Granted Patent B2

US 9,128,959 · App. 14/049,199 · Granted Sep 8, 2015

Abstract

Claims (29)

1. A crowdsourced search and locate platform, comprising:

an application server computer comprising at least a memory and a processor coupled to a digital packet network

and programmable instructions stored in the memory and operable in the processor to provide a client interface application wherein the instructions are adapted to a crowdsourced search and locate platform comprising:

a first list of geolocations corresponding to a plurality of crowdsourced participants stored in a database;

a second list of geolocations corresponding to images stored in the database;

wherein the client interface application:

sends images to crowdsourced participants wherein the corresponding geolocation of the second list is substantially the same as the geolocation of the first list;

receives tagging data from the crowdsourced participants, the tagging data corresponding to a plurality of objects and locations identified by the crowdsourced participants;

displays a first plurality of elements enabling an administrative user to configure a crowdsourced search and locate campaign;

displays a second plurality of elements enabling an administrative user to configure and run a crowdrank algorithm, wherein the crowdrank algorithm takes as input a large number of object tags created by participating users in the crowdsourced search and locate campaign and determines a most likely distribution of actual locations of objects of interest;

displays a plurality of image strips that were viewed by participating users in the crowdsourced search and locate campaign; and

upon the user's selecting a particular object type icon, displays all or a substantial portion of tags of the type selected that were generated by participating users in the crowdsourced search and locate campaign, by placing visual indicators at each tagged location of objects of the selected type within the plurality of image strips;

wherein the crowdrank algorithm performs the steps of:

computing a vector of agreement and disagreement values for each of the plurality of retrieved tags, wherein each agreement or disagreement value is determined by comparing a distance between a location associated with a first retrieved tag with which a first vector is associated and a location associated with a second retrieved tag; and

automatically performs an expectation-maximization or expectation-minimization process iteratively until a configured maximum number of iterations is performed or until an indicia of rate of change between iterations falls below a configured threshold.

2. A method for conducting crowdsourced search and locate operations, the method comprising:

an application server computer comprising at least a memory and a processor coupled to a digital packet network and programmable instructions stored in the memory and operable in the processor, the instructions adapted to a crowdsourced search and locate operation comprising the steps of:

(a) receiving, at the application server computer, a first list of geolocations corresponding to a plurality of crowdsourced participants;

(b) receiving, at the application server computer, a second list of geolocations from a plurality of images;

(c) navigating the first list of geolocations corresponding to crowdsourced participant to a specific geospatial location;

(d) sending a first image to a first crowdsourced participant wherein the geolocation of the second list corresponding to the first crowdsourced participant, the geolocation of the second list being substantially the same to the geolocation of the first list corresponding to the first image;

(e) receiving tagging data from the first crowdsourced participant, the tagging data corresponding to a plurality of objects and locations identified by the first crowdsourced participant;

(f) displaying, on a client computer comprising at least a memory, a processor, and programmable instructions, the programmable instructions stored in the memory and operable in the processor to provide a client interface application, a first plurality of elements enabling an administrative user to configure a crowdsourced search and locate campaign;

(g) displaying, on the client computer, a second plurality of elements enabling an administrative user to configure and run a crowdrank algorithm, wherein the crowdrank algorithm takes as input a large number of object tags created by participating users in the crowdsourced search and locate campaign and determines a most likely distribution of actual locations of objects of interest;

(h) displaying, on the client computer, a plurality of image strips that were viewed by participating users in the crowdsourced search and locate campaign; and

(i) upon the user's selecting a particular object type icon, displaying, on the client computer, all or a substantial portion of tags of the type selected that were generated by participating users in the crowdsourced search and locate campaign, by placing visual indicators at each tagged location of objects of the selected type within the plurality of image strips;

wherein the crowdrank algorithm performs the steps of:

computing a vector of agreement and disagreement values for each of the plurality of retrieved tags, wherein each agreement or disagreement value is determined by comparing a distance between a location associated with a first retrieved tag with which a first vector is associated and a location associated with a second retrieved tag; and

automatically performs an expectation-maximization or expectation-minimization process iteratively until a configured maximum number of iterations is performed or until an indicia of rate of change between iterations falls below a configured threshold.

Assignments (20)