JP7551536B2 - Near-miss incident database generation method and near-miss incident database generation system - Google Patents

Description

The present invention relates to a near-miss database for storing and sharing near-miss information.

Efforts are being made to prevent disasters and accidents by creating a near-miss database to accumulate and share information on near-misses experienced by people such as workers at construction sites and factories, and people in need of care living in nursing homes. A near-miss is, for example, the recognition of an incident that does not progress to a serious disaster or accident, but which could easily lead to one. When a danger occurs, there are often many near-misses lurking beforehand, and collecting and analyzing near-miss cases can help prevent danger.

In recent years, there have also been attempts to attach sensors to the bodies of subjects, such as workers or people requiring care, and monitor the condition of the subjects based on the sensor measurements.

For example, a method for generating a near-miss database is known that involves managing people's status using sensor measurements (for example, Patent Literature 1 and Non-Patent Literature 1).

JP 2013-80304 A

Yoshimitsu Shinagawa et al., "Detection of human walking and falls using acceleration sensors," Kawasaki Medical Welfare Society Journal, 1999, Vol. 9 No. 2 243-250

However, there are concerns that existing near-miss databases make it difficult to understand what the subjects were doing, why, and what happened.

The object of the present invention is to generate a near-miss database that can grasp the situation of the person involved when a near-miss occurs.

One aspect of the present invention is a near-miss database generation method, in which when a subject's condition is determined to be abnormal, a near-miss database is automatically generated by associating identification information for identifying the subject, status information regarding the subject's condition, status information acquisition time information, status information acquisition location information, and an image captured at or near the acquisition location of the status information.

It is possible to automatically generate a near-miss database that can grasp the situation of the person involved when a near-miss occurs.

FIG. 1 is a diagram illustrating an example of a near-miss database generation system according to an embodiment. FIG. 4 is a diagram illustrating an example of information acquired by an acquisition device. FIG. 4 is a diagram illustrating an example of information acquired by an imaging device. FIG. 2 is a diagram illustrating an example of a near-miss database. 10 is a flowchart illustrating an example of an operation of the acquisition device. 4 is a flowchart showing an example of the operation of the imaging apparatus. 13 is a flowchart illustrating an example of an operation of the generating device. FIG. 13 illustrates an example of a computer for implementing the generating device.

Several embodiments of the present invention will be described in detail below with reference to the drawings. Note that the same reference numerals are used to designate corresponding elements in multiple drawings.

In the embodiment described below, it is possible to determine that a near miss has occurred in a subject, such as a worker performing work at a work site or a person requiring care living in a care facility, based on the measurement value of a sensor attached to the subject (the subject's condition is abnormal). When it is determined that the subject's condition is abnormal, the sensor measurement value, acquisition time, and acquisition position can be acquired. Furthermore, images (still images or video images) captured by a fixed surveillance camera installed near the acquisition position of the sensor measurement value, an unmanned mobile body, or an imaging device worn by the user can be included in the near miss database. This allows the subject and the administrator who manages the subject's activities to check the subject's condition from the image, and to understand the situation when the subject's condition becomes abnormal (when, where, who, what was done, why, what happened, etc.) based on the sensor measurement value, acquisition time, and acquisition position. In other words, it is possible to automatically generate a near miss database that can grasp the subject's condition, including the time when a near miss occurs.

FIG. 1 is a diagram showing an example of a near-miss database generation system 1 according to an embodiment. The near-miss database generation system 1 shown in FIG. 1 includes an acquisition device 2, one or more imaging devices 3, and a generation device 4. The generation device 4 may acquire information from the acquisition device 2 and the imaging device 3 via a network such as wireless communication, wired communication, or the Internet, or may acquire information from the acquisition device 2 and the imaging device 3 via a recording medium such as a memory card. In the example shown in FIG. 1, the near-miss database generation system 1 is composed of the acquisition device 2, the imaging device 3, and the generation device 4, but the embodiment is not limited to this. For example, the acquisition device 2, the imaging device 3, and the generation device 4 may be integrated into a single device.

The acquisition device 2 is attached to the subject's body, and includes a status information acquisition unit 21, a time information acquisition unit 22, a location information acquisition unit 23, a storage unit 24, and a control unit 25. The status information acquisition unit 21 may be configured to include the time information acquisition unit 22 and the location information acquisition unit 23. The acquisition device 2 may be held by the subject in the form of an activity meter, a smart watch, a smartphone, a mobile terminal, or the like. The acquisition device 2 may also be embedded in the subject's body.

