# US 2023/0069587 A1 · Named entity recognition in chat dialogues for customer relationship management systems

> Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt

- Number: US 2023/0069587 A1
- Document ID: US20230069587A1
- Status: Published application
- Kind: A1
- Application number: 17/463,361
- Filed: 2021-08-31
- Published: 2023-03-02
- Earliest claimed: 2021-08-31
- Assignees: Paypal, Inc.
- Applicants: Paypal, Inc.
- Inventors: Nikita Alekseyevich Lukyanenko; Alexander Shvid
- Web page: https://patentgrep.com/patent/US20230069587A1

## CPC

- G06F 40/279: Recognition of textual entities
- G06F 40/295: Named entity recognition
- G06F 40/35: Discourse or dialogue representation
- G06F: ELECTRIC DIGITAL DATA PROCESSING (computer systems based on specific computational models G06N)

## Abstract

There are provided systems and methods for named entity recognition in chat dialogues for customer relationship management systems. A service provider, such as an electronic transaction processor for digital transactions, may provide live chat service channels for assistance through live agents and chatbot services. When interacting with these channels, a user may engage in a chat dialogue with live agents. This may include lines of texts corresponding to the exchanged messages and may include named entities for particular types or categories of words that refer to a particular object or thing. To identify these named entities, a natural language processor may utilize machine learning and other engines for named entity recognition in customer relationship management systems to highlight the named entities in live service chats. Agents of the systems may view content that identify the named entities and interact with the named entities to view descriptions.

## Claims

### Claim 1

A system comprising:
a non-transitory memory; and
one or more hardware processors coupled to the non-transitory memory and configured to read instructions from the non-transitory memory to cause the system to perform operations comprising:
accessing a chat dialogue between a user and a chat service of a customer relationship management (CRM) system for a service provider associated with the system, wherein the chat dialogue comprises a plurality of words in a plurality of word groupings;
performing a named entity recognition (NER) operation on the plurality of words, wherein the NER operation identifies one or more named entities in the chat dialogue based on one or more of the plurality of words;
determining the one or more named entities based on the performing the NER operation;
determining additional data for the one or more named entities based on an assistance type provided by the chat service, wherein the assistance type is associated with one or more services provided by the service provider to the user; and
outputting visual chat data with the one or more named entities, wherein the visual chat data comprise one or more processes to view the additional data for the one or more named entities in the chat dialogue.

### Claim 2 (depends on 1)

The system of claim 1, wherein the visual chat data comprise one or more highlights of the one or more named entities over text in the chat dialogue corresponding to the one or more named entities.

### Claim 3 (depends on 1)

The system of claim 1, wherein the operations further comprise:
receiving a selection of a first identification from the visual chat data;
obtaining the additional data for a corresponding named entity of the one or more named entities associated with the first identification; and
displaying the additional data with the corresponding named entity in the chat dialogue.

### Claim 4 (depends on 3)

The system of claim 3, wherein the additional data is obtained from a proprietary database of the service provider that comprises customer data for customers of the service provider, and wherein the corresponding named entity comprises one of the customers.

### Claim 5 (depends on 3)

The system of claim 3, wherein the additional data is obtained from an online search using an identifier of the corresponding named entity, and wherein the additional data comprises at least one of social networking data, financial standing data, website reputational data, or business data.

### Claim 6 (depends on 1)

The system of claim 1, wherein the visual chat data correspond to one or more different types of named entities and are displayed in at least one of a different color or a different format in the chat dialogue.

### Claim 7 (depends on 1)

The system of claim 1, wherein prior to the performing the NER operation, the operations further comprise:
determining an identification frequency of the one or more named entities in the chat dialogue that was established for at least one of the chat dialogue or the chat service,
wherein the NER operation is performed based on the identification frequency.

### Claim 8 (depends on 1)

The system of claim 1, wherein prior to the performing the NER operation, the operations further comprise:
filtering at least one of automated chat replies or scripted chat statements from the chat dialogue.

### Claim 9 (depends on 1)

The system of claim 1, wherein the chat dialogue comprises text between the user and at least one of a live agent or a chatbot for the chat service.

### Claim 10

A method comprising:
receiving chat text by a user with a customer relationship management platform of a service provider, wherein the chat text comprises a plurality of words;
identifying a first named entity in the chat text using named entity recognition (NER) of a natural language processor, wherein the first named entity comprises one or more of the plurality of words in the chat text;
determining a first label of the first named entity using the NER of the natural language processor;
determining a description of the first named entity using at least one of service provider data for the service provider or a search engine response to a search of the first named entity;
highlighting the first named entity in the chat text;
receiving a selection of the highlighted first named entity; and
displaying the description of the first named entity in response to the selection.

### Claim 11 (depends on 10)

The method of claim 10, further comprising:
determining that the chat text further comprises a plurality of second named entities having a plurality of second labels using the NER of the natural language processor.

### Claim 12 (depends on 11)

The method of claim 11, wherein at least one of the first named entity or one or more of the plurality of second named entities are highlighted using a different highlighting based on types of the first label or the plurality of second labels.

### Claim 13 (depends on 11)

The method of claim 11, wherein prior to the determining that the chat text further comprises the plurality of second named entities, the method further comprises:
determining a number or a frequency to highlight the first named entity and the plurality of second named entities in the chat text,
wherein the first named entity and the plurality of second named entities are limited for highlight by the number or the frequency.

### Claim 14 (depends on 13)

The method of claim 13, wherein the number or the frequency is tunable by one of a system administrator for the customer relationship management platform or a live agent viewing the chat text.

### Claim 15 (depends on 10)

The method of claim 10, wherein the highlighting comprises applying a colored highlight over the first named entity in the chat text, and wherein the colored highlight is specific to at least one of the first label or the description.

### Claim 16 (depends on 10)

The method of claim 10, wherein the description comprises at least one of user information, financial information, an online web address, a certificate of standing, a fraud description, a shipping address, a billing address, or an item description.

### Claim 17 (depends on 10)

The method of claim 10, wherein the service provider data comprises proprietary data for the service provider based on a computing service provided by the service provider to customers of the service provider.

### Claim 18 (depends on 10)

The method of claim 10, wherein the displaying the description comprises populating the description in a pop-up window or a text bubble display associated with the first named entity in the chat text.

### Claim 19

A non-transitory machine-readable medium having stored thereon machine-readable instructions executable to cause a machine to perform operations comprising:
highlighting, in a display of a computing device for a live agent of a customer relationship management system of a service provider, a portion of text in a dialogue between a user and the customer relationship management system using named entity recognition (NER) for a natural language processing system, wherein the highlighted portion of the text comprises a named entity;
receiving a selection of the highlighted portion of the text from the live agent in the display;
determining description data for the named entity responsive to the selection; and
displaying the description data in the display with the highlighted portion of the text.

### Claim 20 (depends on 19)

The non-transitory machine-readable medium of claim 19, wherein prior to the highlighting, the operations further comprise:
determining that the portion of the text includes the named entity using the NER for the natural language processing system.
