Precipitation level estimation system and storage medium

Abstract

The invention relates to a precipitation level estimation system and a storage medium. A precipitation level estimation system is provided with a calculation unit that acquires detection data relating to precipitation and calculates the amount of precipitation in a predetermined region included in a region to be observed, the calculation unit calculating a first feature amount in a first predetermined period that is past than the current on the basis of first detection data acquired from a first region including the predetermined region, and calculating a second feature amount in a second predetermined period that is past the current on the basis of second detection data acquired from a second region including the predetermined region. On the basis of second detection data acquired in a second region adjacent to the first region, a second feature amount in a second predetermined period that is past the first predetermined period in the second region is calculated, a precipitation amount is calculated using a precipitation amount estimation model using the first feature amount and the second feature amount as variables, and a precipitation level corresponding to the precipitation amount is calculated.

Description

Technical Field

[0001] The present invention relates to a precipitation level estimating system and a storage medium capable of estimating precipitation amount. Background Art

[0002] In recent years, awareness of disaster prevention for localized heavy rains has been increasing. Japanese Patent Application Laid-Open No. 2020-052962 describes a technique for calculating an index representing the intensity of precipitation in an area where a vehicle is located based on data related to an operating mode of a wiper device of the vehicle. Summary of the invention

[0003] The working mode of the wiper is provided with three working modes, for example, weak, medium, and strong. According to the technology described in Japanese Patent Laid-Open No. 2020-052962, the precipitation intensity is estimated based on data related to the working mode of the wiper. The working mode of the wiper is fixed to the strong level, especially in the case of heavy precipitation, and the correlation between the working mode of the wiper and the precipitation amount becomes low. Therefore, according to the technology described in Japanese Patent Laid-Open No. 2020-052962, there is a possibility that it is difficult to accurately estimate the precipitation level in a certain area.

[0004] An object of the present invention is to provide a precipitation level estimation system and a storage medium capable of accurately calculating a precipitation level using an estimation method based on machine learning, using data related to precipitation acquired from a vehicle.

[0005] A precipitation level estimation system according to a technical solution of the present invention includes a computing unit, wherein the computing unit obtains detection data associated with precipitation detected by a plurality of vehicles existing in an observation target area, and calculates the precipitation amount in a predetermined area included in the observation target area based on the detection data, wherein the computing unit calculates a first feature quantity in a first predetermined period in the past compared to the present based on first detection data obtained from a first area including the predetermined area, calculates a second feature quantity in the second area in a second predetermined period in the past compared to the first predetermined period based on second detection data obtained from a second area adjacent to the first area, calculates the precipitation amount using a precipitation amount estimation model having the first feature quantity and the second feature quantity as variables, and calculates the precipitation level corresponding to the precipitation amount.

[0006] According to the present invention, it is possible to accurately calculate the precipitation level using an estimation method based on machine learning using data related to precipitation acquired from a vehicle. BRIEF DESCRIPTION OF THE DRAWINGS

[0007] Hereinafter, features, advantages, and technical and industrial significance of exemplary embodiments of the present invention will be described with reference to the accompanying drawings, in which like reference numerals represent like elements, and wherein:

[0008] Figure 1 is a block diagram showing the configuration of a precipitation level estimation system according to an embodiment;

[0009] Figure 2 It is a diagram showing the observation method within the observation object area;

[0010] Figure 3 is a diagram showing a predetermined area within an observation target area;

[0011] Figure 4 is a diagram showing the contents of a plurality of feature quantities;

[0012] Figure 5 is a diagram showing mapping data showing precipitation levels;

[0013] Figure 6 is a graph showing the precipitation level in the mapped data over time;

[0014] Figure 7 This is a flowchart showing the processing flow of the precipitation level estimation method. DETAILED DESCRIPTION

[0015] like Figure 1 As shown, the precipitation level estimation system 1 is composed of a server device 10 connected to a network NW and a plurality of vehicles Mn (n is an arbitrary natural number). The plurality of vehicles Mn are present in an observation target area RX that is an observation target. The observation target area RX is set to be a rectangular area of ​​a predetermined area, for example. The server device 10 communicates with the plurality of vehicles Mn and obtains detection data related to precipitation. The server device 10 calculates the precipitation level in the observation target area RX based on the detection data.

