JP6913603B2 - Data processing device and data processing method - Google Patents

Description

The present disclosure relates to a data processing apparatus and a data processing method.

In recent years, in order to prevent accidents or occupational accidents at the workplace, various data are collected at the workplace, and based on the acquired data, the danger is predicted and notified to the workers before the actual accident occurs. Is being done.

In Patent Document 1, as an example of the control method of the danger prediction system as described above, "a mobile information terminal collects work information of a worker and safety information associated with the work of the worker, and predicts the occurrence of an occupational accident. "Control method of safety analysis system" is disclosed. Further, Patent Document 1 describes a method of acquiring the work information and the safety information by observing the worker while moving in the shipyard and inputting the work information or the like into the PDA.

Japanese Unexamined Patent Publication No. 2011-165120

By the way, the method of predicting the danger that may occur in the future is not limited to the method of predicting the danger by grasping the actual behavior of the worker and the work place as described above. For example, it is possible to predict the danger by collecting data at a predetermined position on the work site and distinguishing between the normal data, which is considered to have no potential danger, and the data at the time of abnormality, which deviates from the data. Be done. When this prediction method is adopted, in order to accurately distinguish between normal data and abnormal data, it is desirable to install the measuring device at a specific position and collect it under predetermined conditions.

However, in an actual work site, it is not always possible to install measuring equipment for collecting data. For example, it may not be permissible to install the above-mentioned measuring device at a fixed position from the viewpoint of securing the route and work space of the luggage carrier.

In that case, the data collection for risk prediction needs to be collected by the inspector at a specific position under the conditions determined. However, when an inspector measures data using a measuring device, the measurement conditions may be different from those when the measuring device is fixed. For example, the position where the inspector collects data may deviate from the fixed position, or the tilt of the camera when taking an image may deviate. It may also be difficult for the same inspector to continue collecting data. If the condition when the inspector collects the data varies, it is not possible to accurately determine the data indicating the normal condition without danger, and it is not possible to accurately predict the danger.

The present disclosure has been made in view of the above points, and provides a technique capable of highly accurate risk prediction even when a measuring device cannot be installed.

In order to solve the above problems, a recording unit that stores a data processing program that processes measurement data measured by a measuring device and a processor that reads the data processing program from the recording unit and processes the data are provided. Whether the data acquisition process for acquiring the measurement data by the processor and the state data including the measurement data indicating the state of the measuring device when the measurement data is measured are within the range of the pre-recorded reference. Provided is a data processing apparatus that executes a data determination process for determining whether or not the status data and a data recording process for recording the measurement data when the state data is within the reference range.

Further, a data processing method executed by a computer processor, in which a step of acquiring measurement data and state data including the measurement data indicating a measurement state when the measurement data is measured are recorded in advance. Provided is a data processing method including a step of determining whether or not the state data is within the reference range, and a step of recording the measurement data when the state data is within the reference range.

According to the present disclosure, it is possible to predict a risk with high accuracy even when a measuring device cannot be installed. Issues, configurations and effects other than the above will be clarified by the following description of embodiments.

It is a figure for conceptually explaining the risk prediction management system of this disclosure. It is a figure which shows the structure of the risk prediction management system which concerns on Example. It is a flowchart of the process which a data determination part determines the suitability of data. It is a figure which shows schematic the flow until the data processing apparatus sends a warning signal to a smart device. It is a figure which shows the accident analysis management table which recorded the analysis content of the accident data. It is a figure which shows the data structure of the collected data history table. It is a figure which shows the data structure of the accident occurrence history table. It is a figure which shows the data structure of the average value management table. It is a flowchart of the process which determines whether or not the data processing apparatus generates a warning based on image data. It is a flowchart of the process which determines whether or not the data processing apparatus generates a warning based on sound data. It is a flowchart of the process which determines whether or not the data processing apparatus generates a warning based on odor data. It is a flowchart of the process which determines whether or not the data processing apparatus generates a warning based on the temperature data. It is a flowchart of the process which determines whether or not the data processing apparatus generates a warning based on humidity data.

Hereinafter, examples of the present disclosure will be described with reference to the drawings. The examples of the present disclosure are not limited to the examples described later, and various modifications can be made within the scope of the technical idea. Further, the corresponding parts of the drawings used in the description of each embodiment described later are designated by the same reference numerals, and duplicate description will be omitted.