The status information acquisition unit 21 is an acceleration sensor, tilt sensor, heart rate monitor, blood pressure monitor, skin electrodermal activity sensor, plantar pressure sensor, air pressure sensor, etc., and acquires status information regarding the subject's status, such as the subject's movement, position, posture, and vital data.

For example, when the acquisition device 2 is attached to the center of the subject (such as the waist), the status information acquisition unit 21 is configured with an acceleration sensor or a tilt sensor. When the status information acquisition unit 21 is configured with an acceleration sensor or a tilt sensor in this way, it is possible to measure the acceleration and tilt angle near the center of the subject's body, so that the motion of the subject can be measured while suppressing the influence of the movement of local body parts such as the arms and legs. Alternatively, when the acquisition device 2 is attached to the palm, finger, arm, etc. of the subject, the status information acquisition unit 21 is configured with a heart rate monitor, a blood pressure monitor, an electrodermal activity sensor, etc. When the status information acquisition unit 21 is configured with a heart rate monitor, a blood pressure monitor, an electrodermal activity sensor, etc. in this way, when the subject's condition becomes abnormal, the subject's heart rate increases sharply or cold sweat (psychological sweating) occurs, so that it is possible to determine that the subject's condition has become abnormal by detecting a sharp increase in the measurement value of the heart rate monitor, blood pressure monitor, or electrodermal activity sensor. Alternatively, when the acquisition device 2 is attached to the sole of the subject's foot, the status information acquisition unit 21 is configured with a pressure sensor. In this way, when the condition information acquisition unit 21 is configured with a pressure sensor, if the subject's condition becomes abnormal, the pressure distribution and center of gravity movement of the pressure on the soles of the subject's feet will change compared to normal, and by detecting the change in the measurement value of the pressure sensor, it can be determined that the subject's condition has become abnormal.

The time information acquisition unit 22 is a radio clock or a GPS (Global Positioning System), and acquires status information acquisition time information indicating the time (date and time) when the status information was acquired by the status information acquisition unit 21.

The location information acquisition unit 23 is a GPS or an indoor location information acquisition terminal, and acquires the location information of the acquisition device 2 when the status information is acquired by the status information acquisition unit 21. Note that when the time information acquisition unit 22 and the location information acquisition unit 23 are configured by a GPS, the time information acquisition unit 22 and the location information acquisition unit 23 may be integrated into one.

The storage unit 24 is a RAM (Random Access Memory), a ROM (Read Only Memory), or a memory card, and stores information acquired by the acquisition device 2 (identification information, status information, status information acquisition time information, status information acquisition position information).

The control unit 25 is configured with a CPU (Central Processing Unit) or a programmable device (such as an FPGA (Field Programmable Gate Array) or a PLD (Programmable Logic Device)), and controls the operation of the state information acquisition unit 21, the time information acquisition unit 22, the position information acquisition unit 23, and the storage unit 24. The control unit 25 also stores in the storage unit 24, in association with identification information for identifying the subject, the state information acquired by the state information acquisition unit 21, the time information acquired by the time information acquisition unit 22, and the position information acquired by the position information acquisition unit 23. The information stored in the storage unit 24 is transmitted to the generation device 4 via wireless communication, wired communication, or a network. Alternatively, the information stored in the storage unit 24 is provided to the generation device 4 via a memory card.

The imaging unit 31 may be a fixed surveillance camera installed at a work site or a care facility, a camera equipped on an unmanned mobile body such as a drone or a robot, or a camera attached to a helmet worn by the subject, and captures images (still images or moving images). The camera may be a 360-degree camera or a 3D scanner. When capturing still images, the imaging unit 31 captures images at set intervals. It is preferable that the set interval is appropriately set in consideration of the searchability of the images. Furthermore, when the imaging unit 31 is a fixed surveillance camera or an unmanned mobile body camera, the imaging unit 31 is capable of capturing images of the subject and the subject's surroundings. Furthermore, when the imaging unit 31 is a camera attached to the subject's body, such as a 360-degree camera, the imaging unit 31 is capable of capturing images of the subject's surroundings.

The imaging device 3 also includes an imaging unit 31, a time information acquisition unit 32, a position information acquisition unit 33, a storage unit 34, and a control unit 35.

The time information acquisition unit 32 is a radio clock or GPS, etc., and acquires imaging time information indicating the time (date and time) when an image was captured by the imaging unit 31.

