Demand forecasting device, demand forecasting system, and program

Abstract

To predict a demand for a component more accurately or support the prediction.SOLUTION: An information processing apparatus that provides information to a prediction apparatus for predicting a demand for a vehicle component in preparation for replacement or repair of the component is provided with: a first acquisition unit that acquires a past value of the demand for the component; a second acquisition unit that acquires an operation value related to the operation of vehicles that use the component; and a provision unit that provides the past value and the operation value to the prediction apparatus. Trends in increase and decrease and variation of the operation value in a time series are linked to trends in increase and decrease and variation of the past value.SELECTED DRAWING: Figure 1

Description

[Technical field]

[0001] The present invention relates to an information providing device, a demand forecasting device, an information providing system, a demand forecasting system, and a program. [Background technology]

[0002] Conventionally, a part demand forecasting program has been disclosed that forecasts demand for parts using replacement rates and operation characteristics of the parts (see, for example, Patent Document 1). [Prior art documents] [Patent documents]

[0003] [Patent Document 1] JP 2007-199844 A Summary of the Invention [Problem to be solved by the invention]

[0004] However, the above prediction methods are not always sufficiently accurate. The present invention has been made in consideration of the above circumstances, and has as its object to more accurately predict or assist in predicting demand for parts. [Means for solving the problem]

[0005] An information providing device, a demand forecasting device, an information providing system, a demand forecasting system, and a program according to the present invention employ the following configuration. (1): An information processing device according to one embodiment of the present invention is an information providing device that provides information to a prediction device that predicts demand for vehicle parts in preparation for replacement or repair of the parts, and includes a first acquisition unit that acquires actual values ​​of demand for the parts, a second acquisition unit that acquires operation values ​​related to the operation of the vehicle using the parts, and a providing unit that provides the actual values ​​and the operation values ​​to the prediction device, and the trends of increase / decrease and fluctuation of the operation values ​​over time are linked to the trends of increase / decrease and fluctuation of the actual values.

[0006] (2): A demand forecasting device according to one embodiment of the present invention is a forecasting device that forecasts demand for a vehicle part in preparation for replacement or repair of the part, and includes an acquisition unit that acquires an actual value of demand for the part and an operation value related to the operation of the vehicle that uses the part, and a forecasting unit that predicts the demand based on the actual value and the operation value.

[0007] (3): In the above aspect (2), the trend of increase / decrease in the operating value in the time series is identical to or similar to the trend of increase / decrease in the actual value, and the prediction unit predicts the demand based on the trend of increase / decrease in the operating value in the time series and the trend of increase / decrease in the actual value.

[0008] (4): In the above aspect (2) or (3), the trend of the fluctuation range of the operating value in the time series is identical to or similar to the trend of the fluctuation range of the actual value, and the prediction unit predicts the demand based on the trend of the fluctuation range of the operating value in the time series and the trend of the fluctuation range of the actual value.

[0009] (5): In any of the above aspects (2) to (4), the prediction unit predicts the demand using the actual values ​​and the operating values ​​for a predetermined period, the actual values ​​and the operating values ​​for at least three points in time.

[0010] (6): In any of the above aspects (2) to (5), the acquisition unit acquires the actual value for each predetermined period and the operation value for each predetermined period, and the prediction unit predicts the demand for a third point in time that is in the future than the first point in time based on the displacement of the operation value for a second point in time that is earlier than the first point in time relative to the operation value for the first point in time.

[0011] (7): In the above aspect (6), when the operation value at the first time point tends to increase relative to the operation value at the second time point, the prediction unit predicts the demand at the third time point based on a value obtained by subtracting the magnitude of the difference between the operation value at the first time point and the operation value at the second time point from the existing predicted value obtained in advance for the third time point, and when the operation value at the first time point tends to decrease relative to the operation value at the second time point, the prediction unit predicts the demand at the third time point based on a value obtained by adding the magnitude of the difference between the operation value at the first time point and the operation value at the second time point to the existing predicted value obtained in advance for the third time point.

[0012] (8) In any of the above aspects (2) to (7), the vehicle operation value is information indicating the actual driving status of a vehicle associated with a predetermined area.

[0013] (9): A demand forecasting system according to another embodiment of the present invention is an information provision system that provides information to a prediction device that predicts demand for vehicle parts in preparation for replacement or repair of the parts, wherein the information provision system acquires actual values ​​of demand for the parts and acquires operation values ​​related to the operation of vehicles that use the parts, and provides the actual values ​​or the operation values ​​to the prediction device, and the trends of increase / decrease and fluctuation of the operation values ​​over time are linked to the trends of increase / decrease and fluctuation of the actual values.

