Precipitation level estimation system and program

Abstract

To provide a precipitation level estimation system and a program that can accurately calculate a precipitation level using data related to precipitation obtained from vehicles and using an estimation method based on machine learning.SOLUTION: A precipitation level estimation system 1 comprises an arithmetic unit 12 that acquires detection data related to precipitation detected by multiple vehicle Mn existing in an observation object region RX, calculates multiple feature amounts related to a precipitation amount based on the detection data, inputs the feature amounts into a precipitation amount estimation model for calculating a precipitation amount, and calculates a precipitation amount in a predetermined region included in the observation object region, where the arithmetic unit executes first calculation to calculate a graded precipitation level according to the precipitation amount, and when one region with a different precipitation level is adjacent to another region among multiple regions, execute second calculation based on a calculation method that differs from the first calculation, and re-calculates the precipitation level of one region in the second calculation to change the precipitation level of one region.SELECTED DRAWING: Figure 1

Description

[Technical field]

[0001] The present invention relates to a precipitation level estimation system and a program capable of estimating the amount of precipitation. [Background technology]

[0002] In recent years, awareness of disaster prevention against the occurrence of localized heavy rain has been increasing. Patent Document 1 describes a technique for calculating an index indicating the intensity of precipitation in an area including a vehicle based on data related to the operation mode of the vehicle's wiper device. [Prior art documents] [Patent documents]

[0003] [Patent Document 1] JP 2020-052962 A Summary of the Invention [Problem to be solved by the invention]

[0004] The wiper operation mode has three stages, for example, weak, medium, and strong. According to the technology described in Patent Document 1, the intensity of precipitation is estimated based on data related to the wiper operation mode. When heavy precipitation occurs, the wiper operation mode is fixed to the strong stage, and the correlation between the wiper operation mode and the amount of precipitation becomes small. As a result of the inventor's continued research, he found a method for accurately estimating the precipitation level using data acquired from a vehicle.

[0005] The present invention aims to provide a precipitation level estimation system and program that can accurately calculate precipitation levels using precipitation-related data acquired from a vehicle and an estimation method based on machine learning. [Means for solving the problem]

[0006] One aspect of the present invention is a precipitation level estimation system that includes a calculation unit that acquires detection data related to precipitation detected by a plurality of vehicles present in an observation area, calculates a plurality of feature values ​​related to precipitation based on the detection data, inputs the feature values ​​into a precipitation estimation model for calculating the precipitation amount, and calculates the precipitation amount in a specified area included in the observation area, wherein the calculation unit performs a first calculation to calculate a staged precipitation level according to the precipitation amount, and if one area among the plurality of areas is adjacent to another area having a different precipitation level, performs a second calculation based on a calculation method different from the first calculation, recalculates the precipitation level of the one area in the second calculation, and changes the precipitation level of the one area. Effect of the Invention

[0007] According to the present invention, precipitation levels can be accurately calculated using precipitation related data acquired from a vehicle using machine learning based estimation methods. [Brief description of the drawings]

[0008] [Figure 1] 1 is a block diagram showing a configuration of a precipitation level estimation system according to an embodiment. [Diagram 2] FIG. 1 is a diagram showing an observation method in an observation target area. [Diagram 3] FIG. 2 is a diagram showing a predetermined area within an observation target area. [Figure 4] FIG. 2 is a diagram showing the contents of a plurality of feature amounts. [Diagram 5] FIG. 1 shows mapping data with precipitation levels displayed. [Figure 6] FIG. 13 is a diagram showing an area where an erroneous determination occurs in mapping data. [Figure 7] 1 is a flowchart showing a flow of a first calculation process in a precipitation level estimation method. [Figure 8] 13 is a flowchart showing an example of a process flow of a second calculation for recalculating a first calculation. [Figure 9]13 is a flowchart showing another example of the process flow of the second calculation. [Figure 10] 13 is a flowchart showing another example of the process flow of the second calculation. [Figure 11] 13 is a flowchart showing another example of the process flow of the second calculation. DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS

[0009] As shown in FIG. 1, the precipitation level estimation system 1 includes a server device 10 connected to a network NW and a plurality of vehicles Mn (n: any natural number). The plurality of vehicles Mn are present in an observation target area RX that is the subject of observation. The observation target area RX is set to, for example, a rectangular area of ​​a predetermined area. The server device 10 communicates with the plurality of vehicles Mn and acquires detection data related to precipitation. The server device 10 calculates the precipitation level in the observation target area RX based on the detection data.

[0010] The precipitation level is set, for example, to three levels according to the amount of precipitation as described later. The precipitation level is not limited to three levels and may be set to any level. The server device 10 provides information including the precipitation level to the vehicle Mn in the observation target area RX based on the calculation result. The server device 10 may also provide information to the terminal device 20 connected to the network NW in addition to the vehicle Mn.