The position information acquisition unit 33 is a GPS or an indoor position information acquisition terminal, and acquires imaging position information indicating the position of the imaging device 3 when an image is captured by the imaging unit 31. Note that when the time information acquisition unit 32 and the position information acquisition unit 33 are configured by a GPS, the time information acquisition unit 32 and the position information acquisition unit 33 may be integrated into one.

The storage unit 34 is a RAM, ROM, or memory card, and stores information acquired by the imaging device 3 (images, imaging time information, imaging position information).

The control unit 35 is configured with a CPU or a programmable device, and controls the operation of each of the imaging unit 31, the time information acquisition unit 32, the position information acquisition unit 33, and the storage unit 34. The control unit 35 also stores in the storage unit 34 an image captured by the imaging unit 31, imaging time information acquired by the time information acquisition unit 32, and imaging position information acquired by the position information acquisition unit 33 in association with each other. The information stored in the storage unit 34 is also transmitted to the generation device 4 via wireless communication, wired communication, or a network. Alternatively, the information stored in the storage unit 34 is provided to the generation device 4 via a memory card.

The generation device 4 is composed of a computer such as a personal computer (PC), a mobile PC, a tablet terminal, a smartphone, a mobile phone, or a server computer on a network.

The generating device 4 also includes a determining unit 41, a generating unit 42, and a memory unit 43, and generates a near-miss database using the information acquired by the acquiring device 2 and the information acquired by the imaging device 3.

The judgment unit 41 detects a sudden change in the state information acquired by the acquisition device 2 as a near miss. For example, if the judgment unit 41 judges that the acceleration measured by the acceleration sensor as the state information acquisition unit 21 is included in the acceleration range corresponding to the "stationary state" for a certain period of time, the judgment unit 41 judges that the state of the subject is "stationary state". Next, if the judgment unit 41 determines that the acceleration measured by the acceleration sensor is included in the acceleration range corresponding to the "walking state" for a certain period of time after identifying the "stationary state" as the state of the subject, the judgment unit 41 judges that the state of the subject has changed from the "stationary state" to the "walking state". On the other hand, if the judgment unit 41 determines that the acceleration measured by the acceleration sensor is not included in any of the acceleration ranges prepared in advance after identifying the "stationary state" as the state of the subject, the judgment unit 41 judges that the state of the subject is abnormal, that is, that a near miss has occurred.

The determination range of the acceleration range can be set to thresholds such as minimum and maximum values. For example, the acceleration range corresponding to a "stationary state" is the range from the minimum to maximum of multiple accelerations measured continuously for a certain period by the acceleration sensor when the subject is stationary. Similarly, the acceleration range corresponding to a "walking state" is the range from the minimum to maximum of multiple accelerations measured continuously for a certain period by the acceleration sensor when the subject is walking. Furthermore, the minimum and maximum values of the acceleration range may be fixed values, may be changed depending on the subject, or may be changed depending on the amount of change per unit time in the measurement value of the acceleration sensor.

When the status information acquisition unit 21 of the acquisition device 2 is configured with multiple sensors, the determination unit 41 may be configured to determine whether the subject's status is abnormal using the measurement values measured by the multiple sensors. Alternatively, when the status information acquisition unit 21 of the acquisition device 2 is configured with multiple sensors, the determination unit 41 may be configured to determine whether the subject's status has become abnormal from the specified status after identifying the subject's status. For example, the determination unit 41 may be configured to determine whether the subject's status has become abnormal from the status of descending stairs using the measurement values measured by the acceleration sensor and the measurement values measured by the air pressure sensor after identifying that the subject is descending stairs.

In addition, when the status information acquisition unit 21 of the acquisition device 2 is configured with an imaging device such as a camera, the judgment unit 41 may be configured to judge whether the subject's condition is abnormal or not using an image (still image or moving image) captured by the imaging device. Alternatively, when the status information acquisition unit 21 of the acquisition device 2 is configured with an imaging device, the judgment unit 41 may be configured to use an image captured by the imaging device to identify the subject's condition and then judge whether the subject's condition has become abnormal from the identified condition. For example, the judgment unit 41 may be configured to analyze the moving image and track the subject in the moving image to identify that the subject is walking, and then judge whether the subject's condition has become abnormal from the walking condition.

