System and method for document management and collaboration

Patent metadata

Field	Value
Publication number	US-12511658-B2
Application number	US-202117401034-A
Country	US
Kind code	B2
Filing date	Aug 12, 2021
Priority date	Aug 28, 2020
Publication date	Dec 30, 2025
Grant date	Dec 30, 2025

Abstract

Systems and methods for processing extracted data from different data sources to classify the data as an intent, a concern, and an insight for a client using an intent/concern engine. The system has a handler to route the data to a client domain, a financial product domain, a client insight domain and a client concern domain in some embodiments. The system can determine action or task recommendation based on the intent, concern, and insight for the client using a business rule system, and transmits the action or task recommendation to an advisor interface.

First claim

What is claimed is:

1 . A system for processing electronic interactions and recommending actions for an advisor interface, the system comprising:
data adapters to extract client-specific data received from different data sources in different raw formats, the client-specific data comprising electronic interactions with at least one document from a document communication system, client electronic actions, news, client portfolio data, and market data; non-transitory memory storing the client-specific data and a classification model;
at least one processor executing computer readable instructions stored in the memory to:
process the client-specific data to classify the client-specific data as one or more of an intent, concern, or insight classification for a client using the classification model stored in the memory, wherein the classification model receives the client-specific data as input and generates the one or more of the intent, concern, or insight classification for the client based on the client-specific data and a plurality of advisor category definitions, and wherein a handler routes the client-specific data to a client domain server and data about one or more types of financial products to a financial product domain server;
determine or generate action or task recommendation based on the one or more of the intent, concern, or insight classification for the client using a business rule management system;
transmit the action or task recommendation to the advisor interface.

2 . The system of claim 1 wherein the financial product domain server stores financial product data.

3 . The system of claim 1 wherein the client domain server stores interest data, portfolio data, client intent data, client concern data, and family data.

4 . The system of claim 1 wherein a client insight domain server stores client interest data received from the client domain server and financial product data received from the financial product domain server, and generates events populated with data from the client interest data and the financial product for a business rule management system.

5 . The system of claim 1 wherein a client concern domain server stores client concern data received from the client domain server and client identifiers, and generates events populated with data from the client concern data and the client identifiers for a business rule management system.

6 . The system of claim 1 wherein the data adapters implement data standardization and data normalization on the client-specific data to clean data from the different raw formats and convert data into a common format.

7 . The system of claim 1 wherein the data adapters have an event data tool to transform raw data into events and store the events in an event data storage.

8 . The system of claim 1 wherein the classification model uses key word searching, natural language processing, and machine learning to classify the client-specific data.

9 . The system of claim 1 wherein the processor builds the classification model using training data, the plurality of advisor category definitions, and feedback from the advisor interface, wherein the processor cleans the training data, converts the training data into standardized form, and creates a training model.

10 . The system of claim 1 wherein the processor uses a translator to generate the action or task recommendation from the one or more of the intent, concern, or insight classification for the client.

11 . The system of claim 1 wherein the action or task recommendation comprises automated comments for the advisor interface.

12 . The system of claim 1 wherein a type of interaction captured is a period of time first user spends with the document open.

13 . The system of claim 1 wherein a type of interaction captured is a period of time the user spends on a portion of the document.

14 . The system of claim 1 wherein a type of interaction captured is a number of visits by the user to the document.

15 . The system of claim 1 wherein a type of interaction captured is the date the document is accessed by the user.

16 . The system of claim 1 wherein a type of interaction captured is a period of time the document is accessed by the user.

17 . The system of claim 1 wherein a type of interaction captured is a number of annotations to the document by the user.

18 . The system of claim 1 further comprising the processor configured to receive additional data regarding the user from a user database or data source.

19 . The system of claim 18 further comprising the processor configured to generate a task for another user based on the additional data.

20 . The system of claim 18 further comprising the processor configured to generate a task for another user based on the additional data and the first user's interaction with the document.

21 . A process for virtual document interaction between at least two users comprising:
at a hardware processor,
extracting client-specific data from different data sources in different raw formats, the client-specific data comprising electronic interactions with at least one document from a document communication system, client electronic actions, news, client portfolio data, and market data;
storing the client-specific data and a classification model at a non-transitory memory;
processing the client-specific data to classify the client-specific data as one or more of an intent, concern, or insight classification for a client using the classification model stored in the memory, wherein the classification model receives the client-specific data as input and generates the one or more of the intent, concern, or insight classification for the client based on the client-specific data and a plurality of advisor category definitions, and wherein a handler routes the client-specific data to a client domain server and data about one or more types of financial products to a financial product domain server;
routing the client-specific data to the client domain server and the data about one or more types of financial products to the financial product domain server for event generation;
determining or generating a recommended action or task based on the one or more of the intent, concern, or insight classification for the client using a business rule management system; and
transmitting the action or task recommendation to the advisor interface.

Assignees

• Royal Bank Of Canada

Inventors

• Sheikh Danial
• Mustafa Laiba
• Liu Thomas
• Yang Sophia
• Shah Manish K
• Khodak Leah
• Kuznetsov Lev

Classifications

• G06F40/169

  Annotation, e.g. comment data or footnotes · CPC title

• G06F40/40

  Processing or translation of natural language (natural language analysis G06F40/20; semantic analysis G06F40/30) · CPC title

• H04L51/02

  using automatic reactions or user delegation, e.g. automatic replies or chatbot-generated messages · CPC title

• G06Q30/0201 Primary

  Market modelling; Market analysis; Collecting market data · CPC title

• G06F40/30

  Semantic analysis · CPC title