[0014] (10): A demand forecasting system according to another embodiment of the present invention is a demand forecasting system that forecasts demand for a vehicle part in preparation for replacement or repair of the part, the demand forecasting system acquiring an actual value of demand for the part, acquiring an operation value related to the operation of a vehicle that uses the part, and predicting the demand based on the actual value and the operation value.

[0015] (11): A program according to another aspect of the present invention is a program that causes a computer to provide information to a prediction device that predicts demand for a vehicle part in preparation for replacement or repair of the part, the program causes the computer to obtain actual values ​​of demand for the part and obtain operation values ​​related to the operation of a vehicle that uses the part, and provides the actual values ​​or the operation values ​​to the prediction device, wherein the trends in increase / decrease and fluctuation of the operation values ​​over time are linked to the trends in increase / decrease and fluctuation of the actual values.

[0016] (12): A program according to another aspect of the present invention is a program for causing a computer to predict demand for a vehicle part in preparation for replacement or repair of the part, the program causing the computer to obtain actual values ​​of demand for the part, obtain operating values ​​related to the operation of a vehicle using the part, and predict the demand based on the actual values ​​and the operating values. Effect of the Invention

[0017] According to (1), (9), or (11), the information processing device can support the prediction device in predicting demand for parts by providing the prediction device with actual results values ​​and operation values.

[0018] According to (2)-(8), (10), or (12), by predicting the demand for vehicle parts based on actual values ​​and operation values, the demand for parts can be predicted with greater accuracy. [Brief description of the drawings]

[0019] [Figure 1] 1 is a diagram illustrating an example of a configuration of a prediction system 1 including an information providing device and a demand prediction device. [Diagram 2] 2 is a diagram showing an example of a functional configuration of a vehicle system 10 mounted on a vehicle M. [Diagram 3] FIG. 2 is a diagram illustrating an example of a functional configuration of an information processing device 100 and a prediction device 200. [Figure 4]4 is a flowchart showing an example of the flow of processing executed by the information processing device 100. [Diagram 5] 13 is a diagram showing an example of operation information 144 acquired by a second acquisition unit 120. FIG. [Figure 6] FIG. 13 is a diagram showing an example of tally information 146. [Figure 7] FIG. 11 is a diagram for explaining actual driving information 148. [Figure 8] 13 is a diagram showing a comparison between actual driving information 148 and performance information 142. FIG. [Figure 9] FIG. 13 is a diagram (part 1) for explaining a process for generating second prediction information 258. [Figure 10] FIG. 13 is a diagram (part 2) for explaining the process of generating second prediction information 258. [Figure 11] 13 is a flowchart showing an example of the flow of processing executed by the prediction device 200. [Figure 12] FIG. 13 is a diagram for comparing an existing predicted value with a new predicted value. DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS

[0020] Hereinafter, with reference to the drawings, embodiments of an information providing device, a demand forecasting device, an information providing system, a demand forecasting system, and a program according to the present invention will be described.

[0021] FIG. 1 is a diagram showing an example of the configuration of a prediction system 1 including an information providing device and a demand prediction device. The prediction system 1 includes, for example, one or more vehicles M (M1-Mn in the figure), an information processing device 100, and a prediction device 200. The vehicle M and the information processing device 100 can communicate with each other via a network NW. The network NW includes the Internet, a wide area network (WAN), a local area network (LAN), a public line, a provider device, a dedicated line, a wireless base station, and the like. The information processing device 100 and the prediction device 200 can communicate with each other via the dedicated line or the network NW. The information processing device 100 is an example of an "information providing device" in the claims, and the prediction device 200 is an example of a "demand prediction device" in the claims.

[0022] [vehicle] The one or more vehicles M are vehicles used in a predetermined area. The predetermined area is an area where the vehicle M is mainly used or an area corresponding to a parking space for the vehicle M.

[0023] 2 is a diagram showing an example of the functional configuration of a vehicle system 10 mounted on a vehicle M. The vehicle system 10 includes, for example, a vehicle sensor 20, a navigation device 30, a communication device 40, a processing device 50, and a storage unit 60. In addition to the above-mentioned functional configuration, the vehicle system 10 also includes actuators, electronic devices, and controls for controlling the vehicle (not shown).

[0024] The vehicle sensor 20 includes a vehicle speed sensor that detects the speed of the vehicle M, an acceleration sensor that detects the acceleration, a yaw rate sensor that detects the yaw rate (e.g., the rotational angular velocity around a vertical axis passing through the center of gravity of the vehicle M), and a direction sensor that detects the orientation of the vehicle M. The vehicle sensor 20 may also include, for example, a brake pedal sensor that detects an operation performed on a brake pedal, and a steering sensor that detects the steering amount (e.g., the steering angle) of the host vehicle M. The results detected by the vehicle sensor 20 are output to the processing device 50.

