Component Management System and Component Management Method

Abstract

To provide a component management system that predicts the occurrence of an abnormal condition such as overflow of articles based on a use state of a depository.SOLUTION: Provided is a component management system comprising: a delivery plan information acquisition part that acquires delivery planning information of a component; a prediction part that predicts the occurrence of abnormal conditions in a depository use state of the component based on the acquired delivery planning information of the component; a delivery result information acquisition part that acquires delivery result information of the component; a first influence degree calculation part that calculates a first influence degree based on a difference between the delivery result information of the component and the delivery planning information of the component, and compares the first influence degree with a threshold; a prediction update part that updates the prediction of the prediction part based on the comparison of the calculated first influence degree with the threshold; and a notification part that causes the abnormal condition to be notified of when the abnormal condition is predicted to occur by the prediction update part.SELECTED DRAWING: Figure 1

Description

Technical Field

[0001] The present disclosure relates to a parts management system and a parts management method.

Background Art

[0002] Patent Document 1 discloses a progress management device. The control unit of the progress management device has an information processing unit that manages each information. Further, the control unit calculates planned values, actual values, etc. regarding cost and delivery date for each part, calculates a difference value between the planned cost and the actual cost, etc., and performs a difference process of extracting parts and difference information that meet the conditions. And the difference processing unit. Further, the control unit has a cause processing unit that performs a process of extracting information on a difference cause pattern related to the extracted parts and difference information and displaying it on the screen, and a process that enables the user to specify the difference cause from the information on the difference cause pattern. Further, the control unit has a countermeasure processing unit that performs a process of extracting information on countermeasures related to the specified difference cause and displaying it on the screen, and a process that enables the user to specify the countermeasures to be implemented from the information on the countermeasures.

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0004] Causes of abnormal situations such as overstocking are diverse, including variations in component delivery times and delays in sorting operations, making it difficult to predict abnormal situations. Although the component storage area can be monitored with cameras or the like to detect abnormal situations, it is difficult to respond in a timely manner because workers are performing multitasks. Also, Patent Document 1 does not disclose predicting the occurrence of abnormal situations based on the usage status of each storage area after component delivery. Therefore, an object of the present disclosure is to provide a component management system that predicts the occurrence of abnormal situations such as overstocking based on the usage status of the storage area.

Means for Solving the Problems

[0005] The component management system of the present disclosure includes a delivery plan information acquisition unit that acquires component delivery plan information, a prediction unit that predicts the occurrence of abnormal situations in the usage status of the component storage area based on the acquired component delivery plan information, a delivery result information acquisition unit that acquires the component delivery result information, a first influence degree calculation unit that calculates a first influence degree based on the difference between the acquired component delivery result information and the acquired component delivery plan information, and compares the first influence degree with a threshold value, a prediction update unit that updates the prediction of the prediction unit based on the comparison result between the calculated first influence degree and the threshold value, and a notification unit that notifies the abnormal situation when the prediction update unit predicts that the abnormal situation will occur. The component management system is provided with these components.

[0006] With the above configuration, a component management system that predicts the occurrence of abnormal situations such as overstocking based on the usage status of the storage area can be provided.

[0007] Also, the component management system of the present disclosure is characterized by including a factor analysis unit that analyzes the cause of the abnormal situation when it is predicted that the abnormal situation will occur and reflects it in the first influence degree calculation unit.

[0008] With the above configuration, the cause analysis unit can feedback the cause of the abnormal situation to the first influence degree calculation unit.

[0009] Also, the component management system of the present disclosure The cause analysis unit includes a storage unit that stores a trained machine learning device that learns when a plurality of training data sets composed of combinations of the cause of the abnormal situation and the threshold of the first influence degree are input, and an arithmetic unit that outputs the threshold of the first influence degree when the cause of the abnormal situation is input to the trained machine learning device read from the storage unit.

[0010] With the above configuration, machine learning can be used for cause analysis.

[0011] Also, the component management system of the present disclosure Further, it includes a storage performance information acquisition unit that acquires storage performance information of each storage location of the component, a second influence degree calculation unit that calculates a second influence degree that is the difference between the acquired storage performance information and the acquired delivery plan information, and compares the second influence degree with a threshold, Based on the comparison result between the second influence degree and the threshold, the prediction update unit updates the prediction of the prediction unit.

[0012] With the above configuration, the prediction update unit can update the prediction at an appropriate timing.

[0013] The component management method of the present disclosure includes the steps of acquiring delivery plan information of components, predicting the occurrence of an abnormal situation in the usage status of the storage location of the component based on the acquired delivery plan information of the component, acquiring the delivery actual information of the component, calculating a first influence degree based on the difference between the acquired delivery actual information of the component and the acquired delivery plan information of the component, and comparing the first influence degree with a threshold. Updating the prediction in the predicting step based on the comparison result between the calculated first influence degree and a threshold value; When the prediction in the predicting step is updated and it is predicted that the abnormal situation will occur, notifying the abnormal situation. A component management method comprising these steps.

