Systems and methods for identifying node hierarchies and connections using electronic activities

Patent metadata

Field	Value
Publication number	US-10866980-B2
Application number	US-201916371035-A
Country	US
Kind code	B2
Filing date	Mar 31, 2019
Priority date	May 24, 2018
Publication date	Dec 15, 2020
Grant date	Dec 15, 2020

Abstract

The present disclosure relates to methods, systems, and storage media for identifying node hierarchies and connections using electronic activities. The method may include maintaining node profiles corresponding to unique entities; selecting electronic activities linked to both a first node profile and a second node profile of the plurality of node profiles; generating for each electronic activity of the plurality of electronic activities, a relevancy score based on a respective time at which the electronic activity was transmitted or received; generating a connection profile for a connection between the first node profile and the second node profile based on the respective relevancy score of each electronic activity and storing in a data structure, an association between the connection profile, the first node profile, and the second node profile.

First claim

What is claimed is:

1. A method comprising:
maintaining, by one or more processors, a plurality of node profiles corresponding to a plurality of unique entities, each node profile including a plurality of field-value pairs generated using data extracted from electronic activities linked to the plurality of node profiles;
selecting, by the one or more processors, a plurality of electronic activities linked to both a first node profile and a second node profile of the plurality of node profiles, the first node profile including a first field-value pair corresponding to a first field type and the second node profile including a second field-value pair corresponding to the first field type, the first field type corresponding to one of a job title field type or a company name field type;
generating, by the one or more processors, for each electronic activity of the plurality of electronic activities, a respective relevancy score based on a respective time at which the electronic activity was transmitted or received;
generating, by the one or more processors, a connection profile for a connection between the first node profile and the second node profile based on i) the respective relevancy score of each electronic activity of the plurality of electronic activities, ii) the first field-value pair of the first node profile, and iii) the second field-value pair of the second node profile;
storing, by the one or more processors, in one or more data structures, an association between the connection profile, the first node profile, and the second node profile;
identifying, by the one or more processors, a second electronic activity linked to the first node profile, the second electronic activity transmitted or received after the plurality of electronic activities;
updating, by the one or more processors, based on data extracted from the second electronic activity, the first node profile by associating a new value with the first field type of the first node profile;
updating, by the one or more processors, based on determining that the first node profile has been updated by associating the new value with the first field type of the first node profile, the connection profile for the connection between the first node profile and the second node profile using the new value associated with the first field type of the first node profile;
parsing, by the one or more processors, the plurality of electronic activities to extract data from the plurality of electronic activities;
categorizing, by the one or more processors, the connection between the first node profile and the second node profile into a connection category of a plurality of predefined connection categories based on the extracted data by assigning a first hierarchical value to the first node profile and a second hierarchical value to the second node profile; and
generating, by the one or more processors, a hierarchical data structure specifying a group node linked to a first member node corresponding to the first node profile and a second member node corresponding to the second node profile, the hierarchical data structure used to identify a hierarchy between the first member node and the second member node based on the connection category of the connection between the first node profile and the second node profile and the first hierarchical value and the second hierarchical value.

2. The method of claim 1 , further comprising generating, by the one or more processors, the relevancy score for each electronic activity of the plurality of electronic activities based on a time-decaying function and the respective time at which the electronic activity was transmitted or received.

3. The method of claim 1 , wherein the plurality of electronic activities includes a first plurality of electronic activities and further comprising:
receiving, by the one or more processors, a second plurality of electronic activities linked to both the first node profile and the second node profile subsequent to storing the association between the connection profile, the first node profile, and the second node profile; and
updating, by the one or more processors, the connection profile for the connection between the first node profile and the second node profile based on the second plurality of electronic activities.

4. The method of claim 1 , further comprising:
determining, by the one or more processors at a first time, a field-value pair of the first node profile;
determining, by the one or more processors at a second time occurring after the first time, that a second new value is associated with a second field type of the first node profile; and
recategorizing, by the one or more processors, the connection between the first node profile and the second node profile into a second connection category of the plurality of predefined connection categories responsive to determining that the second new value is associated with the second field type of the first node profile.

5. The method of claim 4 , further comprising updating, by the one or more processors, the hierarchical data structure specifying the group node linked to the first member node corresponding to the first node profile and the second member node corresponding to the second node profile responsive to recategorizing the connection between the first node profile and the second node profile into the second connection category of the plurality of predefined connection categories.

6. The method of claim 1 , further comprising:
identifying, by the one or more processors, from the plurality of electronic activities, a first subset of electronic activities, each electronic activity of the first subset sent by the first node profile to the second node profile in response to a respective initiating electronic activity from the second node profile to the first node profile;
determining, by the one or more processors, a first response metric based on the first subset of electronic activities;
identifying, by the one or more processors, from the plurality of electronic activities, a second subset of electronic activities, each electronic activity of the second subset sent by the first node profile to a recipient different from the second node profile in response to a respective initiating electronic activity from the recipient to the first node profile;
determining, by the one or more processors, a second response metric based on the second subset of electronic activities; and
wherein categorizing the connection between the first node profile and the second node profile comprises categorizing, by the one or more processors, the connection between the first node profile and the second node profile based on the first response metric and the second response metric.

7. The method of claim 6 , wherein the first response metric or the second response metric is at least one of an average response time or a response rate.

8. The method of claim 1 , wherein at least one of the plurality of field-value pairs of the first node profile comprises a value data structure including a value and one or more entries corresponding to respective one or more data points, the method further comprising:
updating, by the one or more processors, the value data structure by adding a first entry to the value data structure identifying a category of a first connection; and
determining a contribution score of the first entry of the value data structure, the contribution score used to determine a confidence score of the value of the value data structure of the first node profile.

9. The method of claim 1 , further comprising:
identifying, by the one or more processors, a first number of electronic activities sent by the first node profile including the second node profile as a par

Assignees

• People Ai Inc

Inventors

• Rogynskyy Oleg
• Hermanek Stefan
• Wulf John
• Rice Devin
• Markovsky Yury

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