[overview]
FIG. 1 is a diagram for conceptually explaining the danger prediction management system S of the present disclosure. The danger prediction management system S includes a smart device 1 (client) that functions as a measuring device and a data processing device 2 (server) that analyzes data and executes danger prediction. The danger prediction management system S of the present disclosure warns the worker when a potential danger is likely to become apparent while the worker is working at a work site such as a factory or a chemical plant.

In FIG. 1, a smart device 1 equipped with various sensors acquires a plurality of environmental data at a work site and transmits the data to the data processing device 2, and analyzes the data acquired by the data processing device 2 installed at a remote location. The flow of issuing a warning when a danger is likely to become apparent is outlined using arrows.

In the example shown in FIG. 1, the smart device 1 acquires image data, sound data, odor data, temperature data, and humidity data of a work site as environmental data using a camera, a microphone, an odor sensor, a thermometer, and a hygrometer. is doing. Each data acquired by the smart device 1 is transmitted to the data processing device 2 and processed inside the data processing device 2.

The data processing device 2 first determines whether or not the data acquired from the smart device 1 is data that can be used for risk prediction at a work site. Specifically, it is determined whether or not the measurement state when the smart device 1 acquires the environmental data conforms to the standard, and if the measurement state meets the standard, the environmental data is recorded inside the data processing device 2. .. In other words, when the smart device 1 can correctly acquire the target data, the data processing device 2 records the environmental data. FIG. 1 shows the INDEX of the environmental data stored in the database. INDEX indicates the ID number of the acquired data. This ID number is assigned to each measurement data in the order recorded in the recording unit, for example.

The data processing device 2 creates standard data based on the data recorded in the recording unit. The standard data is, for example, an average value of data that can be considered to have been acquired in a state where there is no risk of an accident or danger at the work site. The data processing device 2 notifies a warning when data deviating from the standard data is acquired from the smart device 1.

The system of the present disclosure described above can detect a difference from normal times to issue a warning before the danger becomes apparent and prevent workers from being involved in an accident at the work site. The configuration of the danger prediction management system S of the present disclosure will be described in detail below.

<Example>
FIG. 2 is a block diagram showing a hardware configuration of the danger prediction management system S according to the embodiment. As described above, the danger prediction management system S includes a smart device 1 (client) and a data processing device 2 (server).

[Smart device configuration]
The smart device 1 is, for example, a smart glass, a tablet terminal, an autonomous traveling robot, an unmanned aerial vehicle, or the like. The smart device 1 includes a camera 11, a microphone 12, a humidity sensor 13, a temperature sensor 14, an odor sensor 15, a GPS (Global Positioning System) sensor 16, a gyro sensor 17, a first communication unit 18, and a warning device 19. When the smart device 1 is a smart glass or a tablet terminal, an inspector uses the smart device 1 to acquire environmental data related to the work site at a fixed position on the work site.

The camera 11 can acquire image data in response to an instruction from an inspector at a work site, for example. There are various objects such as equipment, tools, materials and processed products at the work site. The image data includes information such as the location, shape, hue, lightness and saturation of the object.

The microphone 12 can acquire sound data in response to an instruction from an inspector at a work site, for example. At the work site, there are various sounds such as a fan sound, a belt conveyor sound, and a sound generated by a device on a regular or irregular basis. The sound data includes each of the above sounds.

The humidity sensor 13 can acquire humidity data in response to an instruction from an inspector at a work site, for example. At the work site, a device for generating vapor and a pipe for transporting liquid may be installed. Humidity data can reflect an unusually high amount of vapor generated by the device, liquid leaking from the pipe, and so on.

The temperature sensor 14 can acquire temperature data in response to an instruction from an inspector at a work site, for example. Various devices that generate heat, such as melting furnaces, drills, and belt conveyors, may be installed at the work site. The temperature data may reflect that the device is operating excessively, that there is an abnormality in the control of the device, and the like.

The odor sensor 15 can acquire odor data in response to an instruction from an inspector at a work site, for example. At the work site, a device that emits gas, a pipe that transports gas, and the like may be installed. The odor data may reflect that the device emits an unusually large amount of gas, that the gas is leaking from the pipe, and so on.

