Framework for anonymous reporting of social incidents

Patent metadata

Field	Value
Publication number	US-9779174-B2
Application number	US-201414274761-A
Country	US
Kind code	B2
Filing date	May 11, 2014
Priority date	May 11, 2014
Publication date	Oct 3, 2017
Grant date	Oct 3, 2017

Abstract

Described herein is a framework to facilitate anonymous reporting of social incidents. In accordance with one aspect of the framework, at least one input report of a social incident is received from at least one user device. The input report may be submitted by a user associated with verified credentials. An equivalence class may be identified for the input report. If a count associated with the equivalence class exceeds a predetermined threshold value, anonymized information based on the input report may be distributed to initiate action responsive to the social incident.

First claim

The invention claimed is:

1. An anonymous reporting system comprising:
a non-transitory memory device for storing computer-readable program code; and
a processor in communication with the memory device, the processor being operative with the computer-readable program code to
verify user credentials of reporting users wishing to submit social incident reports, wherein each social incident report includes personal information of the reporting users based on the user credentials and incident information of a social incident,
register, in response to successful verification of the user credentials, the verified reporting users, wherein the registration enables the verified reporting users to login to the anonymous reporting system to submit incident reports,
receive, from reporting user devices of the verified reporting users, incident reports of at least one social incident,
determine one or more equivalence classes of the incident reports by applying a classifier trained by a machine learning technique that identifies similar incident reports associated with multiple substantially matching parameter values, wherein one or more of said parameter values are associated with at least one victim of the at least one social incident,
select, from the one or more equivalence classes, an equivalence class with a count exceeding a predetermined threshold value,
transform the incident reports into anonymized incident reports, wherein the anonymized incident reports contain no personal information of the verified reporting users, and
distribute, to at least one client device, the anonymized incident reports of the selected equivalence class to initiate action responsive to the social incident by a client user of the client device.

2. The system of claim 1 wherein at least one of the one or more equivalence classes comprises incident reports received within a pre-defined timestamp window.

3. The system of claim 1 wherein the processor is operative with the computer-readable program code wherein each of the incident reports belongs to only one of the one or more equivalence classes.

4. The system of claim 3 wherein at least one of the substantially matching parameter values comprises a geographical location parameter value.

5. The system of claim 1 wherein the social incident comprises an abuse occurrence, a mental disability occurrence or a suspicious activity in a community.

6. A method of anonymous reporting performed by a computer system, comprising:
verifying user credentials of a reporting user wishing to submit a social incident report from a reporting user device;
registering, in response to successful verification of the user credentials, the verified reporting user, wherein the registration enables the verified reporting user to login to the anonymous reporting system to submit the incident report;
receiving, from the reporting user device, at least one input incident report of a social incident submitted by the verified reporting user, wherein the incident report includes personal information of the verified reporting user based on the user credentials and incident information of a social incident;
transforming the input incident report into an anonymized input incident report, the anonymized incident report contains no personal information of the verified reporting user;
storing the input anonymized incident report in an anonymous report storage containing previously submitted anonymized incident reports;
identifying an equivalence class for the input incident report based on the previously submitted anonymized incident reports stored in an incident report database by applying a classifier trained by a machine learning technique that identifies similar incident reports associated with multiple substantially matching parameter values, wherein one or more of said parameter values are associated with at least one victim of the social incident; and
distributing anonymized incident reports to initiate action responsive to the social incident of the anonymized input incident report, wherein the distributing is performed in response to a count associated with the equivalence class exceeding a predetermined threshold value.

7. The method of claim 6 wherein the social incident comprises an abuse occurrence, a mental disability occurrence or a suspicious activity in a community.

8. The method of claim 6 further comprising accepting the verified credentials of the reporting user from a trusted third party system and automatically registering the verified reporting user.

9. The method of claim 6 wherein the input incident report comprises a type of report parameter, a victim description parameter, a perpetrator description parameter, an incident description parameter, or a combination thereof.

10. The method of claim 6 wherein identifying the equivalence class for the input incident report comprises performing a range query to search for incident reports that are substantially similar to the input incident report.

11. The method of claim 6 wherein each of the incident reports belongs to only one of the one or more equivalence classes.

12. The method of claim 11 wherein the matching geographical location parameter value is within a predefined geographic boundary of a residential area.

13. The method of claim 6 further comprising performing causal analysis to determine why the social incident occurred.

14. The method of claim 13 wherein performing the causal analysis comprises comparing the input incident report against multiple causal parameters along a timeline.

15. The method of claim 6 wherein the count represents a number of reports with the equivalence class.

16. The method of claim 6 wherein the count represents a number of reporting users who have submitted incident reports within the equivalence class.

17. The method of claim 6 wherein distributing the anonymized incident reports comprises identifying one or more agencies responsible for the social incident type, and distributing the anonymized incident reports to the identified one or more agencies.

18. A non-transitory computer-readable medium having stored thereon program code, the program code executable by a computer to perform anonymous reporting comprising:
verifying user credentials of a reporting user wishing to submit a social incident report from a reporting user device;
registering, in response to successful verification of the user credentials, the verified reporting user, wherein the registration enables the verified reporting user to login to the anonymous reporting system to submit the incident report;
receiving, from the reporting user device, at least one input incident report of a social incident submitted by the verified reporting user, wherein the incident report includes personal information of the verified reporting user based on the user credentials and incident information of a social incident;
transforming the input incident report into an anonymized input incident report, the anonymized incident report contains no personal information of the verified reporting user;
storing the input anonymized incident report in an anonymous report storage containing previously submitted anonymized incident reports;
identifying an equivalence class for the input incident report based on the previously submitted anonymized incident reports stored in an incident report database by applying a classifier trained by a machine learning technique that identifies similar incident reports associated with multiple substantially matching parameter values, wherein one or more of said pa

Assignees

• Sap Se

Inventors

• Sheik Adam Mohammed Arshad
• Nath Kaushik

Classifications

• H04L63/0407

  wherein the identity of one or more communicating identities is hidden (cryptographic mechanisms or cryptographic arrangements for anonymous credentials or for identity based cryptographic systems H04L9/00) · CPC title

• G06F16/958 Primary

  Organisation or management of web site content, e.g. publishing, maintaining pages or automatic linking · CPC title

• G06F16/2322

  using timestamps · CPC title

• G06F16/21

  Design, administration or maintenance of databases · CPC title

• G06F16/951

  Indexing; Web crawling techniques · CPC title