[0011] The terminal device 20 is configured, for example, by an information processing terminal device such as a personal computer or a smartphone. The terminal device 20 is provided with, for example, a display unit 26 that displays information. The display unit 26 is provided, for example, by a display device such as a liquid crystal display. The terminal device 20 is provided with a communication unit 28 that can communicate with the network NW. The communication unit 28 is provided with a communication interface that can be connected to the network NW. The terminal device 20 is provided with a control unit 22 that executes communication and information display processing.

[0012] The terminal device 20 includes a storage unit 24 that stores data and programs necessary for control. The control unit 22 is configured with at least one hardware processor such as a CPU (Central Processing Unit). The storage unit 24 is configured with a non-transitory storage medium such as a hard disk drive (HDD) or a solid state disk (SSD).

[0013] The server device 10 is composed of a calculation unit 12 that performs various calculation processes, a storage unit 14 that stores data and programs necessary for the calculation processes, and a communication unit 16 that communicates with the network NW. The calculation unit 12 is composed of at least one hardware processor such as a CPU. The storage unit 14 is composed of a non-transitory storage medium such as a hard disk drive or a solid state disk. The communication unit 16 is composed of a communication interface that can be connected to the network NW.

[0014] The calculation unit 12 acquires detection data related to precipitation detected by a plurality of vehicles Mn present in the observation target area RX. The calculation unit 12 calculates the amount of precipitation in the observation target area RX based on the detection data. The details of the calculation process of the calculation unit 12 will be described later. The calculation unit 12 calculates the distribution of precipitation levels in the observation target area RX based on the calculation results. The calculation unit 12 provides information related to the amount of precipitation to the vehicles Mn used by the user via the network NW.

[0015] The vehicle Mn is configured to be able to communicate with the server device 10 via the network NW. The vehicle Mn is equipped with, for example, a detection unit MS that detects various data. The detection unit MS is composed of vehicle equipment such as a plurality of devices and sensors provided in the vehicle Mn. The detection unit MS is composed of vehicle equipment that can acquire control signals required for control, current values ​​required for operation, and data required for controlling the vehicle Mn. The detection unit MS is equipped with, for example, a wiper device MN that wipes the windows of the vehicle Mn.

[0016] The wiper device MN is provided on the front window or rear window of the vehicle Mn. The wiper device MN operates based on three operating modes, for example, weak, medium, and strong. The operating speed of the operating modes increases in the order of weak, medium, and strong. The operating speed is set, for example, by the number of wipes per unit time (number of wipes / minute). The operating modes may be provided with a speed adjustment mode in which the number of wipes per unit time can be arbitrarily adjusted. The wiper device MN operates based on the operation of an occupant of the vehicle Mn. The wiper device MN operates based on a control signal corresponding to the operation of the occupant. The control signal is set to correspond to the stepwise operating modes and the speed adjustment mode.

[0017] The wiper device MN may be provided with a rain sensor ME that detects rainfall. The rain sensor ME is provided on the inside of the windshield and detects changes in the light transmittance of the windshield. The wiper device MN operates automatically, for example, when rainfall is detected by the rain sensor ME. The wiper device MN operates in an operating mode that is automatically set in response to a change in the signal detected by the rain sensor ME.

[0018] The detection unit MS is provided with a camera MC capable of capturing images. The camera MC captures an image of the external environment of the vehicle Mn. The image data captured by the camera MC is used, for example, to control the vehicle Mn. The detection unit MS is provided with a LIDAR device MD that emits laser waves. The LIDAR device MD receives reflected waves of the emitted laser waves and detects objects present around the vehicle Mn. The detection unit MS is provided with a position sensor MG that detects the current position of the vehicle Mn. The position sensor MG is, for example, configured with a GPS (Global Positioning System) sensor.

[0019] The vehicle Mn is provided with a control unit MP that executes various controls. The control unit MP executes controls related to the traveling of the vehicle Mn. The control unit MP transmits data related to precipitation among the data detected by the detection unit MS to the server device 10. The control unit MP is configured with at least one hardware processor such as a CPU.

[0020] The vehicle Mn is provided with a notification unit ML that notifies various pieces of information. The notification unit ML is, for example, configured with a display device that can display an image including the notification content. The notification unit ML may be configured with a speaker that outputs the notification content by voice. The vehicle Mn is provided with a communication unit MU that can be connected to a network NW. The communication unit MU is, for example, configured with a communication interface that can perform wireless communication.

[0021] The vehicle Mn acquires various data while traveling by the detection unit MS. The control unit MP controls the traveling of the vehicle Mn based on the acquired data. The control unit MP transmits data related to precipitation among the data acquired by the detection unit MS to the server device 10. The control unit MP transmits, for example, data related to the control of the wiper device MN to the server device 10. In the server device 10, the data is stored in the memory unit 14. The calculation unit 12 calculates the distribution of precipitation in the observation target area RX based on the data stored in the memory unit 14.