[0016] As described later, the precipitation level is set to three levels, for example, according to the precipitation amount. 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.

[0017] The terminal device 20 is composed of, for example, an information processing terminal device such as a personal computer or a smart phone. The terminal device 20 is provided with, for example, a display unit 26 for displaying information. The display unit 26 is composed of, for example, a display device such as a liquid crystal display. The terminal device 20 is provided with a communication unit 28 capable of communicating with the network NW. The communication unit 28 is composed of a communication interface capable of connecting to the network NW. The terminal device 20 is provided with a control unit 22 for performing communication and information display processing.

[0018] The terminal device 20 has a storage unit 24 storing data and programs required for control. The control unit 22 is composed of at least one hardware processor such as a CPU (Central Processing Unit). The storage unit 24 is composed of a non-transient storage medium such as a hard disk drive (HDD) and a solid state drive (SSD).

[0019] The server device 10 is composed of a computing unit 12 that performs various computing processes, a storage unit 14 that stores data and programs required for the computing processes, and a communication unit 16 that communicates with the network NW. The computing unit 12 is composed of a hardware processor such as at least one CPU. The storage unit 14 is composed of a non-transient storage medium such as a hard disk drive and a solid state drive. The communication unit 16 is composed of a communication interface that can be connected to the network NW.

[0020] The calculation unit 12 obtains detection data related to precipitation detected by a plurality of vehicles Mn existing in the observation target area RX. The calculation unit 12 calculates the precipitation amount in the observation target area RX based on the detection data. The content of the calculation processing 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 result. The calculation unit 12 provides information related to the precipitation amount to the vehicle Mn used by the user via the network NW.

[0021] The vehicle Mn is configured to be able to communicate with the server device 10 via the network NW. The vehicle Mn is provided with, for example, a detection unit MS for detecting various data. The detection unit MS is composed of vehicle equipment such as a plurality of device types (groups), sensor types (groups) and the like provided in the vehicle Mn. The detection unit MS is composed of vehicle equipment capable of obtaining control signals required for control, current values ​​required for operation, and data required for controlling the vehicle Mn. The detection unit MS is provided with, for example, a wiper device MN for wiping the window of the vehicle Mn.

[0022] The wiper device MN is provided on the front window and the 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 increases in the order of the operating modes being weak, medium, and strong. The operating speed is set, for example, based on the number of wiping times per unit time (times / minute). A speed adjustment mode that can arbitrarily adjust the number of wiping times per unit time may also be provided in the operating mode. The wiper device MN operates based on the operation of the occupants of the vehicle Mn. The wiper device MN operates based on a control signal corresponding to the operation of the occupants. The control signal is set corresponding to the step-by-step operating mode and / or the speed adjustment mode.

[0023] The wiper device MN may also be provided with a rain sensor ME for detecting rainfall. The rain sensor ME is provided on the inner side of the front window and detects changes in the light transmittance of the front window. The wiper device MN automatically operates when, for example, rainfall is detected by the rain sensor ME. The wiper device MN automatically sets an operating mode and operates according to changes in the signal detected by the rain sensor ME.

[0024] The detection unit MS is provided with a camera MC capable of capturing images. The camera MC captures the external environment of the vehicle Mn. The captured data captured by the camera MC is used, for example, for controlling the vehicle Mn. The detection unit MS is provided with a LiDAR (laser radar) device MD that radiates laser waves. The LiDAR device MD receives reflected waves of the radiated laser waves and detects objects existing 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 composed of, for example, a GPS (Global Positioning System) sensor.

[0025] The vehicle Mn is provided with a control unit MP that performs various controls. The control unit MP performs controls related to the travel of the vehicle Mn. The control unit MP transmits data related to precipitation among data detected by the detection unit MS to the server device 10. The control unit MP is composed of at least one hardware processor such as a CPU.

[0026] The vehicle Mn is provided with a notification unit ML for notifying (reporting, notifying) various information. The notification unit ML is composed of, for example, a display device capable of displaying an image containing notification content. The notification unit ML may also be composed of a speaker that outputs notification content using voice. The vehicle Mn is provided with a communication unit MU that can be connected to the network NW. The communication unit MU is composed of, for example, a communication interface capable of wireless communication.

