Apparatus, method, and program

Abstract

To provide a device capable of determining whether or not a target sound is an echo sound.SOLUTION: An apparatus includes an acquisition unit that acquires acoustic data detected by a sound collection device capable of moving in a facility and collecting sound, an estimation unit that estimates an estimated sound source position for a sound component included in the acquired acoustic data, and a determination unit that determines whether or not a target sound is a reverberant sound on the basis of a deviation amount of a plurality of estimated sound source positions for a target sound included in acoustic data detected at a plurality of detection positions different from each other. The device may include an extraction unit configured to extract a target sound in accordance with at least one of a sound pressure or a frequency of a sound component included in acoustic data detected at the plurality of detection positions, and the determination unit may determine whether or not the target sound is a reverberant sound on the basis of a deviation amount of a plurality of estimated sound source positions for the target sound extracted by the extraction unit.SELECTED DRAWING: Figure 10

Description

[Technical Field]

[0001] The present invention relates to an apparatus, a method, and a program. [Background technology]

[0002] Patent Documents 1 to 3 describe collecting environmental sounds and identifying the position of an object. [Prior art document] [Patent documents] Patent Document 1: JP 2019-124513 A Patent Document 2: JP 2019-152941 A Patent Document 3: JP 2011-182062 A Summary of the Invention

[0003] In a first aspect of the present invention, there is provided an apparatus comprising: an acquisition unit that acquires sound data detected by a sound collection device that can move within a facility and collect sound; an estimation unit that estimates an estimated sound source position for a sound component contained in the acquired sound data; and a determination unit that determines whether a target sound is an echo sound based on the amount of deviation between multiple estimated sound source positions for a target sound contained in sound data detected at multiple detection positions that are different from each other.

[0004] The above device may include an extraction unit that extracts a target sound according to at least one of the sound pressure or frequency of a sound component included in acoustic data detected at a plurality of detection positions, and the determination unit may determine whether the target sound is a reverberant sound based on the amount of deviation between a plurality of estimated sound source positions for the target sound extracted by the extraction unit.

[0005] In the above device, the extraction unit may extract a target sound having a sound pressure equal to or greater than a predetermined threshold.

[0006] Any of the above devices may include a database connection unit that associates sounds included in acoustic data detected within the facility with sound source positions and records them in a database, and the database connection unit may record target sounds that are determined by the determination unit not to be reverberation sounds in the database by associating them with sound source positions corresponding to the estimated sound source positions.

[0007] In the above-described device, the determination unit may determine that a target sound contained in acoustic data detected at a plurality of different detection positions is an echo sound when the target sound is not recorded in the database in association with a sound source position and the deviation amount between the plurality of estimated sound source positions is equal to or greater than a predetermined threshold value.

[0008] The above-mentioned device may include a sound collection command unit that instructs the sound collection device to collect sound, and when the acquisition unit acquires sound data that includes sound components that are not recorded in the database in association with the sound source position, the sound collection command unit may instruct the sound collection device to collect sound at a detection position different from the detection position of the sound data acquired by the acquisition unit.

[0009] In any of the above devices, the determination unit may further determine whether the target sound is a reverberant sound based on the sound pressure of the target sound included in the sound data detected at a plurality of detection positions that are different from each other.

[0010] In any of the above devices, the sound collection device may have an image sensor, the acquisition unit may acquire image data detected by the image sensor of the sound collection device, and the determination unit may determine whether a target sound contained in the acoustic data detected at a plurality of different detection positions is an echo sound based on the image data detected at the plurality of detection positions.

[0011] In any of the above devices, the determination unit may determine that a target sound contained in acoustic data detected at a plurality of different detection positions is not an echo sound if the amount of deviation of the estimated sound source position is equal to or greater than a predetermined threshold and the direction of movement between the plurality of detection positions is different from the direction of movement between the estimated sound source positions.

[0012] In a second aspect of the present invention, there is provided a method comprising: acquiring sound data detected by a sound collection device that can move within a facility and collect sound; estimating an estimated sound source position for a sound component contained in the acquired sound data; and determining whether the target sound is a reverberant sound based on the amount of deviation between multiple estimated sound source positions for the target sound contained in the sound data detected at multiple different detection positions.

[0013] In a third aspect of the present invention, there is provided a program that is executed by a computer and causes the computer to function as an acquisition unit that acquires sound data detected by a sound collection device that can move around a facility to collect sound, an estimation unit that estimates an estimated sound source position for a sound component contained in the acquired sound data, and a determination unit that determines whether a target sound is an echo sound based on the amount of deviation between multiple estimated sound source positions for a target sound contained in sound data detected at multiple different detection positions.

[0014] The above summary of the invention does not list all of the necessary features of the present invention, and subcombinations of these features may also constitute inventions. [Brief explanation of the drawings]

[0015] [Figure 1] 1 shows a schematic configuration of a facility 1 according to this embodiment. [Figure 2] 1 shows the configuration of a control system 20 according to this embodiment. [Figure 3] 2 shows a processing flow of the control system 20 according to the present embodiment. [Figure 4] 1 shows the configuration of a robot 30 according to this embodiment. [Figure 5] 10 shows a processing flow of the robot 30 according to the present embodiment. [Figure 6] 1 shows the configuration of a monitoring device 40 according to this embodiment. [Figure 7] 1 shows an example of a data structure of a collected information database 50 according to the present embodiment. [Figure 8] 2 shows an example of the data structure of the equipment database 60 according to the present embodiment. [Figure 9] 2 shows an example of the data structure of a robot database 70 according to the present embodiment. [Figure 10] 6 shows the configuration of a monitoring processing unit 650 of the monitoring device 40 according to this embodiment. [Figure 11] 10 shows a processing flow of the monitoring device 40 according to the present embodiment. [Figure 12] 1 shows an explanatory diagram for explaining how a monitoring device 40 according to the present embodiment determines echoes. [Figure 13] 22 illustrates an example computer 2200 in which aspects of the present invention may be embodied, in whole or in part. DETAILED DESCRIPTION OF THE INVENTION

[0016] The present invention will be described below through embodiments of the invention, but the following embodiments do not limit the scope of the invention according to the claims. Furthermore, not all of the combinations of features described in the embodiments are necessarily essential to the solution of the invention.

[0017] FIG. 1 shows a schematic configuration of a facility 1 according to this embodiment. The facility 1 may be a whole or partial segment of a factory or plant, in which multiple devices 10 are located. Examples of such factories or plants include factories for producing various industrial products, chemical or metal industrial plants, plants for managing and controlling wellheads and their surrounding areas, plants for managing and controlling hydroelectric, thermal, or nuclear power generation, plants for managing and controlling solar or wind energy generation, and plants for managing and controlling water supply, sewerage, dams, and the like. The facility 1 may also be a whole or partial building or transportation facility equipped with multiple devices 10 to be controlled and monitored. The facility 1 includes multiple devices 10, a control system 20, one or more robots 30, a monitoring device 40, a collected information database 50, an equipment database 60, and a robot database 70.

[0018] The plurality of devices 10 are provided at various locations within the facility 1. Each of the plurality of devices 10 may be installed either indoors or outdoors within the area of ​​the facility 1. At least some of the devices 10 may be process equipment, power generation equipment, or any other device (or facility equipment) that is controlled by the control system 20, or may be part of such equipment. At least some of the devices 10 may be field devices that operate under control from the control system 20, other devices, or operators. Furthermore, at least some of the devices 10 may be field devices themselves.

[0019] Such field devices may be, for example, sensor devices such as pressure gauges, flow meters, and temperature sensors, valve devices such as flow control valves and on-off valves, actuator devices such as fans and motors, imaging devices such as cameras or videos that capture images of the situation of a plant or an object such as equipment, audio devices such as microphones or speakers that collect abnormal sounds from a plant or equipment or emit alarm sounds, position detection devices that output position information of devices in the facility 1, or other devices. Furthermore, other devices 10 among the plurality of devices 10 may be pipes, storage tanks, supports, bulkheads, or other structures that are not controlled by the control system 20.

[0020] The control system 20 is connected to at least one device 10 to be controlled among the multiple devices 10. The control system 20 may be, for example, a distributed control system (DCS). The control system 20 controls each device 10 in accordance with the state of each device 10 measured by a sensor or the like provided in each device 10 to be controlled.

[0021] Each of the one or more robots 30 is used to monitor at least some of the devices 10 in the facility 1. Each robot 30 can move around the facility 1 and collect sound and take images. Each robot 30 is an example of a sound collection device.

[0022] The monitoring device 40 is communicatively connected to each of one or more robots 30. The monitoring device 40 may be connected to each robot 30 via a wireless network such as a mobile phone network, a wireless WAN, a wireless LAN, or Bluetooth (registered trademark), or may be connected to each robot 30 via a wired network such as wired Ethernet (registered trademark). The monitoring device 40 according to this embodiment is installed within the facility 1. Alternatively, the monitoring device 40 may be installed outside the facility 1 and remotely monitor each device 10 within the facility 1. For example, the monitoring device 40 may be installed within another facility, or may be realized by, for example, a cloud server on the Internet.

[0023] The monitoring device 40 receives collected data, such as acoustic data and image data, collected by each robot 30 within the facility 1, from each robot 30, and uses the collected data to monitor the status of each device 10. When the monitoring device 40 identifies an abnormality in any of the devices 10, it may instruct the control system 20 to perform control to deal with the abnormality.