[0025] The navigation device 30 includes, for example, an HMI (Human machine Interface) 32, a GNSS (Global Navigation Satellite System) receiver 34, a navigation control unit 36, and map information 38. The HMI 32 includes, for example, a touch panel display device, a speaker, a microphone, and the like. The GNSS receiver 34 measures its own position (the position of the vehicle M) based on radio waves arriving from a GNSS satellite (for example, a GPS satellite). The navigation control unit 36 ​​includes, for example, a CPU (Central Processing Unit) and various storage devices, and controls the entire navigation device 30. The storage device stores map information (navigation map) 38. The navigation map is a map in which roads are represented by nodes and links. The navigation device 30 provides the processing device 50 with position information indicating the measured position.

[0026] The communication device 40 is, for example, a communication interface for communicating with other devices via a network NW. The communication device 40 performs wireless communication based on Wi-Fi, DSRC (Dedicated Short Range Communications), Bluetooth (registered trademark), or other communication standards.

[0027] The processing device 50 is realized by a hardware processor such as a CPU executing a program (software) stored in a storage device. The storage unit 60 may be realized, for example, by the above-mentioned various storage devices, or a solid state drive (SSD), a random access memory (RAM), a hard disk drive (HDD), etc. The storage unit 60 stores, for example, information output by the vehicle sensor 20 and information provided by the navigation device 30.

[0028] The processing device 50 provides operation information (information indicating the state of the vehicle including the state of the ignition switch of the vehicle M and the driving state) related to the operation of the vehicle, such as information output by the vehicle sensor 20 and information provided by the navigation device 30, to the information processing device 100.

[0029] [Information processing device] 3 is a diagram showing an example of a functional configuration of the information processing device 100 and the prediction device 200. A part or all of the functional configuration included in the information processing device 100 may be included in the prediction device 200. The functional configuration included in the information processing device 100 or the functions included in the prediction device 200 may be distributed and provided in a plurality of devices. The information processing device 100 or the prediction device 200 is a device managed by a business entity such as an automobile manufacturer that manufactures or sells the vehicle M.

[0030] The information processing device 100 includes, for example, a first acquisition unit 110, a second acquisition unit 120, a processing unit 130 (an example of a "providing unit"), and a storage unit 140. The first acquisition unit 110, the second acquisition unit 120, and the processing unit 130 are realized by a hardware processor such as a CPU executing a program (software). Some or all of these functional configurations may be realized by hardware (including a circuit unit; circuitry) such as an LSI (Large Scale Integration), an ASIC (Application Specific Integrated Circuit), an FPGA (Field-Programmable Gate Array), or a GPU (Graphics Processing Unit), or may be realized by cooperation between software and hardware. The program may be stored in advance in a storage device (a storage device having a non-transient storage medium) such as an HDD or flash memory of the information processing device 100, or may be stored in a removable storage medium such as a DVD or CD-ROM, and installed in the HDD or flash memory of the information processing device 100 by mounting the storage medium (non-transient storage medium) in a drive device.

[0031] The storage unit 140 is realized by, for example, the various storage devices described above, or an SSD, a RAM, an HDD, or the like. The storage unit 140 stores information (performance information 142, operation information 144) acquired by the first acquisition unit 110 and the second acquisition unit 120 described below. The storage unit 140 also stores compiled information 146 and actual driving information 148, which are information processed by the processing unit 130 from the performance information 142 or the operation information 144. Details of the information stored in the storage unit 140 will be described later.

[0032] The first acquisition unit 110 acquires performance information. The performance information is information indicating the shipping performance of parts (information indicating performance values). The performance information is information provided by a management device (not shown) that manages the inventory, shipping, and production of parts. The second acquisition unit 120 acquires operation information. The operation information is information provided to the processing device 50.

[0033] The processing unit 130 stores the performance information 142 acquired by the first acquisition unit 110 and the operation information 144 acquired by the second acquisition unit 120 in the storage unit 140. The processing unit 130 processes the performance information 142 or the operation information 144 to generate information used by the prediction device 200. For example, the processing unit 130 processes the operation information 144 to generate the compilation information 146 and the driving status information 148 indicating the driving status of the vehicle M. The processing unit 130 provides the generated information to the prediction device 200 at a predetermined timing. The processing unit 130 provides the performance information 142 or the operation information 144 to the prediction device 200 in response to a request from the prediction device 200 or at a predetermined cycle, for example. The processing unit 130 may provide the operation information 144 to the prediction device 200, and the prediction device 200 may process the operation information 144.

