# US 11,308,285 B2 · Triangulated natural language decoding from forecasted deep semantic representations

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

- Number: US 11,308,285 B2
- Document ID: US11308285B2
- Status: Granted
- Kind: B2
- Application number: 16/670,773
- Filed: 2019-10-31
- Published: 2021-05-06
- Granted: 2022-04-19
- Earliest claimed: 2019-10-31
- Assignees: International Business Machines Corporation
- Applicants: International Business Machines Corporation
- Inventors: Aaron K. Baughman; Micah Forster; John C. Newell; Stephen C. Hammer
- Web page: https://patentgrep.com/patent/US11308285B2

## CPC

- G06F 40/284: Lexical analysis, e.g. tokenisation or collocates
- G06F 40/30: Semantic analysis
- G06F 16/3347: {using vector based model}
- G06F 40/295: Named entity recognition
- G06F: ELECTRIC DIGITAL DATA PROCESSING (computer systems based on specific computational models G06N)

## Abstract

Computer-implemented method includes developing, via a processor, a words model from a plurality of natural language text based articles relating to a subject and generating, via the processor, a static vector based upon the words model. The computer-implemented method further includes developing, via the processor, an actual articles model from actual articles, generating, via the processor, a bootstrapped vector using the actual articles model, generating, via the processor, a n-dimensional depth item using the static vector and the bootstrapped vector, and determining, via the processor, evidence based on the n-dimensional depth item. The computer-implemented method still further includes presenting, via the processor and a display, the evidence base upon an input query from a user.

## Claims

### Claim 1

A computer-implemented method comprising:
developing, via a processor, a words model from a plurality of natural language text based articles relating to a subject;
generating, via the processor, a static vector based upon the words model;
developing, via the processor, an actual articles model from actual articles;
generating, via the processor, a bootstrapped vector using the actual articles model;
generating, via the processor, a n-dimensional depth item using the static vector and the bootstrapped vector;
determining, via the processor, evidence based on the n-dimensional depth item;
generating, via the processor, a forecast vector based upon historical articles; and
presenting, via the processor and a display, the evidence base upon an input query from a user.

### Claim 2 (depends on 1)

The computer-implemented method according to claim 1, further comprising modifying, via the processor, the n-dimensional depth item using the forecast vector.

### Claim 3 (depends on 1)

The computer-implemented method according to claim 1, wherein the presented evidence determines how keywords are trending over time.

### Claim 4 (depends on 1)

The computer-implemented method according to claim 1, wherein the n-dimensional depth item forms a geographic boundary.

### Claim 5 (depends on 4)

The computer-implemented method according to claim 4, further comprising generating, via the processor, a forecast vector based upon historical articles.

### Claim 6 (depends on 5)

The computer-implemented method according to claim 5, wherein the forecast vector, the static vector and the bootstrapped vector form a triangle area, such that a lowest triangle area produces better evidence for the user.

### Claim 7 (depends on 1)

The computer-implemented method according to claim 1, wherein the presented evidence determines how concepts are trending over time.

### Claim 8 (depends on 1)

The computer-implemented method according to claim 1, wherein the presented evidence determines how entities are trending over time.

### Claim 9

A system comprising:
a memory having computer readable instructions; and
one or more processors for executing the computer readable instructions, the computer readable instructions controlling the one or more processors to perform operations comprising:
developing a words model from a plurality of natural language text based articles relating to a subject;
generating a static vector based upon the words model;
developing an actual articles model from actual articles;
generating a bootstrapped vector using the actual articles model;
generating a n-dimensional depth item using the static vector and the bootstrapped vector;
determining evidence based on the n-dimensional depth item;
generating a forecast vector based upon historical articles; and
presenting, via a display, the evidence base upon an input query from a user.

### Claim 10 (depends on 9)

The system according to claim 9, further comprising modifying the n-dimensional depth item using the forecast vector.

### Claim 11 (depends on 9)

The system according to claim 9, wherein the presented evidence determines how keywords are trending over time.

### Claim 12 (depends on 9)

The system according to claim 9, wherein the n-dimensional depth item forms a geographic boundary.

### Claim 13 (depends on 12)

The system according to claim 12, further comprising generating a forecast vector based upon historical articles.

### Claim 14 (depends on 13)

The system according to claim 13, wherein the forecast vector, the static vector and the bootstrapped vector form a triangle area, such that a lowest triangle area produces better evidence for the user.

### Claim 15 (depends on 9)

The system according to claim 9, wherein the presented evidence determines how concepts are trending over time.

### Claim 16 (depends on 9)

The system according to claim 9, wherein the presented evidence determines how entities are trending over time.

### Claim 17

A computer program product comprising a computer readable storage medium having program instructions embodied therewith, the program instructions executable by a processor to cause the processor to perform operations comprising:
developing a words model from a plurality of natural language text based articles relating to a subject;
generating a static vector based upon the words model;
developing an actual articles model from actual articles;
generating a bootstrapped vector using the actual articles model;
generating a n-dimensional depth item using the static vector and the bootstrapped vector;
determining evidence based on the n-dimensional depth item;
generating a forecast vector based upon historical articles; and
presenting, via a display, the evidence base upon an input query from a user.

### Claim 18 (depends on 17)

The computer program product according to claim 17, wherein the n-dimensional depth item forms a geographic boundary and the forecast vector, the static vector and the bootstrapped vector form a triangle area, such that a lowest triangle area produces better evidence for the user.