Vehicle data collection method

Abstract

This will reduce the consumption of computing resources related to in-vehicle systems. [Solution] The vehicle data collection method is a vehicle data collection method that collects vehicle data relating to a vehicle via a network, and includes a calculation step of calculating the probability of vehicle appearance in an area in which the vehicle is traveling based on the vehicle's location, a modification step of changing the vehicle data collection settings that indicate settings relating to vehicle data based on the vehicle appearance probability, and a transmission step of transmitting the vehicle data collection settings to the vehicle.

Description

[Technical Field]

[0001] This invention relates to the technical field of vehicle data collection methods. [Background technology]

[0002] As an example of this type of method, a method has been proposed in which the amount of vehicle information data is monitored on a region-by-region basis, and the amount of vehicle information uploaded is adjusted according to that data amount (see Patent Document 1). [Prior art documents] [Patent Documents]

[0003] [Patent Document 1] Japanese Patent Publication No. 2019-079422 [Overview of the project] [Problems that the invention aims to solve]

[0004] The technology described in Patent Document 1 has room for improvement. Furthermore, the collected data may be analyzed using a learning model constructed by machine learning.

[0005] This invention has been made in view of the above circumstances, and aims to provide a vehicle data collection method that can collect vehicle data while suppressing the processing load on the vehicle. [Means for solving the problem]

[0006] A vehicle data collection method according to one aspect of the present invention is a vehicle data collection method for collecting vehicle data relating to a vehicle via a network, comprising: a calculation step of calculating the probability of vehicle appearance in an area in which the vehicle is traveling based on the location of the vehicle; a modification step of changing vehicle data collection settings that indicate settings relating to the vehicle data based on the vehicle appearance probability; and a transmission step of transmitting the vehicle data collection settings to the vehicle. [Brief explanation of the drawing]

[0007] [Figure 1] This is a diagram showing the configuration of a vehicle data collection system according to an embodiment. [Figure 2] This diagram shows the operation of the vehicle data collection system according to the embodiment. [Modes for carrying out the invention]

[0008] The vehicle data collection method will be explained with reference to Figures 1 and 2. In Figure 1, the vehicle data collection system 1 comprises a vehicle data collection setting system 10 and databases DB1, DB2, and DB3. For example, the vehicle data collection setting system 10 may be implemented by a server. In this case, the vehicle data collection setting system 10 may be implemented by a single server or by multiple servers. The server may be a cloud server.

[0009] First, an overview of the vehicle data collection system 1 will be provided. The vehicle data collection system 1 may acquire vehicle data from multiple vehicles, including vehicle V, via a network. By analyzing the collected vehicle data, the vehicle data collection system 1 may estimate at least one of the conditions of each vehicle and the conditions of the region. The vehicle data collection system 1 may provide services to each vehicle using the estimation results. At least one of the vehicle data analysis and the provision of services may be performed by a system or device different from the vehicle data collection system 1.

[0010] For example, the vehicle data may include at least one of speed, acceleration, brake frequency, steering operation amount, fuel consumption, and wiper operation information. For example, the vehicle data collection system 1 may estimate at least one of driving behavior and vehicle state based on speed, brake frequency, steering operation amount, fuel consumption, and acceleration pattern. For example, the vehicle data collection system 1 may estimate traffic congestion based on speed, acceleration, and brake frequency. For example, the vehicle data collection system 1 may estimate weather conditions based on wiper operation information. Incidentally, the weather conditions may include information indicating the intensity of rain. For example, the vehicle data collection system 1 may estimate road surface unevenness based on vertical acceleration. Incidentally, the vehicle data collection system 1 may further estimate at least one of road infrastructure degradation degree and road surface roughness based on the estimated road surface unevenness. For example, the vehicle data collection system 1 may estimate the occurrence of a collision based on acceleration in at least one of the front-rear direction and the lateral direction.

[0011] Each vehicle may upload (i.e., transmit) raw data as vehicle data to the vehicle data collection system 1. However, by the in-vehicle device mounted on each vehicle performing preprocessing on the raw data, it is possible to reduce the communication cost involved in uploading, the data storage cost in the vehicle data collection system 1, and the data processing cost in the vehicle data collection system 1.

[0012] By the way, in the situation of the region estimated as described above, there are differences in the occurrence frequency depending on the region. Therefore, when the in-vehicle device mounted on each vehicle performs preprocessing on raw data, if vehicle data is collected uniformly from all vehicles, there is a risk that the computer resources related to the in-vehicle device will be consumed excessively. Therefore, in the present embodiment, by collecting vehicle data based on the future vehicle appearance probability, it is possible to suppress the excessive consumption of computer resources related to the in-vehicle device.

