Information processing device, information processing method, and non-transitory computer readable medium

Patent metadata

Field	Value
Publication number	US-12204069-B2
Application number	US-202217653901-A
Country	US
Kind code	B2
Filing date	Mar 8, 2022
Priority date	Sep 14, 2021
Publication date	Jan 21, 2025
Grant date	Jan 21, 2025

Abstract

According to one embodiment, an information processing device includes a first processor configured to calculate, based on first information indicating a target time point at which weather prediction data is to be acquired and which is a relative time point with respect to a first time point, second information indicating the target time point being a relative time point with respect to a second time point at which weather prediction is started by a prediction device, the prediction device being configured to generate weather prediction data through weather prediction.

First claim

The invention claimed is:

1. An information processing device using a plurality of prediction products, the plurality of prediction products each start weather prediction at a plurality of weather prediction start time points arranged at prediction time intervals to generate weather prediction data for prediction periods beginning at each of the plurality of weather prediction start time points, data generation time being required to generate the weather prediction data in each prediction product, comprising:
a weather prediction storage configured to acquire and store the weather prediction data generated by each of the plurality of prediction products in association with the weather prediction start time points and the prediction period,
a first processor configured to
acquire, from a terminal of a user, first information including a reference time point and a target time point later than the reference time point,
acquire, from a meta data storage, meta information for each of the plurality of prediction products, including the plurality of weather prediction start time points, a length of the data generation time, and a length of the prediction periods,
select, from the plurality of prediction products, a prediction product having a first one of the weather prediction start time points which satisfies a condition that the prediction period includes the target time point and that the first one of the weather prediction start time points plus the length of the data generation time is earlier than the reference time point, and
detect, among the weather prediction start time point points which satisfy the condition with respect to the selected prediction product, a second one weather prediction start time point, which is closest to the reference time point; and

an output processor configured to retrieve from the weather prediction storage a portion of the weather prediction data at the target time point in the weather prediction data generated by the selected prediction product for the prediction period starting from the detected second one of the weather prediction start times, and transmit the portion of the weather prediction data to the terminal, wherein in the terminal, the portion of the weather prediction data is used to execute a prediction model to predict occurrence of a predetermined event at the target time.

2. The information processing device according to claim 1 ,
wherein the plurality of the prediction products generate the weather prediction data by calculating one or more weather variables,
the information processing device further comprises a second processor configured to select a prediction product which calculates, among the one or more weather variables, at least one of target weather variables specified by second information acquired from the terminal, and
the output processor acquires the target weather variables being the portion of the weather prediction data at the target time point generated by the selected prediction product.

3. The information processing device according to claim 2 ,
wherein when a plurality of the prediction products are selected and a same target weather variable is included in the weather variables calculated by the prediction products, the output processor sends a selection request to the terminal instructing the user to select one of the prediction products to transmit the target weather variable calculated by the prediction product selected by the user to the terminal.

4. The information processing device according to claim 3 ,
wherein the plurality of prediction products calculate the one or more weather variables at one or more points each being a geographic location,
the second processor selects a prediction product that calculates the target weather variable at a target point specified by third information acquired from the terminal, and
the output processor acquires the target weather variable at the target point being the portion of the weather prediction data at the target time point generated by the selected prediction product.

5. The information processing device according to claim 4 ,
wherein when a plurality of the prediction products are selected and a same target weather variable at a same target point is included in the weather variables calculated by the prediction products, the output processor sends a selection request to the terminal instructing the user to select one of the prediction products to transmit the target weather variable calculated by the prediction product selected by the user to the terminal.

6. The information processing device according to claim 3 , further comprising
a prediction product recommender configured to select one prediction product to be recommended among the selected prediction products on a basis of the meta information of the selected prediction products, and
wherein the selection request includes recommendation information of recommending the one prediction product, wherein
the prediction product recommender calculates a function that includes, as parameters, a mesh size, a point targeted for prediction by the prediction product, the length of the prediction period, and an output time interval of the weather prediction, and select the one prediction product with a smallest function value.

7. The information processing device according to claim 2 ,
wherein the first information includes a plurality of the target time points belonging on a plurality of past days,
the meta information of the plurality of prediction products includes information on data existence period, which is a period of time during which the weather prediction data was acquired from the plurality of prediction products, respectively, and
the first processor selects the prediction product that the data existence period includes all of the plurality of past days.

8. An information processing method using a plurality of prediction products, the plurality of prediction products each start weather prediction at a plurality of weather prediction start time points arranged at prediction time intervals to generate weather prediction data for prediction periods beginning at each of the plurality of weather prediction start time points, data generation time being required to generate the weather prediction data in each prediction product, the method comprising:
acquiring the weather prediction data generated by each of the plurality of prediction products in association with the weather prediction start time and the prediction period and storing acquired weather prediction data in a weather prediction storage;
acquiring, from a terminal of a user, first information including a reference time point and a target time point later than the reference time point;
acquiring, from a meta data storage, meta information for each of the plurality of prediction products, including the plurality of weather prediction start time points, a length of the data generation time, and a length of the prediction periods;
selecting, from the plurality of prediction products, a prediction product having the weather prediction start time point which satisfies a condition that the prediction period includes the target time point and that the weather prediction start time point plus the length of the data generation time is earlier than the reference time point;
detecting, among the weather prediction start time point, points which satisfy the condition with respect to the selected prediction product, one weather prediction start time point which is closest to the reference time point; and
retrieving from the weather prediction storage a portion of the weather prediction data at the target time point in the weather prediction data generated by the selected prediction product for the prediction peri

Assignees

• Toshiba Kk

Inventors

• Ni Fang
• Shin Hiromasa
• Shiga Yoshiaki
• Kakimoto Mitsuru

Classifications

• G01W1/10 Primary

  Devices for predicting weather conditions (computers per se G06; display devices G09) · CPC title