# US 11,308,964 B2 · Systems and methods for cooperatively-overlapped and artificial intelligence managed interfaces

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

- Number: US 11,308,964 B2
- Document ID: US11308964B2
- Status: Granted
- Kind: B2
- Application number: 16/995,971
- Filed: 2020-08-18
- Published: 2020-12-03
- Granted: 2022-04-19
- Earliest claimed: 2018-06-27
- Assignees: The Travelers Indemnity Company
- Applicants: The Travelers Indemnity Company
- Inventors: Douglas Calegari; Stephen Ziegelmayer
- Web page: https://patentgrep.com/patent/US11308964B2

## CPC

- G10L 15/22: Procedures used during a speech recognition process, e.g. man-machine dialogue
- G06F 3/048: Interaction techniques based on graphical user interfaces [GUI]
- G06F 9/453: {Help systems}
- G06F 16/3329: Natural language query formulation
- G06N 3/04: Architecture, e.g. interconnection topology
- G06N 3/0499: Feedforward networks
- G06N 3/08: Learning methods
- G06N 3/09: Supervised learning
- G06N 3/105: {Shells for specifying net layout}
- G06Q 40/08: Insurance
- H04L 51/02: using automatic reactions or user delegation, e.g. automatic replies or chatbot-generated messages
- G10L: SPEECH ANALYSIS TECHNIQUES OR SPEECH SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING TECHNIQUES; SPEECH OR AUDIO CODING OR DECODING
- 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
- H04L: TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION (arrangements common to telegraphic and telephonic communication H04M)

## Abstract

Systems, apparatus, methods, and articles of manufacture for cooperatively-overlapped and Artificial Intelligence (AI)-managed interfaces. For example, multiple cooperatively and/or partially overlapped interfaces may be provided (e.g., via an electronic and/or touch-screen device), with such interfaces being dynamically managed by various AI components, such as natural language processing, machine learning techniques, and/or neural network data processing.

## Claims

### Claim 1

A method for providing artificial intelligence feedback to guide an interface experience of a user, comprising:
generating, by an electronic processing device executing a primary interface engine, a primary interface comprising a plurality of primary interface elements;
generating, by the electronic processing device executing a secondary interface engine, a secondary interface comprising at least one secondary interface element;
storing, by at least one non-transitory data storage device, (i) structured data, (ii) unstructured data, (iii) at least one natural language model, (iv) at least one neural network model, (v) instructions defining a natural language engine, (vi) instructions defining a neural network engine, and (vii) instructions defining a response engine;
acquiring, by the electronic processing device and from at least one of the plurality of primary interface elements of the primary interface, at least one user input;
analyzing, by the electronic processing device executing the natural language engine and utilizing the at least one natural language model, the at least one user input;
defining, by the electronic processing device executing the natural language engine and based on the analyzing of the at least one user input, a predicted intent of the user;
analyzing, by the electronic processing device executing the neural network engine and utilizing the at least one neural network model, the predicted intent of the user;
defining, by the electronic processing device executing the neural network engine and based on the analyzing of the predicted intent of the user, a query for at least one of the structured data and the unstructured data;
querying, by the electronic processing device and utilizing the query for the at least one of the structured data and the unstructured data, the at least one of the structured data and the unstructured data;
receiving, by the electronic processing device and in response to the querying, a subset of the at least one of the structured data and the unstructured data;
generating, by the electronic processing device executing the response engine and utilizing the predicted intent of the user and the subset of the at least one of the structured data and the unstructured data, a natural language response comprising a sentence that includes data from the subset of the at least one of the structured data and the unstructured data;
identifying, by the electronic processing device, a position of the at least one of the plurality of primary interface elements of the primary interface;
defining, by the electronic processing device executing the secondary interface engine and based on the position of the at least one of the plurality of primary interface elements of the primary interface, at least one of a size and a position of the secondary interface such that the secondary interface selectively overlaps at least a portion of the primary interface, but does not overlap with the at least one of the plurality of primary interface elements of the primary interface; and
providing, by the electronic processing device and via the at least one secondary interface element of the secondary interface, the natural language response.

### Claim 2 (depends on 1)

The method of claim 1, wherein the at least one non-transitory data storage device further stores (viii) a natural language training data set, further comprising:
defining, by the electronic processing device executing the natural language engine and utilizing the natural language training data set, the at least one natural language model.

