US-20260127215-A1 - ANALYSIS AND CLUSTERING OF UNSTRUCTURED COMPUTER TEXT FOR GENERATION OF A STRUCTURED CONVERSATION FLOW FOR A CONVERSATION SERVICE APPLICATION

Abstract

Methods and apparatuses in which unstructured computer text is analyzed for generation of a structured conversation flow for a conversation service application include a server that extracts a sequence of questions from historical voice call transcripts. The server converts each of the extracted questions into a multidimensional embedding using a sentence transformer. The server clusters the multidimensional embeddings into question clusters using a similarity measure algorithm. Each of the question clusters is assigned a cluster identification label. The server generates, for each historical voice call transcript, a sequence of cluster identification labels corresponding to the sequence of questions. The server creates a conversation flow graph for each historical voice call transcript based upon the associated sequence of cluster identification labels.

Inventors

• Pinky Budania
• Nitin Kumar
• SIDDHARTH THAKUR
• Ankit GARG
• Bidhan Roy

Assignees

• FMR LLC

Dates

Publication Date

20260507

Application Date

20241105

Claims (20)

1. 1 . A system used in a computing environment in which unstructured computer text is analyzed for generation of a structured conversation flow for a conversation service application, the system comprising a server computing device having a memory for storing computer-executable instructions and a processor that executes the computer-executable instructions to: extract a sequence of questions from each of a plurality of historical voice call transcripts by executing, using the processor, a combined rule-based and natural language processing machine learning model on the plurality of historical voice call transcripts; convert each of the extracted questions into a multidimensional embedding using a sentence transformer machine learning model; cluster the multidimensional embeddings into one or more question clusters using a similarity measure algorithm, each of the question clusters assigned a cluster identification label; generate, for each historical voice call transcript, a sequence of cluster identification labels corresponding to the sequence of questions extracted from the call transcript; and create a conversation flow graph for each historical voice call transcript based upon the associated sequence of cluster identification labels.
2. 2 . The system of claim 1 , wherein the server computing device modifies a conversation flow of the conversation service application using the conversation flow graph.
3. 3 . The system of claim 2 , wherein modifying a conversation flow of the conversation service application comprises rearranging a sequence of prompts in a conversation flow of the conversation service application, adding one or more prompts to a conversation flow of the conversation service application, removing one or more prompts from a conversation flow of the conversation service application, or changing content of one or more prompts in a conversation flow of the conversation service application.
4. 4 . The system of claim 3 , wherein the conversation service application comprises a chatbot application, an interactive voice response (IVR) application, a virtual assistant application, or a guided service application.
5. 5 . The system of claim 1 , wherein the server computing device preprocesses the plurality of historical voice call transcripts before executing the combined rule-based and natural language processing machine learning model on the plurality of historical voice call transcripts.
6. 6 . The system of claim 5 , wherein preprocessing the plurality of historical voice call transcripts comprises: replacing one or more regular expressions in the historical voice call transcripts with default values; detecting boundaries between sentences in the historical voice call transcripts; and inserting punctuation at each sentence boundary in the historical voice call transcripts.
7. 7 . The system of claim 6 , wherein the server computing device executes a natural language processing model to replace the regular expressions and the server computing device executes a large language model to detect the boundaries and insert the punctuation.
8. 8 . The system of claim 1 , wherein the similarity measure algorithm comprises a k-means clustering algorithm or an hdbscan algorithm.
9. 9 . The system of claim 1 , wherein the conversation flow graph comprises a data structure with a plurality of nodes connected via edges and arranged according to the sequence of cluster identification labels.
10. 10 . The system of claim 1 , wherein the server computing device merges at least two of the conversation flow graphs to generate an aggregate conversation flow graph.
11. 11 . A computerized method in which unstructured computer text is analyzed for generation of a structured conversation flow for a conversation service application, the method comprising: extracting, by a server computing device, a sequence of questions from each of a plurality of historical voice call transcripts by executing, using the processor, a combined rule-based and natural language processing machine learning model on the plurality of historical voice call transcripts; converting, by the server computing device, each of the extracted questions into a multidimensional embedding using a sentence transformer machine learning model; clustering, by the server computing device, the multidimensional embeddings into one or more question clusters using a similarity measure algorithm, each of the question clusters assigned a cluster identification label; generating, by the server computing device for each historical voice call transcript, a sequence of cluster identification labels corresponding to the sequence of questions extracted from the call transcript; and creating, by the server computing device, a conversation flow graph for each historical voice call transcript based upon the associated sequence of cluster identification labels.
12. 12 . The method of claim 11 , further comprising modifying, by the server computing device, a conversation flow of the conversation service application using the conversation flow graph.
13. 13 . The method of claim 12 , wherein modifying the conversation flow of the conversation service application comprises rearranging a sequence of prompts in a conversation flow of the conversation service application, adding one or more prompts to a conversation flow of the conversation service application, removing one or more prompts from a conversation flow of the conversation service application, or changing content of one or more prompts in a conversation flow of the conversation service application.
14. 14 . The method of claim 13 , wherein the conversation service application comprises a chatbot application, an interactive voice response (IVR) application, a virtual assistant application, or a guided service application.
15. 15 . The method of claim 11 , further comprising preprocessing, by the server computing device, the plurality of historical voice call transcripts before executing the combined rule-based and natural language processing machine learning model on the plurality of historical voice call transcripts.
16. 16 . The method of claim 15 , wherein preprocessing the plurality of historical voice call transcripts comprises: replacing one or more regular expressions in the historical voice call transcripts with default values; detecting boundaries between sentences in the historical voice call transcripts; and inserting punctuation at each sentence boundary in the historical voice call transcripts.
17. 17 . The method of claim 16 , further comprising executing, by the server computing device, a natural language processing model to replace the regular expressions and the server computing device executes a large language model to detect the boundaries and insert the punctuation.
18. 18 . The method of claim 11 , wherein the similarity measure algorithm comprises a k-means clustering algorithm or an hdbscan algorithm.
19. 19 . The method of claim 11 , wherein the conversation flow graph comprises a data structure with a plurality of nodes connected via edges and arranged according to the sequence of cluster identification labels.
20. 20 . The method of claim 11 , further comprising merging, by the server computing device, at least two of the conversation flow graphs to generate an aggregate conversation flow graph.

