# US 11,113,026 B2 · System and method for voice-directed website walk-through > Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt - Number: US 11,113,026 B2 - Document ID: US11113026B2 - Status: Granted - Kind: B2 - Application number: 16/214,051 - Filed: 2018-12-08 - Published: 2019-12-12 - Granted: 2021-09-07 - Earliest claimed: 2017-12-08 - Assignees: Toonimo, Inc. - Applicants: Adi Darachi; Dan Kotlicki - Inventors: Adi Darachi; Dan Kotlicki - Web page: https://patentgrep.com/patent/US11113026B2 ## CPC - G06F 3/167: {Audio in a user interface, e.g. using voice commands for navigating, audio feedback} - G06F 40/30: Semantic analysis - G10L 15/16: using artificial neural networks - 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 2015/223: {Execution procedure of a spoken command} - G06F: ELECTRIC DIGITAL DATA PROCESSING (computer systems based on specific computational models G06N) - 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 a user to receive voice prompts and to talk to a website stating what they desire to do. Speech-to-text (speech recognition) and text-to-speech or pre-recorded voice along with graphic overlay provide user guidance. Upon accessing a website, special code is transferred to the client browser from the site server. If the client computer's application interface supports speech recognition and/or text to speech, some or all speech conversions can be performed on the client side. If not, the speech processing can be performed on a dedicated private control site or by an external site that provides speech processing services, or as a distributed service in an on premise installation. After speech is converted to text, an artificial intelligence module, attempts to determine intent. Once intent is determined, correct commands can be sent to the website to bring up proper pages and/or walkthroughs and/or answers. ## Claims ### Claim 1 A method for providing voice-controlled website walk-through comprising: providing a voice prompt to a user upon entering the website using text to voice conversion or a recorded voice prompt; receiving a voice request from the user; converting the voice request to text using voice recognition; analyzing the text with an artificial intelligence module to determine intent: (a) if intent can be determined from the text, presenting a webpage to the user that relates to the intent; (b) if intent cannot be determined from the initial reply, asking a voice question using text to voice conversion or a recorded voice question; (c) receiving a voice response from the user; (d) converting the voice response to text using voice recognition; (e) Repeating steps (a)-(d). ### Claim 2 (depends on 1) The method of claim 1 wherein voice recognition and text-to-voice conversion is performed on the user's computer. ### Claim 3 (depends on 1) The method of claim 1 wherein voice recognition and text-to-voice conversion is performed at a website server. ### Claim 4 (depends on 1) The method of claim 1 wherein voice recognition and text-to-voice conversion is performed on a third-party computer. ### Claim 5 (depends on 1) The method of claim 1 wherein the artificial intelligence module includes dictionaries of words, a neural network or an expert system. ### Claim 6 A method of voice guided website walkthrough comprising: (a) asking an introductory voice question to a user upon the user accessing a website using text to voice conversion or an initial recorded voice question; (b) receiving an initial voice reply from the user; (c) converting the initial voice reply to initial text using voice recognition; (d) analyzing the initial text with an artificial intelligence module to determine intent; (e) if intent can be determined from the initial reply, presenting a webpage to the user that relates to the intent; (f) if intent cannot be determined from the initial reply, asking a further voice question using text to voice conversion or a recorded voice question; (g) receiving a voice answer from the user; (h) converting the voice reply to response text using voice recognition; (i) analyzing the response text with the artificial intelligence module to determine intent; (j) if intent can be determined from the response text, presenting a webpage to the user that relates to the intent; (k) if intent cannot be determined from the reply text repeating steps (f)-(k). ### Claim 7 (depends on 6) The method of claim 6 wherein if intent cannot be determined after repeating steps (f)-(k) a predetermined number of times, the user is presented with a textual representation of options. ### Claim 8 (depends on 6) The method of claim 6 wherein the artificial intelligence module includes dictionaries of words, a neural network or an expert system. ### Claim 9 (depends on 6) The method of claim 6 wherein voice recognition and text-to-voice conversion is performed on the user's computer. ### Claim 10 (depends on 6) The method of claim 6 wherein voice recognition and text-to-voice conversion is performed at a website server. ### Claim 11 (depends on 6) The method of claim 6 wherein voice recognition and text-to-voice conversion is performed on a third-party computer. ### Claim 12 A method of voice guided website walkthrough comprising: transmitting an initial text question from a server to a user computer upon a user entering a website; causing the user computer to convert the initial text question to an initial voice question and to present the initial voice question to the user; allowing the user computer to receive a voice response from the user and to convert the voice response to a text response; allowing the user computer to transmit the text response to the server; analyzing the initial text response at the server to determine a user intent; (a) if intent can be determined from the text response, presenting a webpage to the user that relates to the intent; (b) if intent cannot be determined from the text response, asking a voice question using text to voice conversion or a recorded voice question; (c) receiving a voice response from the user; (d) converting the voice response to a text response using voice recognition; (e) Repeating steps (a)-(d). ### Claim 13 (depends on 12) The method of claim 12 wherein the analyzing is performed by an artificial intelligence module. ### Claim 14 (depends on 13) The method of claim 13 wherein the artificial intelligence module includes dictionaries of words, a neural network or an expert system.