System and method for smart public alerts and notifications

• US 10,074,052 B2
• Filed: 12/05/2013
• Issued: 09/11/2018
• Est. Priority Date: 01/16/2013
• Status: Active Grant

• Current Assignee: TATA Consultancy Services Limited (Tata Sons Pvt Ltd.)
• Original Assignee: TATA Consultancy Services Limited (Tata Sons Pvt Ltd.)
• Inventors: Banerjee, Snehasis, Mukherjee, Debnath, Misra, Prateep
• Primary Examiner(s): Misir, Dave
• Application Number:
  US14/761,463
• Publication Number:
  US 20150363694A1
• Time in Patent Office: 1,741 Days
• Field of Search: 706 46
• CPC Class Codes: G06F 9/542 Event management; Broadcasting; Multicasting; Notifications
• CPC Class Codes: G06N 5/02 Knowledge representation; Symbolic representation
• CPC Class Codes: G06Q 30/02 Marketing; Price estimation or determination; Fundraising
• CPC Class Codes: H04L 67/306 User profiles
• CPC Class Codes: H04L 67/52 specially adapted for the location of the user terminal
• CPC Class Codes: H04L 67/55 Push-based network services

Abstract

Disclosed is a method and system for dynamically generating a customized, personalized and contextual alert for a user based upon personalized, contextual and background knowledge associated with the profile of the user. The system comprises a profile updater module configured to update the profile data of the user extracted either from the social web or from the user. Further, a reasoning module is configured to derive refined background knowledge in context with the updated profile data of the user. A monitoring module is configured to monitor the events sensed by a sensing module. A context extractor module is configured for extracting the context of the events and the context of the user. A knowledge converter module is configured to convert the extracted context into structured format. Finally, the refined background knowledge is steam reasoned to determine whether the events received are relevant to the user and accordingly transmitted.

Claims

1. A method for transmitting at least one real-time customized notification alert to an electronic communication device of at least one user characterized by enabling a software-based platform to process a profile data and a contextual data associated with the at least one user to generate the customized notification, the method comprising computer-implemented steps of:

acquiring the profile data for the user, wherein the profile data comprises user specific contextual information, demographic profile and a list of event types for which a notification alert in a specific format is desired;

pre-processing, filtering, extending and on-demand loading or unloading structured background knowledge comprising geographical information and changing information about a plurality of users in order to derive a refined structured background knowledge relevant to the profile data for the at least one user using a set of one or more rules or one or more queries registered through an application program module communicatively coupled to the electronic communication device;

receiving at least one raw event feed from one or more heterogeneous sources in assorted data formats, wherein the heterogeneous sources are a part of sensor network communicating with the electronic communication device though a communication network;

determining a raw event data and a raw context data from the received raw event feed by using a context mapping database storing the user specific contextual information, wherein the received raw event feed is of at least one data format selected from a group comprising of text, image, video, audio, multimedia and combinations thereof, and wherein the raw event data is selected from a group comprising of traffic jams, robbery, flood, climate updates, traffic accident, road blockage, criminal activity, mutually affecting event among multiple users and combinations thereof;

converting the raw event data and the raw context data into a structured knowledge format;

loading a combined structured knowledge comprising the refined structured background knowledge, the structured raw event data and the structured raw context data into a stream reasoning module;

applying stream reasoning by querying the combined structured knowledge to determine if the received raw event feed is relevant to the acquired profile data and the user-specific contextual information for the user; and

transmitting the notification alert on the electronic communication device of the user in the specified format if the received raw event feed is identified as relevant by the applied stream reasoning.

2. The method of claim 1, wherein the user-specific contextual information includes current and future context data about the user which is either retrieved through a social web using mining technique or is manually inputted by the user through the electronic communication device or is tracked through a GPS device in the electronic communication device.

3. The method of claim 1, wherein the demographic profile is automatically mined through a social web or is manually inputted by the user through the electronic communication device, and wherein the demographic profile includes name, age, sex, location, religion, family details, job profile, places of interests, relatives or combinations thereof.

4. The method of claim 1, wherein the geographical information comprises the knowledge about a particular location such as a city, streets in the city, points of interest in the city, nearby locations to the city and combinations thereof, and wherein the changing information comprises dynamic variance in preference information of the user and the user profile data.

5. The method of claim 1, wherein the pre-processing step comprises identifying domain-dependent knowledge from the background knowledge corresponding to data needed for generating relevant alerts for the user.

6. The method of claim 1, wherein the filtering step comprises selecting at least one knowledge dataset from the background knowledge that is relevant to data needed for generating relevant alerts for the user.

7. The method of claim 1, wherein the extending step comprises identifying at least one new knowledge dataset that is relevant to data needed for generating relevant alerts for the user and not present in the background knowledge.

