Frictionless authentication and monitoring
An identity of a customer within an establishment is authenticated using a variety of captured biometric features obtained from sensors and/or video. Video capturing movements/interactions of the customer is analyzed in real time to identify the customer's behavior and actions. Any staff of the establishment who interact with the customer are identified from the video. Transaction data and other data retained for the customer by the establishment are aggregated and linked with the video and the customer identity. The linked data is analyzed in combination with the customer behavior and actions to determine responses within the establishment to customer-initiated transactions. In an embodiment, the customer is authorized to perform at least one transaction within the establishment based on the authenticated identity and linked data without a presentation by the customer of an identification card, a Personal Identification Number (PIN), a password and/or verification by a staff member.
1 . A server, comprising:
a processor; and
a non-transitory computer-readable storage medium having instructions that when executed by the processor cause the processor to perform operations comprising:
authenticating an individual to a customer identity using frictionless data;
aggregating data associated with the customer identity from a plurality of data sources;
identifying at least one action or at least one behavior of the individual from video analysis;
detecting a transaction request associated with the individual;
determining whether to intervene in a transaction based on one or more of the customer identity, the at least one action, the at least one behavior, and the aggregated data;
providing, by a person tracker, specific pixel features of specific areas within a bounding box for the individual, the specific pixel features associated with tracked biometric features of the individual; and
utilizing, by a behavior-action tracker, the bounding box to perform more detailed pixel analysis on facial features of the individual and identify the at least one behavior identified by a specific behavior identifier; and
evaluating, by a transaction manager, process controls using identifiers and identities of the individual to evaluate conditions in business rules of the process controls to identify actions that are required, permissible, or impermissible while the individual moves about an establishment, and processing automated actions as directed by the process controls.
2 . The server of claim 1 , wherein authenticating further includes biometrically authenticating using features of the individual derived the from video analysis.
3 . The server of claim 1 , wherein aggregating further includes obtaining customer records associated with the individual from the plurality of data sources.
4 . The server of claim 1 , wherein identifying further includes identifying a staff member interacting with the individual from the video analysis.
5 . The server of claim 4 , wherein identifying further includes authenticating the staff member to a staff member identity.
6 . The server of claim 1 , wherein detecting further includes identifying a transaction object in a video associated with a transaction device.
7 . The server of claim 1 , wherein determining further includes evaluating transaction data against predefined rules in process controls.
8 . A method comprising:
biometrically authenticating a customer to a customer identity using frictionless data;
obtaining establishment data for the customer identity;
deriving at least one action or at least one behavior of the customer from video analysis;
identifying a transaction initiated by or for the customer;
providing transaction authentication for the customer to a terminal associated with the transaction;
monitoring and intervening in the transaction based on one or more of the customer identity, the at least one action, the at least one behavior, the establishment data, and transaction data for the transaction;
analyzing pixels in video frames of video feeds and using a bounding box or region of interest within the pixels to track locations of the customer and extremities of the customer with a known area of an establishment based on area identifiers associated with cameras that provide the video feeds; and
assembling, by an aggregator, each biometric feature detectable for the customer starting as soon as the customer is detected within the establishment, generating a current score for the assembled biometric features, comparing the current score against known scores assigned to known customers and their identities, and assigning a customer identity match to the customer when the current score is within a predefined threshold of confidence.
9 . The method of claim 8 , further comprising:
generating an audit data set linking customer data, video, and the transaction data.
10 . The method of claim 8 , further comprising:
detecting a fraudulent action based on flagged behaviors.
11 . The method of claim 8 , wherein deriving further includes tracking an object identified as the customer across images frames of video and associating at least one action identifier or at least behavior identifier with the customer.
12 . The method of claim 8 , wherein identifying further includes detecting a particular action identifier for the at least one action that is associated with a transaction initiation action.
13 . The method of claim 8 , wherein identifying further includes detecting a terminal object in video representing the terminal.
14 . The method of claim 8 , wherein providing further includes sending an authentication code and an account number associated with the customer to the terminal.
15 . The method of claim 8 , wherein monitoring and intervening further includes authenticating and tracking a staff member interacting with the customer from video associated with the transaction.
16 . A method comprising:
receiving, by a terminal, an authentication code from a server, wherein the authentication code identifies a customer and an account of the customer without customer input provided to the terminal;
displaying, by the terminal, a transaction screen to initiate a transaction for the customer based on the authentication code;
processing, by the terminal, the transaction;
sending, by the terminal, transaction data to the server during the transaction;
receiving, by the terminal, an intervention instruction from the server when the server determines an intervention is necessary based on at least one of the customer linked to the account or the transaction data;
modifying, by the terminal, the transaction based on the intervention instruction;
wherein the terminal comprises processing devices that are operated by employees and customers of an establishment during transactions responsive to performing electronic operations, and responsive to obtaining information or providing information;
wherein particular transactions comprise processing actions initiated by the employees in performance of a portion of a task associated with the establishment; and
storing, by the terminal, audit data that associates and tags at least one action, a customer identity, and the transaction data for a customer visit, and linking the audit data to a video indexed to the customer visit such that a reviewer can access a corresponding portion of the video associated with any questionable behavior directly from the audit data.
17 . The method of claim 16 , wherein displaying further includes presenting account information for the customer without requiring customer authentication input at the terminal.
18 . The method of claim 16 , wherein processing further includes capturing biometric data of the customer during the transaction.
19 . The method of claim 16 , wherein modifying further includes one of: suspending the transaction, terminating the transaction, or requesting additional verification from the customer.
20 . The method of claim 16 , further comprising:
updating account information received from the server based on the intervention instruction.