The GPS sensor 16 acquires the position information of the smart device 1 at the same timing as acquiring the environmental data in conjunction with the instruction to acquire the environmental data of the inspector. When the smart device 1 is indoors and the position information cannot be acquired from the GPS sensor 16, for example, the position information may be acquired based on the radio wave intensity of the radio waves received from a plurality of base stations.

The gyro sensor 17 acquires information on the inclination or posture of the smart device 1 at the same timing as acquiring the environmental data in conjunction with the instruction to acquire the environmental data of the inspector.

Each of the image data, the sound data, the humidity data, the temperature data, and the odor data is recorded as data regarding a specific direction in which the smart device 1 is directed, for example, at a specific position on the work site. The above environmental data may be recorded when a mark such as a QR code is included in the image acquired by the camera 11, or is recorded when the values indicated by the GPS sensor 16 and the gyro sensor 17 are within a specific range. You may.

The first communication unit 18 transmits the acquired image data, sound data, humidity data, temperature data, odor data, position data, and data indicating inclination to the data processing device 2. Further, the first communication unit 18 receives data generated by the data processing device 2 such as a warning signal regarding danger and data regarding a possible accident from the data processing device 2.

The warning device 19 issues a warning when the smart device 1 receives a warning signal regarding danger from the data processing device 2. The warning device 19 is, for example, a speaker, a display, a light emitting device, or the like, and performs operations such as sounding an alarm, reading out text data on danger, displaying on a display, or blinking.

[Data processing device configuration]
The data processing device 2 includes a second communication unit 21, a recording unit 22, and a control unit 23. The data processing device 2 transmits / receives data to / from the smart device 1 via the second communication unit 21.

The recording unit 22 includes, for example, a RAM (Random Access Memory) for temporarily recording data and an SSD (Solid State Drive) in which a program executed by the control unit 23 is stored. Environmental data received from the smart device 1, reference data and standard data described later are also recorded in the SSD.

The control unit 23 is, for example, a CPU (Central Processing Unit), and is a data acquisition unit 31 and a data determination unit by reading a program recorded in the recording unit 22, expanding it into a built-in memory (not shown), and executing the program. It functions as 32, a data recording unit 33, an input reception unit 34, a signal output unit 35, and a standard data generation unit 36.

The data acquisition unit 31 acquires environmental data from the smart device 1 via the second communication unit 21. The data acquisition unit 31 notifies the data determination unit 32 of the acquired data.

The data determination unit 32 determines whether or not the state data indicating the measurement state when the measurement data is measured, which is included in the measurement data acquired by the data acquisition unit 31, is within the range of the pre-recorded reference. .. Specifically, the measurement data means the above-mentioned image data, sound data, humidity data, temperature data, odor data, position data and inclination data, and the state data means image data, position data and inclination. Means the data indicating.

That is, the data determination unit 32 determines whether or not the smart device 1 has correctly acquired the environment data based on the state data (image data, position data, and data indicating the inclination). The state data may also include information about the weather or time of measurement. Here, the above-mentioned standard indicates a data range that is considered to maintain sufficient accuracy for predicting danger at a work site, and is a value determined experimentally or empirically.

The data recording unit 33 records the measurement data acquired from the smart device 1 in the recording unit 22 when the state data is within the reference range. That is, the recording unit 22 records the data acquired based on a specific standard. By using this data to perform abnormality detection or risk prediction, the data processing device 2 can improve the accuracy of abnormality detection or risk prediction. The measurement data is recorded in the collected data history table in the recording unit 22.

Hereinafter, the processing of the data determination unit 32 and the data recording unit 33 will be described with reference to FIG.