[0024] The monitoring device 40 uses a collected information database 50, an equipment database 60, and a robot database 70 to monitor each piece of equipment 10 in the facility 1 using one or more robots 30. The collected information database 50 records collected data from each robot 30. The equipment database 60 records equipment data for each piece of equipment 10 in the facility 1 and obstacle data for obstacles within the facility 1. Here, an obstacle may attenuate or reflect sounds other than those from the equipment 10 and not be a sound source under normal conditions. Examples of obstacles include pipes, storage tanks, supports, bulkheads, or other structures within the facility 1. The robot database 70 stores data related to each robot 30. These databases may be storage devices such as a hard disk connected to the monitoring device 40 via wired or wireless connections or cloud storage on the Internet, or may be temporarily stored in the memory of the monitoring device 40.

[0025] 2 shows the configuration of the control system 20 according to this embodiment, together with a display device 240 and an input device 250. The display device 240 displays a display screen output by the control system 20. The input device 250 inputs instructions for the control system 20 from users such as operators, workers, or maintenance personnel of the facility 1 and supplies the instructions to the control system 20. The display device 240 and the input device 250 may be provided in a monitoring console, a user terminal, or the like connected to the control system 20.

[0026] The control system 20 may be a computer such as a workstation, a server computer, a general-purpose computer, or another type of computer, or may be a computer system in which multiple computers are connected. Such a computer system is also a computer in a broad sense. The control system 20 may also be implemented as one or more virtual computer environments executable within a computer. Alternatively, the control system 20 may be a dedicated computer designed for controlling each device 10, or may be dedicated hardware realized by a dedicated circuit. In this embodiment, the control system 20 is installed within the facility 1, but the control system 20 may also be installed outside the facility 1 using a cloud computing system on the Internet, for example.

[0027] The control system 20 includes a status acquisition unit 210, a status determination unit 220, a display processing unit 230, an instruction input unit 260, and a device control unit 270. The status acquisition unit 210 acquires device status data indicating the status of each device 10 from each device 10, such as an internal state value of each device 10 and a measurement value measured by a sensor provided in each device 10. The status acquisition unit 210 may receive the device status data of each device 10 using communication using a communication protocol such as HART (registered trademark), BRAIN, Foundation Fieldbus (registered trademark), or ISA100.11a. The status acquisition unit 210 may receive, from the monitoring device 40, device status data of the device 10 detected by the monitoring device 40 using collected data collected by the robot 30.

[0028] The status determination unit 220 is connected to the status acquisition unit 210. The status determination unit 220 determines whether each device 10 is normal or abnormal using the device status data acquired by the status acquisition unit 210. The status determination unit 220 may calculate a health index indicating the health of operation of the entire facility 1 or a specific area within the facility 1 from at least one of the internal status values ​​or measurement values ​​of two or more devices 10, and determine whether the operation is normal or abnormal. The status determination unit 220 may determine whether at least some of the devices 10 are normal or abnormal by receiving from the monitoring device 40 a determination result of whether the monitoring device 40 determines whether the devices 10 are normal or abnormal, made by using data collected by the robot 30.

[0029] The display processing unit 230 is connected to the status acquisition unit 210 and the status determination unit 220. The display processing unit 230 performs display control to cause the display device 240 to display a display screen including device status data such as the internal status values ​​and measurement values ​​of each device 10, a health index for the entire facility 1 or a specific area within the facility 1, and an abnormality occurrence status of each device 10.

[0030] The instruction input unit 260 receives instructions from the user for the control system 20 from the input device 250. Such instructions may be instructions to change the operation of at least one device 10 from the user viewing the display screen displayed on the display device 240. The instruction input unit 260 may be connected to the monitoring device 40 and may be able to communicate with the monitoring device 40 via a wired or wireless connection. In response to the monitoring device 40 detecting an abnormality in at least one device 10, the instruction input unit 260 may receive, from the monitoring device 40, an instruction to perform control to deal with the abnormality.

[0031] The device control unit 270 is connected to the status acquisition unit 210 and the instruction input unit 260. The device control unit 270 controls each device 10 in accordance with the device status data acquired by the status acquisition unit 210. Upon receiving an instruction from a user or an instruction from the monitoring device 40, the device control unit 270 may control each device 10 in accordance with the instruction.

[0032] 3 shows a processing flow of the control system 20 according to this embodiment. In step 300 (S300), the status acquisition unit 210 acquires device status data indicating the status of each device 10 from each device 10. The status acquisition unit 210 may receive device data indicating the status of at least one device 10 from the monitoring device 40.

[0033] In S310, the status determination unit 220 determines whether each device 10 is normal or abnormal. The status determination unit 220 may determine whether the device 10 is normal (whether it is not abnormal) based on whether at least one of the internal state values ​​or measurement values ​​of the device 10 is within a predetermined normal range corresponding to that value. The status determination unit 220 may also calculate a health index indicating the health of operations in the entire facility 1 or a specific area within the facility 1 from at least one of the internal state values ​​or measurement values ​​of two or more devices 10 using a predefined calculation formula or the like, and determine whether operations in the entire facility 1 or a specific area within the facility 1 are normal based on whether the value of the health index is within the normal range.

[0034] In S320, the display processing unit 230 performs display control to cause the display device 240 to display a display screen including the internal state values ​​and measurement values ​​of each device 10, the health index for the entire facility 1 or a specific area within the facility 1, and the abnormality occurrence status of each device 10. The display processing unit 230 may generate a video output of the display screen and supply it to the display device 240, or may generate html, a script, or the like for generating the display screen and send it to the display device 240.

[0035] In S330, the instruction input unit 260 receives an instruction from the user to the control system 20 from the input device 250. The instruction input unit 260 may receive an instruction to perform control to deal with the abnormality, which is transmitted by the monitoring device 40 that has detected an abnormality in at least one device 10.

[0036] In S340, the device control unit 270 controls each device 10 in accordance with a predetermined control algorithm or control model, etc., using the device status data acquired by the status acquisition unit 210. The device control unit 270 may calculate a control value for each device 10 using PI control, PID control, etc. The device control unit 270 may calculate a control value for each device 10 according to the device status data acquired by the status acquisition unit 210, using various machine learning models, etc. The device control unit 270 may change the control content for each device 10 in response to an instruction from the instruction input unit 260.

[0037] The control system 20 repeats the processes from S300 to S340, thereby enabling the control system 20 to adaptively control each device 10 according to the state of each device 10.

[0038] 4 shows the configuration of a robot 30 according to this embodiment. The robot 30 includes one or more sensors 400, one or more sensors 410, one or more actuators 420, a status acquisition unit 430, a communication unit 440, and an actuator control unit 450.

[0039] Each of the one or more sensors 400 detects or measures conditions within the facility 1. In the example shown in this figure, sensor 400a is an acoustic sensor that detects sounds within the facility 1 and outputs the sound data. Sensor 400b is an image sensor that captures images within the facility 1 and detects the image data. Sensor 400c is a LiDAR sensor. By irradiating light or a laser beam to the outside and detecting the reflected light, sensor 400c measures at least one of the shape of each object within the irradiation range of the light or laser or the distance to each irradiation point, and outputs the measurement result as LiDAR data. The robot 30 may also be equipped with at least one of a temperature sensor, a humidity sensor, a gas sensor, or various other sensors.

[0040] Each of the one or more sensors 410 detects or measures the state of the robot 30. In the example shown in the figure, the sensor 410a is a position sensor that detects the position of the robot 30 and outputs the position data. The sensor 410a may be a GPS, and more specifically, a GPS receiver that receives signals from GPS (Global Positioning System) satellites to identify the position of the robot 30. Alternatively, the sensor 410a may be a sensor for identifying the position of the robot 30 using any position detection system that can detect the position of the robot 30 within the facility 1.

[0041] The sensor 410b is, for example, a direction sensor such as a geomagnetic sensor. The sensor 410b measures the direction of the robot 30 or the direction of the detection direction of each sensor 400. The sensor 410c is an angle sensor, an elevation angle sensor, or the like for measuring the detection direction of each sensor 400. The sensors 410b and 410c output direction data indicating at least one of the direction of the robot 30 or the detection direction of each sensor 400 to the state acquisition unit 430. The robot 30 may also be equipped with at least one of a speed sensor, an acceleration sensor, or various other sensors.

[0042] Each of the one or more actuators 420 is a motor or the like for driving each part of the robot 30. The robot 30 may be equipped with various types of actuators 420, such as an actuator 420 for movement by running, flying, or the like, an actuator 420 for changing the orientation of the entire robot 30 or a part of it, an actuator 420 for operating accessories such as an arm, and the like.

[0043] The state acquisition unit 430 is connected to one or more sensors 400 and one or more sensors 410. The state acquisition unit 430 acquires the state within the facility 1 measured by the one or more sensors 400 and the state of the robot 30 measured by the one or more sensors 410. The state acquisition unit 430 may acquire the state within the facility 1 by receiving various types of measurement data, such as acoustic data, image data, and LiDAR data, from the one or more sensors 400. The state acquisition unit 430 may acquire the state of the robot 30 by receiving various types of measurement data, such as position data and direction data, from the one or more sensors 410.

[0044] The communication unit 440 is connected to the status acquisition unit 430. The communication unit 440 communicates with the monitoring device 40 wirelessly or via a wire. The communication unit 440 transmits various measurement data acquired by the status acquisition unit 430 to the monitoring device 40. The communication unit 440 also receives various instructions for the robot 30 from the monitoring device 40.

[0045] The actuator control unit 450 controls each actuator 420 in accordance with various measurement data acquired by the status acquisition unit 430 and instructions from the monitoring device 40. This allows the robot 30 to perform operations corresponding to the status in the facility 1, the status of the robot 30, and instructions from the monitoring device 40.

