# US 2014/0153709 A1 · System And Method For Automatically Generating Adaptive Interaction Logs From Customer Interaction Text > Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt - Number: US 2014/0153709 A1 - Document ID: US20140153709A1 - Status: Published application - Kind: A1 - Application number: 14/140,649 - Filed: 2013-12-26 - Published: 2014-06-05 - Earliest claimed: 2008-10-27 - Assignees: Nuance Communications, Inc. - Applicants: Nuance Communications, Inc. - Inventors: Roy Jefferson Byrd; Stephen C. Gates; Mary S. Neff; Youngja Park; Wilfried Teiken - Web page: https://patentgrep.com/patent/US20140153709A1 ## CPC - H04M 3/5133: {Operator terminal details} - G10L 15/26: Speech to text systems (G10L15/08 takes precedence) - H04M 3/42221: {Conversation recording systems (at the subscriber's set H04M1/656)} - H04M 3/4936: {Speech interaction details (speech recognition per se G10L15/00)} - H04M 3/51: Centralised call answering arrangements requiring operator intervention {, e.g. call or contact centers for telemarketing} - H04M 3/5191: {interacting with the Internet} - H04M 2201/40: using speech recognition - H04M: TELEPHONIC COMMUNICATION (circuits for controlling other apparatus via a telephone cable and not involving telephone switching apparatus G08) - G10L: SPEECH ANALYSIS TECHNIQUES OR SPEECH SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING TECHNIQUES; SPEECH OR AUDIO CODING OR DECODING ## Abstract A system and method for providing an adaptive Interaction Logging functionality to help agents reduce the time spent documenting contact center interactions. In a preferred embodiment the system uses a pipeline comprising audio capture of a telephone conversation, automatic speech transcription, text normalization, transcript generation and candidate call log generation based on Real-time and Global Models. The contact center agent edits the candidate call log to create the final call log. The models are updated based on analysis of user feedback in the form of the editing of the candidate call log done by the contact center agents or supervisors. The pipeline yields a candidate call log which the agents can edit in less time than it would take them to generate a call log manually. ## Claims ### Claim 1 A method for a computer apparatus for automatically generating a customer interaction log for an interaction between a customer and an agent, the method comprising: automatically analyzing received input corresponding to an interaction in the form of a transcript between a customer and an agent to generate a customer interaction log using at least one model; displaying the customer interaction log for review by the agent at a graphical user interface of an agent computer; enabling the agent to provide feedback by way of the graphical user interface; and automatically updating at least one of the customer interaction log and the at least one model based on the feedback by the agent. ### Claim 2 (depends on 1) The method of claim 1 wherein the received input comprises at least one of: received text of speech from a speech recognition system; received text entered on a Web form; received text of instant messaging; and received text of emails. ### Claim 3 (depends on 2) The method of claim 2 further comprising normalizing the received input by performing at least one of: removing disfluencies from the received input; normalizing vocabulary in the received input; normalizing alphanumeric characters in the received input; correcting misspellings or incorrectly recognized words in the received input; detecting sentence boundaries in the received input; capitalizing letters in sentences in the received input; and detecting call segment boundaries in the received input. ### Claim 4 (depends on 1) The method of claim 1 wherein automatically analyzing the received input to generate the customer interaction log further comprises at least one of: scoring utterances in the received input based on at least one model; identifying selected utterances to be used in the customer interaction log; and correcting words in the selected utterances. ### Claim 5 (depends on 1) The method of claim 1 further comprising initially creating the at least one model by at least one of: enabling manual rule creation; and performing machine learning rule creation. ### Claim 6 (depends on 1) The method of claim 1 further comprising analyzing the feedback and updating the at least one model by performing feedback analysis. ### Claim 7 (depends on 6) The method of claim 6 wherein updating the at least one model includes comparing an edited customer interaction log edited by the agent to the automatically generated customer interaction log. ### Claim 8 (depends on 1) The method of claim 1 wherein automatically updating the at least one model further comprises at least one of: decreasing salience of a rule that generated a deleted sentence; increasing salience of a rule that generated an inserted sentence; finding a most similar sentence in the received input to a newly created sentence; and increasing salience of a rule that generated the most similar sentence. ### Claim 9 (depends on 1) The method of claim 1 further comprising storing the customer interaction log, agent feedback, or both. ### Claim 10 (depends on 9) The method of claim 9 wherein agent feedback is stored for a plurality of interactions between customers and agents and further comprising analyzing the stored feedback and determining updating of a global model based on analyzing the stored feedback. ### Claim 11 (depends on 1) The method of claim 1 further comprising generating the customer interaction log with reference to a realtime model automatically generated for the interaction. ### Claim 12 (depends on 11) The method of claim 11 wherein generating the realtime model is performed automatically from a global model. ### Claim 13 A system for automatically generating a customer interaction log for an interaction between a customer and agent, the system comprising: at least one processing unit configured to execute components; an analysis component configured to automatically analyze received input corresponding to an interaction in the form of a transcript between the customer and the agent to generate the customer interaction log using at least one model; a display generation component configured to generate a display of the customer interaction log for agent review at a graphical user interface of an agent computer; a feedback collection component configured to enable the agent to provide agent feedback by way of the graphical user interface; and at least one learning component configured to analyze agent feedback to determine updating of at least one of the customer interaction log and the at least one model based on agent feedback. ### Claim 14 (depends on 13) The system of claim 13 further comprising a text normalizing component configured to transform the received input comprising at least one of: a disfluency component configured to remove disfluencies from received text; a vocabulary normalizing component configured to normalize vocabulary in the received text; a character normalizing component configured to normalize alphanumeric characters in the received text; a word correction component configured to correct misspellings or incorrectly recognized words in the received text; a sentence detection component configured to detect sentence boundaries in the received text; a sentence capitalization component configured to capitalize letters in sentences in the received text; and a call segment component configured to detect call segment boundaries in the received text. ### Claim 15 (depends on 13) The system of claim 13 wherein the analysis component comprises at least one subcomponent for performing at least one of: scoring utterances in received input based on at least one model; and identifying selected utterances to be used in the customer interaction log. ### Claim 16 (depends on 13) The system of claim 13 further comprising at least one storage component configured to store at least one of the at least one models, the customer interaction log, and the agent feedback. ### Claim 17 (depends on 13) The system of claim 13 wherein the analysis component additionally includes at least one of: an utterance scoring component for scoring utterances in the call transcript based on at least one of a global model and a realtime model; and an utterance selection component configured to identify selected utterances to be used in the interaction log. ### Claim 18 (depends on 16) The system of claim 16 wherein agent feedback is stored for a plurality of interactions between customers and agents and wherein the at least one learning component analyzes the stored feedback and determines updating of a global model based on analyzing the stored feedback. ### Claim 19 (depends on 13) The system of claim 13, wherein the feedback collection component additionally is configured to provide feedback to the agent in the form of a warning. ### Claim 20 A non-transitory computer readable medium having stored thereon a sequence of instructions which, when loaded and executed by a processor coupled to an apparatus, causes the apparatus to: automatically analyze received input corresponding to an interaction in the form of a transcript between a customer and an agent to generate a customer interaction log using at least one model; display the customer interaction log for agent review at a graphical user interface of an agent computer; enable the agent to provide feedback by way of the graphical user interface; and automatically update at least one of the customer interaction log and the at least one model based on the agent feedback.