FIG. 3 is a flow of processing in which the data determination unit 32 determines the suitability of the data, and the data recording unit 33 records the data conforming to the reference in the recording unit 22. The flow will be described below.
(S301)
The data determination unit 32 acquires image data, position data, and data indicating inclination from the data acquisition unit 31.
(S302)
The data determination unit 32 determines whether or not the acquired image data is within the reference range. Specifically, the data determination unit 32 reads out the sample image data recorded in advance from the recording unit 22, compares the image data with the acquired image data, and the degree of similarity is within the reference range. Whether or not (whether the images are similar to each other) is determined. If the image data are similar, it can be seen that the smart device 1 has acquired the data at approximately the same position, direction, and inclination. The similarity of image data can be calculated using a well-known technique such as the Perceptual Hash method. If the acquired image data is within the reference range, the process proceeds to S303. If the acquired image data is not within the reference range, the process proceeds to S305.
(S303)
The data determination unit 32 determines whether or not the acquired position data is within the reference range. Specifically, the data determination unit 32 determines whether or not the acquired GPS data is within a specific area (within a reference range). If the acquired GPS data is within the reference range, the process proceeds to S304. If the acquired GPS data is not within the reference range, the process proceeds to S305.
(S304)
The data determination unit 32 determines whether or not the acquired data indicating the inclination is within the reference range. After determining whether or not the acquired slope data is within the reference range, the process proceeds to S305.
(S305)
When all of the image data, the position data, and the data indicating the inclination are within the reference range, the data determination unit 32 notifies the data recording unit 33 that the state data is within the reference range, and ends the process. .. If any of the image data, the position data, and the data indicating the inclination is not within the reference range, the data determination unit 32 repeats the process from S301.
(S306)
The data recording unit 33 records the data acquired by the data acquisition unit 31 in the recording unit 22.

Since the image data is affected by the weather and time of imaging, the above criteria may be set for each weather or time. In that case, the data determination unit 32 determines whether or not the state data is within the standard range based on the standard that matches the weather or time when the smart device 1 acquires the environmental data. Information about the weather or time may be, for example, acquired by the data processing device 2 from the web, or may be input by the user of the data processing device 2.

The input receiving unit 34 accepts selection of measurement data associated with the occurrence of an accident from the measurement data recorded in the recording unit 22, and assigns an identifier to the selected measurement data (hereinafter referred to as accident data). For example, accident data is data measured immediately before an accident occurs. The accident data selection is executed, for example, by the user of the data processing device 2 selecting and executing the measurement data recorded immediately before on the display provided in the data processing device 2 when an accident occurs at the work site. The identifier is, for example, binary data in which 1 is assigned to the measurement data indicating the accident data and 0 is assigned to the measurement data that is not the accident data.

When selecting the accident data, the user of the data processing device 2 can also register the situation at the time of the accident such as the content and timing of the accident that occurred and the weather. The accident data is recorded in the accident occurrence history table in the recording unit 22. Further, the situation at the time of the accident is recorded in the accident analysis management table in the recording unit 22.

The signal output unit 35 outputs a warning signal when the measurement data acquired by the data acquisition unit 31 is within the above-mentioned reference range and is similar to the accident data. The data processing device 2 transmits a warning signal to the smart device 1 via the second communication unit 21, and the smart device 1 can issue a warning from the warning device 19. The method of determining whether or not the measurement data is similar to the accident data will be described below.

(image data)
As will be described later, for each object included in the image, the numerical parameters that characterize the object can be calculated. By comparing the numerical parameters with each other, the signal output unit 35 determines whether or not the measurement data is similar to the accident data. For example, when the numerical parameter calculated from the measurement data is within a predetermined range including the numerical parameter calculated from the accident data, the signal output unit 35 determines that the measurement data and the accident data are similar.
(Sound data)
By comparing the frequencies of the sounds, the signal output unit 35 determines whether or not the measurement data is similar to the accident data. For example, when the frequency of the measurement data is within a predetermined range including the frequency of the accident data, the signal output unit 35 determines that the measurement data and the accident data are similar. The signal output unit 35 may also compare the sound intensities in order to improve the accuracy. Further, the signal output unit 35 may determine the similarity between the measurement data and the accident data by removing a specific frequency considered to be noise.
(Humidity data)
The signal output unit 35 determines that the measurement data and the accident data are similar, for example, when the humidity of the measurement data is within a predetermined range including the humidity of the accident data.
(Temperature data)
The signal output unit 35 determines that the measurement data and the accident data are similar, for example, when the temperature of the measurement data is within a predetermined range including the temperature of the accident data.
(Odor data)
The signal output unit 35 determines that the measurement data and the accident data are similar, for example, when the numerical value of the odor of the measurement data is within a predetermined range including the numerical value of the odor of the accident data.

The signal output unit 35 may output a warning signal when the measurement data acquired by the data acquisition unit 31 is not within a predetermined range. In that case, the warning signal is a content that prompts the smart device 1 to acquire data again.

