the subject 1 when the peak frequency is high, but the method of determining whether the peak frequency is high is not particularly limited. It may be determined by a predetermined threshold value, or by comparison with other peak frequencies such as walking. Furthermore, the control unit 41 may detect the behavior of the subject 1 based on, for example, the frequency of the continuously occurring peaks.

A case where the user stumbles while walking will be described with reference to FIG. As shown in FIG. 8, the peak pattern appearing in the frequency component distribution during walking includes only relatively low frequency peaks indicating walking (data 2001, data 2002). Although the peak height and frequency vary to some extent depending on walking speed, etc., peaks always occur at relatively low frequencies during walking. Therefore, the control unit 41 can detect that the subject 1 is walking from the peak frequency and continuity. Next, when subject 1 stumbles while walking, the peak pattern appearing in the frequency component distribution during the period including the timing of the trip includes peaks indicating walking as well as peaks having a higher frequency than walking (data 2003). This peak is not included in the peak pattern appearing in the frequency component distribution for the next period (data 2004). Therefore, the control unit 41 can detect that the subject 1 stumbles while walking, based on the frequency and transient nature of the peak.

Here, an example is shown in which the peak is determined to be transient if it disappears within two cycles of the target period. The length may be changed as appropriate. For example, a peak that disappears in less than three cycles of the target period may be determined as a transient peak, and a peak detected continuously over three or more cycles may be determined as a continuous peak.

When the abnormality of the subject 1 is detected in step S3, the abnormality detection device 40 classifies the detected abnormality (step S4). Here, the control section 41 operates as the classification section 44 . For example, the control unit 41 may classify the detected anomaly based on the characteristics of the peak indicating the detected anomaly included in the frequency component distribution.

For example, classification criteria information 3000 stored in the recording unit 46 may be used to classify anomalies based on peak features. For example, as shown in FIG. 9, the classification criteria information 3000 may include features of peaks such as “continuity/transient”, “frequency band”, and “others” for each abnormality classification. . "Other" may include, for example, features such as peak intensity and width. As shown in FIG. 9, the classification criteria information 3000 may include information for classifying everyday behavior in addition to information for classifying anomalies.

In step S<b>4 , classification may be performed using a trained model instead of the classification reference information 3000 . For example, detection results may be classified using a trained model that has previously learned the relationship between peak features converted into vector data, anomalies, and actions.

In step S4, in addition to classifying the detected abnormality, the detected action may be classified. In other words, the control unit 41 may classify the detection results detected by the detection unit 43 regardless of abnormal behavior and daily behavior. Furthermore, the control unit 41 may classify the detection results using other information in addition to the peak characteristics. For example, the control unit 41 may classify the detection results using the information of the sensor 11 (for example, type, installed orientation), or may classify the detection results using data of another sensor.

After the abnormality is classified in step S4, the abnormality detection device 40 records the detected abnormality (step S5). Here, under the control of the control unit 41, the recording unit 46 records the abnormality of the subject 1 detected in step S3 as the abnormality of the category (classification result) classified in step S4. The recording unit 46 may record various information along with the category of abnormality. The recording unit 46 may record, for example, the date and time information of the target period when the abnormality was detected, the position information of the target person 1 in the target period, the information on the behavior of the target person 1 before and after the occurrence of the abnormality, and the like, together with the abnormality category. good. In step S<b>5 , the abnormality detection device 40 records the detected abnormality and transmits an abnormality detection notification including information on the category of the abnormality to the notification device 20 .

Upon receiving the notification from the abnormality detection device 40, the notification device 20 notifies the subject 1 of the information according to the category (step S6). The information according to the category is, for example, a warning that calls the subject 1 to pay attention to the contents according to the category.

As described above, the abnormality detection device 40 can detect an abnormality of the subject 1 by performing all or part of the abnormality detection processing shown in FIGS. 4 and 5, distinguishing it from daily behavior. In particular, the abnormality detection device 40 uses the frequency component of the time-series data of the measured values of the sensor to replace the characteristics of an abnormality that appears as a complex pattern on the time-series data with a relatively simple pattern (for example, in the frequency component distribution). peak). In addition, the abnormality detection device 40 performs time-frequency analysis on the time-series data to compare the frequency components of the time-series data for different periods, and based on the presence or absence of continuity of the simplified pattern Abnormal behavior can be detected by distinguishing it from everyday behavior. Therefore, according to the abnormality detection device 40, the abnormality of the subject 1 can be detected easily and with high accuracy by distinguishing it from daily behavior.

