# US 2023/0055720 A1 · Visualization of training dialogs for a conversational bot

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

- Number: US 2023/0055720 A1
- Document ID: US20230055720A1
- Status: Published application
- Kind: A1
- Application number: 17/981,708
- Filed: 2022-11-07
- Published: 2023-02-23
- Earliest claimed: 2019-04-18
- Assignees: Microsoft Technology Licensing, LLC
- Applicants: Microsoft Technology Licensing, LLC
- Inventors: Lars H. LIDEN; Swadheen K. SHUKLA; Shahin SHAYANDEH; Matthew D. MAZZOLA
- Web page: https://patentgrep.com/patent/US20230055720A1

## CPC

- G06F 9/453: {Help systems}
- G06N 20/00: Machine learning
- G06F 3/0482: Interaction with lists of selectable items, e.g. menus
- G06F 16/9027: {Trees}
- G06N 5/04: Inference or reasoning models
- H04L 51/02: using automatic reactions or user delegation, e.g. automatic replies or chatbot-generated messages
- H04M 3/42382: {Text-based messaging services in telephone networks such as PSTN/ISDN, e.g. User-to-User Signalling or Short Message Service for fixed networks}
- H04M 2203/355: Interactive dialogue design tools, features or methods
- G06F: ELECTRIC DIGITAL DATA PROCESSING (computer systems based on specific computational models G06N)
- G06N: COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- H04L: TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION (arrangements common to telegraphic and telephonic communication H04M)
- H04M: TELEPHONIC COMMUNICATION (circuits for controlling other apparatus via a telephone cable and not involving telephone switching apparatus G08)

## Abstract

This document relates to creating and/or updating a chatbot using a graphical user interface. For example, training dialogs for a chatbot can be displayed in a tree form on a graphical user interface. Based at least on interactions between a developer and the graphical user interface, the training dialogs can be modified in the tree form, and training dialogs can be updated based on the modifications provided on the tree form via the graphical user interface.

## Claims

### Claim at position 1

1-20. (canceled)

### Claim 21

A system comprising:
a processor; and
a storage memory storing computer-readable instructions, which when executed by the processor, cause the processor to:
access data associated with training dialogs that represent interactions with a chatbot, the training dialogs employed to train a machine learning model used by the chatbot;
identify first decisions of the chatbot that are based at least on declarative rules and second decisions of the chatbot that are based at least on machine learning by the machine learning model used by the chatbot; and
present the first decisions and the second decisions in a tree form where the first decisions are presented in the tree form differently from the second decisions.

### Claim 22 (depends on 21)

The system of claim 21, wherein the computer-readable instructions, when executed by the processor, cause the processor to:
depict the first decisions in the tree form as first connections between rounds of dialog performed by the chatbot; and
depict the second decisions in the tree form as second connections between rounds of dialog performed by the chatbot.

### Claim 23 (depends on 22)

The system of claim 22, wherein the first connections and the second connections are conveyed as different types of connecting lines.

### Claim 24 (depends on 22)

The system of claim 22, wherein the first connections are depicted as single lines and the second connections are depicted as double lines.

### Claim 25 (depends on 22)

The system of claim 22, wherein the computer-readable instructions, when executed by the processor, cause the processor to:
receive user input selecting and editing a particular second decision from the tree form; and
update the chatbot based at least on the user input.

### Claim 26 (depends on 25)

The system of claim 25, wherein the computer-readable instructions, when executed by the processor, cause the processor to:
update an entity extractor of the chatbot based at least on a new entity identified by the user input.

### Claim 27 (depends on 25)

The system of claim 25, wherein the computer-readable instructions, when executed by the processor, cause the processor to:
update a response model of the chatbot based at least on new output identified by the user input.

### Claim 28

A method comprising:
accessing data associated with training dialogs that represent interactions with a chatbot, the training dialogs employed to train a machine learning model used by the chatbot;
identifying first decisions of the chatbot that are based at least on declarative rules and second decisions of the chatbot that are based at least on machine learning by the machine learning model used by the chatbot; and
presenting the first decisions and the second decisions in a graph form where the first decisions are presented in the graph form differently from the second decisions.

### Claim 29 (depends on 28)

The method of claim 28, wherein the graph form is a tree.

### Claim 30 (depends on 28)

The method of claim 28, wherein the graph form is a directed graph.

### Claim 31 (depends on 28)

The method of claim 28, further comprising:
depicting the first decisions in the graph form as first connections between rounds of dialog performed by the chatbot; and
depicting the second decisions in the graph form as second connections between rounds of dialog performed by the chatbot.

### Claim 32 (depends on 31)

The method of claim 31, wherein the first connections and the second connections are conveyed as different types of connecting lines.

### Claim 33 (depends on 31)

The method of claim 31, wherein the first connections are depicted as single lines and the second connections are depicted as double lines.

### Claim 34 (depends on 28)

The method of claim 28, further comprising:
receiving user input selecting and editing a particular second decision from the graph form; and
updating the chatbot based at least on the user input.

### Claim 35 (depends on 34)

The method of claim 34, further comprising:
updating an entity extractor of the chatbot based at least on a new entity identified by the user input.

### Claim 36 (depends on 34)

The method of claim 34, further comprising:
updating a response model of the chatbot based at least on new output identified by the user input.

### Claim 37

A method comprising:
accessing data associated with training dialogs that represent interactions with a chatbot;
presenting conversational rounds of the chatbot in a graph form, the conversational rounds being based on one or more of declarative rules, programmatic coding, or machine learning by the chatbot;
receiving input dragging a particular round of the chatbot from a first branch of the graph form to a second branch of the graph form; and
updating the training dialogs based at least on the dragging of the particular round of the chatbot from the first branch of the graph form to the second branch of the graph form.

### Claim 38 (depends on 37)

The method of claim 37, wherein the updating comprises injecting particular training dialogs previously associated with the first branch into the second branch.

### Claim 39 (depends on 38)

The method of claim 38, further comprising:
updating at least one of a response model or an entity extractor of the chatbot based at least on the injecting of the particular training dialogs into the second branch.

### Claim 40 (depends on 37)

The method of claim 37, further comprising:
responsive to further user input, replicating another dialog round of the chatbot in an additional branch of the graph form.