[0014] With the above configuration, a component management method for predicting the occurrence of abnormal situations such as overstocking based on the usage status of the storage area can be provided.

Effect of the Invention

[0015] According to the present disclosure, a component management system for predicting the occurrence of abnormal situations such as overstocking based on the usage status of the storage area can be provided.

Brief Description of the Drawings

[0016]

Figure 1

Figure 2

Figure 3

Modes for Carrying Out the Invention

[0017] Embodiment 1 Hereinafter, embodiments 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 embodiments. Also, not all of the configurations described in the embodiments are essential as means for solving the problems. For clarity of explanation, the following description and drawings have been appropriately omitted and simplified. In each drawing, the same elements are denoted by the same reference numerals, and duplicate explanations are omitted as necessary.

[0018] (Explanation of the component management system according to Embodiment 1) FIG. 1 is a block diagram showing the configuration of the parts management system according to Embodiment 1. While referring to FIG. 1, the parts management system according to Embodiment 1 will be described. In Embodiment 1 and Embodiment 2 described later, the overstocking of the storage location is described as an abnormal situation.

[0019] As shown in FIG. 1, the parts management system 100 according to Embodiment 1 includes a procurement plan information acquisition unit 101, a prediction unit 103, a procurement actual result information acquisition unit 105, a first influence degree calculation unit 107, a prediction update unit 109, and a notification unit 111. Further, the parts management system 100 may include a cause analysis unit 113.

[0020] The procurement plan information acquisition unit 101 is a part having a function of acquiring the procurement plan information of parts. The procurement plan information acquisition unit 101 acquires the procurement plan information of parts from the parts procurement plan information database 201 (see FIG. 2). The procurement plan information is information in which a part number, a planned procurement quantity, a planned procurement time, etc. are associated for each part to be procured. The volume may be known for each part.

[0021] The prediction unit 103 is a part having a function of predicting the occurrence of an abnormal situation in the usage status of the storage location of parts based on the acquired procurement plan information of the parts. The prediction unit 103 acquires the final result of the previous day. The final result is the usage status of the storage location and the stock of parts. The prediction unit 103 acquires the procurement plan information from the procurement plan information acquisition unit 101. Further, the prediction unit 103 acquires the production plan information from the production plan information database 203 (see FIG. 2). The production plan information is information in which a part number, a planned production quantity, a planned production date and time, etc. are associated for each product to be produced. Further, the prediction unit 103 acquires resource information such as the attendance and absence of workers from the resource information database 205 (see FIG. 2). The prediction unit 103 takes in the change point information of the current day based on the procurement plan information, the production plan information, and the resource information. The prediction unit 103 executes a simulation based on the final result and the change point information of the current day, and outputs a prediction of the storage location usage. It is preferable that the prediction unit 103 makes a prediction at the beginning of the procurement day.

[0022] The incoming performance information acquisition unit 105 is a part that has the function of acquiring the incoming performance information of parts. The incoming performance information acquisition unit sequentially generates incoming performance information that is likely to deviate from the plan and imports it at a determined frequency. The incoming performance information includes the part number and the incoming time, etc.

[0023] The first impact degree calculation unit 107 is a part that has the function of calculating the first impact degree based on the difference between the acquired incoming performance information of parts and the acquired incoming plan information of parts, and comparing the first impact degree with a threshold value. The first impact degree calculation unit 107 determines using an algorithm whether the difference between the scheduled incoming time and the actual incoming time affects the level of overstock. As will be described later, the determination threshold value can be changed.

[0024] The prediction update unit 109 is a part that has the function of updating the prediction of the prediction unit 103 based on the comparison result between the calculated first impact degree and the threshold value. The prediction update unit 109, for example, executes prediction update when the first impact degree exceeds the threshold value and is considered to have an impact. The prediction update unit 109 executes a simulation that predicts the usage status of the storage location in the same way as the prediction unit 103. The prediction update unit 109 determines the occurrence of overstock based on the simulation. The determination is made based on a threshold value that can be set in advance.

[0025] The notification unit 111 is a part that has the function of notifying an abnormal situation when an abnormal situation is predicted to occur in the prediction update unit 109. The notification unit 111 issues a warning by display or voice.

[0026] When it is predicted that an abnormal situation will occur, the cause analysis unit 113 is a part that analyzes the cause of the abnormal situation and reflects it on the first influence degree calculation unit 107. The cause analysis unit 113 includes a storage unit that stores a learned machine learning device that learns when a plurality of training data sets are input. The training data set is composed of a combination of the cause of the abnormal situation and the threshold value of the first influence degree. Further, the cause analysis unit 113 includes an arithmetic unit that outputs the threshold value of the first influence degree when the cause of the abnormal situation is input to the learned machine learning device read from the storage unit. That is, the cause analysis unit 113 includes artificial intelligence (AI (Artificial Intelligence)). In this way, machine learning can be used for cause analysis.

