US2021081556A1PendingUtilityA1

Detecting events from features derived from ingested signals

Assignee: SAFEXAI INCPriority: Feb 9, 2018Filed: Nov 17, 2020Published: Mar 18, 2021
Est. expiryFeb 9, 2038(~11.6 yrs left)· nominal 20-yr term from priority
H04L 63/0428H04L 63/04G06F 21/6218G06F 21/554G06F 21/604
59
PatentIndex Score
0
Cited by
0
References
0
Claims

Abstract

The present invention extends to methods, systems, and computer program products for detecting events from features derived from ingested signals. A first signal (e.g., a private signal private to an organization or non-private signal controlled by an organization) is accessed based on organizational data privacy access settings associated with the first signal. First one or more features of the first normalized signal are derived. It is determined that the first one or more features do not satisfy conditions to be identified as an event. The first one or more features are aggregated with second one or more features of a second signal into aggregated features. Access to the aggregated features is configured based on data privacy aggregation settings associated with the first signal and data privacy aggregation settings associated with the second signal. An event is detected from the aggregated features.

Claims

exact text as granted — not AI-modified
What is claimed: 
     
         1 . A system comprising:
 a processor;   system memory coupled to the processor and storing instructions configured to cause the processor to:
 access a normalized private signal defined as private to a first organization based on organizational data privacy access settings; 
 derive first one or more features of the normalized private signal; 
 determine that the first one or more features do not satisfy conditions to be identified as an event; 
 access a normalized non-private signal from a second organization; 
 determine that a first data privacy aggregation setting associated with the first organization permits aggregating the normalized private signal with non-private data signals of the second organization; 
 derive second one or more features of the normalized non-private signal; 
 determine that a second data privacy aggregation setting associated with the second organization permits aggregating the normalized non-private signal with signals of the first organization; 
 aggregate the first one or more features with the second one or more features into aggregated features; 
 configure aggregated feature access control based at least on the organizational data privacy access settings;
 detect an event from the aggregated features; 
 receive a first entity request to utilize the event; and 
 control first entity access to the event in accordance with the configured access control. 
 
   
     
     
         2 . The system of  claim 1 , wherein instructions configured to aggregate the first one or more features with the second one or more features comprise instructions configured to:
 detect a possible event from the first one or more features; and   validate the possible event as an actual event based on the second one or more features.   
     
     
         3 . The system of  claim 1 , further comprising instructions configured to:
 include the normalized private signal in a signal sequence;   determine that the normalized non-private data signal has sufficient temporal similarity to the normalized private signal;   determining that the normalized non-private data signal has sufficient spatial similarity to the normalized private signal; and   include the normalized non-private data signal in the signal sequence.   
     
     
         4 . The system of  claim 3 , wherein instructions configured to aggregate the first one or more features with the second one or more features into aggregated features comprise instructions configured to derive features of the signal sequence from the first one or more features and the second one or more features. 
     
     
         5 . The method of  claim 4 , wherein instructions configured to derive features of the signal sequence comprises instructions configured to derive one or more of: a percentage, a count, a histogram, or a duration. 
     
     
         6 . The system of  claim 1 , wherein accessing a normalized private signal comprises accessing one of: an image, a 911 call, weather data, IoT device data, a sound clip, air quality sensor data, traffic information, or road information. 
     
     
         7 . The system of  claim 1 , further comprising instructions configured to:
 receive a second entity request to utilize the event; and   deny second entity access to the event in accordance with the configured access control.   
     
     
         8 . The system of  claim 1 , wherein instructions configured to access a normalized non-private signal from a second organization comprise instructions configured to access a public signal. 
     
     
         9 . The system of  claim 1 , wherein instructions configured to control first entity access to the event comprise instructions configured to deny first entity access to the event. 
     
     
         10 . The system of  claim 9 , wherein instructions configured to deny first entity access to the event comprise instructions configured to:
 determine that an entity is permitted to access the second one or more features; and   determine that the entity is not permitted to access the first one or more features.   
     
     
         11 . A system comprising:
 a processor;   system memory coupled to the processor and storing instructions configured to cause the processor to:
 access a first normalized non-private signal of a first organization defined as non-private based on first organizational data privacy access settings; 
 derive first one or more features of the first normalized non-private signal; 
 determine that the first one or more features do not satisfy conditions to be identified as an event; 
 access a second normalized non-private signal of a second organization defined as non-private based on second organizational data privacy access settings; 
 derive second one or more features of the second normalized non-private signal; 
 determine that a first data privacy aggregation setting of the first organization permits aggregating the first normalized non-private data signal with non-private data signals of the second organization; 
 determine that a second data privacy aggregation setting of the second organization permits aggregating the second normalized non-private data signal with non-private data signals of the first organization; 
 aggregate the first one or more features with the second one or more features into aggregated features; 
 configure aggregated feature access control based at least on the first organizational data privacy access settings and the second organizational data privacy access settings; 
 detect an event from the aggregated features; 
 receive a first entity request to utilize the event; and 
 control first entity access to the event in accordance with the configured access control. 
   
     
     
         12 . The system of  claim 11 , wherein instructions configured to aggregate the first one or more features with the second one or more features into aggregated features comprise instructions configured to:
 detect a possible event from the first one or more features; and   validate the possible event as an actual event based on the second one or more features.   
     
     
         13 . The method of  claim 11 , further comprising:
 include the first normalized non-private signal in a signal sequence;   determine that the second non-private signal has sufficient temporal similarity to the first normalized non-private signal;   determine that the second non-private signal has sufficient spatial similarity to the first normalized non-private signal; and   include the second non-private signal in the signal sequence.   
     
     
         14 . The system of  claim 13 , wherein instructions configured to aggregate the first one or more features with the second one or more features into aggregated features comprise instructions configured to derive features of the signal sequence from the first one or more features and the second one or more features. 
     
     
         15 . The system of  claim 14 , wherein instructions configured to derive features of the signal sequence comprise instructions configured to derive one or more of: a percentage, a count, a histogram, or a duration. 
     
     
         16 . The system of  claim 11 , wherein accessing a first normalized non-private signal comprises accessing one of: an image, a 911 call, weather data, IoT device data, a sound clip, air quality sensor data, traffic information, or road information. 
     
     
         17 . The system of  claim 11 , further comprising instructions configured to:
 receive a second entity request to utilize the event; and   deny second entity access to the event in accordance with the configured access control.   
     
     
         18 . The system of  claim 11 , wherein instructions configured to access a normalized non-private signal from a second organization comprise instructions configured to access a public signal. 
     
     
         19 . The system of  claim 11 , wherein instructions configured to control first entity access to the event comprise instructions configured to deny first entity access to the event. 
     
     
         20 . The system of  claim 19 , wherein instructions configured to deny first entity access to the event comprise instructions configured to:
 determine that an entity is permitted to access the second one or more features; and   determine that the entity is not permitted to access the first one or more features.

Join the waitlist — get patent alerts

Track US2021081556A1 — get alerts on status changes and closely related new filings.

We store only your email — no account needed. See our privacy policy.