[0027] The vehicle Mn acquires various data through the detection unit MS while traveling. 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 data related to the control of the wiper device MN, for example, to the server device 10. In the server device 10, the data is stored in the storage unit 14. The calculation unit 12 calculates the precipitation amount in the observation target area RX based on the data stored in the storage unit 14.

[0028] like Figure 2As shown, the map data of the observation target area RX includes an area Rm (m is a natural number). The area Rm is set to a rectangular area of ​​1 km square, for example. The size, position and shape of the area Rm can be set arbitrarily. The area Rm is set with an ID number corresponding to the position. The area Rm is managed by the server device 10. The server device 10 communicates with a plurality of vehicles Mn existing in the observation target area RX. In the server device 10, the operation unit 12 obtains the position data of each vehicle Mn and the ID data for identifying the vehicle Mn.

[0029] like Figure 3 As shown, the operation unit 12 compares the ID data RD of the area Rm with the data obtained from the vehicle Mn, and identifies the vehicle Mn existing in the area Rm. The operation unit 12 obtains detection data related to precipitation from multiple vehicles Mn existing in the area Rm. The detection data related to precipitation includes, for example, data related to the operating state of the wiper device MN, vehicle ID data, vehicle position data, and time data. The operation unit 12 obtains detection data from the vehicle Mn existing in the area Rm at a predetermined period (for example, a 1-minute period). The operation unit 12 stores the obtained detection data in the storage unit 14.

[0030] The calculation unit 12 calculates the precipitation in the area Rm. The area Rm includes the user position of the user who receives the information about precipitation from the server device 10. The user's position information is provided to the server device 10 via the vehicle Mn currently riding or the terminal device 20 held by the user. The calculation unit 12 calculates the precipitation in the area Rm including the user's position based on the position information provided by the user.

[0031] like Figure 4 As shown, the calculation unit 12 generates a plurality of feature quantities B to Y for estimating the precipitation amount at a predetermined period (e.g., a 10-minute period) based on the detection data. The plurality of feature quantities B to Y are classified into 24 elements such as a speed component (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 precipitation amount at the user's position based on the data indicating the operating state of the wiper device MN.

[0032] The calculation unit 12 generates the first feature value Ta (feature values ​​B to M) based on the first detection data obtained from the first area Ra included in the observation target area RX. The first area Ra is set, for example, based on a plurality of sample data collection areas including the user position and its surrounding locations. The plurality of sample data collection areas are set, for example, based on a 1 km square area Rm including the user position and a plurality of 1 km square surrounding areas including surrounding locations at a predetermined distance from the user position.

[0033] The surrounding locations include, for example, a location 5 km from the user location and a location 10 km from the user location. The operation unit 12 collects the first detection data of the first area Ra including the user location and the surrounding locations in any direction from the user location. The direction of collecting data is arbitrarily set based on the method of collecting sample data. The operation unit 12 collects, for example, data of the first area Ra in the four azimuths of east, west, south, and north from the user location. The operation unit 12 may also collect data of the first area including any directional elements such as eight azimuths of east, west, south, and north plus northeast, northwest, southwest, and southeast.

[0034] The operation unit 12 obtains the first detection data of the first area Ra within the first predetermined period t1 in the past compared to the present. The first predetermined period t1 is, for example, one hour before the present time. The operation unit 12 generates the feature quantities B to M in four azimuth directions, for example, based on the first detection data obtained in the first area Ra. The operation unit 12 generates the feature quantities B to M, for example, based on the wiper operation data indicating the operating state of the wiper device provided on the vehicle.

[0035] The calculation unit 12 calculates, for example, a characteristic quantity related to the wiper operation time ratio indicating the operation state of the wiper device MN. The wiper operation time ratio is the ratio of the time the wiper device operates in each predetermined period. The wiper operation time ratio includes characteristic quantities B, C, and D calculated based on the maximum time the wiper device operates in each predetermined period (for example, 10 minutes), and characteristic quantities E, F, and G calculated based on the sum of the time the wiper device operates in the predetermined period (for example, 60 minutes).

