# US 2024/0202737 A1 · Method and system for improving customer experience with a technical support entity

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

- Number: US 2024/0202737 A1
- Document ID: US20240202737A1
- Status: Published application
- Kind: A1
- Application number: 18/066,757
- Filed: 2022-12-15
- Published: 2024-06-20
- Earliest claimed: 2022-12-15
- Assignees: Dell Products L.P.
- Applicants: Dell Products L.P.
- Inventors: Parminder Singh Sethi; Lakshmi Saroja Nalam
- Web page: https://patentgrep.com/patent/US20240202737A1

## CPC

- G06Q 30/015: Providing customer assistance, e.g. assisting a customer within a business location or via helpdesk
- H04L 41/5032: {Generating service level reports}
- H04L 41/5064: {Customer relationship management}
- G06Q: INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- H04L: TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION (arrangements common to telegraphic and telephonic communication H04M)

## Abstract

A method for managing a technical support (TS) conversation includes: determining an initial state of a user based on TS history of the user; classifying a first sentence of a TS entity into a first category and a second sentence of the user into a second category; obtaining, based on the first category and the second category, a mapping between the first sentence and the second sentence; obtaining a TS conversation score based on the initial state and the second category; generating a TS recommendation based on the TS history, the mapping, and the TS conversation score; and initiating display of the TS recommendation on a graphical user interface (GUI) accessible to the TS entity.

## Claims

### Claim 1

A method for managing a technical support (TS) conversation, the method comprising:
determining an initial state of a user based on a TS history of the user;
classifying a first sentence of a TS entity into a first category and a second sentence of the user into a second category;
obtaining, based on the first category and the second category, a mapping between the first sentence and the second sentence;
obtaining a TS conversation score based on the initial state and the second category;
generating a TS recommendation based on the TS history, the mapping, and the TS conversation score; and
initiating display of the TS recommendation on a graphical user interface (GUI) accessible to the TS entity.

### Claim 2 (depends on 1)

The method of claim 1, further comprising:
obtaining the TS history, wherein the TS history specifies at least a previous TS recommendation generated for the user.

### Claim 3 (depends on 1)

The method of claim 1, wherein the initial state of the user specifies an emotional condition of the user, wherein the emotional condition specifies at least one selected from a group consisting of normal, sad, angry, and frustrated.

### Claim 4 (depends on 1)

The method of claim 1, wherein the first category is an imperative sentences category, wherein the imperative sentences category comprises an instruction sentences subcategory and an advice sentences subcategory.

### Claim 5 (depends on 4)

The method of claim 4, wherein the advice sentences subcategory comprises at least the TS recommendation.

### Claim 6 (depends on 1)

The method of claim 1, wherein the second category is an interrogative sentences category, wherein the interrogative sentences category comprises a mistrust sentences subcategory and an issue related sentences subcategory.

### Claim 7 (depends on 6)

The method of claim 6, wherein the mistrust sentences subcategory comprises at least the second sentence, wherein the second sentence is generated in response to the first sentence.

### Claim 8 (depends on 1)

The method of claim 1, wherein the second category is a declarative sentences category, wherein the declarative sentences category comprises a mistrust sentences subcategory and an issue related sentences subcategory.

### Claim 9 (depends on 8)

The method of claim 8, wherein the issue related sentences subcategory comprises at least the second sentence, wherein the second sentence is generated in response to the first sentence.

### Claim 10 (depends on 1)

The method of claim 1, wherein the TS conversation score is obtained by implementing a multiple linear regression model.

### Claim 11 (depends on 1)

The method of claim 1, wherein the TS recommendation comprises an imperative-instruction sentence, wherein the imperative-instruction sentence specifies restarting the user's computing device.

### Claim 12

A non-transitory computer readable medium comprising computer readable program code, which when executed by a computer processor enables the computer processor to perform a method for managing a technical support (TS) conversation, the method comprising:
determining an initial state of a user based on a TS history of the user;
classifying a first sentence of a TS entity into a first category and a second sentence of the user into a second category;
obtaining, based on the first category and the second category, a mapping between the first sentence and the second sentence;
obtaining a TS conversation score based on the initial state and the second category;
generating a TS recommendation based on the TS history, the mapping, and the TS conversation score; and
initiating display of the TS recommendation on a graphical user interface (GUI) accessible to the TS entity.

### Claim 13 (depends on 12)

The non-transitory computer readable medium of claim 12, wherein the first category is an imperative sentences category, wherein the imperative sentences category comprises an instruction sentences subcategory and an advice sentences subcategory.

### Claim 14 (depends on 13)

The non-transitory computer readable medium of claim 13, wherein the advice sentences subcategory comprises at least the TS recommendation.

### Claim 15 (depends on 13)

The non-transitory computer readable medium of claim 13, wherein the second category is an interrogative sentences category, wherein the interrogative sentences category comprises a mistrust sentences subcategory and an issue related sentences subcategory.

### Claim 16 (depends on 15)

The non-transitory computer readable medium of claim 15, wherein the mistrust sentences subcategory comprises at least the second sentence, wherein the second sentence is generated in response to the first sentence.

### Claim 17 (depends on 13)

The non-transitory computer readable medium of claim 13, wherein the second category is a declarative sentences category, wherein the declarative sentences category comprises a mistrust sentences subcategory and an issue related sentences subcategory.

### Claim 18 (depends on 17)

The non-transitory computer readable medium of claim 17, wherein the issue related sentences subcategory comprises at least the second sentence, wherein the second sentence is generated in response to the first sentence.

### Claim 19 (depends on 13)

The non-transitory computer readable medium of claim 13, wherein the TS recommendation comprises an imperative-instruction sentence, wherein the imperative-instruction sentence specifies restarting the user's computing device.

### Claim 20

A system for managing a technical support (TS) conversation, the system comprising:
a processor comprising circuitry;
memory comprising instructions, which when executed perform a method, the method comprising:
determining an initial state of a user based on a TS history of the user, wherein the initial state of the user specifies an emotional condition of the user, wherein the emotional condition specifies at least one selected from a group consisting of normal, sad, angry, and frustrated;
classifying a first sentence of a TS entity into a first category and a second sentence of the user into a second category;
obtaining, based on the first category and the second category, a mapping between the first sentence and the second sentence;
obtaining a TS conversation score based on the initial state and the second category;
generating a TS recommendation based on the TS history, the mapping, and the TS conversation score, wherein the TS recommendation comprises an imperative-instruction sentence, wherein the imperative-instruction sentence specifies restarting the user's computing device; and
initiating display of the TS recommendation on a graphical user interface (GUI) accessible to the TS entity.