The standard data generation unit 36 generates standard data indicating average measurement data based on the measurement data recorded by the data recording unit 33. That is, the standard data is measurement data that can be measured at the work site in normal times when there is no danger, and is, for example, an average value of the measurement data. The standard data may be an average value of data obtained by excluding accident data from the measurement data recorded in the recording unit 22. By removing the accident data, the difference between the standard data and the measurement data acquired when the danger can be manifested becomes large, and the data processing device 2 can improve the accuracy of the danger prediction. The standard data is recorded in the average value management table in the recording unit 22.

When the measurement data is image data, the standard data of the image data is generated as follows, for example. First, an object is extracted from the image data by an appropriate algorithm. Subsequently, the average values of hue, lightness, and saturation are calculated for each object. Specifically, the average value of hue, lightness and saturation associated with each pixel constituting the object is calculated, and the average value is used as the hue, lightness and saturation of the object. That is, the standard data of the image data is the data related to the combination of the object included in the image and the three variables (hue, lightness, and saturation) that characterize the object.

The signal output unit 35 outputs a warning signal when the measurement data acquired by the data acquisition unit 31 is within the reference range and does not resemble the standard data. That is, the data processing device 2 can issue a warning to the smart device 1 when it detects that the work site is in an unusual state from the acquired measurement data.

The standard data generation unit 36 generates standard data for each weather or time, and the signal output unit 35 gives a warning signal when the measurement data is not similar to the standard data corresponding to the weather or time when the measurement data is measured. May be output. The data acquired by the smart device 1 is affected by the weather and time. Therefore, the accuracy of risk prediction can be improved by generating standard data for each weather or time of year. Here, the time refers to each division determined by, for example, dividing the calendar by a specific number of days.

The standard data generation unit 36 updates the standard data, for example, when the data recording unit 33 records new measurement data. For example, the standard data generation unit 36 generates an average value of measurement data including the added new measurement data when the data recording unit 33 records new measurement data. By updating the standard data from time to time, it is possible to work on the standard data for elements that change over time regardless of abnormalities at the work site. For example, when discoloration of an object occurs over time, the accuracy of risk prediction can be improved by updating the standard data.

What has been described above will be described again with reference to FIG.
FIG. 4 is a diagram schematically showing a flow until the data processing device 2 transmits a warning signal to the smart device 1. FIG. 4 shows a danger prediction management database created in the recording unit 22. Accident data and standard data are recorded in the danger prediction management database held by the recording unit 22. The user of the data processing device 2 analyzes accidents that have occurred in the past while referring to the accident data recorded in the danger prediction management database. The user analyzes the accident occurrence condition, the degree of deviation between the accident data and the standard data, and reflects it in the determination condition when the signal output unit 35 determines the similarity between the measurement data and the accident data. When the data processing device 2 in which the parameters are set as described above receives the measurement data deviating from the standard data, it outputs a warning signal and notifies the smart device 1.

Subsequently, FIGS. 5 to 8 show the data structures of the accident content, measurement data, accident data, and standard data recorded in the recording unit 22.

FIG. 5 shows an accident analysis management table in which the analysis contents of the accident data are recorded. The accident analysis management table records the time, weather, and details of the accident when the accident occurred. For example, the signal output unit 35 can notify the smart device 1 of the accident content recorded in the accident analysis management table as text data or image data. The user of the smart device 1 can not only receive the warning but also know the specific possible danger by referring to the above data.

FIG. 6 is a diagram showing a data structure of the collected data history table. The data items of the measurement data are described in the collected data history table. An image INDEX table, a sound INDEX table, an odor INDEX table, a temperature INDEX table, and a humidity INDEX table are arranged in a lower hierarchy of the collected data history table. The number N shown in the figure indicates that there are a plurality of recorded items, and the number 1 indicates that there is one recorded item.

FIG. 7 is a diagram showing a data structure of the accident occurrence history table. Data items of accident data are described in the accident occurrence history table. An image INDEX table, a sound INDEX table, an odor INDEX table, a temperature INDEX table, and a humidity INDEX table are arranged in a lower hierarchy of the accident occurrence history table.

FIG. 8 is a diagram showing a data structure of the average value management table. Data items of standard data are described in the average value management table. An image INDEX table, a sound INDEX table, an odor INDEX table, a temperature INDEX table, and a humidity INDEX table are arranged in a lower hierarchy of the average value management table.