[0022] As shown in FIG. 2, the map data of the observation target area RX includes an area Rm (m: natural number). The area Rm is set, for example, to a rectangular area of ​​1 km square. The size, position, and shape of the area Rm are set arbitrarily. An ID number is set for the area Rm in accordance with its position. The area Rm is managed by a server device 10. The server device 10 communicates with a plurality of vehicles Mn present within the observation target area RX. In the server device 10, a calculation unit 12 acquires position data of each vehicle Mn and ID data for identifying the vehicle Mn.

[0023] As shown in FIG. 3, the calculation unit 12 compares the ID data RD of the area Rm with data acquired from the vehicle Mn to recognize the vehicle Mn present within the area Rm. The calculation unit 12 acquires detection data related to precipitation from a plurality of vehicles Mn present within the area Rm. The detection data related to precipitation includes, for example, data related to the operation state of the wiper device MN, vehicle ID data, vehicle position data, time data, and other data. The calculation unit 12 acquires detection data from the vehicle Mn present within the area Rm at predetermined intervals (for example, one-minute intervals). The predetermined interval may be set to any time interval. The calculation unit 12 stores the acquired detection data in the memory unit 14.

[0024] The calculation unit 12 calculates an estimated value of the amount of precipitation in the region Rm. The region Rm includes a user position where a user who receives information about precipitation from the server device 10 is present. The user's position information is provided to the server device 10 via the vehicle Mn in which the user is currently riding or the terminal device 20 that the user possesses. The calculation unit 12 calculates the amount of precipitation in the region Rm including the user's position based on the information provided by the user.

[0025] 4, the calculation unit 12 generates a plurality of feature quantities B to Y used for estimating the amount of precipitation at a predetermined period (e.g., every 10 minutes) based on the detection data. The plurality of feature quantities B to Y are classified into 24 types of elements, such as a speed component of the wiper device MN, a time component, a number component of the vehicles Mn, and an area component. The plurality of feature quantities B to Y are set so that features appear in the calculation of the amount of precipitation at the user position based on data indicating the operation state of the wiper device MN.

[0026] The calculation unit 12 generates a first feature amount Ta (feature amounts B to M) based on, for example, the first detection data acquired from a first region Ra included in the observation target region RX. The first region Ra is set by, for example, a plurality of sample data collection regions including the user position and its surrounding points. The plurality of sample data collection regions is set by, for example, a 1 km square region Rm including the user position and a plurality of 1 km square surrounding regions including surrounding points spaced a predetermined distance from the user position. The predetermined distance is set to an arbitrary distance interval.

[0027] The surrounding points include, for example, a point 5 km away from the user position and a point 10 km away from the user position. The calculation unit 12 collects first detection data of a first region Ra including the user position and surrounding points in any direction from the user position. The direction in which data is collected is set arbitrarily based on the method of collecting sample data. The calculation unit 12 collects data of the first region Ra in four azimuth directions, east, west, south, and north, from the user position. The calculation unit 12 may collect data of the first region including any directional element, such as eight azimuth directions including the east, west, south, and north directions plus the northeast, northwest, southwest, and southeast directions.

[0028] The calculation unit 12 acquires first detection data of the first region Ra in a first predetermined period t1 in the past compared to the present. The first predetermined period t1 is, for example, one hour in the past from the current time. The calculation unit 12 generates feature quantities B to M in each of the four azimuth directions based on the first detection data acquired in the first region Ra, for example. The calculation unit 12 generates feature quantities B to M based on wiper operation data indicating the operation state of a wiper device provided in the vehicle, for example.

[0029] The calculation unit 12 calculates, for example, a feature quantity related to a wiper operation time ratio indicating the operation state of the wiper device MN. The wiper operation time ratio is the ratio of time during which the wiper device is operated in each predetermined period. The wiper operation time ratio includes feature quantities B, C, and D calculated based on the maximum time during which the wiper device is operated in each predetermined period (e.g., 10 minutes), and feature quantities E, F, and G calculated based on the total time during which the wiper device is operated in each predetermined period (e.g., 60 minutes).

[0030] A total of six feature values ​​B, C, and D, which indicate the precipitation level, are sampled over a one-hour period at 10-minute aggregation intervals. By sampling feature values ​​B, C, and D over a short period of time and using the maximum value of those values ​​over the one-hour period and feature values ​​E, F, and G, which indicate the total value over the one-hour period when the wiper device was activated, it is possible to accurately capture the peak value of precipitation, which indicates heavy precipitation.

[0031] Feature values ​​B and E are calculated in a rectangular region of 1 km square including the user position. Feature values ​​C and F are calculated in a rectangular region 5Rm (see FIG. 2) of 1 km square including a point 5 km away from the user position in a predetermined direction. Feature values ​​D and G are calculated in a rectangular region 10Rm (see FIG. 2) of 1 km square including a point 10 km away from the user position in a predetermined direction.

[0032] The above feature value indicating the precipitation level is calculated not only for a 1 km square area Rm including the user position in the first area Ra, but also for areas 5Rm and 10Rm spaced apart in four directions centered on the area Rm. The more the sampling points on which the feature value is calculated are expanded according to the direction, the more the number of vehicles Mn from which data can be collected increases. Also, by sampling according to the direction, it is possible to capture the precipitation trend.