In addition, when the state information acquisition unit 21 of the acquisition device 2 is configured with a sensor such as an acceleration sensor and an imaging device such as a camera, the determination unit 41 may be configured to determine whether the state of the subject is abnormal using both the measurement value of the sensor and the image of the imaging device. Alternatively, when the state information acquisition unit 21 of the acquisition device 2 is configured with a sensor and an imaging device, the determination unit 41 may be configured to determine whether the state of the subject has become abnormal from the specified state after identifying the state of the subject using both the measurement value of the sensor and the image of the imaging device. For example, the determination unit 41 may be configured to determine the state of the subject identified when the state of the subject identified using the measurement value of the sensor and the state of the subject identified using the image of the imaging device match each other. In addition, the determination unit 41 may be configured to determine that the state of the subject is abnormal when it is determined that the state of the subject has become abnormal from the specified state using the measurement value of the sensor and the image of the imaging device.

When the determination unit 41 determines that the subject's condition is abnormal, the generation unit 42 generates a near-miss database by associating identification information for identifying the subject, status information acquisition time information indicating the acquisition time of the status information used when it was determined that the subject's condition is abnormal, status information acquisition position information indicating the acquisition position of the status information used when it was determined that the subject's condition is abnormal, and an image captured at the acquisition position of the status information used when it was determined that the subject's condition is abnormal.

When the near-miss database generation system 1 is configured to include multiple imaging devices 3, the generation unit 42 may be configured to generate the near-miss database by associating the identification information, status information acquisition time information, status information acquisition location information, and images captured by each of the multiple imaging devices 3.

The storage unit 43 is a RAM or a ROM, and stores the information acquired by the acquisition device 2 (identification information, status information, status information acquisition time information, status information acquisition position information), the information acquired by the imaging device 3 (image, imaging time information, imaging position information), and the near-miss database generated by the generation unit 42.

Figure 2 shows an example of information acquired by acquisition device 2.

Information D1 shown in FIG. 2 is information stored in the memory unit 24 of the acquisition device 2 and the memory unit 43 of the generation device 4. Information D1 also has a field F11 in which identification information is stored, a field F12 in which status information is stored, a field F13 in which status information acquisition time information is stored, and a field F14 in which status information acquisition position information is stored. In other words, information D1 is information in which identification information, status information, acquisition time information, and acquisition position information are associated with one another. In the example of FIG. 2, "ID1" is stored in field F11 of each of records R11 to R20 of information D1, and "latitude: 35 degrees 41 minutes 29 seconds, longitude: 139 degrees 44 minutes 16 seconds" is stored in field F14 of each of records R11 to R20. In addition, "1.1 [G]" is stored in the field F12 of record R11 of information D1, and "January 15, 2021, 9:30:31 seconds" is stored in the field F13 of record R11. In addition, "1.0 [G]" is stored in the field F12 of record R12 of information D1, and "January 15, 2021, 9:30:32 seconds" is stored in the field F13 of record R12. In addition, "0.9 [G]" is stored in the field F12 of record R13 of information D1, and "January 15, 2021, 9:30:33 seconds" is stored in the field F13 of record R13. In addition, "0.8 [G]" is stored in the field F12 of record R14 of information D1, and "January 15, 2021, 9:30:34 seconds" is stored in the field F13 of record R14. In addition, "0.6 [G]" is stored in the field F12 of record R15 of information D1, and "January 15, 2021, 9:30:35" is stored in the field F13 of record R15. In addition, "1.1 [G]" is stored in the field F12 of record R16 of information D1, and "January 15, 2021, 9:30:36" is stored in the field F13 of record R16. In addition, "1.0 [G]" is stored in the field F12 of record R17 of information D1, and "January 15, 2021, 9:30:37" is stored in the field F13 of record R17. In addition, "2.9 [G]" is stored in the field F12 of record R18 of information D1, and "January 15, 2021, 9:30:38" is stored in the field F13 of record R18. In addition, "0.8 [G]" is stored in field F12 of record R19 of information D1, and "January 15, 2021, 9:30:39" is stored in field F13 of record R19. In addition, "0.6 [G]" is stored in field F12 of record R20 of information D1, and "January 15, 2021, 9:30:40" is stored in field F13 of record R20.

Figure 3 shows an example of information acquired by the imaging device 3.