[0046] Note that some of the robots 30 may be fixedly installed within the facility 1, and such robots 30 may not be equipped with actuators for movement. Also, within the facility 1, monitoring equipment (such as a monitoring camera or monitoring microphone) that is equipped with one or more sensors 400 but is not classified as a robot may be provided. Such monitoring equipment will have some of the functions and configuration of the robots 30. Therefore, for the sake of convenience in the description, this specification will assume that at least one of the robots 30 may be such a monitoring equipment, and that such monitoring equipment will perform the processes described below within the scope of the implemented functions.

[0047] 5 shows a processing flow of the robot 30 according to this embodiment. In S500, one or more sensors 400 observe the state of the facility 1 in the vicinity of the robot 30. One or more sensors 410 observe the state of the robot 30. The state acquisition unit 430 acquires various measurement data indicating the state of the facility 1 from the one or more sensors 400. The state acquisition unit 430 acquires various measurement data indicating the state of the robot 30 from the one or more sensors 410.

[0048] In S510, the communication unit 440 transmits various measurement data indicating the state of the facility 1 and the state of the robot 30 observed by one or more sensors 400 and one or more sensors 410 to the monitoring device 40. Here, when the measurement center direction of each sensor 400 coincides with the direction of the robot 30, that is, when, for example, a sensor unit or the like that mounts each sensor 400 faces the front of the robot 30, the measurement direction (measurement center direction) of each sensor 400 coincides with the direction of the robot 30. In such a case, if the robot 30 transmits its own direction to the monitoring device 40, the monitoring device 40 can obtain the measurement direction of each sensor 400.

[0049] If the orientation of the sensor unit mounting each sensor 400 is variable with respect to the robot 30 body, the central direction of measurement of each sensor 400 does not necessarily coincide with the orientation of the robot 30. In this case, the robot 30 may transmit to the monitoring device 40 direction data including the orientation of the robot 30 itself and the measurement direction of each sensor 400. Alternatively, the robot 30 may transmit to the monitoring device 40 direction data including the orientation of the robot 30 itself and the difference or offset of the measurement direction of each sensor 400 relative to the orientation of the robot 30 itself. In this case, the monitoring device 40 can obtain the measurement direction of each sensor 400 by adding the difference or offset of the measurement direction of each sensor 400 to the orientation of the robot 30 itself.

[0050] In S520, the communication unit 440 receives an instruction from the monitoring device 40. In S530, the actuator control unit 450 performs an operation in accordance with the instruction from the monitoring device 40. The actuator control unit 450 drives at least one actuator 420 in accordance with an instruction to move, an instruction to change direction, an instruction to change the direction of an acoustic sensor, an image sensor, or the like, received from the monitoring device 40, thereby causing the robot 30 to operate as instructed. The actuator control unit 450 may also set various parameters within the robot 30 in accordance with the instruction from the monitoring device 40.

[0051] The robot 30 repeats the processes from S500 to S530. As a result, the robot 30 can move within the facility 1 in response to instructions from the monitoring device 40, and perform operations such as collecting sound with the sensor 400a, capturing images with the sensor 400b, and acquiring LiDAR data with the sensor 400c.

[0052] 6 shows the configuration of the monitoring device 40 according to this embodiment, together with the collected information database 50, the equipment database 60, the robot database 70, the input device 680, and the display device 690. The input device 680 receives instructions from users, such as operators, workers, or maintenance personnel, of the facility 1, and supplies the instructions to the monitoring device 40. The display device 690 displays a display screen output by the monitoring device 40. The input device 680 and the display device 690 may be provided in a monitoring console or a user terminal connected to the monitoring device 40. The display device 690 and the input device 680 may be shared with the display device 240 and the input device 250 shown in FIG. 2.

[0053] The monitoring device 40 may be an equipment management device that manages each device 10 in the facility 1, or may be a device that realizes some of the functions included in the equipment management device. The monitoring device 40 may be a computer such as a workstation, a server computer, a general-purpose computer, or other computer, or may be a computer system in which multiple computers are connected. Such a computer system is also considered a computer in a broad sense. The monitoring device 40 may also be implemented as one or more virtual computer environments executable within a computer. Such a computer functions as the monitoring device 40 by executing a program for monitoring each device 10 using the robot 30. Alternatively, the monitoring device 40 may be a dedicated computer designed for monitoring each device 10, or may be dedicated hardware realized by dedicated circuits.

[0054] In this embodiment, the monitoring device 40 is installed inside the facility 1, but instead, the monitoring device 40 may be installed outside the facility 1 using a cloud computing system on the Internet or the like. Also, in this embodiment, the monitoring device 40 remotely controls each robot 30, but instead, the monitoring device 40 may be mounted on at least one robot 30 and directly operate each robot 30 or a group of robots including two or more robots 30 on site.

[0055] The monitoring device 40 includes a communication unit 600, a collected information database connection unit 620, an equipment database connection unit 630, a robot database connection unit 640, a monitoring processing unit 650, an input processing unit 660, a display processing unit 665, and a communication unit 670. The communication unit 600 communicates with the robot 30 wirelessly or via a cable. The communication unit 600 includes an acoustic data acquisition unit 602, an image data acquisition unit 604, a LiDAR data acquisition unit 606, a position data acquisition unit 608, a direction data acquisition unit 610, and an instruction transmission unit 612.

[0056] The acoustic data acquisition unit 602 acquires acoustic data detected by an acoustic sensor of the robot 30 within the facility 1. The image data acquisition unit 604 acquires image data captured within the facility 1. The image data acquisition unit 604 may acquire image data by receiving image data detected by the image sensor of the robot 30. The LiDAR data acquisition unit 606 acquires LiDAR data detected by the sensor 400c of the robot 30 within the facility 1.

[0057] The position data acquisition unit 608 acquires position data indicating the position of the robot 30. The position data acquisition unit 608 may acquire the position data by receiving position data transmitted by the robot 30. The direction data acquisition unit 610 acquires direction data indicating the directions of the robot 30 and each sensor 400. The direction data acquisition unit 610 may acquire the direction data by receiving direction data transmitted by the robot 30. The instruction transmission unit 612 transmits to the robot 30 instructions for the robot 30 determined within the monitoring device 40. Note that at least one of the acoustic data acquisition unit 602, the image data acquisition unit 604, the LiDAR data acquisition unit 606, the position data acquisition unit 608, and the direction data acquisition unit 610 is an example of an acquisition unit in the present application.

[0058] The collected information database connection unit 620 is connected to the collected information database 50, the communication unit 600, and the monitoring processing unit 650. The collected information database connection unit 620 records various measurement data acquired by the acoustic data acquisition unit 602, the image data acquisition unit 604, the LiDAR data acquisition unit 606, the position data acquisition unit 608, and the direction data acquisition unit 610 in the communication unit 600 as collected data in the collected information database 50. The collected information database connection unit 620 may add the position data acquired by the position data acquisition unit 608 and the direction data acquired by the direction data acquisition unit 610 to the acoustic data acquired by the acoustic data acquisition unit 602, and record the added data as collected data in the collected information database 50. The collected information database connection unit 620 also accesses the collected information database 50 in response to a request from the monitoring processing unit 650. If there is no need to record the history of collected data, the monitoring device 40 does not need to include the collected information database connection unit 620, and the measurement data acquired by the communication unit 600 may be supplied to the monitoring processing unit 650 without going through the collected information database connection unit 620. In this case, the collected information database 50 is not necessary.

[0059] The equipment database connection unit 630 is connected to the equipment database 60 and the monitoring processing unit 650. The equipment database connection unit 630 accesses the equipment database 60 in response to a request from the monitoring processing unit 650. The robot database connection unit 640 is connected to the robot database 70 and the monitoring processing unit 650. The robot database connection unit 640 accesses the robot database 70 in response to a request from the monitoring processing unit 650.

[0060] The monitoring processing unit 650 is connected to the collected information database connection unit 620, the equipment database connection unit 630, the robot database connection unit 640, the input processing unit 660, and the communication unit 670. The monitoring processing unit 650 reads out the robot data of each robot 30 via the robot database connection unit 640, and uses the robot data to determine the monitoring behavior within the facility 1 that each robot 30 should perform. The monitoring processing unit 650 instructs each robot 30 via the instruction transmission unit 612 in the communication unit 600 to perform each operation included in the determined monitoring behavior.

[0061] The monitoring processing unit 650 also reads out collected data collected by one or more robots 30, which is recorded in the collected information database 50, via the collected information database connection unit 620. Then, the monitoring processing unit 650 uses the collected data to detect the state of each device 10 monitored by each robot 30. The monitoring processing unit 650 uses the collected data to determine whether each device 10 is normal or abnormal. The monitoring processing unit 650 records the processing results for each device 10 in the collected information database 50 via the collected information database connection unit 620. The monitoring processing unit 650 may read out device data for each device 10 via the equipment database connection unit 630 and determine whether each device 10 is normal or abnormal based on the information registered in the device data.

[0062] The monitoring processing unit 650 may cause the display processing unit 665 to generate a display screen that displays the status of each device 10 and the determination result of normality or abnormality, and display the generated screen on the display device 690. The monitoring processing unit 650 may transmit the status of each device 10 and the determination result of normality or abnormality to the control system 20 via the communication unit 670.

[0063] The monitoring processing unit 650 may generate an instruction to perform control to deal with the abnormality in response to detecting an abnormality in at least one device 10 as a result of monitoring each device 10 using one or more robots 30. The monitoring processing unit 650 may transmit the instruction to perform control to deal with the abnormality in the device 10 to the control system 20 via the communication unit 670.

[0064] The input processing unit 660 is connected to the input device 680. The input processing unit 660 accepts information input from the user to the input device 680 and supplies the information to the monitoring processing unit 650. The display processing unit 665 is connected to the monitoring processing unit 650. The display processing unit 665 performs display processing to generate a display screen in response to an instruction from the monitoring processing unit 650 and display the screen on the display device 690.

