Systems and methods for maintaining extracted data in a group node profile from electronic activities

Patent metadata

Field	Value
Publication number	US-11418626-B2
Application number	US-201916418892-A
Country	US
Kind code	B2
Filing date	May 21, 2019
Priority date	May 24, 2018
Publication date	Aug 16, 2022
Grant date	Aug 16, 2022

Abstract

The present disclosure relates to maintaining extracted data in a group node profile from electronic activities. A group node profile associated with a group entity is maintained. A first data point including an electronic activity or a record object is accessed. The first data point is parsed using a value detection policy to obtain a first value. The group node profile is updated based on the first value. An association score between the group node profile and the first value is generated. A second data point is accessed. The second data point is parsed. The association score between the group node profile and the first value is updated.

First claim

What is claimed is:

1. A method, comprising:
maintaining, by one or more processors, for a first entity, a first node profile comprising a plurality of node field-value pairs;
accessing, by the one or more processors, a first data point including first data of one of a first electronic activity or a first record object of one or more systems of record, the first electronic activity is a first email identifying an electronic account identifier of an electronic account associated with the first entity and transmitted or received from the electronic account, the first record object is a first contact record object or a first account record object including one or more object field-value pairs;
parsing, by the one or more processors, the first data point using a value detection policy to identify a plurality of first values to associate with a node profile with which the first data point is matched;
matching, by the one or more processors, the first data point with the first node profile based on comparing one or more values of the plurality of first values of the first data point to corresponding values of the plurality of node field-value pairs of the first node profile;
updating, by the one or more processors, responsive to matching the first data point with the first node profile, the first node profile to i) associate a particular first value of the plurality of first values with a corresponding field of the first node profile or ii) update a value data structure corresponding to the particular first value to include an entry identifying the first data point;
generating, by the one or more processors, an association score between the first node profile and the particular first value based on a first timestamp corresponding to when the first email was transmitted or received or when the first contact record object or the first account record object was updated, the association score indicating a level of association between the first node profile and the particular first value;
accessing, by the one or more processors, a second data point including second data of one of a second electronic activity or a second record object of the one or more systems of record, the second electronic activity is a second email or the second record object is a second contact record object or a second account record object;
matching, by the one or more processors, the second data point with the first node profile based on comparing one or more second values of a plurality of second values of the second data point to corresponding second values of the plurality of node field-value pairs of the first node profile;
identifying, by the one or more processors, by parsing the second data point using the value detection policy, the particular first value from the plurality of second values of the second data point; and
updating, by the one or more processors, responsive to identifying the particular first value from the second data point, the association score between the first node profile and the particular first value based on a second timestamp corresponding to when the second email was transmitted or received or when the second contact record object or the second account record object was updated.

2. The method of claim 1 , further comprising generating the value data structure corresponding to the particular first value, the value data structure including a first entry identifying the first data point and a second entry identifying the second data point.

3. The method of claim 2 , wherein the first entry of the value data structure is assigned a first contribution score and the second entry of the value data structure is assigned a second contribution score, the first contribution score and the second contribution score used to determine the association score.

4. The method of claim 1 , wherein the association score is a first association score, the method further comprising:
accessing, by the one or more processors, a third data point including third data of one of a third electronic activity from one or more data source providers or a third record object of the one or more systems of record;
parsing, by the one or more processors, the third data point using the value detection policy to identify a third value;
updating, by the one or more processors, responsive to matching the third data point with the first node profile, the first node profile to i) associate the third value with a second corresponding field of the first node profile or ii) update a second value data structure corresponding to the third value to include an entry identifying the third data point; and
generating, by the one or more processors, a second association score between the third value and the first node profile.

5. The method of claim 4 , wherein the third value corresponds to at least one of a domain name, a phone number, or a location.

6. The method of claim 4 , further comprising:
accessing, by the one or more processors, a fourth data point including fourth data of one of a fourth electronic activity or a fourth record object of the one or more systems of record; and
matching, by the one or more processors, the fourth data point to the first node profile based on comparing one or more fourth values of the fourth data point to at least one of the particular first value or the third value.

7. The method of claim 4 , further comprising:
detecting, by the one or more processors, an event corresponding to the first entity based on the first association score and the second association score; and
updating, by the one or more processors, a first data structure representing a first system of record of the one or more systems of record corresponding to the first record object using at least one of the third value or the third data point.

8. The method of claim 1 , wherein parsing the first data point using the value detection policy comprises applying a name entity recognition algorithm to identify a name of an entity related to the first entity and a context determination algorithm to determine a context of the name; and
the method further comprising:
selecting, by the one or more processors based on the context, from a plurality of types of values, the name to be a first type of the plurality of types of values; and
assigning, by the one or more processors, to the first node profile, the name as the first type of the plurality of types of values based on the context.

9. The method of claim 1 , wherein parsing the first data point using the value detection policy comprises applying a keyword detection algorithm to the first data point to identify the particular first value based on one or more keywords.

10. The method of claim 1 , further comprising:
updating, by the one or more processors, a first data structure representing a first system of record of the one or more systems of record corresponding to the first record object using the second data point.

11. A system, comprising:
one or more processors configured by machine-readable instructions to:
maintain, for a first entity, a first node profile comprising a plurality of node field-value pairs, each of the plurality of node field-value pairs;
access a first data point including first data of one of a first electronic activity or a first record object of the one or more systems of record, the first electronic activity is a first email identifying an electronic account identifier of an electronic account associated with the first entity and transmitted or received from the electronic account, the first record object is a first contact record object or a first account record object including one or more object field-value pairs;
parse the first data point using a value d

Assignees

• People Ai Inc

Inventors

• Rogynskyy Oleg
• Markovsky Yury
• Brunets Yurii
• Navarro Jose Alberto Muniz

Classifications

• G06N3/08

  Learning methods · CPC title

• G06N3/09

  Supervised learning · CPC title

• G06F16/2358

  Change logging, detection, and notification (replication G06F16/27) · CPC title

• G06F9/542

  Event management; Broadcasting; Multicasting; Notifications · CPC title

• G06Q10/1093

  Calendar-based scheduling for persons or groups · CPC title