[0033] The calculation unit 12 calculates, for example, a wiper operation number ratio indicating the operation state of the wiper device. The wiper operation number ratio includes feature amounts H, I, and J calculated from the maximum number of vehicles Mn whose wiper devices have been operated in each predetermined period (e.g., 10 minutes), and feature amounts K, L, and M calculated from the sum of the number of vehicles Mn whose wiper devices have been operated in each predetermined period (e.g., 60 minutes).

[0034] For example, if all vehicles Mn operated the wiper speed (e.g., 50 times / min) for 10% of the driving time, the feature value of the wiper operation time ratio is calculated as 10%. In this case, the wiper devices of all vehicles Mn were operated for 60 minutes, so the feature value of the wiper operation number ratio is calculated as 100%.

[0035] In calculating the characteristic amount, by calculating the operation rate [%] of the wiper device MN instead of the operation frequency, it is possible to suppress the variation in the calculated value caused by the difference in the number of vehicles Mn traveling in the area to be calculated. By calculating the characteristic amount related to the wiper operation time rate, it is possible to easily capture heavy precipitation. In calculating the characteristic amount, by using the perspective of "number of vehicles" in addition to the perspective of "time", it is possible to easily capture heavy precipitation.

[0036] The calculation unit 12 generates the second feature amount Tb (feature amounts N to Y) based on, for example, second detection data acquired from a second region Rb adjacent to the first region Ra included in the observation target region RX. The second region Rb is set by, for example, a plurality of data collection regions including surrounding points adjacent to the first region Ra. The plurality of data collection regions is set by, for example, a rectangular region of 1 km square including surrounding points separated by a predetermined distance from the user position. The surrounding points include, for example, a point separated by 10 km in a predetermined direction from the user position, a point separated by 20 km from the user position, and a point separated by 30 km in a predetermined direction from the user position.

[0037] The above feature value indicating the precipitation level is calculated for the second region Rb in regions 10Rm, 20Rm, and 30Rm spaced apart in four directions centered on the region Rm. The wider the sampling points that are the basis for calculating the feature value according to the direction, the more vehicles Mn that can collect data. In addition, by sampling the region Rm according to the direction, the precipitation trend can be captured.

[0038] The calculation unit 12, for example, collects second detection data of the second region Rb from the user position. The calculation unit 12 acquires the second detection data of the second region Rb in a second predetermined period t2 that is earlier than the first predetermined period t1. The second predetermined period t2 is, for example, one hour in the past from the start time of the first predetermined period t1. The calculation unit 12, for example, generates feature quantities N to Y in each of the four azimuth directions based on the second detection data acquired in the second region Rb. The calculation unit 12, for example, generates feature quantities N to Y based on wiper operation data that indicates the operation state of a wiper device provided in the vehicle.

[0039] The calculation unit 12 calculates, for example, a wiper operation time ratio indicating the operation state of the wiper device MN. The wiper operation time ratio includes the characteristic quantities N, O, and P calculated from the maximum time that the wiper device MN was operated in each predetermined period (e.g., 10 minutes), and the characteristic quantities Q, R, and S calculated from the sum of the time that the wiper device MN was operated in each predetermined period (e.g., 60 minutes).

[0040] The feature amount N and the feature amount Q are calculated in a rectangular area 10Rm (see FIG. 2) that is 1 km square and includes a point 10 km away from the user position. The feature amount O and the feature amount R are calculated in a rectangular area 20Rm (see FIG. 2) that is 1 km square and includes a point 20 km away from the user position. The feature amount P and the feature amount S are calculated in a rectangular area 30Rm (see FIG. 2) that is 1 km square and includes a point 30 km away from the user position.

[0041] The calculation unit 12 calculates, for example, a wiper operation number ratio indicating the operation state of the wiper device MN. The wiper operation number ratio includes feature amounts T, U, and V calculated from the maximum number of vehicles Mn whose wiper devices have been operated in each predetermined period (e.g., 10 minutes), and feature amounts W, X, and Y calculated from the total number of vehicles Mn whose wiper devices have been operated in a predetermined period (e.g., 60 minutes). The calculation unit 12 calculates feature amounts including the first feature amount Ta and the second feature amount Tb in four directions from the user position.

[0042] As described above, the first feature amount Ta in the first region Ra including the user position is calculated in the most recent first predetermined period t1. The second feature amount Tb in the second region Rb farther from the user position is calculated in the second predetermined period t2 that is earlier than the first predetermined period t1. The calculation unit 12 inputs the calculated first feature amount and second feature amount to a preset precipitation estimation model and calculates the amount of precipitation from the present to the future in the first region Ra included in the observation target region RX.

[0043] The precipitation estimation model is set, for example, by a polynomial nonlinear regression equation that calculates an estimated value of the precipitation in the region Rm including the user position using multiple feature quantities as variables. The nonlinear regression equation is set arbitrarily to a function that can calculate the precipitation quantity. The relationship between the precipitation quantity and the feature quantities related to the operating state of the wiper device MN gradually changes from a linear relationship to a curvilinear relationship. Therefore, the precipitation estimation model using nonlinear regression can more accurately reproduce the different trends between the precipitation levels that are set in stages.

