Systems and methods for matching electronic activities with record objects based on entity relationships

Patent metadata

Field	Value
Publication number	US-11470171-B2
Application number	US-201916716221-A
Country	US
Kind code	B2
Filing date	Dec 16, 2019
Priority date	May 24, 2018
Publication date	Oct 11, 2022
Grant date	Oct 11, 2022

Abstract

The present disclosure relates to systems and methods for matching electronic activities with record objects based on entity relationships. The method can include accessing a plurality of electronic activities, identifying an electronic activity, identifying a first participant associated with a first entity and a second participant associated with a second entity, determining whether a record object identifier is included in the electronic activity, identifying a first record object of the system of record that includes an instance of the record object identifier, and storing an association between the electronic activity and the first record object. The method can include determining a second record object corresponding to the second entity, identifying, using a matching policy, a third record object linked to the second record object and identifying a third entity, and storing, by the one or more processors, an association between the electronic activity and the third record object.

First claim

What is claimed is:

1. A method comprising:
maintaining, by a data processing system including one or more processors, a plurality of node profiles including a plurality of node field-value pairs, each node-field-value pair identifying a node field and one or more node values;
accessing, by the data processing system, a plurality of electronic activities transmitted or received via electronic accounts of one or more data source providers;
accessing, by the data processing system, from one or more servers of a customer relationship management (CRM) system, a plurality of CRM systems of record including a plurality of CRM record objects, each CRM record object of the plurality of CRM record objects corresponding to a record object type and comprising one or more object fields having one or more object field values, each respective CRM system of record of the plurality of the CRM systems of record corresponding to a respective data source provider of the plurality of data source providers;
generating, by the data processing system, a plurality of local record objects corresponding to the plurality of CRM record objects, each respective local record object of the plurality of local record objects storing record object data obtained from the corresponding CRM record object, the record object data stored in the plurality of local record objects used by the data processing system for matching electronic activities to the plurality of local record objects;
identifying, by the data processing system, an electronic activity of the plurality of electronic activities;
identifying, by the data processing system, a first participant of the electronic activity associated with the first entity and a second participant of the electronic activity associated with a second entity based on a first domain name of a first address identifier of the first participant and a second domain name of a second address identifier of the first participant, the first address identifier and the second address identifier included in the electronic activity;
parsing, by the data processing system, the electronic activity to extract data for matching the electronic activity to one or more local record objects of the plurality of local record objects;
responsive to parsing the electronic activity:
determining, by the data processing system, whether a record object identifier indicating a relationship between the first entity and the second entity is included in the electronic activity;
responsive to determining that the record object identifier is included in the electronic activity:
identifying, by the data processing system, a first local record object of the plurality of local record objects that includes an instance of the record object identifier, the first local record object of a first record object type;
storing, by the data processing system, a first association between the electronic activity and the first local record object; and
transmitting, by the data processing system, to the one or more servers of the CRM system, instructions to cause the one or more servers to store a second association between the electronic activity and a first CRM record object with which the first local record object corresponds; and

responsive to determining that the record object identifier is not included in the electronic activity:
determining, by the data processing system, using data included a node profile corresponding to the second entity, a second local record object of a second record object type corresponding to the second entity;
identifying, by the data processing system, using a matching policy, a third local record object of the first record object type linked to the second local record object and identifying a third entity; and
storing, by the data processing system, a third association between the electronic activity and the third local record object;
transmitting, by the data processing system, to the one or more servers of the CRM system, instructions to cause the one or more servers to store a fourth association between the electronic activity and a second CRM record object with which the third local record object corresponds.

2. The method of claim 1 , wherein determining the second record object further comprises:
parsing, by the data processing system, the electronic activity to identify, for each participant of the electronic activity, a respective domain name associated with the participant of the electronic activity; and
selecting, by the data processing system, the second local record object based on the respective domain name associated with the second participant of the electronic activity.

3. The method of claim 1 , further comprising:
identifying, by the data processing system, a plurality of candidate local record objects of the first record object type linked to the second local record object;
selecting, by the data processing system, the third local record object from the plurality of candidate local record objects based on a match score between the third local record object and the electronic activity.

4. The method of claim 1 , further comprising:
identifying, by the data processing system, a plurality of candidate local record objects of the first record object type linked to the second local record object;
and wherein parsing the electronic activity to extract data includes parsing, by the one or more processors, the electronic activity to generate activity field-value pairs; and wherein identifying the third local record object comprises selecting, by the data processing system, the third local record object based on the activity field-value pairs.

5. The method of claim 1 , wherein identifying the third local record object further comprises identifying the third local record object based on an intent of the first participant or the second participant.

6. The method of claim 1 , further comprising:
extracting, by the data processing system, text of a body of the electronic activity;
determining, by the data processing system and using natural language processing, from the text of the body, an identifier identifying the third entity; and
identifying, by the data processing system, the third local record object based on the identifier.

7. The method of claim 6 , further comprising:
determining, by the data processing system, a candidate identifier based on the text of the body of the electronic activity;
identifying, by the data processing system, a plurality of entity identifiers, each of the plurality of entity identifiers associated with a local record object associated with the second local record object; and
selecting, by the data processing system, the identifier associated with the third entity from the plurality of entity identifiers based on a similarity score between the candidate identifier and the identifier associated with the third entity in a vector space satisfying a threshold.

8. The method of claim 1 , further comprising:
determining, by the data processing system, an intent of a participant of the electronic activity based on an embedding vector generated based on text of a body of the electronic activity;
and wherein identifying the third record object of the first record object type is based on the intent of the participant.

9. The method of claim 1 , further comprising:
maintaining, by the data processing system, node graph linking a plurality of nodes corresponding to the plurality of node profiles using the plurality of electronic activities;
identifying, by the data processing system, from the node graph, a first group node corresponding to the first entity;
identifying, by the data processing system, from the node graph, a second group node corresponding to the second entity;
id

Assignees

• People Ai Inc

Inventors

• Rogynskyy Oleg
• Hermanek Stefan
• Halladay Dylan
• Korkuna Ostap
• Navarro Jose Alberto Muniz

Classifications

• G06N3/08

  Learning methods · CPC title

• G06N3/09

  Supervised learning · CPC title

• G06F16/2228

  Indexing structures · CPC title

• G06Q10/06312

  Adjustment or analysis of established resource schedule, e.g. resource or task levelling, or dynamic rescheduling · CPC title

• G06Q10/06315

  Needs-based resource requirements planning or analysis · CPC title