[Processing flow of data processing device]
9 to 13 show a flow of processing executed by the data processing device 2.

[Image data processing flow]
FIG. 9 is a flowchart of a process of determining whether or not the data processing device 2 generates a warning based on the image data.
(S901)
The data acquisition unit 31 acquires image data and state data from the smart device 1.
(S902)
The data determination unit 32 determines whether or not the acquired state data satisfies the standard. If the state data meets the criteria, the process proceeds to S903. If the state data does not meet the criteria, the process is restarted from S901.
(S903)
The signal output unit 35 determines the hue, lightness, and saturation of the object constituting the image and the object from the image data and the accident data recorded in the recording unit 22.
(S904)
The signal output unit 35 determines the similarity between the image data and the accident data. If the image data and the accident data are similar, the process proceeds to S906. If the image data and the accident data are not similar, the process proceeds to S905.
(S905)
The signal output unit 35 determines whether or not the image data is within the permissible range of the standard data. When the image data is within the permissible range of the standard data, the data processing device 2 ends the process. If the image data is not within the permissible range of standard data, the process proceeds to S906.
(S906)
The signal output unit 35 outputs a warning signal and ends the process.

[Sound data processing flow]
FIG. 10 is a flowchart of a process of determining whether or not the data processing device 2 generates a warning based on the sound data.
(S1001)
The data acquisition unit 31 acquires sound data and state data from the smart device 1.
(S1002)
The data determination unit 32 determines whether or not the acquired state data satisfies the standard. If the state data meets the criteria, the process proceeds to S1003. If the state data does not meet the criteria, the process is restarted from S1001.
(S1003)
The signal output unit 35 acquires a frequency obtained by cutting a specific frequency from the sound data and the accident data recorded in the recording unit 22.
(S1004)
The signal output unit 35 determines the similarity between the sound data and the accident data. If the sound data and the accident data are similar, the process proceeds to S1006. If the sound data and the accident data are not similar, the process proceeds to S1005.
(S1005)
The signal output unit 35 determines whether or not the sound data is within the permissible range of the standard data. When the sound data is within the permissible range of the standard data, the data processing device 2 ends the processing. If the sound data is not within the permissible range of the standard data, the process proceeds to S1006.
(S1006)
The signal output unit 35 outputs a warning signal and ends the process.

[Odor data processing flow]
FIG. 11 is a flowchart of a process of determining whether or not the data processing device 2 generates a warning based on the odor data.
(S1101)
The data acquisition unit 31 acquires odor data and state data from the smart device 1.
(S1102)
The data determination unit 32 determines whether or not the acquired state data satisfies the standard. If the state data meets the criteria, the process proceeds to S1103. If the state data does not meet the criteria, the process is restarted from S1101.
(S1103)
The signal output unit 35 determines the similarity between the odor data and the accident data. If the odor data and the accident data are similar, the process proceeds to S1105. If the odor data and the accident data are not similar, the process proceeds to S1104.
(S1104)
The signal output unit 35 determines whether or not the odor data is within the permissible range of the standard data. When the odor data is within the permissible range of the standard data, the data processing device 2 ends the processing. If the odor data is not within the permissible range of the standard data, the process proceeds to S1105.
(S1105)
The signal output unit 35 outputs a warning signal and ends the process.

[Temperature data processing flow]
FIG. 12 is a flowchart of a process of determining whether or not the data processing device 2 generates a warning based on the temperature data.
(S1201)
The data acquisition unit 31 acquires temperature data and state data from the smart device 1.
(S1202)
The data determination unit 32 determines whether or not the acquired state data satisfies the standard. If the state data meets the criteria, the process proceeds to S1203. If the state data does not meet the criteria, the process is restarted from S1201.
(S1203)
The signal output unit 35 determines the similarity between the temperature data and the accident data. If the temperature data and the accident data are similar, the process proceeds to S1205. If the temperature data and the accident data are not similar, the process proceeds to S1204.
(S1204)
The signal output unit 35 determines whether or not the temperature data is within the allowable range of the standard data. When the temperature data is within the permissible range of the standard data, the data processing device 2 ends the process. If the temperature data is not within the permissible range of standard data, the process proceeds to S1205.
(S1205)
The signal output unit 35 outputs a warning signal and ends the process.