[0044] In the precipitation estimation model, a plurality of parameters corresponding to a polynomial consisting of a plurality of feature quantities are set based on machine learning performed in advance in the calculation unit 12. The calculation unit 12 repeatedly executes machine learning by, for example, deep learning using a neural network.

[0045] The calculation unit 12 adjusts parameters set in the precipitation estimation model by repeatedly executing machine learning to calculate an estimated value of precipitation based on the feature amount, using the feature amount calculated based on past detection data as teacher data. The estimated value of precipitation is calculated by inputting the feature amount calculated using the detection data into the precipitation estimation model with adjusted parameters. The precipitation estimation model with adjusted parameters is stored in the storage unit 14 as a computer program. The calculation unit 12 calculates the amount of precipitation at an arbitrary point by inputting the feature amount calculated using the detection data into the precipitation estimation model.

[0046] The calculation unit 12 acquires detection data related to precipitation detected by a plurality of vehicles Mn present in the observation target area RX. The calculation unit 12 calculates the amount of precipitation from the present to the future in a predetermined area included in the observation target area RX based on the detection data.

[0047] The calculation unit 12 calculates a plurality of first feature values ​​Ta for a first predetermined period t1 in the past compared to the present, based on, for example, first detection data acquired from a first region Ra. The calculation unit 12 calculates a second feature value Tb for a second predetermined period t2 in the past compared to the first predetermined period in the second region Rb, based on, for example, second detection data acquired in a second region Rb adjacent to the first region Ra. The calculation unit 12 calculates feature values ​​including a first feature value Ta related to the time ratio when the wiper device MN was operated and a second feature value Tb related to the number ratio when the wiper device was operated, based on wiper operation data indicating the operation state of the wiper device MN provided on the vehicle Mn among the detection data.

[0048] The calculation unit 12 calculates the current amount of precipitation in the region Rm using a precipitation estimation model that uses the first feature amount Ta and the second feature amount Tb as variables. The calculation unit 12 performs a first calculation to calculate a precipitation level in stages according to the amount of precipitation in the region Rm by comparing the calculated value of the amount of precipitation with a precipitation level set according to the amount of precipitation. The calculation unit 12 determines the precipitation level from the following three stages based on the result of the comparison with a preset reference amount of precipitation, for example.

[0049] The calculation unit 12 determines that the precipitation level is the "first precipitation level (High)" when the precipitation level is equal to or greater than a preset first precipitation level (e.g., 20 mm / h). The first precipitation level is set to a precipitation level equal to or greater than a standard requiring attention (e.g., 20 mm / h). The standard is set to an arbitrary precipitation level. The calculation unit 12 determines that the precipitation level is the "second precipitation level (Mid)" when the precipitation level is less than the first precipitation level and equal to or greater than a preset second precipitation level (e.g., 1 mm / h). The calculation unit 12 determines that the precipitation level is the "third precipitation level (Low)" when the precipitation level is less than the second precipitation level (1 mm / h). The precipitation level may be set to three or more gradual levels as described above.

[0050] The calculation unit 12 executes a first calculation to calculate the precipitation level not only in the region Rm including the user position, but also in all other regions Rm in the observation target region RX by repeatedly executing the same calculation process as above, and generates mapping data in which the precipitation level is mapped for each of the multiple regions Rm in the observation target region RX. The calculation unit 12 does not necessarily have to calculate all other regions Rm in the observation target region RX, and may calculate the observation target region RX with one region Rm included in a rectangular region of any size as a representative value, and generate mapping data for the observation target region RX divided by rectangular regions of any size.

[0051] 5, the calculation unit 12 may generate mapping data PP in which the precipitation level is mapped for each region Rm in the observation target region RX. As shown in the figure, the mapping data PP shows the distribution of regions with the current first precipitation level (High), the distribution of regions with the second precipitation level (Mid), and the distribution of regions with the third precipitation level (Low).

[0052] The precipitation estimation model may be set to calculate not only the current precipitation but also the future precipitation by repeatedly executing machine learning based on past detection data. Therefore, the calculation unit 12 may calculate the past and future precipitation levels in the region Rm based on the precipitation estimation model. The calculation unit 12 may calculate, for example, the precipitation amount a predetermined time ago, the current precipitation amount, and the precipitation amount a predetermined time later in the region Rm including the user position. The calculation unit 12 may calculate the past, current, and future precipitation amounts at any time interval. The calculation unit 12 may update the precipitation level estimation model at a predetermined timing using the accumulated detection data.

[0053] Generally, heavy precipitation often moves in large chunks from a distance in conjunction with the movement of rain clouds. Therefore, in addition to calculating the first characteristic amount Ta in the first predetermined period t1, the tendency of precipitation to move can be calculated by calculating the second characteristic amount Tb in the second predetermined period t2.