[0065] The communication unit 670 is connected to the monitoring processing unit 650. The communication unit 670 may be connected to the control system 20 and may be able to communicate with the control system 20 wirelessly or via a wired connection. The communication unit 670 may transmit device status data of each device 10 detected by the monitoring processing unit 650 to the control system 20. The communication unit 670 may transmit the determination result of whether each device 10 is normal or abnormal, determined by the monitoring processing unit 650, to the control system 20. The communication unit 670 may transmit an instruction to perform control to deal with the abnormality, in response to detection of an abnormality in at least one device 10. Note that the communication unit 670 does not need to have the function of transmitting at least one of the device status data of the device 10, the determination result of whether the device 10 is normal or abnormal, or the instruction to perform control to deal with the abnormality, to the control system 20. If the monitoring device 40 does not have any of these functions, the communication unit 670 may not be provided with the communication unit 670.

[0066] According to the monitoring device 40 described above, by monitoring the facility 1 using one or more robots 30 that can move within the facility 1, it is possible to monitor a large number of devices 10 using a relatively small number of robots 30. Furthermore, since the monitoring device 40 can control the robots 30 in accordance with the situation at each observation point to collect necessary information, it becomes possible to detect the state of each device 10 that cannot be collected by sensors or the like that are installed in each device 10 in advance.

[0067] FIG. 7 shows an example of the data structure of the collected information database 50 according to this embodiment. The collected information database 50 records the measurement data collected from each robot 30 as collected data. The collected information database 50 may record one or more records, each of which is a unit of collected data. In the data structure of the collected information database 50 shown in this figure, each record of collected data is arranged in the row direction, and the collected data of each record includes the fields of "robot identification information," "date and time," "detection position," "sound source position," and "measurement data."

[0068] "Robot identification information" is a field for recording data values ​​such as an identification number or serial number for identifying the robot 30 that acquired the measurement data of the corresponding record, or other unique numbers or character strings that enable identification of the robot 30 that acquired the measurement data within the facility 1. "Date and time" is a field for recording the date and time when the measurement data of the corresponding record was detected by the robot 30. "Detection position" is a field for recording at least one position and direction of the robot 30 or each sensor 400 at the time when the measurement data of the corresponding record was detected. The collected information database 50 may record, as the "detection position," at least one of the position detected by the sensor 410a of the robot 30, the orientation of the robot 30 detected by the sensor 410b, or the direction of the robot 30 or each sensor 400 detected by the sensor 410c at the time indicated by the "date and time."

[0069] "Measurement data" is a field for recording measurement data detected by the robot 30 at the timing indicated by "Date and time." The data recorded as "Measurement data" may be various types of measurement data acquired by the robot 30, such as at least one of acoustic data, image data, and LiDAR data. "Sound source location" is a field for recording data indicating the sound source location estimated by the monitoring device 40 for sound components contained in the acoustic data. The data recorded as "Sound source location" may be coordinates indicating the sound source location on a map of the facility 1, or data indicating identification information of the equipment 10 or obstacle identified as the sound source.

[0070] The communication unit 600 in the monitoring device 40 may receive, as separate packets or packet groups, data including the date and time when the measurement data was acquired by the robot 30, the robot identification information of the robot 30, and measurement data related to the position and orientation of the robot 30, and data including the date and time when the measurement data was acquired by the robot 30, the robot identification information of the robot 30, and measurement data related to the state within the facility 1. In this case, the communication unit 600 updates the position and orientation of the robot 30 managed by the monitoring device 40 every time it receives measurement data related to the position and orientation of the robot 30. When the communication unit 600 receives measurement data related to the state within the facility 1, it generates a record of collected data by associating the measurement data with the position and orientation (detected position) of the robot 30 at the date and time when the measurement data was acquired. Alternatively, when the communication unit 440 in the robot 30 transmits various measurement data indicating the state of the facility 1 and the state of the robot 30 observed by each sensor 400 and each sensor 410 to the monitoring device 40 (see S510 in Figure 5), it may assemble one record's worth of collected data from this measurement data, encode it into one or more packets, and transmit it to the monitoring device 40.

[0071] FIG. 8 shows an example of the data structure of the equipment database 60 according to this embodiment. The equipment database 60 records equipment data for each of the multiple pieces of equipment 10 in the facility 1 and obstacle data for each obstacle in the facility 1 (hereinafter, the equipment data and obstacle data will also be referred to as equipment data). The equipment database 60 may record as many records as the number of pieces of equipment 10, each of which is equipment data for one piece of equipment. In the data structure of the equipment database 60 shown in this figure, each record of equipment data is arranged row-wise, and the equipment data of each record includes the fields of "equipment identification information," "equipment name," "equipment information," "position," "template," and "acoustic data."

[0072] The "Device Identification Information" field records a data value such as an identification number that identifies the corresponding device 10, a serial number, or other unique number or character string that enables the device 10 to be identified within the facility 1. The "Device Name" field records a device name assigned to the corresponding device 10 by a user or the like.

[0073] "Device Information" is a field for recording various information about the corresponding device 10. "Location" is a field for recording the location of the device 10 within the facility 1. "Template" is a field for recording image data (template image data) of the exterior of the corresponding device 10 to be used for identifying the device 10 by image matching. "Acoustic Data" is a field for recording at least one of acoustic data collected from the corresponding device 10 or acoustic data emitted by the device 10 when the corresponding device 10 is operating normally.

[0074] Furthermore, in the data structure of the facility database 60 shown in this figure, each record of obstacle data is arranged row-wise, and the obstacle data of each record includes the fields of "obstacle identification information," "position," and "template." "Obstacle identification information" is a field that records a data value such as an identification number, name, or other unique number or character string that identifies the corresponding obstacle within the facility 1. "Position" is a field that records at least one of the position or range of the obstacle within the facility 1. "Template" is a field that records image data (template image data) of the appearance of the corresponding obstacle to be used for identifying the obstacle by image matching.

[0075] FIG. 9 shows an example of the data structure of the robot database 70 according to this embodiment. The robot database 70 records robot data for one or more robots 30 in the facility 1. The robot database 70 may record as many records as there are robots 30, each of which is robot data for one robot. In the data structure of the robot database 70 shown in this figure, each record of robot data is arranged row-wise, and the robot data in each record includes fields for "robot identification information," "robot name," "robot information," "position and direction," and "schedule information."

[0076] "Robot identification information" is a field for recording data values ​​such as an identification number or serial number that identifies the corresponding robot 30, or other unique numbers or character strings that enable the robot 30 to be identified within the facility 1. "Robot name" is a field for recording a robot name assigned to the corresponding robot 30 by a user or the like.

[0077] "Robot information" is a field for recording various information related to the corresponding robot 30. "Position and direction" is a field for recording the position and direction of the corresponding robot 30 within the facility 1, and, if necessary, the direction of each sensor 400 (absolute direction or offset relative to the direction of the robot 30). "Schedule information" is a field for recording the schedule for the corresponding robot 30 to patrol the facility 1 and collect sounds within the facility 1.

[0078] 10 shows the configuration of the monitoring processing unit 650 of the monitoring device 40 according to this embodiment. The monitoring processing unit 650 includes an estimation unit 1010, an extraction unit 1020, a sound collection command unit 1030, a determination unit 1040, an abnormal device identification unit 1050, and an device command unit 1060. The monitoring processing unit 650 determines whether a target sound included in the acoustic data is an echo sound based on the deviation of the estimated sound source position, and detects an abnormality in the device 10.

[0079] The estimation unit 1010 is connected to the collected information database connection unit 620 and the equipment database connection unit 630. The estimation unit 1010 estimates an estimated sound source position for a sound component included in acquired sound data. The estimation unit 1010 reads collected data recorded in the collected information database 50, in which sound data is recorded as measurement data, via the collected information database connection unit 620. As a result, the estimation unit 1010 acquires the sound data, the date and time the sound data was acquired, and the detection position within the facility 1 at which the sound data was detected. The estimation unit 1010 extracts at least one sound component by performing sound source separation or the like on the acquired sound data, and estimates an estimated sound source position of the sound component. The estimation unit 1010 may access the equipment database 60 via the equipment database connection unit 630 and refer to each record to search for a device 10 or an obstacle within the facility 1 that corresponds to the estimated sound source position.

[0080] Here, for convenience of explanation, in this specification, a sound obtained by extracting at least a part of a sound collected by the sensor 400a is referred to as a "sound component," but the "sound component" itself is also sound. Therefore, the acoustic data, which is data on the sound collected by the sensor 400a, and the sound component data, which is data on the sound components, may be in the same data format.

[0081] The extraction unit 1020 is connected to the estimation unit 1010, the collected information database connection unit 620, the equipment database connection unit 630, and the sound collection command unit 1030. The extraction unit 1020 may extract, as the target sound, sound components estimated to have been detected from the same sound source at different detection positions from among sound components included in the sound data detected at multiple detection positions. The extraction unit 1020 may extract the target sound based on at least one of the sound pressure and frequency of the sound components included in the sound data detected at the multiple detection positions. The extraction unit 1020 may access the collected information database 50 or the equipment database 60 via the collected information database connection unit 620 or the equipment database connection unit 630 and refer to each record to search for whether a sound component identical to the sound component included in the sound data is recorded in association with the sound source position. If a sound component identical to the sound component is not recorded in the collected information database 50 or the equipment database 60 in association with the sound source position, the extraction unit 1020 may instruct the sound collection command unit 1030 to collect sound.

