Systems and methods for maintaining confidence scores of entity associations derived from systems of record

Patent metadata

Field	Value
Publication number	US-11934457-B2
Application number	US-202016880799-A
Country	US
Kind code	B2
Filing date	May 21, 2020
Priority date	May 22, 2019
Publication date	Mar 19, 2024
Grant date	Mar 19, 2024

Abstract

The present disclosure is directed to systems and methods of maintaining confidence scores of entity associations derived from systems of record. The system can access a record objects of systems of record. The system can identify, from a record object corresponding to a first group entity, an account relationship data structure specifying a relationship. The system can identify a first group node profile corresponding to the first group entity. The system can identify, for each second group entity, a second group node profile. The system can detect a change in a relationship of the group entities in the account relationship data structure or from electronic activities. The system can determine, between the first and a second group node profile, a relationship type in the change. The system can update, in a node graph, an edge between a first and a second group node profile to indicate the relationship type.

First claim

What is claimed is:

1. A method, comprising:
accessing, by one or more processors of a data processing system in communication with at least one server that stores a plurality of systems of records from the at least one server, a plurality of record objects of one or more systems of record, each record object of the plurality of record objects corresponding to an account record object type and identifying a group entity and comprising one or more object field-value pairs, the one or more systems record associated with one or more data source providers;
generating, by the one or more processors, in one or more data structures maintained by the data processing system, a shadow system of record including a plurality of shadow objects, wherein each shadow object is generated from a corresponding record object of the plurality of record objects by populating shadow field-value pairs using data included in corresponding object field-value pairs of the record object, the one or more processors configured to periodically synchronize the shadow object with the corresponding record object;
identifying, by the one or more processors, from an account relationship data structure of the shadow system of record, a second group entity and a shadow field value identifying a first relationship type between the first group entity and the second group entity;
identifying, by the one or more processors, a first group node profile identifying the first group entity, the first group node profile including one or more node field-value pairs corresponding to the shadow field-value pairs of the shadow object identifying the first group entity;
identifying, by the one or more processors, for the second group entity, a corresponding second group node profile including node field-value pairs generated using data included in one or more shadow field-value pairs of a second shadow object identifying the second group entity;
detecting, by the one or more processors, an update in a relationship type between the first group entity and the second group entity based on (i) detecting that the shadow field value of the account relationship data structure has been changed to identify a second relationship type between the first group entity and the second group entity or (ii) from one or more electronic activities identifying participants corresponding to the first group entity or the second group entity; and
updating, by the one or more processors, in a node graph including the first group node profile and the second group node profile, an edge between the first group node profile and the second group node profile to indicate the second relationship type.

2. The method of claim 1 , wherein detecting the update in the relationship type further comprises detecting the update in the relationship type from a communication pattern among the one or more electronic activities identifying the participants corresponding to the first group entity or the second group entity.

3. The method of claim 1 , wherein detecting the update in the relationship type further comprises detecting the update in the relationship type including a modification of an address in the electronic activities identifying the participants corresponding to the first group entity or the second group entity.

4. The method of claim 1 , wherein detecting the update in the relationship type further comprises detecting a change in a domain name corresponding to the first group entity or the second group entity.

5. The method of claim 1 , wherein detecting the update in the relationship type further comprises detecting a redirection of a website corresponding to the first group entity or the second group entity.

6. The method of claim 1 , wherein detecting the update in the relationship type further comprises detecting the update by applying a natural language processing algorithm on the one or more electronic activities to extract a feature indicating the change.

7. The method of claim 1 , wherein detecting the update in the relationship type further comprises detecting a change in the account relationship data structure specifying the relationship among the group entities from the record object of the plurality of record objects corresponding to the first group entity.

8. The method of claim 1 , wherein detecting the update in the relationship type further comprises detecting a change in a second account relationship data structure of a second record object of the plurality of the plurality of record objects corresponding to the second group entity.

9. The method of claim 1 , further comprising providing, by the one or more processors, in response to updating, the relationship type to populate a record object of the plurality of record objects corresponding to the second group entity.

10. The method of claim 1 , further comprising:
identifying, by the one or more processors, a set of record object from each system of record of the one or more systems of records, each record object of the set having one or more object field-value pairs; and
merging, by the one or more processors, sets of record objects identified from the one or more systems of records based on the one or more field values pairs of the record objects across the sets to generate the plurality of record objects.

11. A system, comprising:
one or more processors of a data processing system in communication with at least one server that stores a plurality of systems of records from the at least one server configured to execute machine-readable instructions to:
access a plurality of record objects of one or more systems of record, each record object of the plurality of record objects corresponding to an account record object type and identifying a group entity and comprising one or more object field-value pairs, the one or more systems record associated with one or more data source providers;
generate, in one or more data structures maintained by the data processing system, a shadow system of record including a plurality of shadow objects, wherein each shadow object is generated from a corresponding record object of the plurality of record objects by populating shadow field-value pairs using data included in corresponding object field-value pairs of the record object, the one or more processors configured to periodically synchronize the shadow object with the corresponding record object;
identify, from an account relationship data structure of the shadow system of record, a second group entity and a shadow field value identifying a first relationship type between the first group entity and the second group entity;
identify a first group node profile identifying the first group entity, the first group node profile including one or more node field-value pairs corresponding to the shadow field-value pairs of the shadow object identifying the first group entity;
identify, for the second group entity, a corresponding second group node profile including node field-value pairs generated using data included in one or more shadow field-value pairs of a second shadow object identifying the second group entity;
detect, an update in a relationship type between the first group entity and the second group entity based on (i) detecting that the shadow field value of the account relationship data structure has been changed to identify a second relationship type between the first group entity and the second group entity or (ii) from one or more electronic activities identifying participants corresponding to the first group entity or the second group entity; and
update, in a node graph including the first group node profile and the second group node profile, an edge between the first group node profile and the second group node profi

Assignees

• People Ai Inc

Inventors

• Rogynskyy Oleg
• Joseph Rajit Kurien
• Jain Vardhman
• Halladay Dylan

Classifications

• G06F16/9024 Primary

  Graphs; Linked lists (G06F16/9027 takes precedence) · CPC title

• G06F16/288

  Entity relationship models · CPC title

• G06F40/30

  Semantic analysis · CPC title

• H04L51/48

  Message addressing, e.g. address format or anonymous messages, aliases · CPC title

• G06F40/205 Primary

  Parsing · CPC title