[0036] The feature quantities B, C, and D representing the precipitation level are sampled 6 times in total within one hour at a total interval of every 10 minutes. By sampling the feature quantities B, C, and D in a short time and using their maximum values ​​within one hour and the feature quantities E, F, and G representing the sum of the time when the wiper device is operating within one hour, the precipitation peak indicating heavy precipitation can be accurately captured.

[0037] The feature quantity B and feature quantity E are calculated in a rectangular area of ​​1 km square including the user's position. A rectangular area 5Rm of 1 km square including a point 5 km away from the user's position in a predetermined direction (see Figure 2 ) calculates the feature quantity C and feature quantity F. In a rectangular area 10Rm (refer to Figure 2 ) within which the feature quantities D and G are calculated.

[0038] For the above-mentioned feature quantity indicating the precipitation level, in the first area Ra, not only the 1km square of the area Rm including the user's position is calculated, but also the areas 5Rm and 10Rm separated from the area Rm in four directions are calculated. The more the sampling points that serve as the basis for calculating the feature quantity are expanded according to the direction, the more vehicles Mn can collect data. In addition, by performing sampling according to the direction, the precipitation trend can be captured.

[0039] The calculation unit 12 calculates, for example, a wiper operating number ratio indicating the operating state of the wiper device. The wiper operating number ratio includes characteristic quantities H, I, and J calculated based on the maximum number of vehicles Mn in which the wiper device is operated within each predetermined period (for example, 10 minutes), and characteristic quantities K, L, and M calculated based on the total number of vehicles Mn in which the wiper device is operated within a predetermined period (for example, 60 minutes).

[0040] For example, when all vehicles Mn operate the wiper device at a wiper speed (e.g., 50 times / minute) for 10% of the driving time, the characteristic amount of the wiper operation time ratio is calculated as 10%. In this case, since all vehicles Mn operate the wiper device for 60 minutes, the characteristic amount of the wiper operation number ratio is calculated as 100%.

[0041] In the calculation of the characteristic quantity, the operating ratio [%] of the wiper device MN is calculated instead of the operating frequency, thereby suppressing the deviation of the calculated value caused by the difference in the number of vehicles Mn traveling in the area to be calculated. By calculating the characteristic quantity related to the wiper operating time ratio, heavy precipitation can be easily captured. In the calculation of the characteristic quantity, in addition to the "time" viewpoint, the "number of vehicles" viewpoint is also used, thereby making it easy to capture heavy precipitation.

[0042] The operation unit 12 generates the second feature quantity Tb (feature quantities N to Y) based on the second detection data obtained from the second area Rb adjacent to the first area Ra included in the observation target area RX. The second area Rb is set, for example, based on a plurality of data collection areas including surrounding locations adjacent to the first area Ra. The plurality of data collection areas are set, for example, based on a rectangular area of ​​1 km square including surrounding locations at a predetermined distance from the user's position. The surrounding locations include, for example, a location 10 km away from the user's position in a predetermined direction, a location 20 km away from the user's position, and a location 30 km away from the user's position in a predetermined direction.

[0043] For the above-mentioned feature quantity indicating the precipitation level, in the second region Rb, regions 10Rm, 20Rm, and 30Rm separated in four directions with the region Rm as the center are calculated. The more the sampling locations that serve as the basis for calculating the feature quantity are expanded according to the direction, the more vehicles Mn can collect data. In addition, by sampling the region Rm according to the direction, the precipitation trend can be captured.

[0044] The operation unit 12 collects the second detection data of the second area Rb from the user's position, for example. The operation unit 12 obtains the second detection data of the second area Rb within the second predetermined period t2 that is past compared to the first predetermined period t1. The second predetermined period t2 is, for example, one hour before the start time of the first predetermined period t1. The operation unit 12 generates the feature quantities N to Y in four azimuth directions, for example, based on the second detection data obtained in the second area Rb. The operation unit 12 generates the feature quantities N to Y, for example, based on the wiper operation data indicating the operating state of the wiper device provided on the vehicle.

