# US 2025/0156642 A1 · Semantic text segmentation based on topic recognition

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

- Number: US 2025/0156642 A1
- Document ID: US20250156642A1
- Status: Published application
- Kind: A1
- Application number: 18/507,322
- Filed: 2023-11-13
- Published: 2025-05-15
- Earliest claimed: 2023-11-13
- Assignees: Microsoft Technology Licensing, LLC
- Applicants: Microsoft Technology Licensing, LLC
- Inventors: Mattan SERRY; Oron NIR
- Web page: https://patentgrep.com/patent/US20250156642A1

## CPC

- G06F 40/30: Semantic analysis
- G06F 40/284: Lexical analysis, e.g. tokenisation or collocates
- G06F: ELECTRIC DIGITAL DATA PROCESSING (computer systems based on specific computational models G06N)

## Abstract

Systems and methods for semantic temporal segmentation based on topic recognition are disclosed. Text classification and segmentation may be used to index media content for subsequent searches. The method may include using a text classification model to semantically analyze sentences in a text file (such as a transcript) to determine topics with which sentences are associated. The output of the text classification model may be provided to a text segmentation model to enable more-accurate identification of text segments (e.g., paragraphs) within the text file. In some examples, the output of a text segmentation model is provided to a text classification model to enable the text classification model to perform more-accurate classification based on text segments rather than (or in addition to) performing classification on single sentences. The classification of the text segments may be used to assign labels to the text segments to enable subsequent searches based on the labels.

## Claims

### Claim 1

A computer-implemented method, comprising:
obtaining a first set of tokens associated with a first sentence of a transcript and a second set of tokens associated with a second sentence of the transcript;
determining, based on the first set of tokens, a first probability that a first class is associated with the first sentence;
determining, based on the second set of tokens, a second probability that the first class is associated with the second sentence;
identifying a first text segment that includes the first sentence and the second sentence based on the first probability, a first timestamp associated with the first sentence, the second probability, and a second timestamp associated with the second sentence; and
determining, based on the first text segment, a third probability that the first class is associated with the first text segment.

### Claim 2 (depends on 1)

The computer-implemented method of claim 1, wherein the first probability, the second probability, and the third probability are determined by a text classification model comprising a neural network, the method further comprising:
adjusting a parameter of the text classification model based on the third probability.

### Claim 3 (depends on 1)

The computer-implemented method of claim 1, further comprising:
determining a label associated with the first text segment based on the third probability; and
outputting the label associated with the first text segment.

### Claim 4 (depends on 3)

The computer-implemented method of claim 3, further comprising:
storing, with the label associated with the first text segment, a first timestamp associated with the first text segment, wherein the first timestamp is determined based on a second timestamp associated with the first sentence, a third timestamp associated with the second sentence, or both.

### Claim 5 (depends on 4)

The computer-implemented method of claim 4, further comprising:
after storing the label and the first timestamp associated with the first text segment, receiving a user input indicating a selection of the label;
in response to receiving the user input, retrieving the first timestamp based on the label;
identifying, based on the first timestamp, a portion of media content corresponding to the first timestamp; and
presenting the portion of the media content.

### Claim 6 (depends on 1)

The computer-implemented method of claim 1, further comprising:
transcribing media content to generate a plurality of sentences including the first sentence and the second sentence;
tokenizing the first sentence to generate the first set of tokens; and
tokenizing the second sentence to generate the second set of tokens.

### Claim 7 (depends on 1)

The computer-implemented method of claim 1, wherein determining the first probability comprises:
encoding the first sentence into an embeddings vector using the first set of tokens; and
determining the first probability based on the embeddings vector.