[0027] The cause analysis unit 113 accumulates the conditions at the time of occurrence of overloading and continuously improves the next determination accuracy by using it for updating the influence determination algorithm. The cause analysis unit 113 changes the determination threshold value of the first influence degree. In this way, the cause analysis unit 113 can feedback the cause of the abnormal situation to the first influence degree calculation unit 107.

[0028] In this way, a parts management system that predicts the occurrence of abnormal situations such as overloading based on the usage status of the storage location can be provided. Further, the above functions can be realized by using an information processing device. The information processing device can be composed of one or a plurality of information processing devices. Further, the information processing device may execute some or all of the functions in the cloud.

[0029] (Explanation of the parts management method according to Embodiment 1) FIG. 2 is a flowchart of the parts management method according to Embodiment 1. The parts management method according to Embodiment 1 will be described with reference to FIG. 2.

[0030] As shown in FIG. 2, the parts management method starts from the end of the transportation work the previous day (step S201). Next, the parts management system 100 acquires the final results of the previous day (step S202). The final results include the usage status of the storage location and the parts stock quantity, etc. Next, the change point information for the current day is imported into the parts management system 100 (step S203). The parts delivery plan information acquisition unit 101 acquires the parts delivery plan from the parts delivery plan information database. Also, the parts management system 100 acquires production information from the production plan information database. Furthermore, the parts management system 100 acquires resource information such as the attendance of workers from the resource information database. The change point information for the current day is information indicating the change in the number of parts at the parts storage location. The change point for the current day is obtained from the parts delivery plan, production information, and resource information. The prediction unit 103 executes a simulation of the usage status of the storage location based on the final results and the change point information for the current day (step S204). The prediction unit 103 outputs a prediction of the usage status of the storage location based on the simulation (step S205).

[0031] Next, the first impact degree calculation unit 107 imports the delivery actual results information for the current day (step S206). The delivery actual results information that is likely to deviate from the plan is imported at a determined frequency. Also, the actual results information includes the part number and the delivery time. Next, the first impact degree calculation unit 107 determines whether the first impact degree based on the delivery actual results and the delivery plan is less than or equal to the threshold value (step S207). The first impact degree calculation unit 107 may obtain a difference value for each part number and calculate the first impact degree from each difference value. It is determined using an algorithm whether the difference between the scheduled delivery time and the actual delivery time affects the level of overstock. If it is less than or equal to the threshold value (Yes in step S207), no abnormal situation occurs, and the display unit of the parts management system 100 displays the storage location usage prediction (step S208). If it is greater than or equal to the threshold value (No in step S207), there is a possibility of an abnormal situation occurring, and the prediction update unit 109 executes a simulation of the usage status of the storage location (step S209). The prediction update unit 109 executes a prediction of the usage status of the storage location.

[0032] As a result of the simulation, the prediction update unit 109 determines whether or not overstocking occurs exceeding the capacity of the storage location (step S210). It is determined whether or not overstocking occurs based on a preset threshold value. If overstocking does not occur (in the case of No in step S210), the prediction update unit 109 does not change the prediction display (step S211). If overstocking occurs (in the case of Yes in step S210), the prediction update unit 109 changes the prediction display (step S212).

[0033] Then, the notification unit 111 issues a warning (step S213). Next, when the operator disposes of the stocked items at the overstocked storage location (step S214), the parts management method ends the processing of the storage location. On the other hand, the parts management method according to the first embodiment accumulates the overstock occurrence conditions (step S215) and utilizes them for updating the influence determination algorithm for the next storage location. Therefore, the cause analysis unit 113 analyzes the cause of the overstock (step S216). At this time, machine learning can be used for the cause analysis. Then, the cause analysis unit 113 updates the influence determination algorithm of the first influence degree calculation unit 107 (step S217). By doing so, the cause analysis unit 113 can feedback the cause of occurrence to the first influence degree calculation unit 107.

[0034] As described above, it is possible to provide a parts management method for predicting the occurrence of abnormal situations such as overstocking based on the usage status of the storage location.

[0035] (Description of the parts management method according to the second embodiment) FIG. 3 is a flowchart of the parts management method according to the second embodiment. The parts management method according to the second embodiment will be described with reference to FIG. 3.