Further, the system 100 can notify the subject 1 of information according to the classification of the abnormality detected by the abnormality detection device 40 by performing the abnormality detection processing shown in FIGS. Therefore, according to the system 100, it is possible to call attention to the subject 1 by notifying information according to the classification of the detected abnormality, thereby preventing the occurrence of a serious accident.

FIG. 10 is a flowchart illustrating a specific example of processing performed by the system according to one embodiment. An embodiment in which the processing shown in FIG. 5 is implemented in a system 100 including a measuring device 10 including at least an acceleration sensor and an inclination sensor as a sensor 11 will be described below with reference to FIG.

In the system 100, first, the measurement device 10 attached to the subject 1 measures acceleration with the sensor 11 (step S101). Next, the abnormality detection device 40 cuts out the data of the target period from the time-series data of the acceleration measured by the sensor 11 and performs Fourier transform (step S102). After that, the abnormality detection device 40 determines whether there is a peak indicating other than walking in the frequency component distribution obtained by the Fourier transform (step S103). The method for determining the presence or absence of peaks other than walking is not particularly limited, but may be performed by, for example, regarding relatively low peaks that occur most frequently as peaks indicating walking.

If there is no peak other than walking (step S103 NO), the system 100 ends the processing shown in FIG. On the other hand, if there is a peak other than walking (step S103 YES), the abnormality detection device 40 determines whether the peak other than walking continues to occur (step S104). In step S104, for example, the continuity of peaks may be evaluated based on whether or not a peak other than the walking has also occurred in the frequency component distribution in the preceding target period.

When the abnormality detection device 40 determines that the peak does not continue (step S104 NO), the abnormality detection device 40 further detects a target other than walking from which a peak is detected based on the measurement value (tilt angle) of the tilt sensor. After the period, it is determined whether or not the subject 1 continues to be in a tilted state (step S105). If the measured value of the tilt sensor indicates that the subject 1 is continuously tilted (step S105 YES), it is assumed that the subject 1 has fallen. is classified as overturning and notified to the notification device 20, and the notification device 20 issues an alarm for falling (step S106). On the other hand, when the measured value of the tilt sensor does not indicate that the subject 1 continues to tilt (step S105 NO), it is assumed that the subject 1 stumbled. is classified as stumbling and notified to the notification device 20, and the notification device 20 issues a warning (for example, a message such as "Please watch your step") for stumbling (step S107).

When the abnormality detection device 40 determines that the peak continues (step S104 YES), it determines whether the width of the peak is less than the threshold (step S108). If the width of the peak is not less than the threshold (step S108 NO), it is assumed that the peak is caused by the behavior of the subject 1. Determine (step S109). Here, for example, the axis of acceleration may be determined based on the measured values of the three-axis acceleration sensor during the target period in which the peak is detected. When the abnormality detection device 40 determines that the axis of acceleration is horizontal, the peak is considered to be due to running. Therefore, the abnormality detection device 40 classifies the behavior of the subject 1 as running (running). is notified to the notification device 20, and the notification device 20 issues a warning (for example, a message such as "Do not run as it is dangerous") (step S110). On the other hand, when the abnormality detection device 40 determines that the axis of acceleration is vertical, the peak is considered to be due to the up-and-down motion, so the abnormality detection device 40 classifies the behavior of the subject 1 as up-and-down. is notified to the notification device 20, and the notification device 20 issues a warning (for example, a message such as "Be careful on the stairs") (step S111). Further, when the width of the peak is less than the threshold in step S108 (YES in step S108), it is assumed that the peak is caused by mechanical vibration. The notification device 20 is notified that it is assumed that there is a heavy machine or the like that generates vibration, and the notification device 20 warns the surroundings (for example, a message such as "Please take a good look at the surroundings and act") (step S112).

As described above, according to the system 100, abnormalities and daily behaviors of the subject 1 can be distinguished and detected based on the information from the measuring device 10 including the acceleration sensor and the tilt sensor. It is also possible to detect the state of the subject 1 whose surroundings require vigilance.