### Claim 8

A computer-implemented method, comprising:
generating a first embeddings vector representing semantic content of a first sentence of a transcript and a second embeddings vector representing semantic content of a second sentence of the transcript;
generating an adjusted first embeddings vector based on the first embeddings vector and the second embeddings vector by adjusting the first embeddings vector;
generating an adjusted second embeddings vector based on the first embeddings vector and the second embeddings vector by adjusting the second embeddings vector;
identifying, based on the adjusted first embeddings vector and the adjusted second embeddings vector, a first text segment that includes the first sentence and the second sentence;
determining, based on the first text segment, a probability that a first class is associated with the first text segment; and
outputting a label associated with the first text segment based on the probability.

### Claim 9 (depends on 8)

The computer-implemented method of claim 8, further comprising:
transcribing media content to generate a transcript comprising the first sentence and the second sentence.

### Claim 10 (depends on 8)

The computer-implemented method of claim 8, wherein the first sentence is associated with a first timestamp and the second sentence is associated with a second timestamp, the method further comprising:
determining a timestamp associated with the first text segment based on the first timestamp, the second timestamp, or both; and
storing the label associated with the first text segment with the timestamp associated with the first text segment.

### Claim 11 (depends on 10)

The computer-implemented method of claim 10, further comprising:
after storing the label and the timestamp associated with the first text segment, receiving a user input indicating a selection of the label;
in response to receiving the user input, retrieving the timestamp based on the label;
identifying, based on the timestamp, a portion of media content corresponding to the timestamp; and
presenting the portion of the media content.

### Claim 12 (depends on 8)

The computer-implemented method of claim 8, wherein the first embeddings vector is generated by a first text encoder in parallel with the second embeddings vector being generated by a second text encoder.

### Claim 13 (depends on 12)

The computer-implemented method of claim 12, wherein a fusion-layer transformer adjusts the first embeddings vector and the second embeddings vector based on an output of a global attention mechanism executed on the first embeddings vector and the second embeddings vector.

### Claim 14

A system, comprising:
one or more processing systems; and
memory storing instructions that, when executed by the one or more processing systems, cause the system to:
obtain a first set of tokens associated with a first sentence of a transcript and a second set of tokens associated with a second sentence of the transcript;
determine, based on the first set of tokens, a first probability that a first class is associated with the first sentence;
determine, based on the second set of tokens, a second probability that the first class is associated with the second sentence;
identify a first text segment that includes the first sentence and the second sentence based on the first probability, a first timestamp associated with the first sentence, the second probability, and a second timestamp associated with the second sentence; and
determine, based on the first text segment, a third probability that the first class is associated with the first text segment.

### Claim 15 (depends on 14)

The system of claim 14, wherein the first probability, the second probability, and the third probability are determined by a text classification model comprising a neural network and the instructions further cause the system to:
adjust a parameter of the text classification model based on the third probability.

### Claim 16 (depends on 14)

The system of claim 14, wherein the instructions further cause the system to:
determine a label associated with the first text segment based on the third probability; and
output the label associated with the first text segment.

### Claim 17 (depends on 16)

The system of claim 16, wherein the instructions further cause the system to:
store, with the label associated with the first text segment, a first timestamp associated with the first text segment, wherein the first timestamp is determined based on a second timestamp associated with the first sentence a third timestamp associated with the second sentence, or both.

### Claim 18 (depends on 17)

The system of claim 17, wherein the instructions further cause the system to:
after storing the label and the first timestamp associated with the first text segment, receive a user input indicating a selection of the label;
in response to receiving the user input, retrieve the first timestamp based on the label;
identify, based on the first timestamp, a portion of media content corresponding to the first timestamp; and
present the portion of the media content.

### Claim 19 (depends on 14)

The system of claim 14, wherein the instructions further cause the system to:
transcribe media content to generate a plurality of sentences including the first sentence and the second sentence;
tokenize the first sentence to generate the first set of tokens; and
tokenize the second sentence to generate the second set of tokens.

### Claim 20 (depends on 14)

The system of claim 14, wherein determining the first probability comprises:
encoding the first sentence into an embeddings vector using the first set of tokens; and
determining the first probability based on the embeddings vector.
