IP Library Granted Patent US 11,333,794
Granted Patent B2
US 11,333,794 · App. 16/167,649 · Granted May 17, 2022

Multimedia derived wind map

Inventors: Ivan M. Milman (Austin, TX); Sushain Pandit (Austin, TX); Charles D. Wolfson (Austin, TX); Su Liu (Austin, TX); Fang Wang (Westford, MA)
Assignee: International Business Machines Corporation
G01W1/10G06F16/2228G06F16/29G06F16/487
View Patent ↗
Loading inventors, assignments & file history…
Monitor This Case
Get email alerts when status or documents change.
Order Certified Copies
Most orders are placed with the USPTO same day — all within 24 business hours.
Order via The Patent Place →
Pre-filled with this patent's details
Quick Facts
Patent No.
US 11,333,794
App. No.
16/167,649
Granted
May 17, 2022
Kind
B2
Abstract

Embodiments of the present invention disclose a method, a computer program product, and a computer system for generating a wind map based on multimedia analysis. A computer receives a multimedia source configuration and builds a wind scale reference database. In addition, the computer extracts and processes both wind speed data and contextual data from the multimedia. Moreover, the computer analyses temporal and spatial features, as well as generates a wind map based on the extracted context, extracted wind speed, and analysed temporal and spatial features. Lastly, the wind map generator validates and modifies the wind scale reference database.

Claims (58)

1. A computer-implemented method for generating a wind map based on multimedia analysis, the method comprising:

deducing a wind speed of wind identified in one or more multimedia based on a wind scale reference database, wherein the one or more multimedia includes at least one of text, audio, image, and video; and wherein extracting the contextual data corresponding to the one or more multimedia further comprises:

transcribing the audio;

applying keyword searching and natural language processing to the transcribed audio and the text; and

applying image recognition technology to the image and the video;

extracting contextual data corresponding to the one or more multimedia that includes a time, a date, and a GPS-determined geotag indicating a geolocation where the one or more multimedia was recorded;

extracting temporal and spatial features from the multimedia, wherein the temporal and spatial features include terrain and topographic wind, building winds, city winds, heat island effects, lake effects, and mountain waves, wherein deducing the wind speed of the wind is further based on the extracted temporal and spatial features;

generating a wind map that layers the deduced wind speed over a map;

receiving user interaction with the wind map that modifies a zoom level and a time frame of the deduced wind speed;

retrieving a verified wind speed from a weather station within a threshold spatial proximity of the extracted geolocation and a threshold temporal proximity to the time and the date;

comparing the verified wind speed to the deduced wind speed; and

modifying the wind scale reference database based on the comparison.

2. The computer-implemented method of claim 1 , wherein extracting the contextual data corresponding to the one or more multimedia further comprises:

extracting an elevation of the wind recorded in the one or more multimedia.

3. The computer-implemented method of claim 1 , further comprising:

removing false positive multimedia from the one or more multimedia by applying natural language processing to the extracted contextual data.

4. The computer-implemented method of claim 2 , wherein extracting the contextual data corresponding to the one or more multimedia further comprises:

extracting a wind direction from the one or more multimedia;

extracting an atmospheric pressure from the one or more multimedia; and

extracting a temperature from the one or more multimedia.

5. A computer program product for generating a wind map based on multimedia analysis, the computer program product comprising:

one or more non-transitory computer-readable storage media and program instructions stored on the one or more non-transitory computer-readable storage media capable of performing a method, the method comprising:

deducing a wind speed of wind identified in one or more multimedia based on a wind scale reference database, wherein the one or more multimedia includes at least one of text, audio, image, and video; and wherein extracting the contextual data corresponding to the one or more multimedia further comprises:

transcribing the audio;

applying keyword searching and natural language processing to the transcribed audio and the text; and

applying image recognition technology to the image and the video;

extracting contextual data corresponding to the one or more multimedia that includes a time, a date, and a GPS-determined geotag indicating a geolocation where the one or more multimedia was recorded;

extracting temporal and spatial features from the multimedia, wherein the temporal and spatial features include terrain and topographic wind, building winds, city winds, heat island effects, lake effects, and mountain waves, wherein deducing the wind speed of the wind is further based on the extracted temporal and spatial features;

generating a wind map that layers the deduced wind speed over a map;

receiving user interaction with the wind map that modifies a zoom level and a time frame of the deduced wind speed;

retrieving a verified wind speed from a weather station within a threshold spatial proximity of the extracted geolocation and a threshold temporal proximity to the time and the date;

comparing the verified wind speed to the deduced wind speed; and

modifying the wind scale reference database based on the comparison.