[Humidity data processing flow]
FIG. 13 is a flowchart of a process of determining whether or not the data processing device 2 generates a warning based on the humidity data.
(S1301)
The data acquisition unit 31 acquires humidity data and state data from the smart device 1.
(S1302)
The data determination unit 32 determines whether or not the acquired state data satisfies the standard. If the state data meets the criteria, the process proceeds to S1303. If the state data does not meet the criteria, the process is restarted from S1301.
(S1303)
The signal output unit 35 determines the similarity between the humidity data and the accident data. If the humidity data and the accident data are similar, the process proceeds to S1305. If the humidity data and the accident data are not similar, the process proceeds to S1304.
(S1304)
The signal output unit 35 determines whether or not the humidity data is within the permissible range of the standard data. When the humidity data is within the permissible range of the standard data, the data processing device 2 ends the processing. If the humidity data is not within the permissible range of standard data, the process proceeds to S1305.
(S1305)
The signal output unit 35 outputs a warning signal and ends the process.

[Summary of Examples]
As described above, the data processing device 2 of the present disclosure records the measurement data acquired when the state at the time of data measurement is within the range of a specific reference in the recording unit 22. By selecting the data in this way, the accuracy of risk prediction can be improved.

Further, the data processing device 2 of the present disclosure issues a warning when the acquired measurement data is within the above standard range and is similar to the past accident data. By selecting the data as described above, the timing of issuing the warning becomes appropriate. Further, the data processing device 2 of the present disclosure can warn the user to remeasure the acquired measurement data when the acquired measurement data is out of the above-mentioned reference range. Therefore, the user can acquire the data conforming to the standard at the time of data measurement.

Further, the data processing device 2 of the present disclosure issues a warning when the acquired measurement data is within the above standard range and is not within the permissible range of the standard data. In this case as well, by selecting the data as described above, the timing of issuing the warning becomes appropriate.

<Modification example 1>
In the description of the embodiment, the smart device 1 has a warning device 19, and the data processing device 2 transmits a signal notifying the smart device 1 of the danger. However, the warning device 19 does not have to be built in the smart device 1. The warning device 19 may exist independently at the work site in a state where it can communicate with the data processing device 2, for example. In that case, the weight of the smart device 1 can be reduced, and the portability of the smart device 1 is increased.

<Modification 2>
In the description of the examples, it has been stated that the standard data generation unit 36 may generate standard data for each weather or time. The standard data generation unit 36 may generate standard data by weighting with the date of the measurement data. In that case, the standard data generation unit 36 weights the measurement data acquired more recently so that the weight is higher, for example. For example, the standard data generation unit 36 sets the weight of the measurement data acquired the previous day to 0.5, the weight of the measurement data acquired two days ago to 0.3, and the weight of the measurement data acquired three days ago to 0. The average value of the measurement data set to 2 is used as the standard data. In this way, the data processing device 2 can determine whether or not an abnormality has occurred by comparing with the data of the most recent work site. That is, it is possible to prevent excessive detection of abnormalities even when predicting danger at a work site where the situation changes over time.

<Modification example 3>
In the embodiment, the smart device 1 and the data processing device 2 send and receive data to each other, and the data processing device 2 plays a role of analyzing the data. The process executed by the data processing device 2 may be configured to be executed by the smart device 1. That is, the smart device 1 may perform both measurement and analysis of data to determine whether or not to issue a warning.

<Modification example 4>
In the description of the embodiment, the signal output unit 35 determines the similarity between the measurement data and the selected accident data. The signal output unit 35 may sequentially compare the measurement data with the plurality of accident data and output a warning signal when similar accident data exists. In this way, the accuracy of risk prediction is improved. Further, the accident data to be compared with the measurement data may be an average value of a plurality of accident data.

<Modification 5>
The number of smart devices 1 with which the data processing device 2 communicates is not limited to one. When the data processing device 2 communicates with a plurality of smart devices 1 and outputs a warning signal based on the measurement data acquired from any of the smart devices 1, the data processing device 2 is configured to output the warning signal to all the smart devices 1. You may.