[0082] The sound collection command unit 1030 is connected to the instruction sending unit 612, the equipment database connection unit 630, and the robot database connection unit 640. The sound collection command unit 1030 determines an action to be performed by each robot 30 and instructs each robot 30 to perform the determined action. In response to a sound collection instruction from the extraction unit 1020, the sound collection command unit 1030 may instruct the corresponding robot 30 to collect sound.

[0083] The determination unit 1040 is connected to the extraction unit 1020, the collected information database connection unit 620, and the equipment database connection unit 630. The determination unit 1040 determines whether a target sound is an echo based on the amount of deviation between multiple estimated sound source positions for the target sound included in sound data detected at multiple different detection positions. The determination unit 1040 may determine that the target sound included in sound data detected at multiple different detection positions is an echo when the target sound is not recorded in association with a sound source position in at least one of the collected information database 50 or the equipment database 60 and the amount of deviation between the multiple estimated sound source positions is equal to or greater than a predetermined threshold. The determination unit 1040 may record information corresponding to the determination regarding the target sound in at least one of the collected information database 50 or the equipment database 60 via at least one of the collected information database connection unit 620 or the equipment database connection unit 630.

[0084] The abnormal device identifying unit 1050 is connected to the determining unit 1040, the equipment database connection unit 630, the device command unit 1060, and the display processing unit 665. The abnormal device identifying unit 1050 may detect an abnormality only for target sounds that the determining unit 1040 has determined not to be reverberation sounds. The abnormal device identifying unit 1050 identifies an abnormality in the device 10 that is the sound source, using sound component data associated with each device 10. The abnormal device identifying unit 1050 may cause the display processing unit 665 to generate a display screen that displays the status of each device 10 detected by the robot 30 on the display device 690, and display the display screen on the display device 690. The abnormal device identifying unit 1050 may also cause the display processing unit 665 to generate a display screen that displays the determination result of whether each device 10 is normal or abnormal on the display device 690, and display the display screen on the display device 690.

[0085] The equipment command unit 1060 is connected to the abnormal equipment identification unit 1050. In response to identification of an abnormality in any of the equipment 10 that is the source of the sound component, the equipment command unit 1060 performs control on at least one of the equipment 10 in which an abnormality has been identified or the other equipment 10 in the facility 1 to deal with the abnormality in the equipment 10. The equipment command unit 1060 transmits an instruction to the instruction input unit 260 in the control system 20 via the communication unit 670 to perform control to deal with the abnormality in the equipment 10.

[0086] The monitoring processing unit 650 described above has the components shown in Fig. 10 in order to realize functions such as identifying the device 10 that is the source of each sound component, identifying the abnormality in the source device 10 based on the abnormality level of the sound component, issuing control instructions to deal with the abnormality in the device 10, and issuing operation instructions to each robot 30. Alternatively, the monitoring processing unit 650 may have a configuration that does not include some of the components shown in Fig. 10.

[0087] For example, the monitoring processing unit 650 may not have the equipment command unit 1060 and may not issue control instructions to deal with an abnormality in the equipment 10. Furthermore, the monitoring processing unit 650 may not have the sound collection command unit 1030 and may not issue operation instructions to the robots 30. Furthermore, the monitoring processing unit 650 may not have the abnormal equipment identification unit 1050 and may not identify an abnormality in the equipment 10 that is the source of the sound based on the degree of abnormality of the sound component. Even in cases where the monitoring device 40 does not have some of the functions exemplified here, the user of the monitoring device 40 can receive information output or displayed by the monitoring device 40, discover an abnormality in the equipment 10, and cause at least one of the equipment 10 in the facility 1 to take technical measures to deal with the abnormality in the equipment 10.

[0088] The monitoring device 40 described above collects acoustic data detected within the facility 1 and determines reflected sounds, thereby enabling highly accurate identification of the devices 10 that are the sound sources of each sound component contained in the acoustic data. This allows the monitoring device 40 to analyze, from the sound components originating from the devices 10, the latent state of each device 10 that may not be detectable from the state of each device 10 collected by the control system 20. Furthermore, the monitoring device 40 can quickly collect abnormal sounds emitted by devices 10 installed in various locations within the facility 1, enabling prompt response to abnormalities in the devices 10.

[0089] Fig. 11 shows a processing flow of the monitoring device 40 according to this embodiment. For ease of explanation, the processing flow of Fig. 11 shows a case where the monitoring device 40 monitors the inside of the facility 1 using one robot 30. The monitoring device 40 may execute the processing flow of Fig. 11 for each of the multiple robots 30.

[0090] In S1100, the sound collection command unit 1030 instructs the target robot 30 to move within the facility 1 via the command transmission unit 612. Here, the sound collection command unit 1030 may obtain a schedule for the target robot 30 to patrol the facility 1 by referring to schedule information recorded in the robot database 70 in association with the target robot 30. This schedule may include information necessary for determining the operation of the robot 30, such as the location of each observation point where the robot 30 should observe the state of the facility 1, the time when the robot 30 should arrive at each observation point, the travel route between the observation points, or the observation direction at each observation point. In accordance with the schedule, the sound collection command unit 1030 moves the robot 30 to the next observation point and issues an instruction to the robot 30 to perform observation at the next observation point. In response to this, the robot 30 moves to the next observation point (see S520 and S530 in FIG. 5). If an area within facility 1 where an abnormality may have occurred is identified, the sound collection command unit 1030 may instruct at least one robot 30 to head toward that area and to move to various positions within that area to acquire acoustic data, etc.

[0091] In S1110, the robot 30 observes the state of the facility 1 and the state of the robot 30 using each sensor 400 at the observation point (see S500 in FIG. 5). The robot 30 transmits various measurement data indicating the observed state of the facility 1 and the state of the robot 30 to the monitoring device 40 (see S510 in FIG. 5). The acoustic data acquisition unit 602 in the monitoring device 40 acquires acoustic data from the measurement data transmitted from the robot 30. The collected information database connection unit 620 may add the position data acquired by the position data acquisition unit 608 and the direction data acquired by the direction data acquisition unit 610 to the acoustic data acquired by the acoustic data acquisition unit 602, and record the added data as collected data in the collected information database 50.

[0092] In S1120, the estimation unit 1010 extracts at least one sound component by performing sound source separation or the like on the sound data from the robot 30. The estimation unit 1010 may perform sound source separation by extracting from the sound data at least one sound component whose sound source directions as seen from the robot 30 are different from each other. The estimation unit 1010 may estimate the estimated sound source position of each sound component (sound source localization).

[0093] Here, each sensor 400a collects sounds from a range of predetermined directions other than the center direction of measurement of the sensor 400a according to its directivity, and therefore collects a sound that is a composite of sounds from various sound sources. The estimation unit 1010 performs a process of separating or decomposing the sounds collected by each sensor 400a into sounds generated by each sound source.

[0094] The estimation unit 1010 may use various sound source separation and sound source localization techniques. For example, the robot 30 may have a sensor unit (e.g., a microphone array) in which two or more sensors 400a are arranged two-dimensionally, and the acoustic data received by the monitoring device 40 may include acoustic data for each channel that records sounds collected by each sensor 400a.

[0095] The estimation unit 1010 may calculate the sound source position of each sound component relative to the robot 30 from the time difference between when each sound component included in the acoustic data reaches each sensor 400a. Here, the estimation unit 1010 may calculate the relative position of the sound source of each sound component with respect to the detection position of a sensor unit including two or more sensors 400a, and calculate the absolute position of the sound source of each sound component within the facility 1 using the absolute positions of the sensor units within the facility 1. Here, the absolute position may be coordinates on a map of the entire facility 1 or a partial area. The relative position means a position expressed with an arbitrarily selected reference position (such as the detection position of the robot 30) as the origin.

[0096] The estimation unit 1010 may also calculate the direction of the sound source of each sound component relative to the robot 30 from the time difference between the arrival times of each sound component included in the acoustic data at each sensor 400a. Here, the estimation unit 1010 may calculate the relative direction of the sound source of each sound component with respect to the measurement direction of a sensor unit including two or more sensors 400a, and add this to the absolute direction in which the sensor unit itself is facing (the direction of the center of measurement), thereby calculating the absolute direction of the sound source of each sound component at the observation point. Here, the absolute direction refers to an angle expressed with a common reference direction (such as north) at least within the facility 1 as the origin, such as the horizontal and vertical angles with north as the reference. The relative direction refers to an angle expressed with an arbitrarily selected reference direction (such as the traveling direction of the robot 30) as the origin.

[0097] The robot 30 may also have a sensor 400a such as a directional microphone, and may acquire acoustic data while changing the orientation of the sensor 400a within a predetermined range of directions relative to the robot 30. For example, the robot 30 may acquire acoustic data while changing the orientation of the sensor 400a within the range of the angle of view of image data captured by the sensor 400b. Using such acoustic data, the estimation unit 1010 may identify the orientation of the sensor 400a when the magnitude (sound pressure) of each sound component is maximum as the direction of the sound source of that sound component.

[0098] The estimation unit 1010 may use the identified direction of the sound source to estimate the estimated position of the sound source from a map that shows the positions of the devices 10 and obstacles in the facility 1. The estimation unit 1010 may estimate, as the estimated position of the sound source, the device 10 or obstacle that is closest to the detection position among the devices 10 or obstacles that overlap with a straight line extending from the detection position in the direction of the sound source on the map.

[0099] Furthermore, the estimation unit 1010 may estimate the estimated sound source position from the acoustic data using the image data acquired by the image data acquisition unit 604. The image data acquisition unit 604 in the monitoring device 40 acquires image data from the measurement data transmitted from the robot 30.