[0045] The calculation unit 12 calculates, for example, a wiper operation time ratio representing the operating state of the wiper device MN. The wiper operation time ratio includes feature quantities N, O, and P calculated based on the maximum time the wiper device MN operates in each predetermined period (for example, 10 minutes), and feature quantities Q, R, and S calculated based on the sum of the time the wiper device MN operates in a predetermined period (for example, 60 minutes).

[0046] In a rectangular area 10Rm (refer to Figure 2 ) calculates the feature quantity N and feature quantity Q. In a rectangular area 20Rm (refer to Figure 2 ) calculates the feature quantity O and feature quantity R. In a rectangular area 30Rm (refer to Figure 2 ) calculates the feature quantity P and feature quantity S.

[0047] The calculation unit 12 calculates, for example, a wiper operating number ratio indicating the operating state of the wiper device MN. The wiper operating number ratio includes feature quantities T, U, and V calculated based on the maximum number of vehicles Mn in which the wiper device is operated within each predetermined period (for example, 10 minutes), and feature quantities W, X, and Y calculated based on the total number of vehicles Mn in which the wiper device is operated within a predetermined period (for example, 60 minutes). The calculation unit 12 calculates feature quantities including the first feature quantity Ta and the second feature quantity Tb at the four directions of the user's position.

[0048] As described above, the first feature value Ta in the first area Ra including the user position is calculated in the most recent first predetermined period t1. The second feature value Tb in the second area Rb far from the user position is calculated in the second predetermined period t2 which is past compared to the first predetermined period t1. The calculation unit 12 inputs the calculated first feature value and second feature value into a preset precipitation estimation model, and calculates the precipitation from the present to the future in the first area Ra included in the observation target area RX.

[0049] The precipitation estimation model is set, for example, based on a polynomial nonlinear regression formula that uses a plurality of feature quantities as variables to calculate an estimated value of the precipitation in the area Rm including the user position. The nonlinear regression formula is arbitrarily set as a function that can calculate the precipitation. The relationship between the precipitation and the feature quantity related to the operating state of the wiper device MN gradually changes from a linear relationship to a curved relationship. Therefore, the precipitation estimation model using nonlinear regression can more accurately reproduce the different trends of the heavy precipitation level and the weak precipitation level.

[0050] In the precipitation estimation model, a plurality of parameters corresponding to the polynomial composed 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 based on deep learning using a neural network, for example.

[0051] The calculation unit 12 uses the feature amount calculated based on the past detection data as the teacher data, repeatedly performs machine learning to calculate the estimated value of precipitation based on the feature amount, and adjusts the parameters set in the precipitation estimation model. The estimated value of precipitation is calculated by inputting the feature amount calculated using the detection data to the precipitation estimation model with the adjusted parameters. The precipitation estimation model with the adjusted parameters is stored in the storage unit 14 as a computer program. The calculation unit 12 calculates the precipitation at an arbitrary location by inputting the feature amount calculated using the detection data to the precipitation estimation model.

[0052] 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 precipitation amount from the present to the future in a predetermined area included in the observation target area RX based on the detection data.

[0053] The calculation unit 12 calculates a plurality of first feature quantities Ta within a first predetermined period t1 that is past compared to the present, for example, based on the first detection data obtained from the first region Ra. The calculation unit 12 calculates a second feature quantity Tb within a second predetermined period t2 that is past compared to the first predetermined period, for example, based on the second detection data obtained in the second region Rb adjacent to the first region Ra. The calculation unit 12 calculates feature quantities including a first feature quantity Ta related to a time ratio during which the wiper device MN is operated and a second feature quantity Tb related to a ratio of the number of wiper devices that are operated, based on wiper operation data indicating an operation state of the wiper device MN provided on the vehicle Mn in the detection data.

[0054] The calculation unit 12 calculates the current precipitation in the region Rm using a precipitation estimation model using the first characteristic value Ta and the second characteristic value Tb as variables. The calculation unit 12 compares the precipitation level set according to the precipitation and the calculated value of the precipitation to calculate the precipitation level in the region Rm. The calculation unit 12 determines the following three precipitation levels based on the comparison result with the precipitation that is set in advance as a reference, for example.