Information D2 shown in FIG. 3 is information stored in the memory unit 34 of the imaging device 3 and the memory unit 43 of the generation device 4. Information D2 also has a field F21 in which an image is stored, a field F22 in which imaging time information is stored, and a field F23 in which imaging position information is stored. That is, information D2 is information in which image information, imaging time information, and imaging position information are associated with each other. In the example of FIG. 3, "Image1" is stored in field F21 of record R21 of information D2, and "January 15, 2021, 9:30:31" is stored in field F22 of record R21. Also, "Image2" is stored in field F21 of record R22 of information D2, and "January 15, 2021, 9:30:32" is stored in field F22 of record R22. In addition, "Image3" is stored in the field F21 of record R23 of information D2, and "January 15, 2021, 9:30:33" is stored in the field F22 of record R23. In addition, "Image4" is stored in the field F21 of record R24 of information D2, and "January 15, 2021, 9:30:34" is stored in the field F22 of record R24. In addition, "Image5" is stored in the field F21 of record R25 of information D2, and "January 15, 2021, 9:30:35" is stored in the field F22 of record R25. In addition, "Image6" is stored in the field F21 of record R26 of information D2, and "January 15, 2021, 9:30:36" is stored in the field F22 of record R26. In addition, "Image7" is stored in the field F21 of record R27 of information D2, and "January 15, 2021, 9:30:37" is stored in the field F22 of record R27. In addition, "Image8" is stored in the field F21 of record R28 of information D2, and "January 15, 2021, 9:30:38" is stored in the field F22 of record R28. In addition, "Image9" is stored in the field F21 of record R29 of information D2, and "January 15, 2021, 9:30:39" is stored in the field F22 of record R29. In addition, "Image10" is stored in the field F21 of record R30 of information D2, and "January 15, 2021, 9:30:40" is stored in the field F22 of record R30. Additionally, "Latitude: 35 degrees 41 minutes 29 seconds, Longitude: 139 degrees 44 minutes 16 seconds" is stored in field F23 of each of records R21 to R30 of information D2.

Figure 4 shows an example of a near-miss database.

The near-miss database D3 shown in Figure 4 is information stored in the memory unit 43 of the generation device 4. The near-miss database D3 also has a field F31 in which identification information is stored, a field F32 in which status information is stored, a field F33 in which status information acquisition time information is stored, a field F34 in which status information acquisition position information is stored, and a field F35 in which images are stored. In other words, the near-miss database D3 is information in which identification information, status information, status information acquisition time information, status information acquisition position information, and images are associated with one another. In the example of FIG. 4, "ID1" is stored in field F31 of record R31 of information D3, "2.9 [G]" is stored in field F32 of record R31, "January 15, 2021, 9:30:38" is stored in field F33 of record R31, "Latitude: 35 degrees 41 minutes 29 seconds, longitude: 139 degrees 44 minutes 16 seconds" is stored in field F34 of record R31, and "Image 8" is stored in field F35 of record R31.

Here, assume that information D1 shown in FIG. 2 and information D2 shown in FIG. 3 are stored in the memory unit 43 of the generating device 4, the minimum value of the acceleration range for identifying the state in which the subject is walking is 0.6 [G], the maximum value is 1.2 [G], and the fixed time is 5 [seconds].

First, when the determination unit 41 of the generating device 4 determines that the state information (1.1 [G], 1.0 [G], 0.9 [G], 0.8 [G], 0.6 [G]) stored in the field F12 of each of the records R11 to R15 for a certain time period (5 [seconds]) among the records R11 to R20 of the information D1 is within the acceleration range (0.6 [G] to 1.2 [G]), it identifies the state of the subject as "walking state". Next, when the determination unit 41 determines that the state information (2.9 [G]) stored in the field F12 of record R18 among the state information stored in the field F12 of each of the records R16 to R20 for the next certain time period (5 [seconds]) among the records R11 to R20 of the information D1 is outside the predetermined range (0.6 [G] to 1.2 [G]), it determines that the state of the subject has changed from "walking state" to abnormal. That is, the determination unit 41 determines that a near miss occurred while the subject was walking. The generation unit 42 may be configured to include the content determined by the determination unit 41 (that a near miss occurred while the subject was walking) in the near miss database.