[0034] [Prediction device] The prediction device 200 includes, for example, an information management unit 210 (an example of an "acquisition unit"), a first prediction unit 220, a second prediction unit 230 (an example of a "prediction unit"), a prediction providing unit 240, and a storage unit 250. The information management unit 210, the first prediction unit 220, the second prediction unit 230, and the prediction providing unit 240 are realized by a hardware processor such as a CPU executing a program (software). Some or all of these functional configurations may be realized by hardware (including circuitry) such as an LSI, ASIC, FPGA, or GPU, or may be realized by cooperation between software and hardware. The program may be stored in advance in a storage device (storage device having a non-transient storage medium) such as an HDD or flash memory of the prediction device 200, or may be stored in a removable storage medium such as a DVD or CD-ROM, and installed in the HDD or flash memory of the information processing device 100 by mounting the storage medium (non-transient storage medium) in a drive device.

[0035] The storage unit 250 is realized by, for example, the various storage devices described above, or an SSD, a RAM, an HDD, etc. The storage unit 250 stores performance information 252 and actual driving status information 254 acquired by the information management unit 210 described below. The storage unit 250 also stores first prediction information 256 regarding the demand for parts predicted by the first prediction unit 220, and second prediction information 258 regarding the demand for parts predicted by the second prediction unit 230.

[0036] The information management unit 210 manages various types of information. The information management unit 210 acquires and manages information provided by the information processing device 100 or information obtained by processing by the prediction device 200. The information management unit 210 stores the performance information 142 and the actual driving information 148 provided by the information processing device 100 in the storage unit 250, and stores the prediction results predicted by the first prediction unit 220 or the second prediction unit 230 in the storage unit 250.

[0037] The first prediction unit 220 predicts the demand for parts. The second prediction unit 230 predicts the demand based on the performance information 252 and the actual driving condition information 254. The second prediction unit 230 predicts the demand for parts for each vehicle model of the vehicle M (or for each group of specific vehicle models), for each part, or for each combination of vehicle model and part. Details of this process will be described later.

[0038] The prediction providing unit 240 provides the prediction result of the second prediction unit 230 to other devices. The other devices are terminal devices of a business entity or department that manages the parts, or terminal devices of a business entity or department that manufactures the parts.

[0039] [Processing of information processing device] FIG. 4 is a flowchart showing an example of the flow of processing executed by the information processing device 100. First, the first acquisition unit 110 acquires the performance information 142 (step S100). Next, the second acquisition unit 120 acquires the operation information 144 from the vehicle M (step S102). Next, the processing unit 130 aggregates the operation information 144 (step S104). The aggregated operation information 144 may be hereinafter referred to as aggregated information. Next, the processing unit 130 processes the aggregated information 146 to generate actual driving information 148 (step S106). Next, the processing unit 130 provides the generated actual driving information 148 to the prediction device 200. This ends the processing of one routine of this flowchart.

[0040] FIG. 5 is a diagram showing an example of the operation information 144 acquired by the second acquisition unit 120. The operation information 144 is information in which, for each vehicle M, a date (or date and time) and information indicating the operation status of the vehicle M are associated with each other. The information indicating the operation status is information indicating the operation state and running state of the vehicle M, such as running time, running distance, and braking count. The running time may be the time from when the ignition switch of the vehicle M is turned on to when it is turned off, or may be the time during which the vehicle M actually runs at a predetermined speed or higher. The braking count is the number of times braking is performed or the number of times a braking operation of a predetermined degree or higher is performed. The operation status may include the number of times the acceleration or deceleration has changed by a predetermined degree or more (the number of times rapid acceleration or deceleration has occurred), the number of times the lateral acceleration of the vehicle M has changed by a predetermined degree or more (the number of times sharp turns have occurred), and the like.

[0041] Instead of (or in addition to) directly acquiring the operation information 144 from the vehicle M, the information processing device 100 may acquire the operation information 144 (or the aggregated information) from a navigation server (not shown) that communicates with the navigation device 30 of the vehicle M to acquire information about the vehicle M, or from another device that acquires information about the vehicle M. Furthermore, the information processing device 100 may acquire position information of the vehicle M (information in which position information and time are associated) from the vehicle M, and generate the operation information 144 based on the acquired position information. For example, the information processing device 100 may generate the traveling distance and traveling time of the vehicle from the position information.

[0042] FIG. 6 is a diagram showing an example of the collected information 146. The collected information 146 is, for example, information showing the collected result of the operation information 144 for each predetermined period, and is information showing the result of collecting the operation information 144 for each combination of vehicles of the same model and vehicles belonging to the same region. The predetermined period is a period determined arbitrarily, such as a month or a week. The region is the region to which the vehicle M of the information source belongs. The region to which the vehicle M belongs is, for example, the region corresponding to the location of the parking lot of the vehicle M (for example, the region where the vehicle M is parked for a long time), the region where the vehicle M is driven for a long time, or the region where the store managing the vehicle M (the dealer or repair shop of the vehicle M) is located. The collected information 146 is, for example, information including the driving time, driving distance, and braking frequency of the vehicle M of model a belonging to the region A for each month. The collected information 146 or the driving status information 148 described later is an example of "information showing the driving status of the vehicle associated with a predetermined area".