[0013] Hereinafter, the operation of the vehicle data collection system 1 will be described with reference to FIG. 2 in addition to FIG. 1. Each of the plurality of vehicles uploads position information indicating the position of the vehicle to the vehicle data collection system 1. After performing predetermined processing on the uploaded position information, the vehicle data collection system 1 stores the position information in the database DB1 (step S101 in FIG. 2). Each vehicle may upload the position information to the vehicle data collection system 1 periodically or irregularly. As a result, time-series data (in other words, history data) related to the position information of each vehicle will be stored in the database DB1.

[0014] In FIG. 2, the vehicle data collection setting system 10 of the vehicle data collection system 1 calculates a vehicle appearance probability matrix P indicating the future vehicle appearance probability based on the position information stored in the database DB1 ij (step S102 in FIG. 2). For example, the future vehicle appearance probability may be calculated according to the target to be focused on (for example, driving behavior, vehicle state, weather condition, traffic jam condition, road surface condition, etc.) and the time scale of the characteristic observation period. For example, when the time scale of the observation period is relatively short (several hours to several days), the future vehicle appearance probability may be calculated using a short-term prediction model such as an ARIMA system, an LSTM system, an XGBoost system, etc. When the time scale of the observation period is relatively long (several weeks to several months), the future vehicle appearance probability may be calculated using a medium- to long-term prediction model such as a Transformers system, a Gaussian process regression system, etc.

[0015] Next, the vehicle data collection setting system 10 calculates the optimal resolution r of each vehicle based on the following formula (1) including the vehicle appearance probability matrix P ij and the importance l of region i i and the resolution r of vehicle j j (step S103 in FIG. 2). Note that "A" and "B" are constants. Note that the initial value of the importance l * j may be set by the operator of the vehicle data collection system 1. The importance l i is stored in the database DB2. i

[0016]

Number

[0017] In this embodiment, the "resolution" is a value proportional to the "utilization rate of computer resources related to in-vehicle devices". The "resolution" may mean the amount of data included in vehicle data. For example, the vehicle data may include data at intervals of a first period (e.g., 0.2 seconds). For example, the vehicle data may include data at intervals of a second period (e.g., 1 second) longer than the first period. In this case, it can be said that the vehicle data including data at intervals of the first period has a higher resolution than the vehicle data including data at intervals of the second period. For example, the vehicle data may include n types of data. For example, the vehicle data may include m types of data more than n. In this case, it can be said that the vehicle data including m types of data has a higher resolution than the vehicle data including n types of data.

[0018] A specific example will be given to explain the process of step S103. The vehicle appearance probability matrix P ij is assumed to be as follows. That is, the appearance probability of vehicle j = 1 is 0.1 in area i = 1, 0.1 in area i = 2, 0.8 in area i = 3, and 0.0 in area i = 4. The appearance probability of vehicle j = 2 is 0.3 in area i = 1, 0.3 in area i = 2, 0.4 in area i = 3, and 0.0 in area i = 4. The appearance probability of vehicle j = 3 is 0.8 in area i = 1, 0.2 in area i = 2, 0.0 in area i = 3, and the appearance probability of vehicle j = 4 is 0.0 in area i = 4. It is assumed that the vehicle appearance probabilities for each vehicle j are normalized.

[0019]

Number

[0020] The importance l of area i iThe following is assumed: the importance of region i=1 is 1.5, the importance of region i=2 is 0.5, the importance of region i=3 is 1.0, and the importance of region i=4 is 1.2.

[0021]

number

[0022] Vehicle j resolution r j The following conditions apply.

[0023]

number

[0024] In this case, the optimal resolution r for each vehicle * j The results are as follows: The optimal resolution for vehicle j=1 is 8.5, the optimal resolution for vehicle j=2 is 8.5, the optimal resolution for vehicle j=3 is 11.5, and the optimal resolution for vehicle j=4 is 11.5.

[0025]

number

[0026] Furthermore, the optimal resolution r for each vehicle * j To suppress variations, the optimal resolution r * j The evaluation function related to this is "-(r max ―r min The constraints )" may be added as a linear combination or as an inequality constraint. Note that the above-mentioned optimal resolution r * j When finding specific examples, the following inequality constraints are added to the evaluation function.