Next, the generation unit 42 of the generation device 4 searches the information D2 for record R28 corresponding to the imaging time information and imaging position information that match the status information acquisition time information and status information acquisition position information of record R18 of information D1. This makes it possible to extract the image (Image8) stored in field F21 of record R28 of information D2 as the image captured at or near the acquisition position of the status information used when it was determined that the subject's condition was abnormal. The generation unit 42 then generates a near-miss database D3 consisting of record R31 by associating the image (Image8) stored in field F21 of record R28 of information D2 with record R18 of information D1. As a result, the subject or the administrator who manages the subject's activities can confirm when ("Latitude: 35°41'29", Longitude: 139°44'16"), where ("January 15, 2021 9:30:35" to "January 15, 2021 9:30:40"), and who ("ID1") by checking each piece of information stored in fields F31 to F34 of record R31 of the near-miss database D3, and can also confirm what was done, why, and what happened (for example, tripping over materials scattered on the floor while walking) by checking the image stored in field F35 of record R31. Note that the information D2 may be set to be recorded only when a near-miss occurs. By recording only when a near-miss occurs, the capacity of the storage device can be reduced. In addition, the amount of data transmitted to the generating device 4 can be reduced. The information D2 may be set to be transmitted collectively at a set time.

The generating unit 42 may be configured to generate the near-miss database D3 from records R16 to R20 before and after record R18, including record R18 in information D1 when the subject's condition becomes abnormal, and each image (Image 6 to Image 10) of records R26 to R30 in information D2 that coincides with the time and position of records R16 to R20. The generating unit 42 may also be configured to generate near-miss databases for multiple subjects. The generating unit 42 may also be configured to analyze and statistically process the situation when the subject becomes abnormal based on the near-miss database, and extract the cause of the subject's abnormality from the analysis and statistical processing. In this way, the subject or the manager can understand the situation before and after the subject's abnormality by checking each image in the near-miss database D3. Therefore, by checking the near-miss database D3, the target person or manager can not only recognize when, where, and who became abnormal (whether a near-miss occurred), but also analyze and statistically process the situation when the abnormality occurred, and extract the cause of the abnormality.

Figure 5 is a flowchart showing an example of the operation of the acquisition device 2. Note that the acquisition device 2 is capable of transmitting and receiving information to and from the generation device 4 via wireless communication, wired communication, or a network.

First, when the control unit 25 of the acquisition device 2 receives an instruction to start acquiring status information (step S11: Yes), it controls the operation of the status information acquisition unit 21, the time information acquisition unit 22, and the position information acquisition unit 23 to acquire identification information, status information, status information acquisition time information, and status information acquisition position information, and associates these pieces of information with each other and stores them in the memory unit 24 (step S12).

Next, if the control unit 25 does not receive an instruction to end status information acquisition (step S13: No), it continues to control the operation of the status information acquisition unit 21, the time information acquisition unit 22, and the position information acquisition unit 23, and accumulates information in which the identification information, status information, status information acquisition time information, and status information acquisition position information are associated with each other in the memory unit 34 (step S12).

On the other hand, when the control unit 25 receives an instruction to end status information acquisition (step S13: Yes), it transmits the information stored in the memory unit 24 to the generation device 4 (step S14).

Figure 6 is a flowchart showing an example of the operation of the imaging device 3. Note that the imaging device 3 is capable of transmitting and receiving information to and from the generating device 4 via wireless communication, wired communication, or a network.

First, when the control unit 35 of the imaging device 3 receives an instruction to start image acquisition (step S21: Yes), it controls the operation of the imaging unit 31, the time information acquisition unit 32, and the position information acquisition unit 33 to acquire an image, imaging time information, and imaging position information, and stores these pieces of information in association with each other in the memory unit 34 (step S22).

Next, if the control unit 35 does not receive an instruction to end image acquisition (step S23: No), it continues to control the operation of the imaging unit 31, the time information acquisition unit 32, and the position information acquisition unit 33, and accumulates information in which the image, imaging time information, and imaging position information are associated with each other in the memory unit 34 (step S22).

On the other hand, when the control unit 35 receives an instruction to end image acquisition (step S23: Yes), it transmits the information stored in the memory unit 34 to the generation device 4 (step S24).

Figure 7 is a flowchart showing an example of the operation of the generating device 4. Note that the generating device 4 is capable of transmitting and receiving information to and from the acquiring device 2 and the imaging device 3 via wireless communication, wired communication, or a network.