[0043] FIG. 7 is a diagram for explaining the actual driving information 148. The actual driving information 148 is information indicating the actual driving state of the vehicle M for each region and vehicle type obtained from the compilation information 146. For example, the actual driving information 148 is information indicating an increase or decrease in a predetermined item (driving time, driving distance, number of braking operations, etc.) of the compilation information 146 for each predetermined period. The actual driving information 148 may be information generated by focusing on an arbitrary item among the items (driving time, driving distance, number of braking operations, etc.) of the compilation information 146, or may be information generated by focusing on all items. The actual driving information 148 may be information obtained by scoring an arbitrary item.

[0044] The example of Fig. 7 shows actual driving information 148 generated by focusing on the driving time (actual value) of the aggregated information 146. The actual driving information 148 of Fig. 7 shows the degree of increase and decrease of the driving time of the vehicle M per month. As shown in Fig. 7, the driving time of the vehicle M tends to alternately increase and decrease, and further, the range of increase and decrease tends to fall within a predetermined range.

[0045] When the actual driving situation information 148 and the actual result information 142 are compared, the tendency and the range of increase and decrease between them tend to be linked. FIG. 8 is a diagram showing a comparison between the actual driving situation information 148 and the actual result information 142. As shown in FIG. 8, the tendency of increase and decrease between the actual result information 142 (actual result value) indicating the number of parts actually shipped in a time series and the tendency of increase and decrease between the actual driving situation information 148 are the same or similar. As shown in FIG. 8, the tendency of the range of increase and decrease between the actual result information 142 (actual result value) indicating the number of parts actually shipped and the tendency of the range of increase and decrease between the actual driving situation information 148 are the same or similar. The increase and decrease in the driving time of the vehicle M per month are linked to the increase and decrease in the number of parts shipped per month (characteristic 1), and the range of increase and decrease between the driving time of the vehicle M per month and the range of increase and decrease between the number of parts shipped per month are linked to each other (characteristic 2).

[0046] The information processing device 100 provides the above-mentioned performance information 142 and driving status information 148 to the prediction device 200, and the prediction device 200 performs more accurate demand prediction for parts by using the provided performance information 142 and the driving status trends (feature 1 and feature 2) indicated by the driving status information 148. In this way, the information processing device 100 can support the prediction device 200 in performing demand prediction for parts.

[0047] [Prediction device processing] The prediction device 200 generates second prediction information 258 based on the performance information 252 (142), the actual driving information 254 (148), and the first prediction information 256.

[0048] The actual result information 252 is the actual result information 142 provided by the information processing device 100, and the actual driving information 254 is the actual driving information 148 provided by the information processing device 100. The first prediction information 256 is information indicating a demand forecast for parts (information indicating existing prediction values) predicted by the first prediction unit 220 based on various indices. The first prediction information 256 is information generated based on trends such as the number of shipments and demand of parts up to the present time and various economic indices. The various economic indices are, for example, GDP (Gross Domestic Product), an index of mining and manufacturing, and the number of orders for machinery.

[0049] 9 is a diagram (part 1) for explaining the process of generating the second prediction information 258. The second prediction unit 230 predicts the demand for parts using actual values ​​and indices at least at three points in time, which are actual values ​​for each predetermined period and indices of the actual driving information 254. For example, the second prediction unit 230 predicts the demand for parts at T+1 using indices of the actual driving information 254 at timings T-1 and T, and predicts the demand for parts at T+2 using indices of the actual driving information 254 at timings T and T+1.

[0050] The second prediction unit 230 predicts the demand at timing T+1 (an example of a "third time point") based on the change in the index of the actual driving information 254 at timing T-1 (an example of a "second time point") relative to the index of the actual driving information 254 at timing T (an example of a "first time point"). If the index of the actual driving information 254 at timing T is on an increasing trend relative to the index of the actual driving information 254 at timing T-1, the second prediction unit 230 lowers the prediction of the demand at timing T+1 below the existing predicted value. If the index of the actual driving information 254 at timing T is on a decreasing trend relative to the index of the actual driving information 254 at timing T-1, the second prediction unit 230 increases the prediction of the demand at timing T+1 above the existing predicted value.

[0051] When the index of the actual driving information 254 at the timing T is on an increasing trend relative to the index of the actual driving information 254 at the timing T-1, the second prediction unit 230 predicts the demand at the timing T+1 based on a value obtained by subtracting the magnitude of the difference between the index of the actual driving information 254 at the timing T and the index of the actual driving information 254 at the timing T-1 from the existing predicted value at the timing T+1. When the index of the actual driving information 254 at the timing T is on a decreasing trend relative to the index of the actual driving information 254 at the timing T-1, the second prediction unit 230 predicts the demand at the timing T+1 based on a value obtained by adding the magnitude of the difference between the index of the actual driving information 254 at the timing T and the index of the actual driving information 254 at the timing T-1 from the existing predicted value at the timing T+1.

