17527950. COMPUTER-BASED SYSTEMS CONFIGURED FOR AUTOMATED EXTRACTION OF DATA FROM INPUTS AND METHODS OF USE THEREOF simplified abstract (Capital One Services, LLC)

From WikiPatents
Jump to navigation Jump to search

COMPUTER-BASED SYSTEMS CONFIGURED FOR AUTOMATED EXTRACTION OF DATA FROM INPUTS AND METHODS OF USE THEREOF

Organization Name

Capital One Services, LLC

Inventor(s)

Bryant Yee of Washington DC (US)

Brian Mcclanahan of Silver Spring MD (US)

Cruz Vargas of Denver CO (US)

COMPUTER-BASED SYSTEMS CONFIGURED FOR AUTOMATED EXTRACTION OF DATA FROM INPUTS AND METHODS OF USE THEREOF - A simplified explanation of the abstract

This abstract first appeared for US patent application 17527950 titled 'COMPUTER-BASED SYSTEMS CONFIGURED FOR AUTOMATED EXTRACTION OF DATA FROM INPUTS AND METHODS OF USE THEREOF

Simplified Explanation

The abstract of this patent application describes a method for automatically generating a call script for conducting a subsequent call with a user based on input text data retrieved from a transcription of a previous call between the user and an agent associated with a call center. The method involves identifying personal information associated with the user, determining key terms within the personal information, and extracting tuples from the input text data. These tuples are then stored in a database and used to automatically generate a call script for the next interaction with the user.

  • The method involves receiving input text data from a transcription of a previous call between a user and a call center agent.
  • Personal information associated with the user is identified using a trained machine learning model.
  • Key terms within the personal information are determined.
  • A confidence positivity score is automatically determined for each key term.
  • Tuples are extracted from the input text data.
  • The extracted tuples are stored in an external database.
  • A call script for the next interaction with the user is automatically generated using the stored tuples.

Potential applications of this technology:

  • Call center operations: This method can be used to automate the process of generating call scripts for subsequent interactions with users, improving efficiency and consistency in call center operations.
  • Customer service: By automatically extracting and analyzing personal information from previous interactions, call center agents can have more personalized and tailored conversations with customers, enhancing the overall customer service experience.
  • Sales and marketing: The extracted information can be used to identify potential sales leads or target specific marketing campaigns towards customers based on their preferences and needs.

Problems solved by this technology:

  • Manual effort: This method eliminates the need for manual analysis of previous call transcriptions and the manual creation of call scripts, saving time and effort for call center agents.
  • Inconsistency: By automating the call script generation process, this technology ensures consistency in the information provided to users during subsequent interactions, reducing the risk of errors or inconsistencies.
  • Personalization: The automatic extraction and analysis of personal information allows for more personalized and tailored conversations with users, improving the overall customer experience.

Benefits of this technology:

  • Efficiency: The automation of call script generation saves time and effort for call center agents, allowing them to focus on more value-added tasks.
  • Consistency: By automatically generating call scripts based on extracted information, this technology ensures consistent and accurate information is provided to users during subsequent interactions.
  • Personalization: The analysis of personal information allows for more personalized and tailored conversations with users, leading to improved customer satisfaction and loyalty.


Original Abstract Submitted

In some embodiments, the present disclosure provides an exemplary method that may include steps of receiving an input text data retrieved from a transcription associated with a previously recorded audio data file between a user of a plurality of users and an agent associated with a call center; identifying personal information associated with the user of the plurality of users from the input text data by inputting the input text data into a trained machine learning model; determining at least one key term within the personal information associated with the user of the plurality of users; automatically determining a confidence positivity score associated with the at least one key term; automatically extracting a plurality of tuples from the input text data; storing the plurality of tuples in an external database; and automatically generating a call script for conducting a subsequent call with the user.