Work determination method

Abstract

To provide a work determination method designed to omit a sensor having a low contribution to determining work.SOLUTION: A work determination method includes: executing first determination on work using n (n is a natural number) sensors; executing second determination on work using (n-1) sensors excluding the k-th (k is a natural number of n or less) sensor in the n sensors; and employing, when the first determination shows a degree of similarity equal to or higher than a predetermined value with the second determination, determining the work using the (n-1) sensors excluding the k-th sensor.SELECTED DRAWING: Figure 2

Description

[Technical field]

[0001] The present invention relates to an operation determination method. [Background technology]

[0002] Systems that measure the body by attaching a biosensor have been developed. Patent Document 1 discloses a determination device that determines the mental and physical state of a person to be determined from the person's biosignal. The control unit of the determination device adjusts the determination criteria for the mental and physical state according to the subject's situation, which is the state of the person to be determined, and determines the mental and physical state of the person to be determined from the biosignal using the adjusted determination criteria. [Prior art documents] [Patent documents]

[0003] [Patent Document 1] JP 2023-71507 A Summary of the Invention [Problem to be solved by the invention]

[0004] The determination device in the above-mentioned patent document determines the state from multiple sensors, but the amount of data increases due to multiple sensor data, which causes a decrease in calculation speed and requires the reservation of calculation resources. Therefore, an object of the present disclosure is to provide an activity determination method that omits sensors that contribute little to activity determination. [Means for solving the problem]

[0005] The task determination method of the present disclosure includes: A first determination of the work is performed using n sensors (n is a natural number); A second determination of the task is performed using n-1 sensors excluding a k-th sensor (k is a natural number equal to or less than n) among the n sensors; The task determination method employs a method for determining the task using n-1 sensors excluding the k-th sensor when the first determination has a similarity to the second determination that is equal to or greater than a predetermined value.

[0006] The above configuration provides an activity determination method that omits sensors that make a low contribution to activity determination.

[0007] The task determination method of the present disclosure includes: If the similarity between the first judgment and the second judgment is less than a predetermined value, the second judgment of the task is performed again, excluding the lth sensor (l is a natural number less than or equal to n and not k) out of the n sensors.

[0008] With the above configuration, it is possible to find sensors that contribute less to the judgment of the task.

[0009] The task determination method of the present disclosure includes: Furthermore, when the first judgment has a similarity to the second judgment that is equal to or greater than a predetermined value, a third judgment of the work is performed using n-2 sensors excluding the k-th and m-th sensors (m is a natural number equal to or less than n and not including k); When the first judgment has a similarity to the third judgment that is equal to or greater than a predetermined value, the task is judged using n-2 sensors excluding the k-th and m-th sensors.

[0010] With the above configuration, sensors that contribute less to determining the work can be further omitted.

[0011] The operation determination system of the present disclosure includes: A first determination of the work is performed using n sensors (n is a natural number); A second determination of the task is performed using n-1 sensors excluding a k-th sensor (k is a natural number equal to or less than n) among the n sensors; The activity determination system employs a method for determining the activity using n-1 sensors excluding the k-th sensor when the first determination has a similarity to the second determination that is equal to or greater than a predetermined value.

[0012] The above configuration provides an activity determination system that omits sensors that make a low contribution to activity determination.

[0013] The operation judgment program disclosed herein is A first determination of the work is performed using n sensors (n is a natural number); A second determination of the task is performed using n-1 sensors excluding a k-th sensor (k is a natural number equal to or less than n) among the n sensors; The task judgment program causes an information processing device to execute the task judgment program to adopt a method of judging the task using n-1 sensors excluding the k-th sensor when the first judgment has a similarity to the second judgment that is equal to or greater than a predetermined value.