[0054] As shown in Fig. 6, in the mapping data PP based on the first calculation for calculating the precipitation level, there is a region Rm(Error) where an error occurs between the actual precipitation level and the calculated precipitation level. When the mapping data PP is examined, the probability that an error occurs between the actually observed precipitation level and the precipitation level calculated based on the first calculation is high in a boundary region where one region having a different precipitation level is adjacent to another region among the multiple regions Rm. After performing the first calculation for calculating the precipitation level, the calculation unit 12 performs a second calculation for correcting the error.

[0055] The calculation unit 12 re-determines the precipitation level of each region Rm included in a boundary region where one region and another region having different precipitation levels are adjacent to each other among the multiple regions Rm in the mapping data PP. The calculation unit 12 recalculates the precipitation level of the one region among the boundary regions based on a calculation method different from the first calculation, and if a predetermined criterion is satisfied, executes a second calculation to change the precipitation level of the one region. If the precipitation level of the one region has changed after the second calculation is completed, the calculation unit 12 generates mapping data PP to which the changed precipitation level has been applied.

[0056] 7 is a flowchart showing the procedure of the precipitation level estimation method executed in the precipitation level estimation system 1. The precipitation level estimation method is processed based on a program installed in a computer constituting the precipitation level estimation system 1. The program causes the computer to execute the following steps related to the precipitation level estimation method.

[0057] The calculation unit 12 executes a first calculation (steps S100 to S114) for calculating the stepwise precipitation levels, and then executes a second calculation (steps S200 to S404) for recalculating the precipitation levels. The calculation unit 12 acquires detection data related to precipitation detected by a plurality of vehicles Mn present in the observation target area (step S100). The calculation unit 12 calculates a plurality of feature amounts to be used for estimating the amount of precipitation based on the detection data (step S102). The calculation unit 12 inputs the calculated plurality of feature amounts into a precipitation estimation model, and calculates the amount of precipitation in a predetermined area included in the observation target area (step S104).

[0058] The calculation unit 12 determines whether the amount of precipitation in the predetermined area is equal to or greater than the first precipitation amount (step S106). If the amount of precipitation is equal to or greater than the first precipitation amount, the calculation unit 12 determines the precipitation level of the predetermined area to be the first precipitation level (step S108). If the amount of precipitation is less than the first precipitation amount, the calculation unit 12 determines whether the amount of precipitation is equal to or greater than the second precipitation amount (step S110). If the amount of precipitation is equal to or greater than the second precipitation amount, the calculation unit 12 determines that the amount of precipitation is the second precipitation level (step S112). If the amount of precipitation is less than the second precipitation amount, the calculation unit 12 determines that the amount of precipitation is the third precipitation level (step S114).

[0059] The calculation unit 12 executes a first calculation to calculate a stepwise precipitation level according to the amount of precipitation in the region Rm (steps S108, S112, S114), and executes a second calculation to change the precipitation level based on the calculation result of the first calculation (step S116). When one region and another region having different precipitation levels are adjacent to each other in the region Rm determined to be the first precipitation level, the second precipitation level indicating a lower amount of precipitation than the first precipitation level, or the third precipitation level indicating a lower amount of precipitation than the second precipitation level, the calculation unit 12 executes the second calculation based on a calculation method different from the first calculation, and recalculates the precipitation level of the one region. The calculation unit 12 recalculates the precipitation level of the one region in the second calculation, and changes the precipitation level of the one region if a predetermined condition is satisfied.

[0060] Fig. 8 shows a process flow (step S116(B)) of the second calculation for recalculating the second precipitation level determined in step S112 (see Fig. 7). In the boundary region between the region Rm of the first precipitation level and the region Rm of the second precipitation level, the region may be erroneously determined to be the second precipitation level even though it is actually the first precipitation level (see Fig. 6).

[0061] The calculation unit 12 determines whether at least one other area adjacent to the one area calculated to be at the second precipitation level is at the first precipitation level (step S200). When the other area at the first precipitation level is adjacent to the one area at the second precipitation level (step S200: Yes), the calculation unit 12 determines whether the precipitation amount of the one area is equal to or greater than the third precipitation amount (e.g., 10 mm / h or more) (step S202). For example, the third precipitation amount is set to a value (10 mm / h) lower than the value of the first precipitation amount (20 mm / h) in order to facilitate the change from the second precipitation level to the first precipitation level in the second calculation. When the precipitation amount of the one area is equal to or greater than the third precipitation amount, the calculation unit 12 changes the second precipitation level of the one area to the first precipitation level (step S204).

[0062] 9 shows a flow of processing (B1) when the one region of the second precipitation level is not adjacent to another region of the first precipitation level in step S200 (see FIG. 8) (step S200: No). When the one region of the second precipitation level is not adjacent to another region of the first precipitation level in step S200, the calculation unit 12 determines whether or not at least one other region adjacent to the one region is at the third precipitation level (step S206). For example, the calculation unit 12 compares the precipitation amount of the one region with a fourth precipitation amount (e.g., 5 mm / h or more) and determines whether or not the precipitation amount of the one region is equal to or greater than the fourth precipitation amount (step S208).