The present invention is not limited to the above-described examples, and includes various modifications. For example, the above-described embodiment has been described in detail in order to explain the present invention in an easy-to-understand manner, and is not necessarily limited to the one including all the described configurations. Further, it is possible to replace a part of the configuration of one embodiment with the configuration of another embodiment, and it is also possible to add the configuration of another embodiment to the configuration of one embodiment. Further, it is possible to add / delete / replace a part of the configuration of each embodiment with another configuration. Further, each of the above configurations, functions, processing units, processing means and the like may be realized by hardware by designing a part or all of them by, for example, an integrated circuit. Further, each of the above configurations, functions, and the like may be realized by software by the processor interpreting and executing a program that realizes each function. Information such as programs, tables, and files that realize each function can be placed in a memory, a recording device such as a hard disk or SSD, or a recording medium such as an IC card, SD card, or DVD.

S ... Danger prediction management system, 1 ... Smart device, 2 ... Data processing device 11 ... Camera, 12 ... Mike, 13 ... Humidity sensor, 14 ... Temperature sensor, 15 ... Odor sensor 16 ... GPS sensor, 17 ... Gyro sensor, 18 ... 1st communication unit, 19 ... Warning device 21 ... 2nd communication unit, 22 ... Recording unit, 23 ... Control unit 31 ... Data acquisition unit, 32 ... Data judgment unit, 33 ... Data recording unit, 34 ... Input reception unit 35 … Signal output unit, 36… Standard data generation unit

Claims (9)

A recording unit that stores a data processing program that processes measurement data measured by a measuring device, a processor that reads the data processing program from the recording unit, and performs data processing.
With
The processor
Data acquisition process to acquire measurement data and
A data determination process for determining whether or not the state data including the measurement data, which indicates the state of the measuring device when the measurement data is measured, is within the range of a pre-recorded reference.
A data recording process for recording the measurement data when the state data is within the reference range, and
An input reception process that accepts the selection of measurement data related to the occurrence of an accident from the recorded measurement data and assigns an identifier to the selected measurement data.
Signal output processing that outputs a warning signal when the acquired measurement data is within the range of the reference and is similar to the measurement data to which the identifier is given.
A data processing device that runs. A recording unit that stores a data processing program that processes measurement data measured by a measuring device , a processor that reads the data processing program from the recording unit, and performs data processing.
With
The processor
Data acquisition process to acquire measurement data and
A data determination process for determining whether or not the state data including the measurement data, which indicates the state of the measuring device when the measurement data is measured, is within the range of a pre-recorded reference.
A data recording process for recording the measurement data when the state data is within the reference range, and
A standard data generation process that generates standard data indicating average measurement data based on the recorded measurement data, and
Signal output processing that outputs a warning signal when the acquired measurement data is within the range of the standard and is not similar to the standard data.
The real line to Lud over data processing apparatus. The condition data includes data on weather or time of year.
The processor
Generate the standard data for each weather or season,
When the measurement data is not similar to the standard data corresponding to the weather or time when the measurement data is measured, the warning signal is output.
The data processing apparatus according to claim 2. The pre-recorded reference includes at least one of the position information and tilt information of the measuring device and the image information acquired by the measuring device as parameters.
The data processing apparatus according to claim 1. When the processor records new measurement data in the recording unit, the processor updates the standard data.
The data processing apparatus according to claim 2. The processor
Signal output processing that outputs a warning signal when the acquired measurement data is not within the reference range.
The data processing apparatus according to claim 1. The data processing device includes the measuring device.
The data processing apparatus according to claim 1. A data processing method performed by a computer processor
Steps to get measurement data and
A step of determining whether or not the state data including the measurement data, which indicates the measurement state when the measurement data is measured, is within the range of the pre-recorded reference.
A step of recording the measurement data when the state data is within the reference range, and
A step of accepting the selection of measurement data to be associated with the occurrence of an accident from the recorded measurement data and assigning an identifier to the selected measurement data.
A step of outputting a warning signal when the acquired measurement data is within the range of the reference and is similar to the measurement data to which the identifier is given.
Data processing method having. A data processing method performed by a computer processor
Steps to get measurement data and
A step of determining whether or not the state data including the measurement data, which indicates the state of the measuring device when the measurement data is measured, is within the range of a pre-recorded reference.
A step of recording the measurement data when the state data is within the reference range, and
Based on the recorded measurement data, a step of generating standard data showing the average measurement data, and
A step of outputting a warning signal when the acquired measurement data is within the range of the standard and is not similar to the standard data.
Data processing method having.

Images