# US 2025/0384875 A1 · Systems and methods for artificial intelligence based reinforcement training and workflow management for one or more chatbots

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

- Number: US 2025/0384875 A1
- Document ID: US20250384875A1
- Status: Published application
- Kind: A1
- Application number: 19/217,706
- Filed: 2025-05-23
- Published: 2025-12-18
- Earliest claimed: 2024-06-13
- Assignees: State Farm Mutual Automobile Insurance Company
- Applicants: State Farm Mutual Automobile Insurance Company
- Inventors: Matthew Mifflin
- Web page: https://patentgrep.com/patent/US20250384875A1

## CPC

- H04L 51/02: using automatic reactions or user delegation, e.g. automatic replies or chatbot-generated messages
- G06F 40/279: Recognition of textual entities
- G06N 20/00: Machine learning
- G10L 15/04: Segmentation; Word boundary detection
- G10L 15/063: {Training}
- G10L 15/16: using artificial neural networks
- G10L 15/1815: {Semantic context, e.g. disambiguation of the recognition hypotheses based on word meaning}
- G10L 15/1822: {Parsing for meaning understanding}
- G10L 15/22: Procedures used during a speech recognition process, e.g. man-machine dialogue
- G10L 15/26: Speech to text systems (G10L15/08 takes precedence)
- G10L 15/30: Distributed recognition, e.g. in client-server systems, for mobile phones or network applications
- G10L 25/93: Discriminating between voiced and unvoiced parts of speech signals (G10L25/90 takes precedence)
- G10L 15/18: using natural language modelling
- G10L 2015/225: {Feedback of the input speech}
- 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)
- G06N: COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G10L: SPEECH ANALYSIS TECHNIQUES OR SPEECH SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING TECHNIQUES; SPEECH OR AUDIO CODING OR DECODING

## Abstract

A computer system for training a plurality of chatbots using artificial intelligence (AI) tools to process statements is provided. The computer system includes an orchestration computing device, and an AI module. The AI module is programmed to: (i) receive a verbal statement of the user including a plurality of words; (ii) translate the verbal statement into a text statement; (iii) augment the text statement by determining at least one intent of the text statement; (iv) provide recommendations for responding to the augmented text statement; (v) analyze the augmented text statement and the recommendations; (vi) generate data representing an audio response to the analyzed augmented text statement; and (vii) present the audio response to the user by causing a selected chatbot to execute the generated data.

## Claims

### Claim 1

A computer system for training a plurality of chatbots using artificial intelligence (AI) tools to process statements, the computer system comprising:
an orchestration computing device comprising at least one first processor in communication with at least one first memory device, and further in communication with a plurality of chatbots and a user computer device associated with a user; and
an AI module comprising at least one second processor in communication with at least one second memory device, and further in communication with the orchestration computing device, the at least one second processor of the AI module programmed to:
receive, from the user computer device via the orchestration computing device, a verbal statement of the user including a plurality of words;
translate the verbal statement into a text statement;
augment the text statement by determining at least one intent of the text statement;
provide recommendations for responding to the augmented text statement;
analyze the augmented text statement and the recommendations;
generate data representing an audio response to the analyzed augmented text statement; and
present the audio response to the user by causing a selected chatbot to execute the generated data.

### Claim 2 (depends on 1)

The computer system of claim 1, wherein the AI module includes an augmentation engine for augmenting the text statement, the augmenting including using cadence matching and utterance detection to determine the at least one intent included in the text statement of the user, wherein cadence matching is used to determine speech patterns of the user thereby enabling subsequent speech to text translations to capture entire thoughts or ideas together in an utterance, and wherein utterance detection is used to capture an entire thought or idea of the user together as a processable grouping of words.

### Claim 3 (depends on 1)

The computer system of claim 1, wherein the AI module includes an augmentation engine for augmenting the text statement, the augmenting including using utterance concatenation and lip reading tools to determine the at least one intent included in the text statement of the user, wherein utterance concatenation is used to identify when the user or caller continues to speak after an utterance is collected thereby providing a more complete idea to be processed and avoid misinterpretations.

### Claim 4 (depends on 1)

The computer system of claim 1, wherein the AI module includes an augmentation engine for augmenting the text statement, the augmenting including using: (i) spelling and grammar correction tools on the text statement, (ii) translation tools, (iii) natural language processing and understanding tools, (iv) data validation tools to validate the data included in the text statement, (v) sensitive data identification for identifying sensitive data included in the text statement, and (vi) data masking of sensitive data.

### Claim 5 (depends on 1)

The computer system of claim 1, wherein the AI module includes a recommendation engine for providing the recommendations for responding to the augmented text statement including use case classification recommendations, wherein a use case classification recommendation is generated and provided to a representative via a representative user interface, and wherein the use case classification recommendation includes a summary of what the user or caller is trying to accomplish with the verbal statement.

### Claim 6 (depends on 1)

The computer system of claim 1, wherein the AI module includes a recommendation engine for providing the recommendations for responding to the augmented text statement including data entry recommendations, wherein a data entry recommendation is generated and provided to a representative via a representative user interface, and wherein the data entry recommendation includes automatically providing labels to data collected for responding to the verbal statement and displaying the labels on the representative user interface to facilitate presentment of the response to the user.

### Claim 7 (depends on 1)

The computer system of claim 1, wherein the AI module includes a recommendation engine for providing the recommendations for responding to the augmented text statement including data request recommendations, wherein a data request recommendation identifies any missing data that is needed to generate the audio response.

