JP7572889B2 - Parts demand trend analysis system and method - Google Patents

Description

The present invention relates to a demand trend analysis system and method for analyzing demand trends for parts.

To keep construction machinery in operation for a long period of time while maintaining its quality and functionality at the site of use, continuous and proper maintenance (inspection, repair, parts replacement, etc.) is necessary after the sale of the machinery. Because construction machinery is operated all over the world, in order to perform maintenance quickly and properly, it is necessary to set up maintenance bases around the world, predict the number of parts required at each base in advance, and ensure that the necessary parts are in stock at each base.

In this case, to avoid running out of parts, it is possible to secure large quantities of parts as inventory at each location. However, from the perspective of management efficiency, it is not desirable for each location to have large quantities of surplus parts as inventory, due to issues with warehouse maintenance and management costs and the asset nature of inventory.

In order to secure the necessary number of parts in advance without generating excess inventory, it is essential to forecast future demand. However, since demand for parts in each region fluctuates depending on the situation at the time, it is difficult to accurately forecast demand for parts.

As a method for solving such problems, Patent Document 1 discloses a method for predicting parts demand from past parts replacement history. This method predicts future demand from the timing at which parts were installed on machines and the lifespan of the parts. However, this method is based on the assumption that each machine will operate for the same operating hours as before, so it is difficult to accurately predict sudden increases or decreases in demand that occur due to regional differences, global situations, etc.

International Publication No. 2015/198453

The present invention provides a parts demand trend analysis system and method that enables accurate prediction of demand for construction machinery parts at each base.

In order to solve the above problems, the parts demand judgment system according to the present invention includes an economic indicator acquisition unit that acquires economic indicator data, a planned order quantity data acquisition unit that acquires planned order quantity data related to the planned order quantity of parts for the construction machine at the base of the construction machine, an economic indicator selection unit that selects, from the economic indicator data acquired by the economic indicator acquisition unit, economic indicator data that has a predetermined correlation with past parts order data related to past orders for the parts at each of the bases, a demand trend analysis unit that calculates demand trend data by analyzing the demand trend of the parts at each of the bases based on the economic indicator data selected by the economic indicator selection unit, an order quantity calculation unit that calculates recommended order quantity data, which is the order quantity of the parts to be recommended, based on the demand trend data and the planned order quantity data, and a transmission unit that transmits the demand trend data and the recommended order quantity data to a base device.

The present invention provides a parts demand trend analysis system and method that enables accurate prediction of demand for construction machinery parts at each base.

1 is a block diagram illustrating a demand trend analysis system according to an embodiment. FIG. 2 is a block diagram for explaining the details of each of devices 1 to 3 in the system of FIG. 1. 1 is a conceptual diagram for explaining the flow of data between the trend analysis terminal 5 and the base terminal 6 or the economic index acquisition terminal 4, and the procedure of judgment. FIG. 2 is a block diagram illustrating a detailed configuration example of the economic index acquisition device 1 (economic index acquisition terminal 4). The economic index data is acquired and stored in the economic index data storage unit 9. An example of data items included in the acquired and stored economic index data is shown below. 2 is a schematic diagram for explaining the details of the configuration and operation of the trend analysis device 2. FIG. The past parts order data for each base, which is acquired and stored in the data storage unit 15, will be described. 1 is a schematic diagram for explaining the procedure for selecting economic indicator data with high relevance (large correlation coefficient) in the indicator selection unit 16. FIG. 11 is a graph illustrating a trend analysis method in the trend analysis unit 17. 11 is a schematic diagram illustrating a method for calculating a recommended order amount in the tendency analysis unit 17. FIG. 10 is a schematic diagram illustrating transmission of trend information acquired by a trend analysis unit 17 to a transmitting device 3. FIG. 2 is a schematic diagram for explaining the details of the configuration of a base device 3. FIG. An example of a screen display in the tendency analysis result display unit 21 will be described.

Hereinafter, the present embodiment will be described with reference to the attached drawings. In the attached drawings, functionally identical elements may be indicated by the same numbers. Note that the attached drawings show embodiments and implementation examples according to the principles of the present disclosure, but these are for understanding the present disclosure and are in no way used to interpret the present disclosure in a restrictive manner. The descriptions in this specification are merely typical examples and do not limit the scope or application examples of the present disclosure in any sense.

