Warning system, warning method, and computer program product

1. A warning system comprising:

a hardware processor configured to function as:

an acquisition unit configured to acquire, from first sensor data including information on a target that is a machine in a factory or at a construction site, condition information on an operation of a motion of the target;

an analysis unit configured to analyze, from second sensor data including information on a region, current state information on an object that differs from the target and that is included in the region and action prediction information on the object; and

a calculation unit configured to calculate a degree of caution, based on the condition information on the target, the current state information on the object, and the action prediction information on the object, wherein,

the region is a place where work requires a predetermined number of persons including a specific person, and

the calculation unit calculates

a first degree of caution when a number of persons in the region is less than the predetermine number of persons,

a second degree of caution when no specific person is present in the region, and

a third degree of caution when the predetermined number of persons including the specific person are present in the region and an improper person is present in the region.

2. The warning system according to claim 1 , wherein

in a case where it is identified from the condition information on the target that the target is in operation or in motion, the calculation unit calculates the degree of caution higher as the object is more likely to approach or come in contact with the target, based on the current state information on the object and the action prediction information on the object.

3. The warning system according to claim 1 , wherein

the acquisition unit receives first image data as the first sensor data and acquires the condition information on the target from the first image data, and

the analysis unit receives second image data as the second sensor data and analyzes the current state information on the object and the action prediction information on the object from the second image data.

4. The warning system according to claim 3 , wherein

the analysis unit:

receives a plurality of pieces of the second image data on a time-series basis;

tracks the object included in the plurality of pieces of the second image data; calculates a travel direction and a speed of the object; and

analyzes the action prediction information on the object, based on the travel direction and the speed of the object.

5. The warning system according to claim 1 , wherein the hardware processor is further configured to function as:

an alert notification unit configured to issue an alert notification in a case where the degree of caution calculated by the calculation unit is higher than a first threshold.

6. The warning system according to claim 1 , wherein the hardware processor is further configured to function as:

a recording unit configured to record, in a case where the degree of caution calculated by the calculation unit is higher than a second threshold, at least one of the first sensor data, the second sensor data, the condition information on the target, the current state information on the object, the action prediction information on the object, and the degree of caution.

7. The warning system according to claim 1 , wherein the hardware processor is further configured to function as:

a control unit configured to make, in a case where the degree of caution calculated by the calculation unit is higher than a third threshold, the target to be in a safe state.

8. The warning system according to claim 1 , wherein the hardware processor is further configured to function as:

a display unit configured to display information including at least one of the condition information on the target, the current state information on the object, the action prediction information on the object, and the degree of caution.

9. The warning system according to claim 1 , wherein the hardware processor is further configured to function as:

a setting unit configured to set a parameter used for controlling an operation of the acquisition unit, a parameter used for controlling an operation of the analysis unit, and a parameter used for controlling an operation of the calculation unit.

10. The warning system according to claim 9 , wherein

the first sensor data includes information on a plurality of targets,

the second sensor data includes information on a plurality of regions, and

the setting unit sets the parameter used for controlling the operation of the acquisition unit to each of the plurality of the targets and sets the parameter used for controlling the operation of the analysis unit to each of the plurality of the regions.

11. The warning system according to claim 1 , wherein

the object is a person,

the hardware processor is further configured to function as:

a recognition unit configured to collate the person with known person information, to recognize the person, and

the calculation unit calculates the degree of caution, based further on information identified from the person.

12. A warning method implemented by a computer, the method comprising:

acquiring, by a warning system, from first sensor data including information on a target that is a machine in a factory or at a construction site, condition information on an operation of a motion of the target;

analyzing, by the warning system, from second sensor data including information on a region, current state information on an object that differs from the target and that is included in the region and action prediction information on the object; and

calculating a degree of caution by the warning system, based on the condition information on the target, the current state information on the object, and the action prediction information on the object, wherein,

the region is a place where work requires a predetermined number of persons including a specific person, and

calculating the degree of caution includes calculating

a first degree of caution when a number of persons in the region is less than the predetermine number of persons,

a second degree of caution when no specific person is present in the region, and

a third degree of caution when the predetermined number of persons including the specific person are present in the region and an improper person is present in the region.

13. The warning method according to claim 12 , wherein

the calculating includes calculating, in a case where it is identified from the condition information on the target that the target is in operation or in motion, the degree of caution higher as the object is more likely to approach or come in contact with the target, based on the current state information on the object and the action prediction information on the object.

14. The warning method according to claim 12 , wherein

the acquiring includes receiving first image data as the first sensor data and acquiring the condition information on the target from the first image data, and

the analyzing includes receiving second image data as the second sensor data and analyzing the current state information on the object and the action prediction information on the object from the second image data.

15. A computer program product having a non-transitory computer readable medium including programmed instructions, wherein the instructions, when executed by a computer, cause the computer to function as:

an acquisition unit configured to acquire, from first sensor data including information on a target that is a machine in a factory or at a construction site, condition information an operation of a motion of on the target;

an analysis unit configured to analyze, from second sensor data including information on a region, current state information on an object that differs from the target and that is included in the region and action prediction information on the object; and

a calculation unit configured to calculate a degree of caution, based on the condition information on the target, the current state information on the object, and the action prediction information on the object, wherein,

the region is a place where work requires a predetermined number of persons including a specific person, and

calculating the degree of caution includes calculating

a first degree of caution when a number of persons in the region is less than the predetermine number of persons,

a second degree of caution when no specific person is present in the region, and

a third degree of caution when the predetermined number of persons including the specific person are present in the region and an improper person is present in the region.

16. The computer program product according to claim 15 , wherein

in a case where it is identified from the condition information on the target that the target is in operation or in motion, the calculation unit calculates the degree of caution higher as the object is more likely to approach or come in contact with the target, based on the current state information on the object and the action prediction information on the object.

17. The computer program product according to claim 15 , wherein

the acquisition unit receives first image data as the first sensor data and acquires the condition information on the target from the first image data, and

the analysis unit receives second image data as the second sensor data and analyzes the current state information on the object and the action prediction information on the object from the second image data.