System architecture for customer genome construction and analysis

Patent metadata

Field	Value
Publication number	US-2016055499-A1
Application number	US-201514835187-A
Country	US
Kind code	A1
Filing date	Aug 25, 2015
Priority date	Aug 25, 2014
Publication date	Feb 25, 2016
Grant date	—

Abstract

A computer system constructs a robust recipient profile. The system receives data associated with recipient digital interactions from, e.g., streaming and/or batch sources. The recipient data may include digital transactional data, social media data, or other recipient-specific information. The system may employ heuristic data ingestion processing to derive further data based on the data inputs and attributization, and thereby may develop a robust recipient profile by aggregating the processed and derived data. The system may implement production rules to determine recipient-specific custom metadata based on the robust recipient profile to transmit to the recipient.

First claim

1 . A method for generating a robust recipient profile, comprising:
receiving data from a plurality of data channels, where the received data comprises batch data and stream data; processing the received data to generate the robust recipient profile by:
matching the received data to a recipient;
assigning a recipient identifier to the received data, the recipient identifier corresponding to the matched recipient; and
analyzing a selected portion of the received data to determine one or more attributes of the recipient;
ranking the determined attributes of the recipient; determining which attributes are tagged to the recipient and assigning corresponding tags to the recipient; and monitoring the plurality of data channels for additional data.

2 . The method of claim 1 , where the received data comprises transactional data and product data comprising different product attributes and analyzing the selected portion of the received data to determine one or more attributes of the recipient further comprises:
combining the product data and transactional data to form a dataspace; calculating a term frequency score for each of the product attributes for the recipient; calculating an inverse document frequency for each of the product attributes for the recipient; combining the term frequency and inverse document frequency to form an attribute of the recipient.

3 . The method of claim 1 , where processing the received data to create the robust recipient profile further comprises:
cross-referencing the selected portion of the received data with pre-analyzed data.

4 . The method of claim 1 , where processing the received data to create the robust recipient profile further comprises:
performing reconciliation of received data from multiple data sources by:
determining whether one or more data objects in the received data contain information regarding a common attribute of the recipient;
determining a level of trust of the one or more data objects based on the data source of the data object; and
adjusting the common attribute of the recipient based on the determined level of trust of the one or more data objects.

5 . The method of claim 1 , where processing the received data to create the robust recipient profile further comprises:
determining if a real-time update is present; updating the robust recipient profile in real-time based on a determination that a real-time update flag is present; and updating the robust recipient profile through a batch update based on a determination that a real-time update flag is not present.

6 . The method of claim 1 , wherein the robust recipient profile is updated periodically, on-demand, in response to a trigger, or a combination thereof.

7 . The method of claim 1 , further comprising:
determining a recipient-specific custom metadata recommendation based on the robust recipient profile by:
retrieving metadata and an attribute configuration file from a metadata database, the metadata comprising a set of generalized metadata in the metadata database;
matching the determined attributes of the customer with the metadata based on the attribute configuration file to determine relevant recipient-specific custom metadata;
assigning a fit factor to the relevant recipient-specific custom metadata based on a level of correlation between the relevant recipient-specific custom metadata and the determined attributes of the recipient;
categorizing the relevant recipient-specific custom metadata based on the assigned fit factor; and
ranking the relevant recipient-specific custom metadata based on a significance of the relevant recipient-specific custom metadata to a business; and
presenting the recipient-specific custom metadata recommendation to the recipient.

8 . The method of claim 7 , where categorizing the relevant recipient-specific custom metadata further comprises:
determining whether particular metadata in the metadata comprises a contextual parameter; determining whether the particular metadata is valid by assessing whether the contextual parameter has been satisfied; and categorizing the particular metadata as contextual metadata based on a determination that the particular metadata is valid.

9 . The method of claim 7 , where categorizing the relevant recipient-specific custom metadata further comprises:
identifying regular recipient-specific custom metadata and extended recipient-specific custom metadata, where regular recipient-specific custom metadata meets or exceeds a first predetermined fit factor threshold, and where extended recipient-specific custom metadata falls below the first predetermined fit factor threshold and exceeds a second predetermined fit factor threshold.

10 . The method of claim 7 , further comprising:
deriving a transaction mapping based on the robust recipient profile, the transaction mapping having one or more nodes and edges, where each node in the transaction mapping corresponds to particular metadata in the metadata, and where each edge in the transaction mapping has a weight that reflects the conditional probability of customer acceptance of a particular metadata corresponding to a second node based on customer acceptance of a particular metadata corresponding to a first node; matching the determined attributes of the recipient against the one or more nodes, where a matching node indicates recipient acceptance of the particular metadata corresponding to the matching node; and categorizing one or more of the relevant recipient-specific custom metadata as an extended recipient-specific custom metadata by:
identifying nodes that have a common edge with the matching node; and
determining if the weight of the common edge exceeds a predetermined probability threshold.

11 . The method of claim 1 , where the received data comprises traditional data, alternate data, or a combination thereof.

12 . A system comprising circuitry operable to:
receive data from a plurality of data channels, where the received data comprises batch data and stream data; process the received data to generate a robust recipient profile, where the circuitry is operable to:
match the received data to a recipient;
assign a recipient identifier to the received data, the recipient identifier corresponding to the matched recipient; and
analyze the selected portion of the received data to determine one or more attributes of the recipient;
rank the determined attributes of the recipient; determine which attributes are tagged to the recipient and assign corresponding tags to the recipient; and monitor the plurality of data channels for additional data.

13 . The system of claim 12 , where the received data comprises transactional data and product data comprising different product attributes and the circuitry is operable to analyze the selected portion of the received data to determine one or more attributes of the recipient further by:
combining the product data and transactional data to form a dataspace; calculating a term frequency score for each of the product attributes for the recipient; calculating an inverse document frequency for each of the product attributes for the recipient; combining the term frequency and inverse document frequency to form an attribute of the recipient.

14 . The system of claim 12 , where the circuitry is further operable to:
cross-reference a selected portion of the received data with pre-analyzed data.

15 . The system of claim 12 , where the circuitry is further operable to:
perform reconciliation of received data from multiple data sources, wherein the circuitry is operable to:
dete

Assignees

• Accenture Global Services Ltd

Inventors

• Hawkins Christopher John
• Dang Leeann Chau Tuyet
• Nguyen David Tong
• Chu Hyon S
• Cheng Serena Tsiao-Yi
• Walker Bryan Michael

Classifications

• G06Q10/40

  Business processes related to social networking or social networking services · CPC title

• G06Q30/0204 Primary

  Market segmentation · CPC title

• G06Q30/0271

  Personalized advertisement · CPC title

• G06Q50/01

  Physics · mapped topic

• G06Q10/42

  Determination of affinities or common interests between users · CPC title