Researchers Submit Patent Application, “Systems and Methods for Disturbance Detection and Identification Based on Disturbance Analysis”, for Approval (USPTO 20230326322): Allstate Insurance Company

2023 OCT 26 (NewsRx) -- By a News Reporter-Staff News Editor at Insurance Daily News -- From Washington, D.C., NewsRx journalists report that a patent application by the inventors Florescu, Corina (Northbrook, IL, US); Giri, Deepak Baban (Northbrook, IL, US); Kottegoda, Manjula (Northbrook, IL, US), filed on March 3, 2023, was made available online on October 12, 2023.

The patent’s assignee is Allstate Insurance Company (Northbrook, Illinois, United States).

News editors obtained the following quote from the background information supplied by the inventors: “Older models of smart devices tend to be recycled or otherwise discarded upon a user purchasing a newer model. Such devices, however, are still capable of being used with their computational architecture for different applications. Accordingly, a need exists for alternative solutions to repurpose and utilize the older models of the smart devices.”

As a supplement to the background information on this patent application, NewsRx correspondents also obtained the inventors’ summary information for this patent application: “According to the subject matter of the present disclosure, an intelligent disturbance detection system may include a mobile smart device remote from a user, an application tool downloaded on the mobile smart device, the application tool comprising a disturbance detection neural network model and a disturbance set, the disturbance set comprising one or more disturbance labels, one or more processors communicatively coupled to the application tool, one or more memory components communicatively coupled to the one or more processors, and machine readable instructions stored in the one or more memory components. The machine readable instructions may cause the intelligent disturbance detection system to perform at least the following when executed by the one or more processors: capture a disturbance comprising a sound, an image, or combinations thereof via the application tool on the mobile smart device remote from the user, extract features from the disturbance to generate one or more extracted features, compare the one or more extracted features to the one or more disturbance labels in a comparison by the disturbance detection neural network model, and generate a disturbance label from the one or more disturbance labels when the one or more extracted features match the disturbance label in the comparison. The machine readable instructions may further cause the intelligent disturbance detection system to perform at least the following when executed by the one or more processors: train the disturbance detection neural network model to generate a custom disturbance label associated with the one or more extracted features when the one or more extracted features do not match the one or more disturbance labels in the comparison, and generate an automatic alert via the mobile smart device to transmit an identification of the disturbance to the user based on the disturbance label, the custom disturbance label, or combinations thereof.

“According to another embodiment of the present disclosure, a method of implementing an intelligent disturbance detection system may include capturing a disturbance comprising a sound, an image, or combinations thereof via an application tool on a mobile smart device of the intelligent disturbance detection system remote from a user, extracting features from the disturbance to generate one or more extracted features, comparing the one or more extracted features to one or more disturbance labels of a disturbance set in a comparison by a disturbance detection neural network model of the application tool, generating a disturbance label from the one or more disturbance labels when the one or more extracted features match the disturbance label in the comparison. The method may further include training the disturbance detection neural network model to generate a custom disturbance label associated with the one or more extracted features when the one or more extracted features do not match the one or more disturbance labels in the comparison, and generating an automatic alert via the mobile smart device to transmit an identification of the disturbance to the user based on the disturbance label, the custom disturbance label, or combinations thereof.

“According to yet another embodiment of the present disclosure, a method of implementing an intelligent disturbance detection system may include capturing a disturbance comprising a sound, an image, or combinations thereof via an application tool on a mobile smart device of the intelligent disturbance detection system remote from a user, extracting features from the disturbance to generate one or more extracted features, comparing the one or more extracted features to one or more disturbance labels of a disturbance set in a comparison by a disturbance detection neural network model of the application tool, generating a disturbance label from the one or more disturbance labels when the one or more extracted features match the disturbance label in the comparison, and training the disturbance detection neural network model to generate a custom disturbance label associated with the one or more extracted features when the one or more extracted features do not match the one or more disturbance labels in the comparison. The method may further include generating an automatic alert via the mobile smart device to transmit an identification of the disturbance to the user based on the disturbance label, the custom disturbance label, or combinations thereof, wherein the automatic alert comprises a timestamp and a confidence level associated with the identification of the disturbance.

“Although the concepts of the present disclosure are described herein with primary reference to a disturbance detection solution of a home environment, it is contemplated that the concepts will enjoy applicability to any setting for purposes of disturbance detection solutions, such as alternative business settings or otherwise.”

The claims supplied by the inventors are:

“1. An intelligent disturbance detection system comprising: an application tool executed by a mobile smart device, the application tool comprising a disturbance detection neural network model and a disturbance set, the disturbance set comprising one or more disturbance labels; one or more processors communicatively coupled to the application tool; one or more memory components communicatively coupled to the one or more processors; and machine readable instructions stored in the one or more memory components that cause the intelligent disturbance detection system to perform at least the following when executed by the one or more processors: capture a disturbance comprising a sound, an image, or combinations thereof via the application tool on the mobile smart device remote from a user; extract features from the disturbance to generate one or more extracted features; compare the one or more extracted features to the one or more disturbance labels in a comparison by the disturbance detection neural network model; generate a disturbance label from the one or more disturbance labels when the one or more extracted features match the disturbance label in the comparison; train the disturbance detection neural network model to generate a new disturbance label for the disturbance set associated with the one or more extracted features when the one or more extracted features do not match the one or more disturbance labels in the comparison; and generate an automatic alert via the mobile smart device to transmit an identification of the disturbance to the user based on the disturbance label, the new disturbance label, or combinations thereof, wherein the automatic alert comprises a display graph over a period of time, the display graph over the period of time comprising at least one disturbance time portion associated with the identification of the disturbance.