[0063] The fourth precipitation is set to a value (5 mm / h) higher than the value of the second precipitation (1 mm / h) so that the second precipitation level can be easily changed to the third precipitation level in the second calculation. If the precipitation of the one region is less than the fourth precipitation (step S208: No), the calculation unit 12 changes the second precipitation level of the one region to the third precipitation level (step S210). If the precipitation of the one region is equal to or greater than the fourth precipitation (step S208: Yes), the calculation unit 12 maintains the second precipitation level of the one region.

[0064] Fig. 10 shows the flow of the second calculation process (step S116(C)) for recalculating the third precipitation level determined in step S114 (see Fig. 7). During the time period when it starts to rain, the precipitation level of the region Rm that was determined to be the third precipitation level until just before is actually the second precipitation level of 1 mm / h or more, and an erroneous determination may occur (see Fig. 6). When one region calculated to be at the third precipitation level is adjacent to at least one other region calculated to be at the second precipitation level, the calculation unit 12 recalculates the precipitation level of the one region.

[0065] The calculation unit 12 determines whether the precipitation level of the one area calculated to be the third precipitation level has continued for a certain period of time (e.g., 10 minutes) (step S300). If the third precipitation level of the one area has continued for a certain period of time (step S300: Yes), the calculation unit 12 determines whether at least one other area adjacent to the one area is at the second precipitation level (step S302). The calculation unit 12 compares the precipitation amount of the one area with a fifth precipitation amount (e.g., 0.05 mm / h or more) and determines whether the precipitation amount of the one area is the fifth precipitation amount or more (step S304).

[0066] The fifth precipitation is set to a value (0.05 mm / h) lower than the value of the second precipitation (1 mm / h) so that the third precipitation level can be easily changed to the second precipitation level in the second calculation. If the precipitation of the one region is equal to or greater than the fifth precipitation (step S304: Yes), the calculation unit 12 changes the third precipitation level of the one region to the second precipitation level (step S306). If the precipitation of the one region is less than the fifth precipitation, the calculation unit 12 maintains the third precipitation level of the one region.

[0067] FIG. 11 shows the flow of the second calculation process (step S116(A)) for recalculating the first precipitation level determined in step S108 (see FIG. 7). When an area Rm of the first precipitation level is adjacent to an area Rm of a different precipitation level, the area may be erroneously determined to be the first precipitation level even though it is actually the second precipitation level. The calculation unit 12 determines whether or not at least one other area of ​​a different precipitation level, the second precipitation level or the third precipitation level, is adjacent to the area calculated to be the first precipitation level (step S400).

[0068] When the first precipitation level region is adjacent to another region having a different precipitation level (step S400: Yes), the calculation unit 12 compares the precipitation amount of the region with a sixth precipitation amount (e.g., 5 mm / h) and determines whether the precipitation amount of the region is equal to or greater than the sixth precipitation amount (step S402). For example, the sixth precipitation amount is set to a value (30 mm / h) higher than the value of the first precipitation amount (20 mm / h) in order to facilitate the change from the first precipitation level to the second precipitation level in the second calculation. When the precipitation amount of the region is less than the sixth precipitation amount (step S402: No), the calculation unit 12 changes the first precipitation level of the region to the second precipitation level. When the precipitation amount of the region is equal to or greater than the sixth precipitation amount (step S402: Yes), the calculation unit 12 maintains the first precipitation level of the region.

[0069] The calculation unit 12 updates the mapping data PP recalculated based on the second calculation. Based on the above process, the calculation unit 12 can bring the precipitation level calculated based on the first calculation closer to the actual amount of precipitation.

[0070] The calculation unit 12 may extract an area Rm in the observation target area RX where the amount of precipitation is a first precipitation level that is equal to or higher than a standard amount, based on the generated mapping data, and provide information on the amount of precipitation to a user present in the area Rm. The calculation unit 12 may cause a notification unit ML of a vehicle Mn in which a user in the extracted area Rm is riding to notify predetermined information that the area is at the first precipitation level, via a network NW. The calculation unit 12 may extract an area Rm where the amount of precipitation is the first precipitation level within a predetermined time in the future, based on the generated mapping data, and provide information on the amount of precipitation to a user present in the area Rm. The predetermined time in the future may be set arbitrarily.

[0071] The vehicle Mn may perform driving control corresponding to rainfall based on the provided predetermined information. The driving control corresponding to rainfall may be applied to the vehicle Mn that runs based on automatic driving. The driving control corresponding to rainfall may be driving support for the vehicle Mn that runs based on manual driving. The calculation unit 12 may cause the display unit 26 of the user's terminal device 20 to display predetermined information related to the first precipitation level via the network NW.