[0027]

number

[0028] The vehicle data collection setting system 10 uses the optimal resolution r calculated in the process of step S103. * j Based on this, a vehicle data collection setting file is created for each vehicle (step S104 in Figure 2). The vehicle data collection setting system 10 sends the vehicle data collection setting file to each vehicle. As a result, the in-vehicle device of each vehicle is configured according to the settings indicated in the vehicle data collection setting file (for example, optimal resolution r * j Based on this, the raw data is preprocessed. Then, each vehicle uploads the preprocessed data as vehicle data to the vehicle data collection system 1. The vehicle data collection system 1 stores the vehicle data uploaded from each vehicle in the database DB3 (step S105 in Figure 2).

[0029] The vehicle data collection system 1 determines whether sufficient vehicle data has been stored in the database DB3 (step S106 in Figure 2). If it is determined in step S106 that sufficient vehicle data has not been stored in the database DB3 (step S106: No), the process in step S105 is repeated. In other words, the processes in steps S105 and S106 are repeated until it is determined in step S106 that sufficient vehicle data has been stored in the database DB3.

[0030] In step S106, if it is determined that sufficient vehicle data has been accumulated in the database DB3 (step S106: Yes), the vehicle data collection system 1 determines the importance of area i based on the vehicle data stored in the database DB3. i Update (step S107 in Figure 2).

[0031] The vehicle data collection system 1 determines whether or not to terminate the collection of vehicle data (step S108 in Figure 2). If it is determined in step S108 that the collection of vehicle data should not be terminated (step S108: No), the process in step S101 is repeated. On the other hand, if it is determined in step S108 that the collection of vehicle data should be terminated (step S108: Yes), the operation shown in Figure 2 is terminated.

[0032] (Technical effects) For example, in the vehicle data collection system 1, the optimal resolution r is determined for vehicles passing through areas with a relatively high probability of future vehicle appearance. * j The resolution can be set relatively low because a relatively large amount of vehicle data can be collected in such areas. For example, in vehicle data collection system 1, the optimal resolution r is set for vehicles passing through areas where the probability of future vehicle appearance is relatively low and the importance is relatively high. * j This can be set relatively high. This is because setting it in this way allows for the collection of a relatively large amount of vehicle data from a relatively small number of vehicles. Thus, in this embodiment, by calculating the future vehicle appearance probability, it is possible to collect a relatively large amount of vehicle data for areas of relatively high importance without wasting computing resources related to the vehicle's onboard equipment (in other words, while suppressing excessive consumption of computing resources).

[0033] The embodiments of the invention derived from the above-described embodiments are described below.

[0034] A vehicle data collection method according to one aspect of the invention is a vehicle data collection method for collecting vehicle data relating to a vehicle via a network, comprising: a calculation step of calculating the probability of vehicle appearance in an area in which the vehicle is traveling based on the location of the vehicle; a modification step of changing vehicle data collection settings that indicate settings relating to the vehicle data based on the vehicle appearance probability; and a transmission step of transmitting the vehicle data collection settings to the vehicle.

[0035] In one example of the vehicle data collection method, the settings relating to the vehicle data may include the utilization rate of the vehicle's computing resources, and in the modification step, the utilization rate may be changed based on the vehicle's appearance probability.

[0036] In this case, an importance level may be assigned to the area, and in the modification process, the utilization rate may be changed based on the vehicle appearance probability and the importance level.

[0037] The present invention is not limited to the embodiments described above, and can be modified as appropriate without contradicting the gist or idea of ​​the invention as can be read from the claims and specification as a whole. Vehicle data collection methods involving such modifications are also included within the technical scope of the present invention. [Explanation of symbols]

[0038] 1...Vehicle data collection system, 10...Vehicle data collection setting system

Claims

1. A vehicle data collection method for collecting vehicle data about a vehicle via a network, A calculation step of calculating the probability of vehicle appearance in the area in which the vehicle is traveling, based on the position of the vehicle, A modification step of changing the vehicle data collection settings that indicate the settings related to the vehicle data based on the vehicle appearance probability, A transmission step of transmitting the vehicle data collection settings to the vehicle, A method for collecting vehicle data, including the data itself.

2. The settings relating to the aforementioned vehicle data include the utilization rate of the vehicle's computing resources, In the modification process, the utilization rate is changed based on the vehicle appearance probability. The vehicle data collection method according to claim 1.

3. The aforementioned area has an importance level assigned to it. In the modification process, the utilization rate is changed based on the vehicle appearance probability and the importance. The vehicle data collection method according to claim 2.

Images