First, when the determination unit 41 of the generating device 4 determines that the subject has entered a predetermined location such as a work site or a care facility (step S31: Yes), it transmits an instruction to start acquiring status information to the acquiring device 2 and an instruction to start acquiring images to the imaging device 3 (step S32). For example, the generating device 4 determines that the subject has entered the work site or care facility by using an RFID (Radio Frequency Identification) receiver, a magnetic reader, an infrared sensor, or face recognition that is installed near the entrance to the work site or care facility. Alternatively, the generating device 4 determines that the subject has entered the work site or care facility by detecting that the subject has pressed a measurement start button installed near the entrance to the work site or care facility or provided on a device worn by the subject.

Next, when the determination unit 41 determines that the subject has left a predetermined location such as a work site or a care facility (step S33: Yes), it transmits an instruction to end status information acquisition to the acquisition device 2 and an instruction to end image acquisition to the imaging device 3 (step S34). For example, the generation unit 42 determines that the subject has left the work site or care facility by using an RFID receiver, magnetic reader, infrared sensor, or face recognition installed near the exit of the work site or care facility. Alternatively, the generation device 4 determines that the subject has left the work site or care facility by detecting that the subject has pressed a measurement end button installed near the exit of the work site or care facility or provided on a device worn by the subject.

Next, when the determination unit 41 receives information from the acquisition device 2 and from the imaging device 3 (step S35: Yes), it determines whether the subject's condition is abnormal (step S36).

Next, if the generation unit 42 determines that the received information does not include condition information that determines that the subject's condition is abnormal (step S36: No), it ends the near-miss database generation process without creating a near-miss database.

On the other hand, if the received information includes status information that determines that the subject's condition is abnormal (step S36: Yes), the generation unit 42 of the generation device 4 generates a near-miss database using the status information, information related to the status information (identification information, status information acquisition time information, and status information acquisition position information), and an image captured at the acquisition position of the status information, and stores the near-miss database in the memory unit 43, thereby terminating the near-miss database generation process (step S37).

In this way, the near-miss database generation system 1 of the embodiment is configured to generate a near-miss database that includes not only the status information used when the subject's status was determined to be abnormal, but also the image captured at the acquisition position of that status information. This allows subjects and managers to automatically generate a near-miss database that enables them to understand the subject's status when a near-miss occurs by checking the near-miss database. This makes it easier for subjects and managers to take measures to prevent the occurrence of near-misses.

The near-miss database D3 can also be collected for multiple subjects. It can also be applied to multiple work sites. A near-miss database can be created by collecting near-miss information for multiple subjects. By constructing a near-miss database, analysis and statistical processing can be performed on the location, situation, time, etc. of near-miss occurrences at multiple work sites, etc., and the results can be used to improve the work site environment and work styles.

Figure 8 shows an example of a computer for implementing the generation device 4.

The computer 80 shown in FIG. 8 includes a processor 81, a memory 82, a storage device 83, a reader 84, a communication interface 85, and an input/output interface 86. The processor 81, memory 82, storage device 83, reader 84, communication interface 85, and input/output interface 86 are connected to each other via a bus 87.

The processor 81 is configured as a single processor, a multi-processor, a multi-core, or the like. The processor 81 also reads out a program stored in the storage device 83, and uses the memory 82 to execute a program that describes the procedure of the flowchart shown in FIG. 7, thereby providing some or all of the functions of the determination unit 41 and the generation unit 42.

Memory 82 may be a semiconductor memory or the like, and may include a RAM area and a ROM area.

The storage device 83 is a semiconductor memory such as a hard disk or flash memory, or an external storage device.

The reader 84 accesses the removable storage medium 89 according to instructions from the processor 81. The removable storage medium 89 is realized by a semiconductor device, a medium where information is input and output by magnetic action, a medium where information is input and output by optical action, etc. The semiconductor device is a USB (Universal Serial Bus) memory, etc. The medium where information is input and output by magnetic action is a magnetic disk, etc. The medium where information is input and output by optical action is a CD (Compact Disc)-ROM, a DVD (Digital Versatile Disc), a Blu-ray Disc (Blu-ray is a registered trademark), etc.

The storage unit 43 may include, for example, a memory 82, a storage device 83, and a removable storage medium 89. For example, the storage device 83 stores information D1 shown in FIG. 2, information D2 shown in FIG. 3, and a near-miss database D3 shown in FIG. 4.

The communication interface 85 communicates with other devices according to instructions from the processor 81. For example, the generating device 4 may collect information from the acquiring device 2 and the imaging device 3 via the communication interface 85.

The input/output interface 86 may be, for example, an interface between an input device and an output device. The input device is a device such as a keyboard, mouse, or touch panel that accepts instructions from the subject or administrator. The output device is a display device such as a display, or an audio device such as a speaker.