8. The method of claim 1, wherein the on-demand loading step comprises loading of ad-hoc knowledge required by the stream reasoning for processing of the background knowledge in context with data needed for generating relevant alerts for the user, and wherein the on-demand unloading step comprises unloading of knowledge required by the stream reasoning from the background knowledge that is irrelevant to application needed data for generating relevant alerts for the user.

9. The method of claim 1, wherein the one or more heterogeneous sources are selected from a group comprising physical sensors, soft sensors, social web, Personal calendar, Historical behavior Pattern, Social media updates, RSS feeds, news agencies, dynamically changing contextual information such as GPS location and combinations thereof.

10. The method of claim 1, wherein the raw context data comprises information related to said raw event data selected from a group comprising time, location, current and future activity, environmental conditions and combinations thereof.

11. The method of claim 1, wherein the raw event data and the raw context data are converted into the structured knowledge format using keyword pattern matching, information extraction techniques, Natural-Language Processing (NLP) algorithms and combinations thereof, and wherein the structured knowledge format is one of a Triple, n-triple, Resource Description Framework (RDF), Web Ontology Language (OWL) and combinations thereof.

12. The method of claim 1, wherein the electronic communication device is capable of displaying customized alert into at least one data format selected from a group comprising a text data, an audio data, a video data, an image data, a multimedia data, live multimedia streaming and combinations thereof.

13. A system for transmitting at least one real-time customized notification alert to at least one user, the system comprising:

at least one electronic communication device;

a sensor network comprising one or more sensor devices;

a smart public alert system communicatively coupled with the at least one electronic communication device and the sensor network through a communication network;

the at least one electronic communication device further comprising a user interface unit configured for retrieving relevant alerts and updating the user profile data;

the smart public alert system further comprising;

at least one processor electronically coupled with a memory, the memory comprising a plurality of modules executed by the at least one processor, the modules comprising;

a profile database storing profile data related to plurality of users, wherein the profile data comprises user specific contextual information, demographic profile and a list of event types for which a notification alert in a specific format is desired;

a reasoning module configured for reasoning a background knowledge module to pre-process, filter and extend a background knowledge stored in the background knowledge module to derive a refined structured background knowledge;

a sensing module configured to sense at least one raw event feed from the at least one sensor device in the sensor network or the at least one electronic communication device;

a monitoring module adapted to monitor the raw event feed sensed and to determine a raw event data and a raw context data from the received raw event feed, wherein the raw event feed is of at least one data format selected from a group comprising of text, image, video, audio, multimedia and combinations thereof, and wherein the raw event data is selected from a group comprising of traffic jams, robbery, flood, climate updates, traffic accident, road blockage, criminal activity, mutually affecting event among multiple users and combinations thereof;

a context extractor module configured for extracting context from the electronic communication device and the monitoring module using a context mapping database storing the user specific contextual information;

a knowledge converter module configured to convert the raw event data and the raw context data into a structured knowledge format;

loading a combined structured knowledge comprising the refined structured background knowledge, the structured raw event data and the structured raw context data into a stream reasoning module;

applying stream reasoning by querying the combined structured knowledge to determine if the sensed raw event feed is relevant to the profile data and the user-specific contextual information for the user;

an application program module configured for processing alerts output from the stream reasoning module, transmitting the alerts to the electronic communication device and registering rules and queries received through the user interface unit to obtain the relevant alerts; and

the stream reasoning module in response to the queries and rules registered adapted to stream reasoned the refined structured background knowledge, the structured raw event data and the structured raw context data to determine if the raw event feed is relevant to the profile data and the user-specific contextual information of the user and accordingly transmit the notification alert to the user interface unit through the application program module if the raw event feed is determined as relevant.

14. The system of claim 13, wherein the stream reasoning module further comprises a memory unit for storing the structured knowledge in at least one format selected from a group comprising of a Triple, n-triple, Resource Description Framework (RDF), Web Ontology Language (OWL) or combinations thereof.

15. The system of claim 13, wherein the application program module further comprises:

a profile updater configured for updating the profile data including the user-specific contextual information and the demographic profile mined through the profile database;

a query listener adapted to monitor query results coming from the stream reasoning module;

an alert processor adapted to transmit the notification alert generated based on processing of results of query execution and

an alert translator configured for translating the generated notification alert in to user-specified format before transmitting the alert to the electronic communication device.

16. The system of claim 13, wherein the raw event data and the raw context data are converted into the structured knowledge format using keyword pattern matching, information extraction techniques, Natural-Language Processing (NLP) algorithms and combinations thereof, and wherein the structured knowledge format is one of a Triple, n-triple, Resource Description Framework (RDF), Web Ontology Language (OWL) and combinations thereof.