### Claim 3 (depends on 1)

The method of claim 1, wherein the at least one non-transitory data storage device further stores (viii) a neural network training data set, further comprising:
defining, by the electronic processing device executing the neural network engine and utilizing the neural network training data set, the at least one neural network model.

### Claim 4 (depends on 3)

The method of claim 3, wherein the at least one non-transitory data storage device further stores (ix) at least one topic model, further comprising:
selecting, by the electronic processing device executing the neural network engine and utilizing the at least one topic model, the neural network training data set from a plurality of available neural network training data sets.

### Claim 5 (depends on 1)

The method of claim 1, wherein the at least one user input comprises data defining an underwriting action.

### Claim 6

A non-transitory data storage device for providing artificial intelligence feedback to guide an interface experience of a user, the non-transitory data storage device storing (i) structured data, (ii) unstructured data, (iii) at least one natural language model, (iv) at least one neural network model, (v) instructions defining a natural language engine, (vi) instructions defining a neural network engine, and (vii) instructions defining a response engine, wherein execution of the (a) instructions defining the natural language engine, (b) instructions defining the neural network engine, and (c) instructions defining the response engine, by an electronic processing device, results in:
generating, by the electronic processing device executing a primary interface engine, a primary interface comprising a plurality of primary interface elements;
generating, by the electronic processing device executing a secondary interface engine, a secondary interface comprising at least one secondary interface element;
acquiring, by the electronic processing device and from at least one of the plurality of primary interface elements of the primary interface, at least one user input;
analyzing, by the electronic processing device executing the natural language engine and utilizing the at least one natural language model, the at least one user input;
defining, by the electronic processing device executing the natural language engine and based on the analyzing of the at least one user input, a predicted intent of the user;
analyzing, by the electronic processing device executing the neural network engine and utilizing the at least one neural network model, the predicted intent of the user;
defining, by the electronic processing device executing the neural network engine and based on the analyzing of the predicted intent of the user, a query for at least one of the structured data and the unstructured data;
querying, by the electronic processing device and utilizing the query for the at least one of the structured data and the unstructured data, the at least one of the structured data and the unstructured data;
receiving, by the electronic processing device and in response to the querying, a subset of the at least one of the structured data and the unstructured data;
generating, by the electronic processing device executing the response engine and utilizing the predicted intent of the user and the subset of the at least one of the structured data and the unstructured data, a natural language response comprising a sentence that includes data from the subset of the at least one of the structured data and the unstructured data;
identifying, by the electronic processing device, a position of the at least one of the plurality of primary interface elements of the primary interface;
defining, by the electronic processing device executing the secondary interface engine and based on the position of the at least one of the plurality of primary interface elements of the primary interface, at least one of a size and a position of the secondary interface such that the secondary interface selectively overlaps at least a portion of the primary interface, but does not overlap with the at least one of the plurality of primary interface elements of the primary interface; and
providing, by the electronic processing device and via the at least one secondary interface element of the secondary interface, the natural language response.

### Claim 7 (depends on 6)

The non-transitory data storage device of claim 6, wherein the non-transitory data storage device further stores (viii) a natural language training data set, and wherein execution of the (a) instructions defining the natural language engine, (b) instructions defining the neural network engine, and (c) instructions defining the response engine, by the electronic processing device, further results in:
defining, by the electronic processing device executing the natural language engine and utilizing the natural language training data set, the at least one natural language model.

### Claim 8 (depends on 6)

The non-transitory data storage device of claim 6, wherein the non-transitory data storage device further stores (viii) a neural network training data set, and wherein execution of the (a) instructions defining the natural language engine, (b) instructions defining the neural network engine, and (c) instructions defining the response engine, by the electronic processing device, further results in:
defining, by the electronic processing device executing the neural network engine and utilizing the neural network training data set, the at least one neural network model.

### Claim 9 (depends on 8)

The non-transitory data storage device of claim 8, wherein the non-transitory data storage device further stores (ix) at least one topic model, and wherein execution of the (a) instructions defining the natural language engine, (b) instructions defining the neural network engine, and (c) instructions defining the response engine, by the electronic processing device, further results in:
selecting, by the electronic processing device executing the neural network engine and utilizing the at least one topic model, the neural network training data set from a plurality of available neural network training data sets.

### Claim 10 (depends on 6)

The non-transitory data storage device of claim 6, wherein the at least one user input comprises data defining an underwriting action.