# US 2020/0401770 A1 · Applied Artificial Intelligence Technology for Performing Natural Language Generation (NLG) Using Composable Communication Goals and Ontologies to Generate Narrative Stories

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

- Number: US 2020/0401770 A1
- Document ID: US20200401770A1
- Status: Published application
- Kind: A1
- Application number: 16/987,509
- Filed: 2020-08-07
- Published: 2020-12-24
- Earliest claimed: 2017-02-17
- Assignees: Narrative Science Inc.
- Applicants: Narrative Science Inc.
- Inventors: Andrew R. Paley; Nathan Drew Nichols; Matthew Lloyd Trahan; Maia Jane Lewis Meza; Lawrence A. Birnbaum; Kristian J. Hammond
- Web page: https://patentgrep.com/patent/US20200401770A1

## CPC

- G06F 40/56: Natural language generation
- G06F 16/367: {Ontology}
- G06F 40/166: Editing, e.g. inserting or deleting
- G06F 40/169: Annotation, e.g. comment data or footnotes
- G06F 40/174: Form filling; Merging
- G06F 40/20: Natural language analysis (semantic analysis of natural language G06F40/30)
- G06F 40/295: Named entity recognition
- G06F 40/30: Semantic analysis
- G06N 5/02: Knowledge representation; Symbolic representation
- G06N 5/022: Knowledge engineering; Knowledge acquisition
- G06N 5/025: Extracting rules from data
- G06N 5/043: Distributed expert systems; Blackboards
- G06Q 10/10: Office automation; Time management
- G06F 40/106: Display of layout of documents; Previewing
- G06N 5/04: Inference or reasoning models
- G06F: ELECTRIC DIGITAL DATA PROCESSING (computer systems based on specific computational models G06N)
- G06N: COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- 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

## Abstract

Artificial intelligence (AI) technology can be used process natural language statements to facilitate the automated generation of narratives about data sets that achieve a desired communication goal without any need for a user to directly author computer code. This AI technology permits NLG systems to determine the appropriate content for inclusion in the narrative in a manner that will satisfy the desired communication goal.

## Claims

### Claim 1

An artificial intelligence system for generating a natural language narrative from structured data, the system comprising:
a memory configured to store a plurality of narrative analytics;
a processor for cooperation with the memory, the processor configured to:
process a natural language statement by mapping the natural language statement to (i) a subset of the narrative analytics and (ii) a plurality of data requirements for the narrative analytics within the subset, wherein the natural language statement corresponds to a communication goal to be achieved by the natural language narrative;
map the data requirements to data within the structured data;
execute the narrative analytics within the subset based on the mapped data within the structured data to determine a plurality of content items for inclusion in the natural language narrative; and
perform natural language generation (NLG) on the determined content items to generate the natural language narrative, wherein the natural language narrative expresses the determined content items in a manner that satisfies the communication goal.

### Claim 2 (depends on 1)

The system of claim 1 wherein the narrative analytics comprise parameterized computer code that performs analytical operations on the structured data in order to facilitate a determination as to what content is to be included in the natural language narrative so that the communication goal is satisfied.

### Claim 3 (depends on 2)

The system of claim 2 wherein the parameterized code for the narrative analytics within the subset are configured for execution to determine the content using the mapped data within the structured data as parameters for the execution.

### Claim 4 (depends on 3)

The system of claim 3 wherein the processor is further configured to receive the natural language statement as input from a user.

### Claim 5 (depends on 4)

The system of claim 4 wherein the processor is arranged to perform its operations to generate the natural language narrative without requiring the user to directly author program code.

### Claim 6 (depends on 1)

The system of claim 1 wherein the memory is further configured to store an ontology, and wherein the processor is further configured to process the natural language statement in coordination with the ontology to map the natural language statement to (i) the subset of the narrative analytics and (ii) the data requirements for the narrative analytics within the subset.