In this embodiment, the disclosure is described in sufficient detail for a person skilled in the art to implement the disclosure, but it should be understood that other implementations and forms are possible, and that changes to the configuration and structure and substitutions of various elements are possible without departing from the scope and spirit of the technical ideas of the disclosure. Therefore, the following description should not be interpreted as being limited to this.

A demand trend analysis system according to an embodiment will be described with reference to the block diagram of FIG. 1. This demand trend analysis system is broadly composed of an economic indicator acquisition device 1, a trend analysis device 2, and a base device 3. In this system, the trend analysis device 2 selects economic indicator data related to information on past orders of parts at each base where the base device 3 is installed (past parts order data), and the trend analysis device 2 performs a trend analysis of future demand for parts at each base from the selected economic indicator data and past parts order data. Then, the system performs a more accurate forecast of demand for parts by calculating recommended order quantity data obtained by adding the analysis results to information on planned orders for parts for each base (planned parts order data).

The details of each of the devices 1 to 3 in the system of FIG. 1 will be described with reference to the block diagram of FIG. 2. The economic index acquisition device 1 includes an economic index acquisition terminal 4, the trend analysis device 2 includes a trend analysis terminal 5, and the base device 3 includes a base terminal 6. The base terminal 6 is connected to the trend analysis terminal 5 and the economic index acquisition terminal 4 via a network.

The economic indicator acquisition terminal 4 is connected not only to the internal network but also to the external Internet, and has the function of automatically acquiring various economic indicators from the Internet. The trend analysis terminal 5 acquires economic indicator data from the economic indicator acquisition terminal 4, and also acquires past parts order data and parts order schedule data from the base terminal 6.

The trend analysis terminal 5 and the base terminal 6 are configured, as in a general computer, with, for example, a CPU 101, ROM 102, RAM 103, a hard disk drive 104, a flash memory 105, an input unit (keyboard, touch panel, pen device, mouse, etc.) 106, a display unit 107 (display), a communication control unit 108, a speaker 109, a microphone 110, and a camera 111. The hard disk drive 104 and the flash memory 105 function as storage units that store various data. In addition, the hard disk drive 104 etc. stores a computer program that executes the parts demand trend analysis described below.

The data flow and judgment procedure between the trend analysis terminal 5 and the base terminal 6 or the economic indicator acquisition terminal 4 will be described with reference to FIG. 3. The trend analysis terminal 5 acquires past parts order data and economic indicator data from the base terminal 6 and the economic indicator acquisition terminal 4, respectively, and selects economic indicator data suitable for prediction according to the results of a comparison with the past parts order data. Economic indicator data that has a high correlation (high correlation coefficient) with the past parts order data is selected as economic indicator data suitable for prediction. Then, using the selected economic indicator data, a judgment is made on the demand trend for parts at the base where the base terminal 6 is located, and trend analysis data is generated. The generated trend analysis data is transmitted to the base terminal 6.

Next, a detailed configuration example of the economic index acquisition device 1 (economic index acquisition terminal 4) will be described with reference to FIG. 4. As an example, the economic index acquisition terminal 4 includes an economic index data acquisition unit 8 and an economic index data storage unit 9.

The economic indicator data acquisition unit 8 automatically collects various economic indicator data from data 7 on the Internet (on the WEB) using WEB crawling technology. The collected economic indicator data is acquired and stored in the economic indicator data storage unit 9. The acquired and stored economic indicator data may include time series information and the numerical values of the indicators as data items, as exemplified in FIG. 5.