[0100] The estimation unit 1010 detects one or more devices 10 and obstacles captured in the image data by performing image recognition or the like on the image data from the robot 30. The estimation unit 1010 may extract one or more objects captured in the image data, and search the equipment database 60 for devices 10 or obstacles corresponding to each object, thereby detecting the devices 10 or obstacles corresponding to each object. Here, the estimation unit 1010 may search the equipment database 60 for devices 10 or obstacles located in the direction of the robot 30 or the sensor 400b at the time the image data is acquired, based on the position of the robot 30 at this time.

[0101] The estimation unit 1010 may recognize each device 10 or each obstacle included in the image data using vision-based augmented reality (AR) technology. For example, the estimation unit 1010 may recognize each device 10 or each obstacle included in the image data using markerless AR technology. The estimation unit 1010 may detect at least one device 10 or each obstacle included in the image data by matching it with a predetermined template. For example, the estimation unit 1010 extracts one or more objects captured in the image data and searches the equipment database 60 for devices 10 or obstacles associated with template image data that matches or is most similar to the image of each object. The estimation unit 1010 may detect the device 10 or obstacle found for each object as a device 10 or obstacle located in an image range in the image data that includes the object. The estimation unit 1010 may determine that the equipment 10 or obstacle corresponds to the object when the template image data associated with the equipment 10 or obstacle searched from the equipment database 60 using the position of the robot 30 and the direction of the robot 30 or the sensor 400b at the time the image data was acquired matches or is similar to the image of the object in the image data in the image range corresponding to the direction of the sensor 400b based on the position of the robot 30 with a similarity equal to or greater than a predetermined threshold.

[0102] The estimation unit 1010 may recognize each device 10 or each obstacle included in the image data using AR technology that uses markers. In this case, the device data and obstacle data stored in the equipment database 60 may store identification information of the marker attached to the corresponding device 10 or obstacle. The estimation unit 1010 may search the equipment database 60 for a device 10 or obstacle associated with device data or obstacle data that stores identification information that matches the identification information of the marker included in the image data.

[0103] The estimation unit 1010 identifies which device 10 or obstacle captured in the image data is the source of each sound component included in the sound data. For each sound component extracted from the sound data, the estimation unit 1010 may identify, among the devices 10 or obstacles detected from the image data, the device 10 or obstacle located in an area in the image data corresponding to the direction of the sound source as the estimated sound source position. As an example, for a sound component and a certain device 10 or obstacle detected from the sound data and image data observed by the robot 30 at the same position at the same time or at different times, the estimation unit 1010 may determine that the estimated sound source of the sound component is the device 10 or obstacle if the absolute direction of the sound component and the absolute direction of the device 10 or obstacle as viewed from the observation point are the same, or if the difference between the absolute directions is within a predetermined error range. For equipment 10 or obstacles that have already been registered in the equipment database 60, it may be assumed that the sound source of the sound component is this equipment 10 or obstacle, provided that the equipment 10 or obstacle is located in the absolute direction of the sound component as seen from the observation point of the acoustic data.

[0104] In S1130, the extraction unit 1020 extracts target sounds estimated to be sound components from the same sound source from among sound components included in sound data from a plurality of different detection positions. The extraction unit 1020 may extract, as the target sounds, sound components having the same vibration pattern (frequency and sound pressure) on the time axis from among sound components included in sound data detected at a plurality of different detection positions. The extraction unit 1020 may extract, as the target sounds, sound components whose similarity, calculated by comparing Mel spectra obtained by Fourier transforming sound components included in sound data detected at a plurality of different detection positions, is within a predetermined range (i.e., sound components that are similar or match each other). The extraction unit 1020 may extract, as the target sounds, sound components whose difference in sound pressure (maximum value or average value) is within a predetermined range from among sound components included in sound data from a plurality of different detection positions.

[0105] The extraction unit 1020 may compare sound components at different detection positions in either the time domain or the frequency domain. When performing the comparison in the time domain, the extraction unit 1020 may adjust the phase difference so that the time integral of the difference (such as the absolute value of the difference) between the data of the sound components at different detection positions is minimized, and may use the time integral of the difference between the data at the adjusted phase difference as the similarity. In this case, the extraction unit 1020 may adjust the amplitude so that the average amplitude matches, for example, to match the loudness of the data of the sound components. The extraction unit 1020 may extract, as the target sound, a sound component whose calculated similarity is within a predetermined range (i.e., the sound components are similar or match). Here, the similarity may be a value indicating that the sound components are more similar to each other, with a smaller value.

[0106] When comparing sound components in the frequency domain, the extraction unit 1020 may calculate the similarity by integrating, in the frequency domain, the difference (such as the absolute value of the difference) for each frequency between the frequency spectrum of sound component data corresponding to one detection position and the frequency spectrum of sound component data corresponding to the other detection position. In this case, the extraction unit 1020 may adjust the volume of the sound so that the sound component data can be compared. The extraction unit 1020 may extract, as the target sound, a sound component whose calculated similarity is within a predetermined range (i.e., the sound components are similar or identical). Here, the similarity may be a value indicating that the sound components are more similar to each other, with a smaller value.

[0107] The extraction unit 1020 may extract the target sound from sound components included in the acoustic data where the distance between the detection positions is less than a predetermined threshold. The extraction unit 1020 may extract the target sound from a plurality of different detection positions for each of the areas obtained by dividing the facility 1 into a plurality of areas. The extraction unit 1020 may extract the target sound from a plurality of different detection positions where the period between the different detection times is within a predetermined range. This allows the extraction unit 1020 to extract the target sound from a plurality of detection positions that are closer to each other.

[0108] Furthermore, the extraction unit 1020 may extract the target sound using the estimated sound source position. When the estimated sound source position of a sound component included in the sound data is not recorded as a sound source position in the collected information database 50 or the equipment database 60, the extraction unit 1020 may extract the sound component as the target sound. The extraction unit 1020 may search for a sound source position corresponding to the estimated sound source position of the sound component included in the sound data by accessing the equipment database 60 via the equipment database connection unit 630 and referring to each record of the data. The extraction unit 1020 may search for a sound source position corresponding to the estimated sound source position of the sound component included in the sound data by accessing the collected information database 50 via the collected information database connection unit 620 and referring to each record of the data. The extraction unit 1020 may search for the device 10 or the obstacle estimated as the estimated sound source position of the sound component in the collected information database 50 or the equipment database 60.

[0109] Furthermore, when the estimated sound source position of a sound component included in the sound data is recorded as a sound source position in the collected information database 50 or the equipment database 60, the extraction unit 1020 may extract the sound component included in the sound data as the target sound if the similarity between the sound component recorded in association with the sound source position and the sound component included in the sound data is outside a predetermined range (i.e., the recorded sound component and the sound component included in the sound data are not similar or do not match).

[0110] The extraction unit 1020 may instruct the sound collection command unit 1030 to acquire new sound data corresponding to the target sound at a different detection position in order to determine the reverberant sound. When the sound component included in the sound data is not recorded in the collected information database 50 or the equipment database 60 in association with the sound source position, the extraction unit 1020 may instruct the sound collection command unit 1030 to collect sound at a detection position different from the detection position of the extracted target sound. The extraction unit 1020 may instruct the sound collection command unit 1030 of a detection position at which to detect new sound data. The extraction unit 1020 may instruct the sound collection command unit 1030 to set a position within a predetermined range based on the detection position of the target sound as the detection position at which to detect the new sound data. As a result, when the sound data acquisition unit 602 acquires sound data including sound components that are not recorded in association with a sound source position in the collected information database 50 or the equipment database 60, the sound collection command unit 1030 can instruct the robot 30 to collect sound at a detection position different from the detection position of the sound data acquired by the sound data acquisition unit 602. The sound collection command unit 1030 may send command data to the sound collection device to collect sound at the detection position instructed by the extraction unit 1020. The monitoring device 40 may execute S1100-S1130 for newly detected sound data.

[0111] The extraction unit 1020 may extract a target sound whose sound pressure is equal to or greater than a predetermined threshold. The extraction unit 1020 may extract a target sound whose maximum or average sound pressure is equal to or greater than a predetermined threshold. The extraction unit 1020 may use a predetermined threshold input by a user. The extraction unit 1020 may use a value according to the sound pressure of multiple sound components of the sound data at one detection position (for example, the average value of the maximum sound pressures of the multiple sound components of the sound data, or the average value of the sound pressures of the multiple sound components of the sound data) as the predetermined threshold. This allows the extraction unit 1020 to exclude sound components whose sound pressure has decreased due to multiple reverberations from the target sound, thereby reducing the number of times the reverberation sound is determined.

[0112] The extraction unit 1020 may output the extracted data of the target sound and the estimated sound source position to the determination unit 1040. The extraction unit 1020 may record data of sound components other than the target sound in the collected information database 50 or the equipment database 60 via the collected information database connection unit 620 or the equipment database connection unit 630 in association with the sound source position.

[0113] In S1140, the determination unit 1040 determines whether the target sound extracted by the extraction unit 1020 is a reverberation sound based on the amount of deviation between multiple estimated sound source positions for the target sound. The determination unit 1040 may determine that the target sound is a reverberation sound when the amount of deviation between the estimated sound source positions for the target sound included in sound data detected at multiple different detection positions is equal to or greater than a predetermined threshold. On the other hand, the determination unit 1040 may determine that the target sound is not a reverberation sound (i.e., a direct sound) when the amount of deviation between the estimated sound source positions for the target sound included in sound data detected at multiple different detection positions is less than a predetermined threshold. The determination unit 1040 may calculate the distance between the estimated sound source positions corresponding to the multiple detection positions of the target sound as the amount of deviation. The determination unit 1040 may use a predetermined threshold input by the user. Furthermore, the determination unit 1040 may set a larger value as the predetermined threshold as the distance between the corresponding detection positions increases.