[0014] The above configuration provides an activity judgment program that omits sensors that make a low contribution to activity judgment. Effect of the Invention

[0015] The present disclosure provides an activity determination method that omits sensors that contribute little to activity determination. [Brief description of the drawings]

[0016] [Figure 1] 1 is a block diagram showing a configuration of an operation determination system according to an embodiment. [Diagram 2] 1 is a flowchart of an operation determination method according to an embodiment. DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS

[0017] Embodiment Hereinafter, an embodiment of the present invention will be described with reference to the drawings. However, the invention according to the claims is not limited to the following embodiment. Furthermore, not all of the configurations described in the embodiment are necessarily essential as means for solving the problem. For clarity of explanation, the following description and drawings are omitted and simplified as appropriate. In each drawing, the same elements are given the same reference numerals, and repeated explanations are omitted as necessary.

[0018] Fig. 1 is a block diagram showing the configuration of an operation determination system according to an embodiment. The operation determination system according to the embodiment will be described with reference to Fig. 1. The operation determination system 100 is a system that inputs data acquired from various sensors into AI (Artificial Intelligence), determines the type of operation, and outputs the result.

[0019] 1, a worker performs work equipped with multiple sensors such as sensor 1, sensor 2, sensor 3, sensor 4, sensor 5, and sensor 6. Examples of sensors include a GPS (Global Positioning System) tag, a band IMU (Inertial Measurement Unit), a smart glove equipped with a vibration / pressure sensor, a microphone, smart glasses, and a first-person camera.

[0020] The GPS tag is a sensor that receives GPS signals and determines the worker's location. The band IMU is an inertial measurement unit that is attached to the worker's waist to determine the worker's movement. The smart gloves are equipped with vibration and pressure sensors, a microphone, etc. The smart gloves detect the vibration, pressure, and sound of the tools the worker touches with his or her hand. The smart glasses and first-person camera capture images from the worker's viewpoint during work and acquire voice data.

[0021] As shown in the upper diagram of Figure 1, the task judgment system inputs various data obtained from these sensors into a machine learning machine and outputs a task judgment.

[0022] Here, an example is shown in which six sensors are used to judge a task, but the more sensors there are, the more data is acquired, and there is a risk that the judgment will take a long time. Therefore, a first judgment of the task is first performed using n sensors (n is a natural number). Next, a second judgment of the same task is performed using n-1 sensors, excluding the kth sensor (k is a natural number less than or equal to n), out of the n sensors. If the similarity between the first judgment and the second judgment is equal to or greater than a predetermined value, the task is judged using the n-1 sensors excluding the kth sensor.

[0023] For example, as shown in the lower diagram of Figure 1, a task for which a first judgment was made using sensors 1 to 6 is judged a second time using sensors 1 to 5. If the first and second judgments are similar by a predetermined value or more, the task is judged using sensors 1 to 5.

[0024] In this way, the number of sensors that judge the work can be reduced, the amount of data acquired can be reduced, and the time required for judgment can be shortened.

[0025] Furthermore, if the similarity between the first judgment and the second judgment is equal to or greater than a predetermined value, a third judgment of the work is performed using n-2 sensors excluding the k-th and m-th sensors (m is a natural number equal to or less than n but not k).If the similarity between the first judgment and the third judgment is equal to or greater than a predetermined value, the work is judged using n-2 sensors excluding the k-th and m-th sensors.

[0026] For example, as shown in the lower diagram of Figure 1, a task in which a first judgment was made using sensors 1 to 6 is judged a third time using sensors 1 to 4, and if the first and third judgments are similar by a predetermined value or more, the task is judged again using sensors 1 to 4.

[0027] Similarly, the work determined using sensors 1 to 6 may be determined using sensors 1 to 3.

[0028] In this way, the number of sensors that judge the work can be further reduced, the amount of data acquired can be reduced, and the time required for judgment can be shortened.

[0029] On the other hand, the result of removing any sensor may change the judgment of the task. If the similarity between the first judgment and the second judgment is less than a predetermined value, the lth sensor (l is a natural number less than or equal to n and not including k) out of the n sensors is removed and the second judgment of the task is performed again.