“2. The intelligent disturbance detection system of claim 1, wherein the automatic alert comprises a text to the user, an email to the user, or combinations thereof.

“3. The intelligent disturbance detection system of claim 1, further comprising machine readable instructions that cause the intelligent disturbance detection system to perform at least the following when executed by the one or more processors: transmit the automatic alert to a second device of the user.

“4. The intelligent disturbance detection system of claim 1, further comprising machine readable instructions that cause the intelligent disturbance detection system to perform at least the following when executed by the one or more processors: generate the automatic alert based on a frequency associated with the automatic alert, the frequency comprising a number of times to send the automatic alert, a time period within which to send the automatic alert as one or more alerts, a time period between each subsequent automatic alert of the automatic alert, or combinations thereof.

“5. The intelligent disturbance detection system of claim 1, wherein the automatic alert comprises a timestamp associated with the identification of the disturbance.

“6. The intelligent disturbance detection system of claim 1, wherein the automatic alert comprises a confidence level associated with the identification of the disturbance.

“7. The intelligent disturbance detection system of claim 1, wherein the display graph comprises at least one time portion not associated with the identification of the disturbance.

“8. The intelligent disturbance detection system of claim 1, wherein the at least one disturbance time portion is associated with a disturbance detection, the disturbance detection comprising the identification of the disturbance, an identification of another disturbance from the disturbance set, or combinations thereof.

“9. The intelligent disturbance detection system of claim 8, wherein the display graph over the period of time comprises at least one time portion not associated with the disturbance detection.

“10. The intelligent disturbance detection system of claim 1, wherein the disturbance label comprises the identification of one of a dog barking sound, a fire alarm sound, or a doorbell ringing sound.

“11. The intelligent disturbance detection system of claim 1, wherein the new disturbance label comprises the identification of a door opening sound.

“12. The intelligent disturbance detection system of claim 1, wherein the application tool is configured to transmit instructions to add the new disturbance label to the disturbance set based on an approval of the user, the approval of the user comprising a user setting of the new disturbance label.

“13. The intelligent disturbance detection system of claim 12, wherein the user setting comprises a naming of the new disturbance label, an upload by the user of an image for the new disturbance label, or combinations thereof.

“14. The intelligent disturbance detection system of claim 1, further comprising machine readable instructions that cause the intelligent disturbance detection system to perform at least the following when executed by the one or more processors: upload an image associated with the new disturbance label; and add the new disturbance label to the disturbance set.

“15. A method of implementing an intelligent disturbance detection system, the method comprising: capturing a disturbance comprising a sound, an image, or combinations thereof via an application tool on a mobile smart device of the intelligent disturbance detection system remote from a user; extracting features from the disturbance to generate one or more extracted features; comparing the one or more extracted features to one or more disturbance labels of a disturbance set in a comparison by a disturbance detection neural network model of the application tool; generating a disturbance label from the one or more disturbance labels when the one or more extracted features match the disturbance label in the comparison; training the disturbance detection neural network model to generate a new disturbance label for the disturbance set associated with the one or more extracted features when the one or more extracted features do not match the one or more disturbance labels in the comparison; and generating an automatic alert via the mobile smart device to transmit an identification of the disturbance to the user based on the disturbance label, the new disturbance label, or combinations thereof, wherein the automatic alert comprises a display graph over a period of time, the display graph over the period of time comprising at least one disturbance time portion associated with the identification of the disturbance.

“16. The method of claim 15, further comprising: generating the automatic alert based on a frequency associated with the automatic alert, the frequency comprising a number of times to send the automatic alert as one or more alerts, a time period within which to send the automatic alert as the one or more alerts, a time period between each subsequent automatic alert of the automatic alert, or combinations thereof.

“17. The method of claim 16, further comprising: setting by the user a name of the new disturbance label during an approval of the user; uploading by the user an image for the new disturbance label during the approval of the user; and adding the new disturbance label to the disturbance set based on the approval of the user.

“18. A method of implementing an intelligent disturbance detection system, the method comprising: capturing a disturbance comprising a sound, an image, or combinations thereof via an application tool on a mobile smart device of the intelligent disturbance detection system remote from a user; extracting features from the disturbance to generate one or more extracted features; comparing the one or more extracted features to one or more disturbance labels of a disturbance set in a comparison by a disturbance detection neural network model of the application tool; generating a disturbance label from the one or more disturbance labels when the one or more extracted features match the disturbance label in the comparison; training the disturbance detection neural network model to generate a new disturbance label for the disturbance set associated with the one or more extracted features when the one or more extracted features do not match the one or more disturbance labels in the comparison; generating an automatic alert via the mobile smart device to transmit an identification of the disturbance to the user based on the disturbance label, the new disturbance label, or combinations thereof, wherein the automatic alert comprises a timestamp and a confidence level associated with the identification of the disturbance; and generating the automatic alert based on a frequency associated with the automatic alert, the frequency comprising a number of times to send the automatic alert, a time period within which to send the automatic alert as one or more alerts, a time period between each subsequent automatic alert of the automatic alert, or combinations thereof.

“19. The method of claim 18, wherein the automatic alert further comprises a display graph over a period of time, the display graph over the period of time comprising at least one disturbance time portion associated with the identification of the disturbance.”

For additional information on this patent application, see: Florescu, Corina; Giri, Deepak Baban; Kottegoda, Manjula. Systems and Methods for Disturbance Detection and Identification Based on Disturbance Analysis. U.S. Patent Application Number 20230326322, filed March 3, 2023 and posted October 12, 2023. Patent URL (for desktop use only): https://ppubs.uspto.gov/pubwebapp/external.html?q=(20230326322)&db=US-PGPUB&type=ids

(Our reports deliver fact-based news of research and discoveries from around the world.)