[0055] When the precipitation is greater than a preset first precipitation amount V1 (for example, 20 mm / h), the operation unit 12 determines it as a "strong precipitation level (High)". The strong precipitation level is set to a precipitation amount greater than a benchmark (for example, 20 mm / h) that requires attention. The benchmark is set to an arbitrary precipitation amount. When the precipitation is less than the first precipitation amount V1 and greater than a preset second precipitation amount V2 (for example, 1 mm / h), the operation unit 12 determines it as a "weak precipitation level (Mid)". When the precipitation is less than the second precipitation amount V2 (1 mm / h), the operation unit 12 determines it as "no precipitation (Low)".

[0056] The calculation unit 12 may calculate not only the precipitation level in the area Rm including the user position, but also the precipitation levels of all other areas Rm in the observation target area RX by repeatedly performing the same calculation processing as described above. The calculation unit 12 does not necessarily need to calculate all other areas Rm in the observation target area RX, and may calculate the observation target area RX using one area Rm included in a rectangular area of ​​an arbitrary size as a representative value, and generate mapping data of the observation target area RX divided by rectangular areas of an arbitrary size.

[0057] like Figure 5As shown, the operation unit 12 may also 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 strong precipitation level (High), the distribution of regions with the weak precipitation level (Mid), and the distribution of regions with no precipitation (Low).

[0058] The precipitation estimation model may also be set to calculate not only the current precipitation but also the future precipitation by repeatedly performing machine learning based on past detection data. Therefore, the operation unit 12 may also calculate the past and future precipitation levels in the area Rm based on the precipitation estimation model. The operation unit 12 may, for example, calculate the precipitation before a predetermined time, the current precipitation, and the precipitation after a predetermined time in the area Rm including the user's location. The operation unit 12 may also calculate the past, current, and future precipitation at any time interval. The operation unit 12 may also use the accumulated detection data to update the precipitation level estimation model at a predetermined timing.

[0059] Generally speaking, heavy precipitation often moves in large masses in conjunction with the movement of rain clouds from a distance. Therefore, by calculating the second characteristic value Tb in the second predetermined period t2 in addition to calculating the first characteristic value Ta in the first predetermined period t1, the trend of precipitation movement can be calculated.

[0060] The operation unit 12 may also extract the area Rm where the precipitation in the observation target area RX is above the benchmark and becomes a heavy precipitation level based on the generated mapping data, and provide information related to the precipitation to the user in the area Rm. The operation unit 12 may also cause the notification unit ML of the vehicle Mn that the user in the extracted area Rm is riding to notify the scheduled information indicating the heavy precipitation level through the network NW. The operation unit 12 may also extract the area Rm that will become a heavy precipitation level within a scheduled time in the future based on the generated mapping data, and provide information related to the precipitation to the user in the area Rm. The scheduled time in the future can be set arbitrarily.

[0061] The vehicle Mn can perform driving control corresponding to rainfall based on the provided predetermined information. The driving control corresponding to rainfall can be applied to the vehicle Mn that is driven based on automatic driving. The driving control corresponding to rainfall can also be driving assistance for the vehicle Mn that is driven based on manual driving. The computing unit 12 can also display the predetermined information related to the first precipitation level on the display unit 26 of the user's terminal device 20 via the network NW.

[0062] For example, information on the state of heavy precipitation level rainfall and / or information indicating that heavy precipitation level rainfall is approaching is displayed on the display unit 26. The user's terminal device 20 does not necessarily need to be within the extracted area Rm. The user only needs to be a user of the service provided with precipitation level information.

[0063] exist Figure 7 , a flow chart is used to show the process 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 involved in the precipitation level estimation method.

[0064] The operation unit 12 obtains detection data related to precipitation detected by a plurality of vehicles existing in the observation target area (S100). The operation unit 12 calculates a first feature quantity in a first predetermined period past compared to the present based on the first detection data obtained from the first area Ra included in the observation target area RX (S102). The operation unit 12 calculates a second feature quantity in a second predetermined period t2 past compared to the first predetermined period t1 in the second area Rb based on the second detection data obtained in the second area Rb adjacent to the first area Ra (S104).

