# US 10,484,542 B1 · System and method for hybridized chat automation > Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt - Number: US 10,484,542 B1 - Document ID: US10484542B1 - Status: Granted - Kind: B1 - Application number: 16/235,628 - Filed: 2018-12-28 - Granted: 2019-11-19 - Earliest claimed: 2018-12-28 - Applicants: Genesys Telecommunications Laboratories, Inc. - Inventors: Brent Rager - Web page: https://patentgrep.com/patent/US10484542B1 ## CPC - H04M 3/5183: {Call or contact centers with computer-telephony arrangements} - G06F 40/279: Recognition of textual entities - G06F 40/35: Discourse or dialogue representation - 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 2203/2061: Language aspects - H04M: TELEPHONIC COMMUNICATION (circuits for controlling other apparatus via a telephone cable and not involving telephone switching apparatus G08) - G06F: ELECTRIC DIGITAL DATA PROCESSING (computer systems based on specific computational models G06N) - H04L: TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION (arrangements common to telegraphic and telephonic communication H04M) ## Abstract In a system for managing blended agent and automated chat in a contact center setting, the system includes: a chat orchestration server invoking natural language processing on a received communication, selecting a standardized text communication responsive to the natural-language-processed communication, and transmitting the standardized text communication to an agent device; and a knowledge management server for determining confidence values and populating ranked lists of responsive standardized text communications. ## Claims ### Claim 1 A method of managing chat in a contact center setting, wherein the chat comprises a blended agent and automated chat, the method comprising: (a) receiving from a chat orchestration server a first signal indicating an initiating communication; (b) invoking by the chat orchestration server natural language processing on the initiating communication; (c) retrieving, by the chat orchestration server, a standardized text communication responsive to the natural-language-processed communication from a memory coupled to a knowledge management server; (d) determining, by the knowledge management server, a confidence value of the standardized text communication responsive to the natural-language-processed communication; (e) populating, by the knowledge management server, a determined ranked order of standardized text communications, wherein the rank order is configured in response to the confidence value of the standardized text communication; (f) transmitting, by the chat orchestration server, an instruction to display on an agent device the determined ranked order; (g) receiving, by the chat orchestration server, a second signal indicating a selection from the agent device of a standardized text communication responsive to the natural-language-processed initiating communication; (h) directing, by the chat orchestration server, an automated standardized-text-communication chat for communication with an end user based on the received second signal indicating the selection from the agent device of the standardized text communications; and repeating steps (a)-(h) until an action occurs as indicated by a third signal received by the chat orchestration server. ### Claim 2 (depends on 1) The method of claim 1, wherein the initiating communication is a chat-based communication from an end user. ### Claim 3 (depends on 2) The method of claim 2, wherein the end user interacts with the contact center through a webchat. ### Claim 4 (depends on 1) The method of claim 1, wherein step (c) and (d) are repeated for a plurality of standardized text communications responsive to the natural-language-processed communication, and wherein the ranked order of standardized text communications determined in step (e) is comprised of said plurality of standardized text communications responsive to the natural-language-processed communication. ### Claim 5 (depends on 1) The method of claim 1, further comprising the knowledge management server live training the confidence value of the standardized text communication in response to the selection from the agent device of a standardized text communication responsive to the natural-language-processed initiating communication. ### Claim 6 (depends on 1) The method of claim 1, wherein step (d) of determining, by the knowledge management server, a confidence value of the standardized text communication responsive to the natural-language-processed communication comprises: (d1) determining, by the knowledge management server, a confidence value of the standardized text communication responsive to the natural-language-processed communication; (d2) determining, by the knowledge management server, a threshold for the determined confidence value of the standardized text communication responsive to the natural-language-processed communication; and (d3) transmitting, by the knowledge management server, the standardized text communication for population in the ranked order if the determined confidence value meets or exceeds the determined threshold. ### Claim 7 (depends on 6) The method of claim 6, wherein the determined confidence values of a plurality of standardized text communications responsive to the natural-language-processed communication influences the determined threshold. ### Claim 8 (depends on 6) The method of claim 6, wherein the knowledge management server is configured to