[0114] The determination unit 1040 may determine that a target sound included in sound data detected at a plurality of different detection positions is not a reverberation sound if the amount of deviation of the estimated sound source position is equal to or greater than a predetermined threshold and the direction of movement between the plurality of detection positions differs from the direction of movement between the estimated sound source positions. The determination unit 1040 may determine that the target sound is not a reverberation sound if the direction of movement from the estimated sound source position of the target sound at an earlier detection time to the estimated sound source position of the target sound at a later detection time does not match the direction of movement from the detection position at the earlier detection time to the detection position at the later detection time or is deviated by a predetermined angle. On the other hand, the determination unit 1040 may determine that a target sound included in sound data detected at a plurality of different detection positions is a reverberation sound if the amount of deviation of the estimated sound source position is equal to or greater than a predetermined threshold and the direction of movement between the plurality of detection positions matches the direction of movement between the estimated sound source positions. The determination unit 1040 may use a predetermined angle input by the user. Furthermore, the greater the distance between the corresponding detection positions, the greater the value set as the predetermined angle by the determination unit 1040. This allows the determination unit 1040 to distinguish sound components when the sound source itself is moving from reverberation.

[0115] The determination unit 1040 may further determine whether the target sound is a reverberation sound based on the sound pressure of the target sound included in the sound data detected at a plurality of different detection positions. The determination unit 1040 may further determine that the target sound is a reverberation sound if the difference in sound pressure of the target sound at a plurality of different detection positions (for example, the difference in maximum sound pressure or the difference in average sound pressure) is equal to or greater than a predetermined threshold. The determination unit 1040 may use a predetermined threshold input by a user. The determination unit 1040 may set the difference in maximum or average sound pressure of sound components other than the target sound at a plurality of different detection positions as the predetermined threshold. This allows the determination unit 1040 to detect reverberation sounds from different obstacles according to the sound pressure of the target sound.

[0116] The determining unit 1040 may determine whether a target sound included in sound data detected at a plurality of different detection positions is a reverberant sound based on image data detected at the plurality of detection positions. The determining unit 1040 may determine that a target sound whose estimated sound source position estimated by the estimating unit 1010 in S1120 is an obstacle (such as a partition wall, for example) is a reverberant sound.

[0117] In S1150, the determination unit 1040 may instruct at least one of the collected information database connection unit 620 and the equipment database connection unit 630 to record data of the target sound in at least one of the collected information database 50 and the equipment database 60, in response to the determination. In response to the instruction from the determination unit 1040, at least one of the collected information database connection unit 620 and the equipment database connection unit 630 may record data of the target sound determined by the determination unit 1040 not to be an echo sound in at least one of the collected information database 50 and the equipment database 60, in association with a sound source position corresponding to the estimated sound source position. The determination unit 1040 may instruct at least one of the collected information database connection unit 620 and the equipment database connection unit 630 to record data of the target sound determined to be an echo sound in at least one of the collected information database 50 and the equipment database 60, in association with information indicating that the target sound is an echo sound (for example, a label, etc.).

[0118] In S1160, the abnormal device identifying unit 1050 detects the degree of abnormality of the sound components and identifies the abnormality of the device using the sound component data associated with each device 10. Here, the degree of abnormality may be expressed as a real number or an integer within a predetermined range such as 0 to 1 or 0 to 100%, or may be a binary value such as normal or abnormal.

[0119] If the acoustic data emitted by the device 10 when the device 10 is normal is recorded in the equipment database 60, the abnormal device identifying unit 1050 may calculate, as the degree of abnormality, a value indicating how much the sound component data of the target originating from the device 10 differs from the acoustic data emitted by the device 10 when normal. For example, the abnormal device identifying unit 1050 may determine the degree of abnormality according to the result of comparing the acoustic data when normal with the sound component data of the target.

[0120] The abnormal device identifying unit 1050 identifies an abnormality in the device 10 that is the source of the sound component based on the abnormality level of the sound component associated with the device 10. For example, the abnormal device identifying unit 1050 may identify the device 10 that is the source of the sound component as abnormal if the abnormality level of the sound component exceeds a predetermined threshold. The abnormal device identifying unit 1050 may cause the display processing unit 665 to display on the display device 690 a display screen that displays the status of each device 10 detected by the robot 30.

[0121] In S1170, when an abnormality is identified in any of the devices 10 that are sound sources, the device command unit 1060 performs control to deal with the abnormality in the device 10, on at least one of the device 10 in which the abnormality is identified or the other devices 10. The device command unit 1060 transmits an instruction to the control system 20 via the communication unit 670 to perform control to deal with the abnormality in the device 10.

[0122] As an example, the equipment command unit 1060 may instruct the control system 20 to perform control to stop the operation of the equipment 10 in which an abnormality has been identified. The equipment command unit 1060 may acquire, from the equipment database 60, other equipment 10 that is related to the equipment 10 in which an abnormality has been identified (for example, equipment 10 in an upstream or downstream process of the equipment 10 in which an abnormality has been identified), and instruct the control system 20 to perform control to stop the other equipment 10. The equipment command unit 1060 may also instruct the control system 20 to perform control to stop the operation of both the equipment 10 in which an abnormality has been identified and the other equipment 10 that is related to the equipment 10 in which an abnormality has been identified. The monitoring device 40 advances the process to S1100 and continues monitoring the facility 1 with the robot 30.

[0123] Fig. 12 is an explanatory diagram for explaining the determination of echoes of acoustic data at multiple detection positions. In Fig. 12, the robot 30 moves from detection position a to detection position b and detects acoustic data at each detection position. In Fig. 12, the dashed arrow indicates the echoes of sound from the device 10 reflected by a partition wall, and the solid arrow indicates the direct sound from the device 10 to the robot 30.

[0124] The sound data acquisition unit 602 acquires sound data detected at detection position a and detection position b, respectively. The estimation unit 1010 estimates an estimated sound source position a corresponding to the sound component of reflected sound a from the sound data detected at detection position a, and estimates an estimated sound source position corresponding to the sound component of direct sound. The estimation unit 1010 estimates an estimated sound source position b corresponding to the sound component of reflected sound b from the sound data detected at detection position b, and estimates an estimated sound source position corresponding to the sound component of direct sound. The extraction unit 1020 extracts reflected sound a and reflected sound b, whose estimated sound source positions are shifted, as target sounds. The extraction unit 1020 does not extract the direct sound as target sound because the direct sound is recorded in association with the device 10 in the equipment database 60 and the estimated sound source positions are not shifted. The determining unit 1040 determines that the sound components corresponding to the estimated sound source positions a and b are reverberation sounds because the distance (amount of deviation) between the estimated sound source positions a and b is equal to or greater than a predetermined threshold and the direction of movement of the robot (direction from detection position a toward detection position b) and the direction of deviation (direction from estimated sound source position a toward estimated sound source position b) match. The determining unit 1040 instructs the collected information database connecting unit 620 to associate the data of the sound components corresponding to the estimated sound source positions a and b that have been determined to be reverberation sounds with a label indicating that they are reverberation sounds and record them in the collected information database 50.

[0125] The monitoring device 40 of this embodiment can record acoustic data detected within the facility 1 while distinguishing between reverberant sounds and sound components contained in the acoustic data, and can accurately identify equipment abnormalities from the acoustic data.

[0126] Various embodiments of the present invention may be described with reference to flowcharts and block diagrams, where the blocks may represent (1) stages of a process in which operations are performed or (2) sections of an apparatus responsible for performing the operations. Particular stages and sections may be implemented by dedicated circuitry, programmable circuitry provided with computer-readable instructions stored on a computer-readable medium, and / or a processor provided with computer-readable instructions stored on a computer-readable medium. Dedicated circuitry may include digital and / or analog hardware circuitry, and may include integrated circuits (ICs) and / or discrete circuits. Programmable circuitry may include reconfigurable hardware circuitry, including logical AND, OR, XOR, NAND, NOR, and other logical operations, flip-flops, registers, memory elements such as field programmable gate arrays (FPGAs), programmable logic arrays (PLAs), and the like.

[0127] A computer-readable medium may include any tangible device capable of storing instructions that are executed by an appropriate device, such that the computer-readable medium having instructions stored thereon comprises an article of manufacture containing instructions that can be executed to create means for performing the operations specified in the flowcharts or block diagrams. Examples of computer-readable media may include electronic, magnetic, optical, electromagnetic, and semiconductor storage media. More specific examples of computer-readable media may include floppy disks, diskettes, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), electrically erasable programmable read-only memory (EEPROM), static random access memory (SRAM), compact disc read-only memory (CD-ROM), digital versatile disc (DVD), Blu-ray disc, memory stick, integrated circuit card, and the like.

[0128] The computer readable instructions may include either assembler instructions, Instruction Set Architecture (ISA) instructions, machine instructions, machine-dependent instructions, microcode, firmware instructions, state-setting data, or source or object code written in any combination of one or more programming languages, including object-oriented programming languages ​​such as Smalltalk®, JAVA®, C++, etc., and conventional procedural programming languages ​​such as the “C” programming language or similar programming languages.

[0129] The computer-readable instructions may be provided to a processor or programmable circuitry of a programmable data processing apparatus, such as a general-purpose computer, special-purpose computer, or other computer, either locally or over a wide-area network (WAN) such as a local area network (LAN), the Internet, etc., which executes the computer-readable instructions to create means for performing the operations specified in the flowcharts or block diagrams. Examples of processors include computer processors, processing units, microprocessors, digital signal processors, controllers, microcontrollers, etc.