FIG. 11 is a diagram showing the relationship between the functional configuration of the system and the device configuration according to the embodiment described above. In the system 100 described above, among the functional configurations for performing the abnormality detection processing described above, the measuring device (measuring device 10) serves as the sensor unit, the reporting device (notifying device 20) serves as the reporting unit, and other functional units (conversion unit, detection unit, classification unit, and recording unit) is adopted by the abnormality detection device (abnormality detection device 40), but the relationship between the functional configuration and the device configuration is not limited to this example, and for example, FIG. to FIG. 15 may be adopted. In addition, since the configuration shown in FIG. 11 is a configuration in which functions other than those necessary for the subject 1 side are concentrated on the server side, it is possible to efficiently provide the same functions to a plurality of subjects 1. desirable.

FIG. 12 is a diagram showing the relationship between the functional configuration of the system and the device configuration according to another embodiment. A system 200 shown in FIG. 12 differs from the system 100 in that the sensor section and the notification section are realized by the same device (measurement notification device). Other points are the same. The configuration shown in FIG. 12 is desirable in that it minimizes the number of devices required on the subject's side.

FIG. 13 is a diagram showing the relationship between the functional configuration of the system and the device configuration according to still another embodiment. A system 300 shown in FIG. 13 differs from the system 100 in that the measuring device also serves as a conversion unit. Other points are the same. The configuration shown in FIG. 13 may be adopted depending on the performance of the measuring device.

FIG. 14 is a diagram showing the relationship between the functional configuration of the system and the device configuration according to still another embodiment. In the system 400 shown in FIG. 14, the abnormality detection device serves as the functional units other than the notification unit. In this configuration, since the anomaly detection device is provided on the subject side, it is preferable in that it is less susceptible to communication delays and communication failures than when the anomaly detection device is arranged on the Internet, for example. In addition, since another device (notification device) takes charge of only the notification unit, an existing terminal (for example, a smartphone owned by the subject 1, etc.) can be effectively used.

FIG. 15 is a diagram showing the relationship between the functional configuration of the system and the device configuration according to still another embodiment. In the system 500 shown in FIG. 15, the abnormality detection device takes charge of all functional units. Similar to the system 200 shown in FIG. 12, this configuration is desirable in that it can avoid the effects of communication delays and communication failures while minimizing the number of devices required on the subject side.

FIG. 16 is a diagram exemplifying the hardware configuration of the computer 50 for realizing the abnormality detection device according to the embodiment described above. The hardware configuration shown in FIG. 16 includes a processor 51, memory 52, storage device 53, reader 54, communication interface 56, and input/output interface 57, for example. The processor 51, memory 52, storage device 53, reader 54, communication interface 56, and input/output interface 57 are connected to each other via a bus 58, for example.

The processor 51 may be, for example, a single processor, a multiprocessor, or a multicore. The processor 51 uses the memory 52 to execute a program describing all or part of the procedure of the operation flow described above, for example, thereby providing a part or all of the functions of the control unit 41 described above. By reading and executing the programs stored in the storage device 53, it operates as, for example, the conversion unit 42, the detection unit 43, and the classification unit 44.

The memory 52 is, for example, a semiconductor memory and may include a RAM area and a ROM area. The storage device 53 is, for example, a hard disk, a semiconductor memory such as a flash memory, or an external storage device.

The reader 54 accesses the removable storage medium 55 according to instructions from the processor 51, for example. The removable storage medium 55 is realized by, for example, a semiconductor device, a medium in which information is input/output by magnetic action, a medium in which information is input/output by optical action, or the like. The semiconductor device is, for example, a USB (Universal Serial Bus) memory. A medium for inputting and outputting information by magnetic action is, for example, a magnetic disk. Media for inputting and outputting information by optical action include, for example, CD (Compact Disc)-ROM, DVD (Digital Versatile Disc), Blu-ray Disc, etc. (Blu-ray is a registered trademark).

The recording unit 46 described above may include a memory 52, a storage device 53, and a removable storage medium 55, for example. The communication interface 56 communicates with other devices according to instructions from the processor 51, for example. For example, computer 50 may collect measurements from sensor 11 via communication interface 56 . The communication interface 56 is an example of the communication section 45 described above.

The input/output interface 57 is, for example, an interface between an input device and an output device. The input device is, for example, a device such as a keyboard, mouse, or touch panel that receives instructions from the user. The output device is, for example, a display device such as a display and an audio device such as a speaker.