[0065] The calculation unit 12 calculates the precipitation in the predetermined area Rm included in the observation target area RX using the precipitation estimation model with the first characteristic value Ta and the second characteristic value Tb as variables (S106). The calculation unit 12 determines whether the precipitation is greater than or equal to the first precipitation value V1 (S108). When the precipitation is greater than or equal to the first precipitation value V1, the calculation unit 12 determines that it is a "heavy precipitation level" (S110).

[0066] When the precipitation is less than the first precipitation amount V1, the calculation unit 12 determines whether the precipitation is greater than or equal to the second precipitation amount V2 (S112). When the precipitation is greater than or equal to the second precipitation amount V2, the calculation unit 12 determines that it is a "weak precipitation level" (S114). When the precipitation is less than the second precipitation amount V2, the calculation unit 12 determines that it is "no precipitation" (S116). The calculation unit 12 provides information on the precipitation level to users in the area that has become a heavy precipitation level (S118).

[0067] As described above, according to the precipitation level estimation system 1, by calculating a plurality of feature quantities based on the detection data related to the operating state of the wiper device MN, the precipitation level can be accurately estimated. According to the precipitation level estimation system 1, by inputting a plurality of feature quantities into a precipitation amount estimation model whose parameters are adjusted based on machine learning, the precipitation level can be accurately estimated. According to the precipitation level estimation system 1, by using nonlinear regression for the precipitation amount estimation model, the precipitation level can be accurately estimated.

[0068] In the above-mentioned embodiment, the feature quantity is calculated based on the data of the operating state of the wiper device MN. The feature quantity may be calculated not only based on the detection data of the wiper device MN, but also based on 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 quantity may also be calculated by the operation unit 12 repeatedly performing machine learning based on the image data obtained by capturing the rainfall conditions by the camera MC.

[0069] The characteristic quantity may also be calculated by the operation unit 12 repeatedly performing 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 rainfall, the characteristic quantity may also be calculated by the operation unit 12 repeatedly performing machine learning based on the detection data of the LiDAR device MD. The characteristic quantity may also be calculated based on 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. As long as the detection data associated with precipitation can be detected, any data may be used to calculate the characteristic quantity.

[0070] 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 (storage medium) such as a semiconductor memory, a magnetic recording medium, or an optical recording medium.

Claims

1. A precipitation level estimation system, A calculation unit is provided, the calculation unit acquiring detection data related to precipitation detected by a plurality of vehicles present in an observation target area, and calculating the precipitation amount in a predetermined area included in the observation target area based on the detection data, The operation unit, calculating a first feature quantity in a first predetermined period in the past compared to the present based on first detection data acquired from a first area including the predetermined area, calculating a second feature quantity in the second area within a second predetermined period that is past compared to the first predetermined period based on second detection data acquired in a second area adjacent to the first area, calculating the precipitation using a precipitation estimation model using the first characteristic value and the second characteristic value as variables, A precipitation level corresponding to the precipitation amount is calculated.

2. The precipitation level estimation system according to claim 1, The operation unit, Based on wiper operation data indicating the operating state of the wiper device provided on the vehicle in the detection data, characteristic quantities including the first characteristic quantity related to the time ratio of the wiper device operation and the second characteristic quantity related to the number ratio of the wiper devices in operation are calculated, Based on the characteristic amount, the precipitation amount is calculated.

3. The precipitation level estimation system according to claim 1, The operation unit, calculating the precipitation level in the area, Map data in which the precipitation level is mapped for each of the regions within the observation target region is generated.

4. The precipitation level estimation system according to claim 3, The operation unit, extracting the area in the observation target area where the precipitation amount reaches the precipitation level above a reference based on the mapping data; Information related to the precipitation level is provided to users present in the area.

5. A storage medium storing a program, wherein the program causes a computer to execute: acquiring detection data related to precipitation detected by a plurality of vehicles existing in the observation target area, calculating a first feature quantity in a first predetermined period in the past compared to the present, based on first detection data acquired from a first area included in the observation target area; calculating a second feature quantity in the second area within a second predetermined period that is past compared to the first predetermined period based on second detection data acquired in a second area adjacent to the first area, using a precipitation estimation model using the first characteristic value and the second characteristic value as variables to calculate precipitation in a predetermined area included in the observation target area, A precipitation level corresponding to the precipitation amount is calculated.

Images