[0052] For example, the present is timing T, and a process of obtaining the second prediction information 258 at future timing T+1 will be described. Since the actual driving value of the actual driving information 254 at timing T (FIG. 9, P1) is plus 4% compared to the actual driving value of the actual driving information 254 at timing T-1, the second prediction unit 230 generates the second prediction information 258 by subtracting the existing prediction value (FIG. 9, P2) of the first prediction information 256 at the next timing T+1 by 4% as a new prediction value (FIG. 9, P3). The second prediction unit 230 predicts that there is a tendency for a decrease to occur after an increase in demand using the above-mentioned characteristic 1, and predicts that the demand will decrease by the amount of the increase because the fluctuation tends to be the same using the above-mentioned characteristic 2.

[0053] Note that, instead of using a value obtained by subtracting 4% from the existing predicted value as the new predicted value, a value obtained by applying to a function the difference between the actual driving value at timing T and the actual driving value at timing T-1, or a value calculated using a coefficient may be used as the new predicted value. Also, instead of a value, a trend such as an increasing trend or a decreasing trend compared to the existing predicted value may be obtained in the above process.

[0054] As described above, when the actual driving value at the timing of interest is on the increase compared to the previous timing, the second prediction unit 230 predicts a new predicted value by correcting the existing predicted value based on the actual driving value on the increase. This enables the prediction device 200 to predict the demand for parts with higher accuracy.

[0055] In addition, when the actual driving value at the timing of interest is on a decreasing trend compared to the previous timing, the second prediction unit 230 may predict a new predicted value by correcting the existing predicted value based on the actual driving value on a decreasing trend. This enables the prediction device 200 to predict the demand for parts with higher accuracy.

[0056] In this way, the second prediction unit 230 can more accurately predict demand for parts by calculating a new predicted value that corrects the existing predicted value for the next timing based on the characteristic (operating value at the first time point and operating value at the second time point) that the actual driving value at the next timing has an opposite trend to the increase / decrease trend of the past actual driving values, and the existing predicted value for the next timing.

[0057] FIG. 10 is a diagram (part 2) for explaining the process of generating the second prediction information 258. The second prediction unit 230 predicts demand based on the actual value of demand, the actual driving value, and the existing predicted value. The second prediction unit 230 predicts demand based on the relative relationship between the index obtained from the actual driving value, the existing predicted value, and the index obtained from the actual value. For example, the second prediction unit 230 determines whether to adopt the existing predicted value as the predicted value or to adopt a value obtained by correcting the existing predicted value as the predicted value based on the relative relationship between the index obtained from the actual driving value, the existing predicted value, and the index obtained from the actual value.

[0058] For example, the present is timing T+1, and a process for obtaining the second prediction information 258 at future timing T+2 will be described. Since the actual driving value of the actual driving information 254 at timing T+1 (FIG. 10, P4) is minus 3% compared to the actual driving value of the actual driving information 254 at timing T, the second prediction unit 230 provisionally sets the predicted value for the next timing T+2 as a new predicted value (FIG. 10, P6) that is 3% higher than the existing predicted value (FIG. 10, P5) of the first prediction information 256. The provisionally set new predicted value is an example of an "index obtained from the actual driving value." The outcome value described later is an example of an "index obtained from the actual value" or an "index based on the actual value."

[0059] Next, the second prediction unit 230 obtains a trend value (FIG. 10, P7) of the actual value at timing T+2. The trend value is a value obtained from the tendency of past actual values. The trend value is, for example, a value obtained by linearly extending a line connecting the actual value at timing T and the actual value at timing T+1.

[0060] The second prediction unit 230 compares the course value of the actual value at timing T+2 (FIG. 10, P7) with the existing predicted value at timing T+2 (FIG. 10, P5), and if the existing predicted value is an upward deviation prediction for the course value of the actual value (if the sign is positive when the course value is subtracted from the existing predicted value), it sets the existing predicted value as the new predicted value (FIG. 10, P5) without correcting the provisionally set new predicted value.

[0061] In addition, in a case where the existing predicted value is higher than the actual value, a value based on the existing predicted value may be used as the new predicted value instead of the existing predicted value. The value based on the existing predicted value is, for example, a value corrected to increase (or decrease) the existing predicted value. For example, the second prediction unit 230 may determine the new predicted value based on the provisionally set new predicted value (the value obtained by increasing the existing predicted value) and the existing predicted value (the existing predicted value at the third time point) (for example, based on a value based on the difference).