6. The computer program product of claim 5 , wherein extracting the contextual data corresponding to the one or more multimedia further comprises:

extracting an elevation of the wind recorded in the one or more multimedia.

7. The computer program product of claim 5 , further comprising:

removing false positive multimedia from the one or more multimedia by applying natural language processing to the extracted contextual data.

8. The computer program product of claim 6 , wherein extracting the contextual data corresponding to the one or more multimedia further comprises:

extracting a wind direction from the one or more multimedia;

extracting an atmospheric pressure from the one or more multimedia; and

extracting a temperature from the one or more multimedia.

9. A computer system for generating a wind map based on multimedia analysis, the computer system comprising:

one or more computer processors, one or more computer-readable storage media, and program instructions stored on one or more of the computer-readable storage media for execution by at least one of the one or more processors capable of performing a method, the method comprising:

deducing a wind speed of wind identified in one or more multimedia based on a wind scale reference database, wherein the one or more multimedia includes at least one of text, audio, image, and video; and wherein extracting the contextual data corresponding to the one or more multimedia further comprises:

transcribing the audio;

applying keyword searching and natural language processing to the transcribed audio and the text; and

applying image recognition technology to the image and the video;

extracting contextual data corresponding to the one or more multimedia that includes a time, a date, and a GPS-determined geotag indicating a geolocation where the one or more multimedia was recorded;

extracting temporal and spatial features from the multimedia, wherein the temporal and spatial features include terrain and topographic wind, building winds, city winds, heat island effects, lake effects, and mountain waves, wherein deducing the wind speed of the wind is further based on the extracted temporal and spatial features;

generating a wind map that layers the deduced wind speed over a map;

receiving user interaction with the wind map that modifies a zoom level and a time frame of the deduced wind speed;

retrieving a verified wind speed from a weather station within a threshold spatial proximity of the extracted geolocation and a threshold temporal proximity to the time and the date;

comparing the verified wind speed to the deduced wind speed; and

modifying the wind scale reference database based on the comparison.

10. The computer system of claim 9 , wherein extracting the contextual data corresponding to the one or more multimedia further comprises:

extracting an elevation of the wind recorded in the one or more multimedia.

11. The computer system of claim 9 , further comprising:

removing false positive multimedia from the one or more multimedia by applying natural language processing to the extracted contextual data.

Assignments (5)
CORRECTIVE ASSIGNMENT TO CORRECT THE CONVEYING PARTY FROM IBM RESEARCH AND INTELLECTUAL PROPERTY TO INTERNATIONAL BUSINESS MACHINED CORPORATION AND TO CORRECT THE RECEIVING PARTY FROM ZEPHYR BUYER L.P. TO ZEPHYR BUYER, L.P. PREVIOUSLY RECORDED AT REEL: 66795 FRAME: 858. ASSIGNOR(S) HEREBY CONFIRMS THE ASSIGNMENT. Recorded Mar 20, 2024
From: INTERNATIONAL BUSINESS MACHINES CORPORATION
To: ZEPHYR BUYER, L.P.
Reel/Frame 066838/0157 →
CORRECTIVE ASSIGNMENT TO CORRECT THE CONVEYING PARTY NAME PREVIOUSLY RECORDED AT REEL: 66796 FRAME: 188. ASSIGNOR(S) HEREBY CONFIRMS THE ASSIGNMENT. Recorded Mar 20, 2024
From: ZEPHYR BUYER, L.P.
To: THE WEATHER COMPANY, LLC
Reel/Frame 067188/0894 →
ASSIGNMENT OF ASSIGNOR'S INTEREST Recorded Mar 13, 2024
From: IBM RESEARCH AND INTELLECTUAL PROPERTY
To: ZEPHYR BUYER L.P.
Reel/Frame 066795/0858 →
ASSIGNMENT OF ASSIGNOR'S INTEREST Recorded Mar 13, 2024
From: ZEPHYR BUYER L.P.
To: THE WEATHER COMPANY, LLC
Reel/Frame 066796/0188 →
ASSIGNMENT OF ASSIGNOR'S INTEREST Recorded Oct 23, 2018
From: MILMAN, IVAN M.; PANDIT, SUSHAIN; WOLFSON, CHARLES D.; LIU, SU; WANG, FANG
To: INTERNATIONAL BUSINESS MACHINES CORPORATION
Reel/Frame 047274/0061 →
Continuity (1)
Related Publication 20200124767A1 · Apr 23, 2020