[0030] That is, another arbitrary sensor is removed and a second judgment of the work is performed. Since the k-th sensor was important for judging the work, the l-th sensor is omitted and a second judgment is performed.

[0031] If the lth sensor is not very important and the judgment does not change, the lth sensor can be omitted. On the other hand, if the lth sensor is important and the judgment changes, another sensor is omitted and the judgment is performed.

[0032] In this way, the sensors necessary for determining the work can be selected, so that the work can be determined using the minimum number of sensors necessary and in the minimum time necessary.

[0033] (Description of the Work Judgment Method According to the Embodiment) 2 is a flowchart of the activity determination method according to the embodiment. The activity determination method according to the embodiment will be described with reference to FIG.

[0034] As shown in FIG. 1, first, a task is judged using all sensors (step S201). For example, n (n is a natural number) sensors are used to judge the task. Next, the number of sensors used is reduced by one and judgment is performed (step S202). The same task as in step 201 is judged by reducing the number of sensors by one. For example, the kth sensor (k is a natural number equal to or less than n) out of n sensors is reduced and the task is judged.

[0035] Next, it is determined whether the similarity is greater than q% (step S203). If the similarity is greater than q% (YES in step S203), additional sensors are added to be removed and a determination is made (step S205). If steps S201 and S202 are more similar than a predetermined value, further sensors are removed and the same work is determined. For example, the mth sensor (m is a natural number less than or equal to n and not k) is removed and the same work is determined. Then, the process returns to step S203.

[0036] If the similarity is less than q% (NO in step S203), the sensor to be removed is changed and judgment is performed (step S204). If steps S201 and S202 are not similar by a predetermined value, the sensor to be removed is changed and the same work is judged. For example, the lth sensor (l is a natural number equal to or smaller than n and not k) is removed and the same work is judged. Then, the process returns to step S203.

[0037] When the above determination has been made for all sensors, the process ends. In this way, it becomes possible to determine the work using the minimum number of sensors required. The above process is executed by an information processing device. The information processing device includes a processor such as a CPU (Central Processing Unit) that executes a program to perform the process, and a memory that stores the program. The information processing device may be configured as one device, or may be configured as multiple devices. The information processing device may be configured as a cloud server that executes some or all of the functions in a distributed manner. An work determination program that causes the information processing device to execute the above process is provided.

[0038] In addition, a part or all of the processing in the above-mentioned information processing device can be realized as a computer program. Such a program can be stored using various types of non-transitory computer-readable media and supplied to a computer. The non-transitory computer-readable medium includes various types of tangible recording media. Examples of the non-transitory computer-readable medium include magnetic recording media (e.g., flexible disks, magnetic tapes, hard disk drives), magneto-optical recording media (e.g., magneto-optical disks), CD-ROMs (Read Only Memory), CD-Rs, CD-R / Ws, and semiconductor memories (e.g., mask ROMs, PROMs (Programmable ROMs), EPROMs (Erasable PROMs), flash ROMs, and RAMs (Random Access Memory)). The program may also be supplied to a computer by various types of temporary computer-readable media. Examples of the temporary computer-readable medium include electrical signals, optical signals, and electromagnetic waves. The temporary computer-readable medium can supply the program to a computer via a wired communication path such as an electric wire and an optical fiber, or via a wireless communication path.

[0039] The present invention is not limited to the above-described embodiment, and can be modified as appropriate without departing from the spirit and scope of the present invention. [Explanation of symbols]

[0040] 100 Work Judgment System

Claims

[Claim 1] A first determination of the work is performed using n sensors (n is a natural number); A second determination of the work is performed using n-1 sensors excluding a k-th sensor (k is a natural number equal to or less than n) among the n sensors; The task determination method employs a method for determining the task using n-1 sensors excluding the k-th sensor when the first determination has a similarity to the second determination that is equal to or greater than a predetermined value.

Images