[0062] Also, if the outcome value is greater than (or the same as or close to) the existing predicted value, the provisionally set new predicted value (FIG. 10, P6) may be used as the normal new predicted value, or the existing predicted value may be used as the normal new predicted value.

[0063] As described above, the second prediction unit 230 uses the actual driving value, the course value, and the existing predicted value to determine whether to adopt the existing predicted value as the new predicted value or to adopt a value corrected based on the actual driving value as the new predicted value. This allows the prediction device 200 to predict the demand for parts with higher accuracy.

[0064] Note that the process described above with reference to FIG. 10 may be omitted, and the process described with reference to FIG. 9 may be executed.

[0065] [flowchart] 11 is a flowchart showing an example of the flow of processing executed by the prediction device 200. First, the second prediction unit 230 of the prediction device 200 determines whether or not it is possible to predict that the actual driving value at the next prediction timing has a decreasing trend compared to the actual driving value at the current timing, based on the trend of the past actual driving values ​​(step S200).

[0066] If it is predicted that the driving condition is decreasing, the second prediction unit 230 obtains the degree of increase of the current driving condition value relative to the previous driving condition value (step S202). Next, the second prediction unit 230 decreases the existing predicted value by the absolute value of the degree of increase (step S204). Next, the second prediction unit 230 sets the decreased existing predicted value as a new predicted value (step S206). This ends the processing of one routine of this flowchart.

[0067] If it is predicted that the trend is not decreasing (if it is predicted that the trend is increasing), the second prediction unit 230 obtains the degree of decrease of the current actual driving value relative to the previous actual driving value (step S208). Next, the second prediction unit 230 provisionally sets a new predicted value by increasing the existing predicted value by the absolute value of the decrease degree (step S210). Next, the second prediction unit 230 obtains a result value based on the actual value (step S212).

[0068] Next, the second prediction unit 230 judges whether the existing predicted value is above the course value (step S214). If the existing predicted value is above the course value, the second prediction unit 230 sets the existing predicted value as the normal new predicted value without correcting the provisionally set new predicted value (step S216). If the existing predicted value is not above the course value, the second prediction unit 230 sets the provisionally set new predicted value as the normal new predicted value (step S218). This ends the processing of one routine of this flowchart.

[0069] The order of the above processes may be changed, or some of the processes may be omitted. For example, if the existing forecast value is higher than the eventual value, the process of provisionally setting a new forecast value may be omitted.

[0070] In addition, in the above process, if the existing predicted value is below the course value, a process similar to the above may be performed. For example, if the provisionally set new predicted value is smaller than the existing predicted value and the existing predicted value is smaller than the course value, the second prediction unit 230 may not set the provisionally set new predicted value as the regular new predicted value, but may set the existing predicted value as the regular new predicted value.

[0071] Fig. 12 is a diagram for comparing the existing predicted value with the new predicted value. Fig. 12 shows the error of the existing predicted value with respect to the actual value in a specified period, and the error of the new predicted value with respect to the actual value in a specified period. As shown in Fig. 12, the error of the new predicted value in a specified period tends to be smaller than the error of the existing predicted value. It can be seen that the new predicted value is a prediction result with higher accuracy than the existing predicted value.

[0072] Furthermore, it can be seen that in a specific period of the predetermined period, the new predicted value is more accurate than the existing predicted value. The specific period is a period in which changes have occurred in the social environment. Specifically, it is a period in which social life has been restricted and economic activity has stagnated due to the influence of the coronavirus. In the specific period, the error of the existing predicted value is larger than in other periods, but the error of the new predicted value tends to remain stable without increasing too much. This is because, as described above, the prediction device 200 derives the new predicted value by reflecting the actual driving conditions of the vehicle M, which cannot be measured from parts demand records and economic indicators (not reflected in the existing predicted value).

[0073] As described above, the prediction device 200 can perform more accurate demand prediction for parts.

[0074] The prediction device 200 may perform the above process when predicting the demand for parts of a specific vehicle model or a specific part. For example, the prediction device 200 may perform the above process when predicting the demand for vehicles with a predetermined rank or lower, front parts, or parts with a demand scale of a predetermined degree or higher. This is because the prediction accuracy of vehicles with a predetermined rank or lower is higher than the prediction accuracy of vehicles with a rank higher than the predetermined rank, the prediction accuracy of front parts is higher than the prediction accuracy of other parts (e.g., rear parts), and the prediction accuracy of parts with a demand scale of a predetermined degree or higher tends to be higher than the prediction accuracy of parts with a demand scale less than the predetermined degree.

[0075] According to the embodiment described above, the information processing device 100 provides the prediction device 200 with performance values ​​and operation values, thereby helping the prediction device 200 to predict demand for parts with higher accuracy.

[0076] According to the embodiment described above, the prediction device 200 can predict the demand for parts with higher accuracy based on the performance value and the operation value.