### Claim 8 (depends on 1)

The computer system of claim 1, wherein the AI module includes a recommendation engine for providing the recommendations for responding to the augmented text statement including conversation navigation recommendations, wherein a conversation navigation recommendation is generated by applying conversation templates to determine needs of the user from the text statement and how to navigate a conversation with the user using one of the plurality of chatbots.

### Claim 9 (depends on 1)

The computer system of claim 1, wherein the AI module includes a recommendation engine for providing recommendations for responding to the augmented text statement including action recommendations, wherein an action recommendation is generated to update the AI module using re-training techniques that are based upon the augmented text statement and the recommendations generated.

### Claim 10 (depends on 1)

The computer system of claim 1, wherein the AI module includes an augmentation engine for augmenting the text statement, the augmenting including:
detecting one or more pauses in the verbal statement;
dividing the verbal statement into a plurality of utterances based upon the one or more pauses;
identifying, for each of the plurality of utterances, an intent using the orchestration computing device;
selecting, for each of the plurality of utterances, based upon the intent corresponding to the utterance, one of the plurality of chatbots to analyze the utterance; and
generating the audio response by applying the selected chatbot for each of the plurality of utterances.

### Claim 11 (depends on 10)

The computer system of claim 10, wherein the at least one second processor of the AI module is further programmed to:
generate the audio response by determining a priority of each of the plurality of utterances based upon the intents corresponding to each of the plurality of utterances; and
process each of the plurality of utterances in an order corresponding to the determined priority of each utterance.

### Claim 12

A computer-implemented method for training a plurality of chatbots using artificial intelligence (AI) tools to process statements, the computer-implemented method implemented by an AI module including at least one processor in communication with at least one memory device, and further in communication with an orchestration computing device in communication with a plurality of chatbots and a user computer device associated with a user, the computer-implemented method comprising:
receiving, from the user computer device via the orchestration computing device, a verbal statement of the user including a plurality of words;
translating the verbal statement into a text statement;
augmenting the text statement by determining at least one intent of the text statement;
providing recommendations for responding to the augmented text statement;
analyzing the augmented text statement and the recommendations;
generating data representing an audio response to the analyzed augmented text statement; and
presenting the audio response to the user by causing a selected chatbot to execute the generated data.

### Claim 13 (depends on 12)

The computer-implemented method of claim 12, wherein the AI module includes an augmentation engine for augmenting the text statement, the augmenting including using cadence matching and utterance detection to determine the at least one intent included in the text statement of the user, wherein cadence matching is used to determine speech patterns of the user thereby enabling subsequent speech to text translations to capture entire thoughts or ideas together in an utterance, and wherein utterance detection is used to capture an entire thought or idea of the user together as a processable grouping of words.

### Claim 14 (depends on 12)

The computer-implemented method of claim 12, wherein the AI module includes an augmentation engine for augmenting the text statement, the augmenting including using utterance concatenation and lip reading tools to determine the at least one intent included in the text statement of the user, wherein utterance concatenation is used to identify when the user or caller continues to speak after an utterance is collected thereby providing a more complete idea to be processed and avoid misinterpretations.

### Claim 15 (depends on 12)

The computer-implemented method of claim 12, wherein the AI module includes an augmentation engine for augmenting the text statement, the augmenting including using: (i) spelling and grammar correction tools on the text statement, (ii) translation tools, (iii) natural language processing and understanding tools, (iv) data validation tools to validate the data included in the text statement, (v) sensitive data identification for identifying sensitive data included in the text statement, and (vi) data masking of sensitive data.

### Claim 16 (depends on 12)

The computer-implemented method of claim 12, wherein the AI module includes a recommendation engine for providing the recommendations for responding to the augmented text statement including use case classification recommendations, wherein a use case classification recommendation is generated and provided to a representative via a representative user interface, and wherein the use case classification recommendation includes a summary of what the user or caller is trying to accomplish with the verbal statement.

### Claim 17 (depends on 12)

The computer-implemented method of claim 12, wherein the AI module includes a recommendation engine for providing the recommendations for responding to the augmented text statement including data entry recommendations, wherein a data entry recommendation is generated and provided to a representative via a representative user interface, and wherein the data entry recommendation includes automatically providing labels to data collected for responding to the verbal statement and displaying the labels on the representative user interface to facilitate presentment of the response to the user.

### Claim 18 (depends on 12)

The computer-implemented method of claim 12, wherein the AI module includes a recommendation engine for providing the recommendations for responding to the augmented text statement including data request recommendations, wherein a data request recommendation identifies any missing data that is needed to generate the audio response.

### Claim 19 (depends on 12)

The computer-implemented method of claim 12, wherein the AI module includes a recommendation engine for providing the recommendations for responding to the augmented text statement including conversation navigation recommendations, wherein a conversation navigation recommendation is generated by applying conversation templates to determine needs of the user from the text statement and how to navigate a conversation with the user using one of the plurality of chatbots.

### Claim 20

At least one non-transitory computer-readable media having computer-executable instructions embodied thereon, when executed by at least one processor of an AI module in communication with an orchestration computing device, the orchestration computing device further in communication with a plurality of chatbots and a user computer device associated with a user, the computer-executable instructions cause the at least one processor to:
receive, from the user computer device via the orchestration computing device, a verbal statement of the user including a plurality of words;
translate the verbal statement into a text statement;
augment the text statement by determining at least one intent of the text statement;
provide recommendations for responding to the augmented text statement;
analyze the augmented text statement and the recommendations;
generate data representing an audio response to the analyzed augmented text statement; and
present the audio response to the user by causing a selected chatbot to execute the generated data.