The economic indicator data acquired by the economic indicator data acquisition unit 8 is deployed to the trend analysis device 2 via the network connection unit 10. It is essential that the economic indicator data selected is related to the construction machinery industry. However, there is a possibility that economic indicator data that is generally thought to be unrelated to the construction machinery industry actually has a high correlation with the demand trend of construction machinery parts. For this reason, it is preferable for the economic indicator acquisition device 1 not to narrow down the field as much as possible, but to collect all indicators that can be acquired by WEB crawling. For example, data that is directly related to the construction machinery industry, such as the number of construction cases in each country, the number of housing starts, and the price of mineral resources obtained in mines where mining machines are operating, must be acquired. In addition, it is preferable for the economic indicator acquisition device 1 of this embodiment to acquire indicators that are not directly related to the construction machinery industry, such as the gross domestic product of the country where each base is located, economic comprehensive indexes such as NASDAQ, agricultural sector indexes, and food prices.

In addition, it is also possible to collect economic indicator data generated by combining multiple economic indicators and use it as a candidate for selection. As an example, economic indicator data A and economic indicator data B may be multiplied by a predetermined weighting coefficient and then added to generate new economic indicator data, which may be used as one of the candidates for economic indicator data that may be selected.

The economic indicator data acquisition unit 8 may be configured to collect all economic indicator data without setting conditions when collecting economic indicator data, or to set certain conditions and collect only economic indicator data that meets those conditions in order to improve data processing speed.

The selected economic indicator data may differ for each base device 3. As described above, the base devices 3 are located in different locations around the world. For this reason, the past part order data provided by each base device 3 is influenced by the economic and political situations that differ for each base, and the economic indicator data with a large correlation coefficient may also differ for each base.

Referring to FIG. 6, the detailed configuration and operation of the trend analysis device 2 are shown in FIG. 6. The trend analysis device 2 (trend analysis terminal 5) is composed of a data acquisition unit 14, a data storage unit 15, an index selection unit 16, a trend analysis unit 17, an order amount calculation unit 18, and a data transmission unit 19.

The data acquisition unit 14 has the function of acquiring past parts order data for each base and parts order schedule data indicating parts ordering schedules from the memory units (22, 23) of the base device 3, and acquiring economic indicator data from the economic indicator data memory unit 9 of the economic indicator acquisition device 1. In other words, the data acquisition unit 14 functions as an economic indicator acquisition unit that acquires economic indicator data, and as a planned order quantity data acquisition unit that acquires planned order quantity data for construction machine parts at the construction machine base. The data memory unit 15 is a memory unit that stores the data acquired by the data acquisition unit 14.

The index selection unit 16 has a function of selecting, for each base, economic index data having a large correlation coefficient in relation to the past parts order data for each base acquired from each base device 3. The trend analysis unit 17 has a function of determining future demand trends at each base from the economic index data selected for each base by the index selection unit 16 and the past parts order data, and outputting the result as demand trend data. The order quantity calculation unit 18 assigns the demand trend data obtained by the trend analysis unit 17 to the parts order schedule data held by each base device 3, and calculates the order quantity (recommended order quantity) of the part recommended at each base based on this. The data created by the trend analysis unit 17 and the order quantity calculation unit 18 is transmitted to the base device 3 by the data transmission unit 19.

An example of the data structure of past parts order data for each base acquired and stored in the data storage unit 15 will be described with reference to FIG. 7. The past parts order data may include the name of the base to which the data pertains, the part number which is a code for identifying the part, the machine classification indicating the classification of the machine on which the part is to be installed, the order date, the order quantity, the order amount, etc. In addition to the items exemplified in FIG. 7, the past parts order data may also include data such as the delivery date of the part, the number of days delivery was delayed, and the name of the company that manufactured the part.

The procedure for selecting economic indicator data with high relevance (large correlation coefficient) in the index selection unit 16 will be described with reference to FIG. 8. The index selection unit 16 first compares the past parts order data acquired from the base device 3 with the acquired economic indicator data group (economic indicator data A, B, C, ...) to calculate a correlation coefficient. The economic indicator data A, B, C, ... are candidates for the economic indicator data to be finally selected. The index selection unit 16 advances the economic indicator data by a predetermined period (e.g., April) ahead of the past parts order data, compares the numerical value of the parts order data at a certain point in time with the numerical value of the economic indicator data that precedes that point in time by a predetermined period, and calculates the correlation coefficient based on the result of the comparison. Note that the length of time for which the economic indicator data is advanced is arbitrary and is not limited to four months.