[0077] According to the embodiment described above, the prediction device 200 can predict the demand for parts with higher accuracy, further based on the actual value, the actual driving value, and the existing predicted value.

[0078] The above describes the form for carrying out the present invention using an embodiment, but the present invention is not limited to such an embodiment, and various modifications and substitutions can be made within the scope that does not deviate from the gist of the present invention. [Explanation of symbols]

[0079] 1. Prediction system, 10. Vehicle system, 20. Vehicle sensor, 30. Navigation device, 100. Information processing device, 110. First acquisition unit, 120. Second acquisition unit, 130. Processing unit, 142. Performance information, 144. Operation information, 146. Aggregated information, 148. Actual driving information, 200. Prediction device, 210. Information management unit, 220. First prediction unit, 230. Second prediction unit, 240. Prediction providing unit, 252. Performance information, 254. Actual driving information, 256. First prediction information, 258. Second prediction information

Claims

1. A prediction device for predicting demand for a vehicle part in preparation for replacement or repair of the part, comprising: an acquisition unit that acquires a performance value of the demand for the part for each predetermined period and an operation value related to an operation of a vehicle using the part for each predetermined period; a prediction unit that predicts the demand based on the performance value and the operation value, The prediction unit is predicting the demand at a third time point that is in the future than the first time point based on a displacement of an operation value at a second time point that is prior to the first time point relative to the operation value at the first time point; When the operation value at the first time point is on an increasing trend relative to the operation value at the second time point, predicting the demand at the third time point based on a value obtained by subtracting a magnitude of a difference between the operation value at the first time point and the operation value at the second time point from an existing predicted value at the third time point that has been calculated in advance; when the operation value at the first time point shows a decreasing trend relative to the operation value at the second time point, predicting the demand at the third time point based on a value obtained by adding a magnitude of a difference between the operation value at the first time point and the operation value at the second time point to an existing predicted value obtained in advance at the third time point; Demand forecasting device.

2. The trend of increase or decrease in the operation value over time is the same as or similar to the trend of increase or decrease in the actual value; The prediction unit predicts the demand based on a trend of increase / decrease in the operation value and a trend of increase / decrease in the actual value in the time series. The demand forecasting device according to claim 1 .

3. The trend of the fluctuation range of the operation value in time series is the same as or similar to the trend of the fluctuation range of the actual value, The prediction unit predicts the demand based on a trend of a fluctuation range of the operation value and a trend of a fluctuation range of the actual value in the time series. The demand forecasting device according to claim 1 or 2.

4. The prediction unit predicts the demand using the actual value and the operation value for each predetermined period, the actual value and the operation value at at least three points in time. The demand forecasting device according to claim 1 .

5. The vehicle operation value is information indicating the actual driving status of a vehicle associated with a predetermined area. The demand forecasting device according to claim 1 .

6. A demand forecasting system for forecasting demand for a vehicle part in preparation for replacement or repair of the part, The demand forecasting system comprises: Acquire a performance value of the demand for the part for each predetermined period; Acquire an operation value related to an operation of a vehicle using the part for each predetermined period; predicting the demand based on the actual value and the operation value; predicting the demand at a third time point that is in the future than the first time point based on a displacement of an operation value at a second time point that is prior to the first time point relative to the operation value at the first time point; When the operation value at the first time point is on an increasing trend relative to the operation value at the second time point, predicting the demand at the third time point based on a value obtained by subtracting a magnitude of a difference between the operation value at the first time point and the operation value at the second time point from an existing predicted value at the third time point that has been calculated in advance; when the operation value at the first time point shows a decreasing trend relative to the operation value at the second time point, predicting the demand at the third time point based on a value obtained by adding a magnitude of a difference between the operation value at the first time point and the operation value at the second time point to an existing predicted value obtained in advance at the third time point; Demand forecasting system.

7. A program for causing a computer to predict demand for a vehicle part in preparation for replacement or repair of the part, comprising: The computer includes: Acquire a performance value of the demand for the part for each predetermined period; acquiring an operation value relating to an operation of a vehicle using the part for each of the predetermined periods; The demand is predicted based on the actual performance value and the operation value; predicting the demand at a third time point that is in the future than the first time point based on a displacement of an operation value at a second time point that is prior to the first time point relative to the operation value at the first time point; when the operation value at the first time point is on an increasing trend relative to the operation value at the second time point, predicting the demand at the third time point based on a value obtained by subtracting the magnitude of a difference between the operation value at the first time point and the operation value at the second time point from an existing predicted value obtained in advance at the third time point; when the operation value at the first time point shows a decreasing trend relative to the operation value at the second time point, predicting the demand at the third time point based on a value obtained by adding a magnitude of a difference between the operation value at the first time point and the operation value at the second time point to an existing predicted value obtained in advance at the third time point; program.

Images