[0036] As shown in FIG. 3, Embodiment 2 differs from Embodiment 1 in steps S206A and S207A. In step S206A, the incoming performance information acquisition unit 105 acquires the incoming performance information of parts at a determined frequency, and the storage performance information acquisition unit acquires the storage performance information of the storage location. Then, in step S207A, it is determined whether both the first influence degree of the incoming performance and the incoming plan and the second influence degree of the storage performance and the incoming plan are below the threshold. The second influence degree is, for example, the difference obtained by subtracting the number of parts in the incoming plan from the number of parts in the storage performance. The parts management system 100 may obtain the difference value for each part and calculate the second influence degree. The first influence degree calculation unit 107 calculates the first influence degree, and the second influence degree calculation unit calculates the second influence degree. Based on the comparison results of the first influence degree, the second influence degree, and the threshold, for example, if both are below the threshold (in the case of Yes in step S207A), no abnormal situation occurs, and the display unit of the parts management system 100 displays the predicted use of the storage location (step S208). If either exceeds the threshold (in the case of No in step S207A), there may be an abnormal situation, and the parts management system 100 executes a simulation of the storage location usage status (step S209).

[0037] The cause analysis unit 113 can change not only the threshold of the first influence degree but also the threshold of the second influence degree. That is, the cause analysis unit 113 analyzes the cause and can change the threshold of the second influence degree according to the occurrence cause.

[0038] By using not only the first influence degree but also the second influence degree, the prediction update unit can update the prediction at an appropriate timing.

[0039] Furthermore, part or all of the processing in the information processing apparatus described above 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. Non-transitory computer-readable media include various types of tangible recording media. Examples of non-transitory computer-readable media include magnetic recording media (e.g., flexible disks, magnetic tapes, hard disk drives), magneto-optical recording media (e.g., magneto-optical disks), CD-ROM (Read Only Memory), CD-R, CD-R / W, semiconductor memories (e.g., mask ROM, PROM (Programmable ROM), EPROM (Erasable PROM), flash ROM, RAM (Random Access Memory)). Also, the program may be supplied to the computer by various types of temporary computer-readable media. Examples of temporary computer-readable media include electrical signals, optical signals, and electromagnetic waves. The temporary computer-readable media can supply the program to the computer via wired communication paths such as electric wires and optical fibers, or wireless communication paths.

[0040] Note that the present invention is not limited to the above-described embodiments and can be appropriately modified without departing from the gist.

Explanation of Reference Numerals

[0041] 100 Parts management system, 101 Procurement plan information acquisition unit, 103 Prediction unit, 105 Procurement performance information acquisition unit, 107 First influence degree calculation unit, 109 Prediction update unit, 111 Notification unit, 113 Cause analysis unit, 201 Parts procurement plan information database, 203 Production plan information database, 205 Resource information database

Claims

1. A procurement plan information acquisition unit that acquires procurement plan information of parts; A prediction unit that predicts the occurrence of overstocking in the placement usage status of parts based on the acquired procurement plan information of the parts; A procurement result information acquisition unit that acquires the procurement result information of the parts; A first impact degree calculation unit that calculates a first impact degree based on the difference between the acquired procurement result information of the parts and the acquired procurement plan information of the parts, and compares the first impact degree with a threshold value; A prediction update unit that updates the prediction of the prediction unit based on the comparison result between the calculated first impact degree and the threshold value; A parts management system comprising a notification unit that notifies of the overstocking when it is predicted by the prediction update unit that the overstocking will occur.

2. The parts management system according to claim 1, further comprising a factor analysis unit that analyzes the cause of the overstocking when it is predicted that the overstocking will occur and reflects it in the first impact degree calculation unit.

3. The factor analysis unit includes a storage unit that stores a learned machine learning device that learns when a plurality of training data sets composed of combinations of the cause of the overstocking and the threshold value of the first impact degree are input; The parts management system according to claim 2, further comprising an arithmetic unit that outputs the threshold value of the first impact degree when the cause of the overstocking is input to the learned machine learning device read from the storage unit.

4. Furthermore, a storage result information acquisition unit that acquires the storage result information of each placement of the parts; A second impact degree calculation unit that calculates a second impact degree, which is the difference between the acquired storage result information and the acquired procurement plan information, and compares the second impact degree with a threshold value; The parts management system according to claim 1, wherein the prediction update unit updates the prediction of the prediction unit based on the comparison result between the second impact degree and the threshold value.

5. An information processing apparatus performs a step of acquiring procurement plan information of parts; a step of predicting the occurrence of overstocking in the placement usage status of parts based on the acquired procurement plan information of the parts; a step of acquiring the procurement result information of the parts; a step of calculating a first impact degree based on the difference between the acquired procurement result information of the parts and the acquired procurement plan information of the parts, and comparing the first impact degree with a threshold value; a step of updating the prediction in the step of predicting based on the comparison result between the calculated first impact degree and the threshold value; A parts management method comprising: a step of updating a prediction in the predicting step and notifying the overload when it is predicted that the overload will occur.

Images