Each program according to the embodiment is provided to the computer 50 in the following form, for example.
(1) Pre-installed in the storage device 53 .
(2) provided by a removable storage medium 55;
(3) provided by a server such as a program server;

Note that the hardware configuration of the computer 50 for realizing the abnormality detection device described with reference to FIG. 16 is an example, and the embodiment is not limited to this. For example, some of the configurations described above may be deleted, and new configurations may be added. In another embodiment, for example, some or all of the functions of the control unit 41 described above are FPGA (Field Programmable Gate Array), SoC (System-on-a-Chip), ASIC (Application Specific Integrated Circuit), and hardware such as a PLD (Programmable Logic Device).

Several embodiments are described above. However, it should be understood that the embodiments are not limited to the embodiments described above, but encompass various variations and alternatives of the embodiments described above. For example, it will be appreciated that various embodiments can be embodied with varying elements without departing from the spirit and scope thereof. Also, it will be understood that various embodiments can be implemented by appropriately combining a plurality of constituent elements disclosed in the above-described embodiments. Furthermore, various embodiments can be implemented by deleting some components from all the components shown in the embodiments or by adding some components to the components shown in the embodiments. It will be understood by those skilled in the art.

For example, in the above-described embodiment, an example of informing the subject 1 himself of the abnormality of the subject 1 was shown, but the subject of notification is not limited to the subject 1 . When the subject 1 encounters an accident or the like, the abnormality of the subject 1 may be notified to people around the subject 1 rather than to the subject 1 himself. In addition, if the target person 1 is working at a construction site or the like, the site supervisor or the like may be notified. In addition, the system administrator may be notified, or an arbitrary person determined in advance may be notified of the abnormality of the target person 1 .

Further, in the above-described embodiment, an example in which the measurement data acquired by the measurement device 10 provided on the side of the subject 1 is transmitted to the abnormality detection device 40 via the network was shown, but the exchange of data used network communication. method is not limited. For example, measurement data acquired by the measurement device 10 may be input to the abnormality detection device 40 by exchanging a recording medium such as a memory card.

Further, in the above-described embodiment, when an abnormality of the subject 1 is detected, an example is shown in which information corresponding to the abnormality is notified, but the detected abnormality does not necessarily have to be notified. By collecting information on anomalies and constructing a near-miss database, information to which attention should be paid may be shared by all concerned parties including the subject 1 .

1 subject 10 measurement device 11 sensor 20 notification device 40 abnormality detection device 41 control unit 42 conversion unit 43 comparison unit 44 classification unit 45 communication unit 46 recording unit 50 computer 51 processor 100, 200, 300, 400, 500 system

Claims (8)

A detection unit that detects anomalies of a subject based on a comparison of frequency components of the time-series data of the measured values of a sensor that measures information on the state of the subject, the time-series data covering different periods. An abnormality detection device comprising: The abnormality detection device according to claim 1, further comprising:
A conversion unit that converts the time-series data into a frequency component distribution for each period of the time-series data,
The abnormality detection device, wherein the comparison of frequency components of the time-series data for different periods includes comparison of peak patterns appearing in frequency component distributions of the time-series data for different periods. In the abnormality detection device according to claim 2,
The detection unit is
Detecting an abnormality of the subject based on the transience of the peak pattern identified by the comparison of the peak patterns,
An anomaly detection device, wherein the behavior of the subject is detected based on the continuity of the peak pattern specified by the comparison of the peak patterns. The abnormality detection device according to any one of claims 1 to 3, further comprising:
An anomaly detection device comprising the sensor for measuring information on the state of the subject. The abnormality detection device according to any one of claims 1 to 4, further comprising:
An anomaly detection device, comprising: a notification unit that notifies the subject of information according to a classification result obtained by classifying detection results obtained by the detection unit. a sensor that measures information about the subject's condition;
and an anomaly detection device,
The abnormality detection device is
Abnormality detection, comprising a detection unit that detects an abnormality of the subject based on a comparison of frequency components of the time-series data of the measured values of the sensor for different periods. system. The anomaly detection system according to claim 6, further comprising:
An anomaly detection system, comprising: a notification device that notifies the target person of information according to a classification result obtained by classifying the detection result of the detection unit. Comparing the frequency components of the time-series data of the measured values of a sensor that measures information on the state of the subject and targeting different periods,
An anomaly detection method, comprising: detecting an anomaly of the subject based on a result of comparing frequency components of the time-series data.

Images