live train the confidence value of the standardized text communication if the confidence value is below the determined threshold. ### Claim 9 (depends on 8) The method of claim 8, wherein the live training of the confidence value of the standardized text communication is determined in response to the selection from the agent device of a standardized text communication responsive to the natural-language-processed initiating communication. ### Claim 10 (depends on 1) The method of claim 1, wherein the third signal received by the chat orchestration server indicates completion of a chat conversation between the end user and an agent operating the agent device. ### Claim 11 A system for managing chat in a contact center setting, wherein the chat comprises a blended agent and automated chat, the system comprising: a chat orchestration server processor; and a memory coupled to the chat orchestration server processor, wherein the memory stores instructions that, when executed by the chat orchestration server processor, cause the chat orchestration server processor to: receive a first signal indicating an initiating communication; invoke natural language processing on the initiating communication; retrieve a standardized text communication responsive to the natural-language-processed communication from a memory coupled to a knowledge management server; transmit an instruction to display on an agent device a determined ranked order of standardized text communications; receive a second signal indicating a selection from an agent device of a standardized text communication responsive to the natural-language-processed initiating communication; and direct an automated standardized-text-communication chat for communication with an end user based on the received second signal indicating the selection from the agent device of the standardized text communications; and a knowledge management server processor; and a memory coupled to the knowledge management server processor, wherein the memory stores instructions that, when executed by the knowledge management server processor, cause the knowledge management server processor to: determine a confidence value of the standardized text communication responsive to the natural-language-processed communication; and populate the determined ranked order of standardized text communications, wherein the rank order is configured in response to the confidence value of the standardized text communication. ### Claim 12 (depends on 11) The system of claim 11, wherein the initiating communication is a chat-based communication from an end user. ### Claim 13 (depends on 12) The system of claim 12, wherein the end user interacts with the contact center through a webchat. ### Claim 14 (depends on 11) The system of claim 11, wherein the instructions that cause the chat orchestration server processor to retrieve a standardized text communication responsive to the natural-language-processed communication from a memory coupled to a knowledge management server and the instructions that cause the knowledge management server processor to determine a confidence value of the standardized text communication responsive to the natural-language-processed communication are repeated for a plurality of standardized text communications responsive to the natural-language-processed communication, and wherein the ranked order of standardized text communications populated by the knowledge management server processor is comprised of said plurality of standardized text communications responsive to the natural-language-processed communication. ### Claim 15 (depends on 11) The system of claim 11, further comprising the instructions causing the knowledge management server processor to live train the confidence value of the standardized text communication in response to the selection from the agent device of a standardized text communication responsive to the natural-language-processed initiating communication. ### Claim 16 (depends on 11) The system of claim 11, wherein the instructions further cause the knowledge management server processor to: determine a threshold for the determined confidence value of the standardized text communication responsive to the natural-language-processed communication; and transmit the standardized text communication for population in the ranked order if the determined confidence value meets or exceeds the determined threshold. ### Claim 17 (depends on 16) The system of claim 16, wherein the determined confidence values of a plurality of standardized text communications responsive to the natural-language-processed communication influences the determined threshold. ### Claim 18 (depends on 16) The system of claim 16, wherein the knowledge management server processor is configured with instructions to live train the confidence value of the standardized text communication if the confidence value is below the determined threshold. ### Claim 19 (depends on 18) The system of claim 18, wherein the live training of the confidence value of the standardized text communication is determined in response to the selection from the agent device of a standardized text communication responsive to the natural-language-processed initiating communication. ### Claim 20 (depends on 11) The system of claim 11, the instructions for the chat orchestration server processor and the knowledge management server are configured to repeat until an action occurs as indicated by a third signal received by the chat orchestration server processor.