### Claim 7 (depends on 6)

The system of claim 6 wherein the natural language statement comprises an operator expressed in natural language and at least one parameter expressed in natural language, and wherein the processor is further configured to (1) determine the mapped narrative analytics subset based at least in part on the operator, (2) map the at least one parameter to an ontological object within the ontology, and (3) determine the data requirements based at least in part on the mapped ontological object.

### Claim 8 (depends on 1)

The system of claim 1 wherein at least one of the narrative analytics within the narrative analytics subset is configured to generate a characterization of the structured data in response to execution of the at least one narrative analytic, and wherein the natural language narrative expresses the characterization in natural language.

### Claim 9 (depends on 1)

The system of claim 1 wherein the processor comprises a plurality of processors.

### Claim 10

A computer program product for applying artificial intelligence to generate a natural language narrative from structured data, the computer program product comprising
a plurality of instructions resident on a non-transitory computer-readable storage medium, wherein the instructions are executable by a processor to a cause the processor to:
access a memory that is configured to store a plurality of narrative analytics;
process a natural language statement by mapping the natural language statement to (i) a subset of the narrative analytics and (ii) a plurality of data requirements for the narrative analytics within the subset, wherein the natural language statement corresponds to a communication goal to be achieved by the natural language narrative;
map the data requirements to data within the structured data;
execute the narrative analytics within the subset based on the mapped data within the structured data to determine a plurality of content items for inclusion in the natural language narrative; and
perform natural language generation (NLG) on the determined content items to generate the natural language narrative, wherein the natural language narrative expresses the determined content items in a manner that satisfies the communication goal.

### Claim 11

A method of applying artificial intelligence to generate a natural language narrative from structured data, the method comprising:
a processor accessing a memory in which a plurality of narrative analytics are stored;
the processor processing a natural language statement by mapping the natural language statement to (i) a subset of the narrative analytics and (ii) a plurality of data requirements for the narrative analytics within the subset, wherein the natural language statement corresponds to a communication goal to be achieved by the natural language narrative;
the processor mapping the data requirements to data within the structured data;
the processor executing the narrative analytics within the subset based on the mapped data within the structured data to determine a plurality of content items for inclusion in the natural language narrative; and
the processor performing natural language generation (NLG) on the determined content items to generate the natural language narrative, wherein the natural language narrative expresses the determined content items in a manner that satisfies the communication goal.

### Claim 12 (depends on 11)

The method of claim 11 wherein the narrative analytics comprise parameterized computer code that performs analytical operations on the structured data in order to facilitate a determination as to what content is to be included in the natural language narrative so that the communication goal is satisfied.

### Claim 13 (depends on 12)

The method of claim 12 wherein the executing step comprises executing the parameterized code for the narrative analytics within the subset to determine the content using the mapped data within the structured data as parameters for the execution.

### Claim 14 (depends on 13)

The method of claim 13 further comprising:
the processor receiving the natural language statement as input from a user.

### Claim 15 (depends on 14)

The method of claim 14 wherein the processor performs the method steps to generate the natural language narrative without requiring the user to directly author program code.

### Claim 16 (depends on 11)

The method of claim 11 further comprising:
the processor accessing an ontology; and
wherein the processing step comprises the processor processing the natural language statement in coordination with the accessed ontology to map the natural language statement to (i) the subset of the narrative analytics and (ii) the data requirements for the narrative analytics within the subset.

### Claim 17 (depends on 16)

The method of claim 16 wherein the natural language statement comprises an operator expressed in natural language and at least one parameter expressed in natural language, and wherein the processing step further comprises the processor (1) determining the mapped narrative analytics subset based at least in part on the operator, (2) mapping the at least one parameter to an ontological object within the ontology, and (3) determining the data requirements based at least in part on the mapped ontological object.

### Claim 18 (depends on 11)

The method of claim 11 wherein the executing of at least one of the narrative analytics within the narrative analytics subset generates a characterization of the structured data, and wherein the natural language narrative expresses the characterization in natural language.

### Claim 19 (depends on 11)

The method of claim 11 wherein the processor comprises a plurality of processors.
