Danger prediction device, system and method, and recording medium storing program
A prediction device and dangerous technology are applied in the field of recording media recorded with programs, which can solve problems such as insufficient data assurance and prediction of adverse effects, and achieve the effect of improving prediction accuracy.
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Method used
Image
Examples
no. 1 approach
[0044] like figure 1 As shown, the hazard prediction system 10 of the first embodiment is configured to include a plurality of vehicle 12, a vehicle 14, a central server 30, and an information providing server 50. The vehicle 12 is mounted with an in-vehicle device 20, and the vehicle 14 is mounted with a notification device 40. Vehicle 12 is an example of driving vehicles, and the central server 30 is an example of a hazard prediction device.
[0045]20 of the vehicle mounted device 12, the notification means 40 of the vehicle 14 and the center server 30 are connected to each other via a network CN1. Further, the center server 30 and the information providing server 50 connected to each other via a network CN2. Further, the center server 30 and the information providing server 50 may be connected via a network CN1.
[0046] (vehicle)
[0047] like figure 2 , The vehicle of the present embodiment comprises a vehicle-mounted device 12 is configured to 20, a plurality of the ECU 22,...
no. 2 approach
[0110] In the first embodiment, the use of a predictive model 110 to predict the risk, but in the second embodiment, as Figure 11A It is shown, in accordance with the predictive model 110 is provided for each attribute this embodiment different from the first embodiment. Hereinafter, the same as the first embodiment are denoted by the same reference numerals, and description thereof will be omitted. Hereinafter, differences from the first embodiment will be described.
[0111] Predictive model 110 exists for each attribute predictive model 110 of the present embodiment. More specifically, the predictive model 110 includes a first group G1 with the predictive model 111, and a second group G2 with the predictive model 112, a third group G3 with predictive model 113 and a fourth group G4 with the predictive model 114.
[0112] Prediction unit 280 of the present embodiment is inputted to the activity information corresponding to the predictive model 110 to predict the risk group. That...
no. 3 approach
[0117] In the first embodiment, in the case where the aggregate data set 120 is updated, the behavior information acquired directly input to the predictive model 110. On the other hand, in the third embodiment, as Figure 12b Shown, at this point the updated summary data 120 set for the prediction and the prediction model update 110, different from the first embodiment. Hereinafter, the same as the first embodiment are denoted by the same reference numerals, and description thereof will be omitted. Hereinafter, differences from the first embodiment will be described.
[0118] First, the prediction unit 280 of the present embodiment acts to enter information into a predictive model 110 to predict risk. That is, if Figure 12A , The first aggregated data 121, the second aggregated data 122, the third 123 and fourth data aggregated summary data 124 is input to the prediction model 110. In addition, based on the predicted dangerous place to generate attention information.
[0119] Here,...
PUM
Login to View More Abstract
Description
Claims
Application Information
Login to View More