The index selection unit 16 selects economic indicator data from among multiple sets of economic indicator data according to the calculation result of the correlation coefficient. For example, the economic indicator data with the largest correlation coefficient (e.g., economic indicator C) is selected from the multiple sets of economic indicator data. The economic indicator data selected by the index selection unit 16 is not limited to only one set (only the economic indicator data with the largest correlation coefficient), and multiple sets of economic indicator data may be selected. The number of sets of economic indicator data to be selected is arbitrary. For example, in addition to selecting the economic indicator data with the highest correlation coefficient, it is also possible to select economic indicator data with correlation coefficients that are second (runner-up) to fifth. The number of sets of economic indicator data to be selected is not limited to a specific number. For example, when there is a large number of economic indicator data that satisfy a predetermined condition, the number of economic indicator data to be selected can be changed depending on the situation without imposing a limit on the number of economic indicator data to be selected.

Next, referring to Figures 9A and 9B, we will explain how the trend analysis unit 17 performs trend analysis and how the order quantity calculation unit 18 calculates the recommended order quantity.

As shown in FIG. 9A, assume that economic indicator data that precedes the past parts order data by four months and has the highest correlation coefficient has been obtained. As shown in FIG. 9A, the past parts order data is data up to July 2020, and economic indicator data C is selected as the economic indicator data with the highest correlation coefficient. In this case, a prediction of the trend of parts orders from August to November 2020 is made based on the changes in economic indicator data C from four months prior, and a trend analysis value is obtained according to this prediction (see FIG. 9B). Here, the trend analysis value is a numerical value that indicates the increase or decrease in the following several months, with the most recent month's data of economic indicator data C (July 2020 in the example of FIG. 9A) being set as 100%. The trend analysis value for a certain month is calculated in the trend analysis unit 17 based on the economic indicator data C from four months prior.

The order quantity calculation unit 18 of the trend analysis device 2 modifies the parts order schedule data obtained from the base device 3 based on this trend analysis value, and calculates this modified value as recommended order quantity data. Specifically, the recommended order quantity data is calculated by multiplying the number of parts order schedules for a certain month by the trend analysis value. The parts order schedule data is modified by the trend analysis value (trend analysis data) calculated based on economic indicator data C that is determined to have a high correlation with the parts past order data, making it possible to order parts that more accurately reflect demand. Trend information including the calculated recommended order quantity data is transmitted (information provided) to the corresponding base device 3 (see FIG. 10). The recommended order quantity data is calculated for each base based on the parts past order data etc. provided by the base device 3, and the recommended order quantity data calculated for that base is transmitted to the base device 3 of the corresponding base.

The detailed configuration of the base device 3 will be described with reference to FIG. 11. As an example, the base device 3 includes a trend data acquisition unit 20, a trend analysis result display unit 21, a parts past order data storage unit 22, an order schedule data storage unit 23, and a data transmission unit 24.

The trend data acquisition unit 20 acquires the trend analysis values, recommended order volume data, etc. calculated by the trend analysis unit 17 and order volume calculation unit 18 of the trend analysis device 2 as trend analysis data. The trend analysis result display unit 21 displays the trend analysis data acquired by the trend data acquisition unit 20.

The parts past order data storage unit 22 stores parts past order data at the base where the base device 3 is located. The order schedule data storage unit 23 stores parts order schedule data for parts at the base where the base device 3 is located. The data transmission unit 24 has a function of transmitting the parts past order data and parts order schedule data stored in the parts past order data storage unit 22 and the order schedule data storage unit 23 to the trend analysis device 2.

An example of a screen display in the trend analysis result display unit 21 will be described with reference to FIG. 12. This screen includes, as an example, a selection index display unit 45, a selection index trend display unit 46, a correlation coefficient top index display unit 47, a graph display unit 48, and a recommended order quantity list display unit 49.

The selection index display unit 45 displays the name of the base where the base device 3 is located (e.g., base 1), the part number (e.g., A0001) that identifies the part that is the subject of the demand forecast, and the name of the economic index data selected to forecast the demand trend of that part (e.g., XX price). The selection index trend display unit 46 displays the demand trend of the part predicted for the most recent few months (e.g., 4 months) according to the selected economic index data.