Each program according to the embodiment is provided to the generating device 4 in the following form, for example.
(1) It is pre-installed in the storage device 83.
(2) Provided by a removable storage medium 89.
(3) Provided from a server such as a program server.

The hardware configuration of the computer 80 for realizing the generating device 4 described with reference to FIG. 8 is an example, and the embodiment is not limited to this. For example, part of the above-mentioned configuration may be deleted, or new configuration may be added. In another embodiment, for example, part or all of the functions of the above-mentioned generating device 4 may be implemented as hardware such as an FPGA, a System-on-a-Chip (SoC), an Application Specific Integrated Circuit (ASIC), or a PLD.

In the above, several embodiments are described. However, the embodiments are not limited to the above embodiments, and should be understood to include various modified and alternative forms of the above embodiments. For example, it will be understood that the various embodiments can be embodied by modifying the components without departing from the spirit and scope of the embodiments. It will also be understood that various embodiments can be implemented by appropriately combining multiple components disclosed in the above-mentioned embodiments. Furthermore, it will be understood by those skilled in the art that 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.

Reference Signs List 1 Near-miss database generation system 2 Acquisition device 3 Imaging device 4 Generation device 21 Status information acquisition unit 22 Time information acquisition unit 23 Position information acquisition unit 24 Memory unit 25 Control unit 31 Imaging unit 32 Time information acquisition unit 33 Position information acquisition unit 34 Memory unit 35 Control unit 41 Determination unit 42 Generation unit 43 Memory unit

Claims (4)

A near-miss database generating method in a generating device that generates a near-miss database, comprising:
The generating device comprises:
storing a first record in a storage unit in which identification information for identifying the subject, status information regarding a status of the subject, status information acquisition time information indicating a time when the status information was acquired, and status information acquisition position information indicating a position of the acquisition device when the status information was acquired are associated with each other, the first record being transmitted from the acquisition device;
storing in the storage unit a second record in which an image captured by an imaging unit included in the imaging device, imaging time information indicating the time when the image was captured, and imaging position information indicating the position of the imaging device when the image was captured are associated with each other, the second record being transmitted from the imaging device;
when it is determined that the condition of the subject is abnormal based on the condition information, searching the storage unit for the second record corresponding to the imaging time information and the imaging position information whose time and position match the condition information acquisition time information and the condition information acquisition position information of the first record corresponding to the condition information that determined that the condition of the subject is abnormal,
A near-miss database generation method for generating the near-miss database by associating the image of the searched second record with the first record corresponding to the condition information that determines that the subject's condition is abnormal. A generating device;
An acquisition device;
An imaging device including an imaging unit;
Equipped with
The generating device comprises:
a storage unit that stores a first record in which identification information for identifying a subject, status information related to a status of the subject, status information acquisition time information indicating the time when the status information was acquired, and status information acquisition position information indicating the position of the acquisition device when the status information was acquired are associated with each other, the first record being transmitted from the acquisition device, and the storage unit that stores a second record in which an image captured by the imaging unit, imaging time information indicating the time when the image was captured, and imaging position information indicating the position of the imaging device when the image was captured are associated with each other, the first record being transmitted from the acquisition device,
a determination unit that determines whether a condition of the subject is abnormal based on the condition information;
a generation unit that, when the determination unit determines that the subject's condition is abnormal, searches the storage unit for the second record corresponding to the image capture time information and the image capture position information whose time and position match the status information acquisition time information and the status information acquisition position information of the first record corresponding to the status information that determined that the subject's condition is abnormal, and generates a near-miss database by associating the image of the searched second record with the first record corresponding to the status information that determined that the subject's condition is abnormal;
A near-miss database generation system comprising: 2. The method for generating a near-miss database according to claim 1,
When the generating device determines that the target person has left a predetermined location, the generating device receives the identification information, the status information, the status information acquisition time information, and the status information acquisition time information transmitted from the acquiring device, and also receives the image, the imaging time information, and the imaging position information transmitted from the imaging device.
How to generate a near-miss database. 3. The near-miss database generation system according to claim 2,
When the generating device determines that the target person has left a predetermined location, the generating device receives the identification information, the status information, the status information acquisition time information, and the status information acquisition time information transmitted from the acquiring device, and also receives the image, the imaging time information, and the imaging position information transmitted from the imaging device.
Near-miss database generation system.

Images