Description

TECHNICAL FIELD This application relates generally to methods and apparatuses, including computer program products, for analysis and clustering of unstructured computer text for generation of a structured conversation flow for a conversation service application. BACKGROUND Recent advances in artificial intelligence (AI)-based computer technology enable systems to automatically parse large corpuses of unstructured computer text, convert the text into computer-readable representations, and execute one or more machine learning algorithms on the output to gain various actionable insights. One area where these techniques can be particularly useful is customer relationship management (CRM) and customer service. In one example, customer contact call centers often record most, if not all, incoming calls between a customer and an agent, and the corresponding call transcript is frequently converted into unstructured computer text and stored in a database for data analysis and data mining. However, in a typical customer contact environment, conversation flows that occur on live calls between customers and agents can vary significantly from conversation flows executed by automated conversation service applications-such as interactive voice response (IVR) systems, chatbots, and/or virtual assistants. In such cases, it may be determined that the conversation flows occurring in the voice calls are more efficient in resolving customer questions, leading to increased customer satisfaction or engagement, or otherwise providing an improved customer experience. Call flow designers and conversation analysts typically do not generate conversation flows that cover all possible scenarios and/or sufficiently promote increased customer engagement. As a result, it is important to utilize advanced computing systems to understand and extract voice call question flows that lead to successful customer interactions and to integrate those flows seamlessly into the corresponding conversation service software applications. SUMMARY Therefore, what is needed are methods and systems that utilize a large corpus of historical voice call transcript data in an artificial intelligence framework to generate conversation flow graphs which can then be used to modify and improve conversation flows for automated conversation service applications. The techniques described herein provide the technical advantage of machine learning-based question extraction and clustering from historical voice call transcripts to automatically create graph data structures that reflects the sequence of questions in one or more transcripts. The methods and systems can leverage the graph data structures to dynamically adapt conversation flows of software-based conversation appliances (e.g., interactive voice response systems, chatbots, virtual assistants, guided service applications). The invention, in one aspect, features a system used in a computing environment in which unstructured computer text is analyzed for generation of a structured conversation flow for a conversation service application. The system includes a server computing device having a memory for storing computer-executable instructions and a processor that executes the computer-executable instructions. The server computing device extracts a sequence of questions from each of a plurality of historical voice call transcripts by executing, using the processor, a combined rule-based and natural language processing machine learning model on the plurality of historical voice call transcripts. The server computing device converts each of the extracted questions into a multidimensional embedding using a sentence transformer machine learning model. The server computing device clusters the multidimensional embeddings into one or more question clusters using a similarity measure algorithm, each of the question clusters assigned a cluster identification label. The server computing device generates, for each historical voice call transcript, a sequence of cluster identification labels corresponding to the sequence of questions extracted from the call transcript. The server computing device creates a conversation flow graph for each historical voice call transcript based upon the associated sequence of cluster identification labels. The invention, in another aspect, features a computerized method in which unstructured computer text is analyzed for generation of a structured conversation flow for a conversation service application. A server computing device extracts a sequence of questions from each of a plurality of historical voice call transcripts by executing, using the processor, a combined rule-based and natural language processing machine learning model on the plurality of historical voice call transcripts. The server computing device converts each of the extracted questions into a multidimensional embedding using a sentence transformer machine learning model. The server computing device clusters the multidimensional