The top correlation coefficient indicator display section 47 is a section that displays, apart from the economic indicator data with the highest correlation coefficient used in the demand forecast, other economic indicator data that are recognized to have high correlation coefficients (e.g., top 2 to 6), along with the name of the indicator, its correlation coefficient, and the year-on-year change from the same month.

The graph display unit 48 displays a graph showing changes over time in economic indicator data selected for demand forecasting and data showing past orders for the parts that are the subject of the demand forecast (parts past order data). The recommended order quantity list display unit 49 displays a list of the recommended order quantities calculated by the order quantity calculation unit 18 together with the part numbers related to the forecast, the planned order quantities, the planned order month, the order amount difference, etc.

By displaying the above information on the base device 3, the administrator of the base device 3 can visually grasp information including the recommended order quantity, and can use this information as a reference when ordering parts.

As described above, according to the parts demand trend prediction system of this embodiment, economic indicator data that has a high correlation with past parts order data at each base is selected from the acquired economic indicator data, and a demand trend is calculated based on the selected economic indicator. Then, recommended order quantity data is calculated based on the demand trend data and planned order quantity data. Since the recommended order quantity data is calculated based on the highly correlated economic indicator data and transmitted to each base, it becomes possible to accurately predict demand for parts at each base.

The present invention is not limited to the above-described embodiments, and includes various other modified examples. For example, the above-described embodiments have been described in detail to clearly explain the present invention, and are not necessarily limited to those having all of the configurations described. It is also possible to replace 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. It is also possible to add, delete, or replace part of the configuration of each embodiment with other configurations.

1...economic index acquisition device 2...trend analysis device 3...base side device 4...economic index acquisition terminal 5...trend analysis terminal 6...base side terminal 8...economic index data acquisition unit 9...economic index data storage unit 10...network connection unit 14...data acquisition unit 15...data storage unit 16...index selection unit 17...trend analysis unit 18...order quantity calculation unit 19...data transmission unit 20...trend data acquisition unit 21...trend analysis result display unit 22...parts past order data storage unit 23...order schedule data storage unit 24...data transmission unit 45...selected index display unit 46...selected index trend display unit 47...correlation coefficient top index display unit 48...graph display unit 49...recommended order quantity list display unit

Claims (6)

an economic indicator acquisition unit that acquires economic indicator data;
a planned order quantity data acquisition unit that acquires planned order quantity data regarding the planned order quantity of parts for the construction machine at a base of the construction machine;
an economic indicator selection unit that selects, from the economic indicator data acquired by the economic indicator acquisition unit, economic indicator data having a predetermined correlation with past part order data related to orders for the parts at each of the bases in the past;
a demand trend analysis unit that calculates demand trend data by analyzing a demand trend of the parts at each of the bases based on the economic index data selected by the economic index selection unit;
an order quantity calculation unit that calculates recommended order quantity data, which is an order quantity of the part to be recommended, based on the demand trend data and the planned order quantity data;
a transmission unit that transmits the demand trend data and the recommended order quantity data to a base device. The parts demand trend forecasting system according to claim 1, wherein the economic indicator selection unit calculates a correlation coefficient between the parts past order data and the economic indicator data that precedes the parts past order data by a predetermined period, and selects the economic indicator data from the calculation result. The parts demand trend forecasting system according to claim 1, wherein the economic indicator acquisition unit acquires economic indicator data that is not related to the construction machinery industry as well as economic indicator data that is directly related to the construction machinery industry. The parts demand trend forecasting system according to claim 1, wherein the economic indicator selection unit selects economic indicator data that has the largest correlation coefficient with the parts past order data. The parts demand trend forecasting system according to claim 4, wherein the economic indicator selection unit selects multiple sets of economic indicator data that satisfy a predetermined condition in addition to the economic indicator data with the largest correlation coefficient. The parts demand trend forecasting system according to claim 5, further comprising a display unit that lists and displays the sets of economic indicator data selected by the economic indicator selection unit, the display unit being provided in the base device.

Images