[0072] For example, information on the state of rainfall at the first precipitation level or information that rainfall at the first precipitation level is approaching is displayed on the display unit 26. The user's terminal device 20 does not necessarily have to be located within the extracted region Rm. The user only needs to be a user of a service that provides information on the precipitation level.

[0073] As described above, the precipitation level estimation system 1 can accurately estimate the precipitation level by calculating a plurality of feature amounts based on detection data related to the operating state of the wiper device MN. The precipitation level estimation system 1 can improve the accuracy of the precipitation level estimation result by executing the second calculation to recalculate the precipitation level calculated based on the first calculation.

[0074] In the above-described embodiment, the feature amount is calculated based on data on the operating state of the wiper device MN. The feature amount may be calculated based on not only the detection data of the wiper device MN but also the detection data of the rain sensor ME, the image data of the surrounding environment of the vehicle Mn captured by the camera MC, and the detection data detected by the lidar device MD. The feature amount may be calculated by the calculation unit 12 repeatedly executing machine learning based on the image data of the rainfall state captured by the camera MC.

[0075] The feature amount may be calculated by the calculation unit 12 repeatedly executing machine learning based on the detection data of rainfall detected by the rain sensor ME. Since the detection data of the LIDAR device MD deteriorates due to the occurrence of rainfall, the feature amount may be calculated by the calculation unit 12 repeatedly executing machine learning based on the detection data of the LIDAR device MD. The feature amount may be calculated using a combination of one or more of the detection data of the wiper device MN, the camera MC, the rain sensor ME, and the LIDAR device MD. The feature amount may be calculated using any detection data related to precipitation as long as it can be detected. The feature amount may be calculated based on other calculation methods as long as it is possible to calculate the tendency of precipitation.

[0076] The computer program executed in each component of the precipitation level estimation system 1 may be provided in a form recorded on a computer-readable portable recording medium such as a semiconductor memory, a magnetic recording medium, or an optical recording medium. The vehicle Mn may be a manually operated vehicle or an autonomous vehicle. [Explanation of symbols]

[0077] 1 Precipitation level estimation system, 10 Server device, 12 Calculation unit, 14 Memory unit, 16 Communication unit, 20 Terminal device, 22 Control unit, 24 Memory unit, 26 Display unit, 28 Communication unit, MC Camera, MD Lidar device, ME Rain sensor, MG Position sensor, ML Notification unit, Mn Vehicle, MN Wiper device, MP Control unit, MS Detection unit, MU Communication unit, NW Network, PP Mapping data, Ra First region, Rb Second region, Rm Region, RX Observation target region

Claims

1. Acquire precipitation-related detection data detected by a plurality of vehicles present in an observation target area; Calculating a plurality of features related to the amount of precipitation based on the detection data; a calculation unit that inputs the feature amount into a precipitation estimation model for calculating a precipitation amount, and calculates a precipitation amount in a predetermined area included in the observation target area; The calculation unit executes a first calculation to calculate a stepwise precipitation level according to the precipitation amount, When one area and another area having different precipitation levels are adjacent to each other among the plurality of areas, a second calculation is performed based on a calculation method different from the first calculation; recalculating the precipitation level of the one area in the second calculation and changing the precipitation level of the one area; Precipitation level estimation system.

2. the calculation unit, in the first calculation, determines the precipitation level of the region as one of a first precipitation level in order of decreasing precipitation amount, a second precipitation level indicating an amount of precipitation lower than the amount of precipitation of the first precipitation level, and a third precipitation level indicating an amount of precipitation lower than the second precipitation level; When the one area among the plurality of areas that is calculated to have the second precipitation level and at least one other area that is calculated to have the first precipitation level are adjacent to each other and a predetermined condition is satisfied in the second calculation, the second precipitation level of the one area is changed to the first precipitation level. The precipitation level estimation system of claim 1 .

3. the calculation unit changes the second precipitation level of the one region to the third precipitation level when the one region among the plurality of regions that is calculated to be the second precipitation level and at least one other region that is calculated to be the third precipitation level indicating the precipitation amount lower than the second precipitation level are adjacent to each other and a predetermined condition is satisfied in the second calculation. The precipitation level estimation system of claim 2 .

4. the calculation unit changes the third precipitation level of the one area to the second precipitation level when the one area, among the plurality of areas, calculated to be the third precipitation level and at least one other area, calculated to be the second precipitation level, are adjacent to each other and satisfy a predetermined condition in the second calculation. The precipitation level estimation system of claim 2 .

5. Obtaining detection data related to precipitation detected by a plurality of vehicles present in an observation target area; Calculating a feature amount based on the detection data; inputting the feature amount into a precipitation estimation model for calculating the precipitation amount; Calculating the amount of precipitation in a predetermined area included in the observation target area; execute a first calculation for calculating a graded precipitation level according to the precipitation amount; When one area and another area having different precipitation levels are adjacent to each other among the plurality of areas, a second calculation is performed based on a calculation method different from the first calculation; A program for causing a computer to execute a process of recalculating the precipitation level of the one area and changing the precipitation level of the one area in the second calculation.

Images