# US 10,374,982 B2 · Response retrieval using communication session vectors

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

- Number: US 10,374,982 B2
- Document ID: US10374982B2
- Status: Granted
- Kind: B2
- Application number: 15/639,282
- Filed: 2017-06-30
- Published: 2019-01-03
- Granted: 2019-08-06
- Earliest claimed: 2017-06-30
- Assignees: Microsoft Technology Licensing, LLC
- Applicants: Microsoft Technology Licensing, LLC
- Inventors: Emmanouil Koukoumidis; Joseph Edwin Johnson, Jr.; Hailong Mu; Matthew W Schuerman; Ying Wang
- Web page: https://patentgrep.com/patent/US10374982B2

## CPC

- H04L 51/02: using automatic reactions or user delegation, e.g. automatic replies or chatbot-generated messages
- G06F 40/30: Semantic analysis
- H04L 51/04: Real-time or near real-time messaging, e.g. instant messaging [IM]
- H04L: TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION (arrangements common to telegraphic and telephonic communication H04M)
- G06F: ELECTRIC DIGITAL DATA PROCESSING (computer systems based on specific computational models G06N)

## Abstract

Systems and methods are disclosed for response retrieval using communication session vectors. In one implementation, a first communication session is received. The first communication session includes a first communication. The first communication session is encoded as a first vector. A second vector is identified within a defined proximity of the first vector. The second vector represents a second communication session that includes a second communication. The second communication is provided within the first communication session in response to the first communication.

## Claims

### Claim 1

A system comprising:
a processing device; and
a memory coupled to the processing device and storing instructions that, when executed by the processing device, cause the system to perform operations comprising:
receiving a first communication session comprising a first communication;
identifying an emotion associated with the first communication session;
encoding the first communication session and the emotion as a first vector;
identifying a second vector within a defined proximity of the first vector, the second vector representing a second communication session that includes a second communication; and
responsive to identifying the second vector as being within the defined proximity, providing the second communication within the first communication session in response to the first communication.

### Claim 2 (depends on 1)

The system of claim 1, wherein identifying the second vector comprises identifying the second vector based on the emotion.

### Claim 3 (depends on 1)

The system of claim 1, wherein encoding the first communication session comprises encoding a plurality of communications as the first vector.

### Claim 4 (depends on 1)

The system of claim 1, wherein the first communication session comprises a communication session associated with a first user.

### Claim 5 (depends on 1)

The system of claim 1, wherein the second communication session comprises a communication session associated with a second user.

### Claim 6 (depends on 1)

The system of claim 1, wherein identifying the second vector comprises identifying the second vector within a vector space.

### Claim 7 (depends on 1)

The system of claim 1, wherein identifying the second vector comprises identifying the second vector within a vector index.

### Claim 8

A method comprising:
receiving a first communication session comprising a first communication;
identifying an emotion associated with the first communication session;
encoding the first communication session and the emotion as a first vector;
based on the emotion, identifying a second vector within a defined proximity of the first vector, the second vector representing a second communication session that includes a second communication; and
providing the second communication within the first communication session in response to the first communication.

### Claim 9 (depends on 8)

The method of claim 8, wherein encoding the first communication session comprises encoding a plurality of communications as the first vector.

### Claim 10 (depends on 8)

The method of claim 8, wherein the first communication session comprises a communication session associated with a first user.

### Claim 11 (depends on 8)

The method of claim 8, wherein the second communication session comprises a communication session associated with a second user.

### Claim 12 (depends on 8)

The method of claim 8, wherein identifying the second vector comprises identifying the second vector within a vector space.

### Claim 13 (depends on 8)

The method of claim 8, wherein identifying the second vector comprises identifying the second vector within a vector index.

### Claim 14

A non-transitory computer-readable medium having instructions stored thereon that, when executed by a processing device, cause the processing device to perform operations comprising:
receiving a first communication session comprising a first communication;
identifying an emotion associated with the first communication session;
encoding the first communication session and the emotion as a first vector;
identifying, within a vector space, a second vector within a defined proximity of the first vector, the second vector representing a second communication session that includes a second communication; and
providing the second communication within the first communication session in response to the first communication.

### Claim 15 (depends on 14)

The computer-readable medium of claim 14, wherein identifying the second vector comprises identifying the second vector based on the emotion.

### Claim 16 (depends on 14)

The computer-readable medium of claim 14, wherein encoding the first communication session comprises encoding a plurality of communications as the first vector.