Event detection from signal data removing private information
The present invention extends to methods, systems, and computer program products for event detection from signal data removing private information. A signal is ingested. A portion of the signal is selected from within the signal. A first score is computed from the selected portion. The first score indicates a likelihood of the signal including information related to an event type. It is determined that processing of another signal is warranted based on the indicated likelihood. Resources are allocated to process the other signal. The other signal is ingested. Parameters associated with the other signal are accessed. A second score is computed from the parameters utilizing the allocated resources. A previously unidentified event of the event type is identified based on the second score and utilizing the allocated resources. A privacy infrastructure spans signal ingestion, event detection, and event notification and protects the integrity of private information.
1. A method comprising:
ingesting a signal that includes sensitive user information;
removing at least a portion of the sensitive user information from the signal;
subsequent to removing the at least a portion of the sensitive user information, computing a first score from a portion of the signal and indicating a likelihood of the signal including event information related to an event type;
determining processing of another signal is warranted based on the indicated likelihood;
allocating computing resources to process the other signal;
computing a second score from parameters associated with the other signal utilizing the allocated computing resources; and
detecting a previously unidentified event of the event type based on the second score.
2. The method of claim 1 , wherein ingestion a signal comprises ingesting a signal that includes one or more of: confidential information, patient information, personally identifiable information (PII), personal health information (PHI), sensitive personal information (SPI), or Payment Card Industry information (PCI).
3. The method of claim 1 , wherein removing at least a portion of the sensitive user information from the signal comprises removing one or more of: confidential information, patient information, personally identifiable information (PII), personal health information (PHI), sensitive personal information (SPI), or Payment Card Industry information (PCI) from the signal.
4. The method of claim 1 , wherein ingesting a signal that includes sensitive user information comprises ingesting a signal that includes pandemic related information;
wherein removing at least a portion of the sensitive user information from the signal comprises removing a portion of the pandemic related information; and
wherein detecting a previously unidentified event of the event type comprises detecting one of: when and where pandemic symptoms are occurring, an indication of tests given and positive diagnoses related to a pandemic, emergency department waiting times, or medical equipment availability.
5. The method of claim 1 , wherein ingesting a signal comprises ingesting a database signal;
wherein computing a first score from a portion of the signal comprises computing a first score from a portion of the database signal; and
wherein detecting a previously unidentified event of the event type comprises detecting an available bed at a treatment facility.
6. The method of claim 1 , wherein computing a first score from a portion of the signal comprises computing a first score from a portion of a text stream; and
wherein computing a second score from parameters associated with the other signal comprises computing the second score from parameters associated with one of:
an audio stream, a video stream, or a sensor data stream.
7. The method of claim 1 , wherein computing a first score from a portion of the signal comprises computing a first score from a portion of a video stream; and
wherein computing a second score from parameters associated with the other signal comprises computing the second score from parameters associated with one of: an audio stream, a text stream, or a sensor data stream.
8. The method of claim 1 , wherein computing a first score from a portion of the signal comprises computing a first score from a portion of a sensor data stream; and
wherein computing a second score from parameters associated with the other signal comprises computing the second score from parameters associated with one of: an audio stream, a video stream, or a text stream.
9. The method of claim 1 , wherein computing a first score from a portion of the signal comprises computing the first score subsequent to removing the at least a portion of the user information.
10. The method of claim 1 , further comprising:
accessing the other signal including other user information;
removing at least a portion of the other user information from the other signal;
deriving the parameters associated with the other signal subsequent to removing the at least a portion of the other user information.
11. A system comprising:
a processor;
system memory coupled to the processor and storing instructions configured to cause the processor to:
ingest a signal that includes sensitive user information;
remove at least a portion of the sensitive user information from the signal;
subsequent to removing the at least a portion of the sensitive user information, compute a first score from a portion of the signal and indicating a likelihood of the signal including event information related to an event type;
determine processing of another signal is warranted based on the indicated likelihood;
allocate computing resources to process the other signal;
compute a second score from parameters associated with the other signal utilizing the allocated computing resources; and
detect a previously unidentified event of the event type based on the second score.
12. The computer system of claim 11 , wherein instructions configured to ingest a signal comprise instructions configured to ingest a signal that includes one or more of:
confidential information, patient information, personally identifiable information (PII), personal health information (PHI), sensitive personal information (SPI), or Payment Card Industry information (PCI).
13. The system of claim 11 , wherein instructions configured to remove at least a portion of the sensitive user information from the signal comprises instructions configured to remove one or more of: confidential information, patient information, personally identifiable information (PII), personal health information (PHI), sensitive personal information (SPI), or Payment Card Industry information (PCI) from the signal.
14. The system of claim 11 , wherein instructions configured to ingest a signal that includes sensitive user information comprise instructions configured to ingest a signal that includes pandemic related information;
wherein instructions configured to remove at least a portion of the sensitive user information from the signal comprise instructions configured to remove a portion of the pandemic related information; and
wherein instructions configured to detect a previously unidentified event of the event type comprise instructions configured to detect one of: when and where pandemic symptoms are occurring, an indication of tests given and positive diagnoses related to a pandemic, emergency department waiting times, or medical equipment availability.
15. The system of claim 11 , wherein instructions configured to ingest a signal comprise instructions configured to ingest a database signal;
wherein instructions configured to compute a first score from a portion of the signal comprise instructions configured to compute a first score from a portion of the database signal; and
wherein instructions configured to detect a previously unidentified event of the event type comprise instructions configured to detect an available bed at a treatment facility.
16. The system of claim 11 , wherein instructions configured to compute a first score from a portion of the signal comprise instructions configured to compute a first score from a portion of a text stream; and
wherein instructions configured to compute a second score from parameters associated with the other signal comprises instructions configured to compute the second score from parameters associated with one of: an audio stream, a video stream, or a sensor data stream.
17. The system of claim 11 , wherein instructions configured to compute a first score from a portion of the signal comprise instructions configured to compute a first score from a portion of a video stream; and
wherein instructions configured to compute a second score from parameters associated with the other signal comprise instructions configured to compute the second score from parameters associated with one of: an audio stream, a text stream, or a sensor data stream.
18. The system of claim 11 , wherein instructions configured to compute a first score from a portion of the signal comprise instructions configured to compute a first score from a portion of a sensor data stream; and
wherein instructions configured to compute a second score from parameters associated with the other signal comprise instructions configured to compute the second score from parameters associated with one of: an audio stream, a video stream, or a text stream.
19. The system of claim 11 , wherein instructions configured to compute a first score from a portion of the signal comprise instructions configured to compute the first score subsequent to removing the at least a portion of the user information.
20. The system of claim 11 , further comprising instructions configured to:
access the other signal including other user information;
remove at least a portion of the other user information from the other signal;
derive the parameters associated with the other signal subsequent to removing the at least a portion of the other user information.