[0130] 13 illustrates an example of a computer 2200 in which aspects of the present invention may be embodied, in whole or in part. Programs installed on the computer 2200 may cause the computer 2200 to function as or perform operations associated with an apparatus or one or more sections of the apparatus according to embodiments of the present invention, and / or to perform a process or steps of a process according to embodiments of the present invention. Such programs may be executed by the CPU 2212 to cause the computer 2200 to perform specific operations associated with some or all of the blocks in the flowcharts and block diagrams described herein.

[0131] A computer 2200 according to this embodiment includes a CPU 2212, a RAM 2214, a graphics controller 2216, and a display device 2218, which are interconnected by a host controller 2210. The computer 2200 also includes input / output units such as a communication interface 2222, a hard disk drive 2224, a DVD-ROM drive 2226, and an IC card drive, which are connected to the host controller 2210 via an input / output controller 2220. The computer also includes legacy input / output units such as a ROM 2230 and a keyboard 2242, which are connected to the input / output controller 2220 via an input / output chip 2240.

[0132] The CPU 2212 operates according to programs stored in the ROM 2230 and RAM 2214, thereby controlling each unit. The graphics controller 2216 acquires image data generated by the CPU 2212 into a frame buffer or the like provided in the RAM 2214 or into the graphics controller 2216 itself, and causes the image data to be displayed on the display device 2218.

[0133] The communications interface 2222 communicates with other electronic devices via a network. The hard disk drive 2224 stores programs and data used by the CPU 2212 in the computer 2200. The DVD-ROM drive 2226 reads programs or data from the DVD-ROM 2201 and provides the programs or data to the hard disk drive 2224 via the RAM 2214. The IC card drive reads programs and data from an IC card and / or writes programs and data to an IC card.

[0134] The ROM 2230 stores therein a boot program or the like that is executed by the computer 2200 upon activation, and / or programs that depend on the hardware of the computer 2200. The input / output chip 2240 may also connect various input / output units to the input / output controller 2220 via a parallel port, a serial port, a keyboard port, a mouse port, etc.

[0135] The programs are provided by a computer-readable medium such as a DVD-ROM 2201 or an IC card. The programs are read from the computer-readable medium, installed in the hard disk drive 2224, RAM 2214, or ROM 2230, which are also examples of computer-readable media, and executed by the CPU 2212. Information processing described in these programs is read by the computer 2200, and brings about cooperation between the programs and the various types of hardware resources described above. An apparatus or method may be configured by realizing information manipulation or processing in accordance with the use of the computer 2200.

[0136] For example, when communication is performed between the computer 2200 and an external device, the CPU 2212 may execute a communication program loaded into the RAM 2214 and instruct the communication interface 2222 to perform communication processing based on the processing described in the communication program. Under the control of the CPU 2212, the communication interface 2222 reads transmission data stored in a transmission buffer processing area provided in the RAM 2214, the hard disk drive 2224, the DVD-ROM 2201, or a recording medium such as an IC card, and transmits the read transmission data to the network, or writes reception data received from the network to a reception buffer processing area or the like provided on the recording medium.

[0137] The CPU 2212 may also cause all or a necessary portion of a file or database stored on an external recording medium such as the hard disk drive 2224, the DVD-ROM drive 2226 (DVD-ROM 2201), an IC card, etc. to be read into the RAM 2214, and perform various types of processing on the data on the RAM 2214. The CPU 2212 then writes back the processed data to the external recording medium.

[0138] Various types of information, such as various types of programs, data, tables, and databases, may be stored on the recording medium and may undergo information processing. The CPU 2212 may perform various types of processing on data read from the RAM 2214, including various types of operations, information processing, conditional judgment, conditional branching, unconditional branching, information search / replacement, etc., as described throughout this disclosure and specified by the instruction sequences of the programs, and write the results back to the RAM 2214. The CPU 2212 may also search for information in a file, database, etc. on the recording medium. For example, if multiple entries each having an attribute value of a first attribute associated with an attribute value of a second attribute are stored on the recording medium, the CPU 2212 may search for an entry that matches a condition specified by the attribute value of the first attribute from among the multiple entries, read the attribute value of the second attribute stored in the entry, and thereby obtain the attribute value of the second attribute associated with the first attribute that satisfies a predetermined condition.

[0139] The above-described programs or software modules may be stored in a computer-readable medium on or near the computer 2200. A recording medium such as a hard disk or RAM provided in a server system connected to a dedicated communication network or the Internet can also be used as a computer-readable medium, thereby providing the programs to the computer 2200 via the network.

[0140] Although the present invention has been described above using embodiments, the technical scope of the present invention is not limited to the scope described in the above embodiments. It will be apparent to those skilled in the art that various modifications and improvements can be made to the above embodiments. It is clear from the claims that such modifications and improvements can also be included within the technical scope of the present invention.

[0141] It should be noted that the execution order of each process, such as operations, procedures, steps, and stages, in the devices, systems, programs, and methods shown in the claims, specifications, and drawings is not specifically stated as "before," "prior to," etc., and that the processes can be performed in any order unless the output of a previous process is used in a subsequent process. Even if the operational flow in the claims, specifications, and drawings is described using "first," "next," etc. for convenience, this does not mean that the processes must be performed in this order. [Explanation of symbols]

[0142] 1 facility 10 equipment 20 Control System 30 Robot 40 Monitoring equipment 50 Collected Information Database 60 Facility Database 70 Robot Database 210 Status acquisition unit 220 Status determination unit 230 Display processing unit 240 Display device 250 Input Device 260 Instruction input section 270 Control Unit 400a~c sensor 410a~b Sensor 420 Actuator 430 Status acquisition unit 440 Communications Department 450 control section 600 Communications Department 602 Acoustic data acquisition unit 604 Image data acquisition unit 606 LiDAR data acquisition unit 608 Location data acquisition unit 610 Direction data acquisition unit 612 Instruction transmission unit 620 Collection Information Database Connection 630 Facility Database Connection 640 Robot Database Connection 650 Monitoring Processing Unit 660 Input Processing Unit 665 Display processing section 670 Communications Department 680 Input Device 690 Display device 1010 Estimation section 1020 Extraction part 1030 Sound collection command section 1040 Decision Section 1050 Abnormal device identification section 1060 Equipment Control Department 2200 Computer 2201 DVD-ROM 2210 host controller 2212 CPU 2214 RAM 2216 Graphics Controller 2218 Display Device 2220 Input / Output Controller 2222 communication interface 2224 hard disk drive 2226 DVD-ROM drive 2230 ROM 2240 I / O chip 2242 keyboard

Claims

1. an acquisition unit that acquires acoustic data detected by a sound collection device that can move within the facility and collect sound; an estimation unit that estimates an estimated sound source position for a sound component included in the acquired acoustic data; a determination unit that determines whether a target sound is a reverberant sound based on the amount of deviation between a plurality of estimated sound source positions for the target sound included in the acoustic data detected at a plurality of different detection positions. Device.

2. an extraction unit that extracts the target sound in accordance with at least one of a sound pressure and a frequency of a sound component included in the acoustic data detected at the plurality of detection positions; The determination unit determines whether the target sound is a reverberation sound based on the amount of deviation of the plurality of estimated sound source positions for the target sound extracted by the extraction unit.

10. The apparatus of claim 1.

3. The extraction unit extracts the target sound whose sound pressure is equal to or greater than a predetermined threshold.

3. The apparatus of claim 2.

4. a database connection unit that records sound components included in the sound data detected within the facility in a database in association with sound source positions; The database connection unit records the target sound determined by the determination unit not to be the reverberation sound in the database in association with a sound source position corresponding to the estimated sound source position.

10. The apparatus of claim 1.

5. The determination unit determines that the target sound included in the acoustic data detected at the plurality of different detection positions is a reverberant sound when the target sound is not recorded in the database in association with the sound source position and the deviation amount of the plurality of estimated sound source positions is equal to or greater than a predetermined threshold.

5. The apparatus of claim 4.

6. a sound collection command unit that commands the sound collection device to collect sound, When the acquisition unit acquires the acoustic data including the sound component that is not recorded in the database in association with the sound source position, the sound collection command unit instructs the sound collection device to collect sound at a detection position different from the detection position of the acoustic data acquired by the acquisition unit.

6. The apparatus of claim 5.

7. The determination unit further determines whether the target sound is a reverberant sound based on the sound pressure of the target sound included in the acoustic data detected at a plurality of detection positions different from each other.

10. The apparatus of claim 1.

8. The sound collection device has an image sensor, the acquisition unit acquires image data detected by an image sensor of the sound collection device, The determination unit determines whether the target sound included in the acoustic data detected at a plurality of detection positions different from each other is a reverberation sound based on the image data detected at the plurality of detection positions.

10. The apparatus of claim 1.

9. The determination unit determines that the target sound included in the acoustic data detected at a plurality of different detection positions is not a reverberant sound when the amount of deviation of the estimated sound source position is equal to or greater than a predetermined threshold and the direction of movement between the plurality of detection positions is different from the direction of movement between the estimated sound source positions.

10. The apparatus of claim 1.

10. Acquiring acoustic data detected by a sound collection device that can move around the facility and collect sound; estimating an estimated sound source position for a sound component included in the acquired acoustic data; determining whether the target sound is a reverberant sound based on the amount of deviation between a plurality of estimated sound source positions for the target sound included in the acoustic data detected at a plurality of different detection positions; method.

11. The method is executed by a computer, causing the computer to: an acquisition unit that acquires acoustic data detected by a sound collection device that can move within the facility and collect sound; an estimation unit that estimates an estimated sound source position for a sound component included in the acquired acoustic data; The sound source detecting unit is configured to function as a determining unit that determines whether a target sound is a reverberant sound or not based on the amount of deviation between a plurality of estimated sound source positions for the target sound included in the acoustic data detected at a plurality of different detection positions. program.

Images