# US 12,223,003 B2 · Streaming of chat in SERP > Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt - Number: US 12,223,003 B2 - Document ID: US12223003B2 - Status: Granted - Kind: B2 - Application number: 18/336,000 - Filed: 2023-06-15 - Published: 2024-08-01 - Granted: 2025-02-11 - Earliest claimed: 2023-01-31 - Assignees: Microsoft Technology Licensing, LLC - Applicants: Microsoft Technology Licensing, LLC - Inventors: Mahmoud Adada; Elbio Renato Torres Abib; Bradley Moore Abrams; Justin Daniel Harris - Web page: https://patentgrep.com/patent/US12223003B2 ## CPC - G06F 16/9536: Search customisation based on social or collaborative filtering - G06F 16/9535: Search customisation based on user profiles and personalisation - G06F 40/20: Natural language analysis (semantic analysis of natural language G06F40/30) - G06F: ELECTRIC DIGITAL DATA PROCESSING (computer systems based on specific computational models G06N) ## Abstract A computing system is disclosed that includes a processor and memory. The memory stores instructions that, when executed by the processor, cause the processor to perform several acts. The acts include generating a prompt that is to be input to a generative language model. The prompt includes conversational input set forth by a user. The acts further comprise providing the prompt as input to the generative language model, and receiving conversational output from the generative language model, where the generative language model generated the conversational output based upon the prompt. Additionally, the acts comprise streaming the conversational output on one of a SERP or webpage to which the user has navigated from the SERP. ## Claims ### Claim 1 A computing system comprising: a processor; and memory storing instructions that, when executed by the processor, cause the processor to perform acts comprising: receiving a query provided by a user; generating a prompt that is to be input to a generative language model, where the prompt includes an instruction for the generative language model to generate conversational output based upon the query; providing the prompt as input to the generative language model, wherein the generative language model generates conversational output based upon the prompt; streaming the conversational output to a search engine results page (SERP) in a chat window, such that the conversational output appears to the user as though it is being typed in real time in the chat window; receiving an indication that a search result in the SERP has been selected by the user; and causing a webpage corresponding to the selected search result to be displayed, wherein the chat window is caused to be maintained on the webpage. ### Claim 2 (depends on 1) The computing system of claim 1, wherein generating the prompt further includes providing a search system with the query, wherein the search system identifies search results based upon the query and includes a portion of the search results in the prompt. ### Claim 3 (depends on 2) The computing system of claim 2, wherein the acts further include: receiving an indication of user interaction with the SERP responsive to the conversational output; retrieving additional search results in response to the user interaction; generating and transmitting to the generative language model an updated prompt based on a portion of the additional search results and the user interaction; receiving updated conversational output from the generative language model; and streaming the updated search results and the updated conversational output to the SERP on the computing device. ### Claim 4 (depends on 1) The computing system of claim 1, the acts further comprising: providing supplemental content related to the conversational output for display on a dynamically updatable display pane on the computing device; and updating the supplemental content responsive to at least one of additional user interaction and updated conversational output. ### Claim 5 (depends on 4) The computing system of claim 4, the acts further comprising: synchronizing streaming of the supplemental content to the conversational output by comparing metadata associated with the conversational output and the supplemental content. ### Claim 6 (depends on 1) The computing system of claim 1, the acts further comprising; identifying offensive content in at least one of the conversational output and the supplemental content; and prior to rendering, at least one of: removing the offensive content; and removing the source of the offensive content. ### Claim 7 (depends on 1) The computer system of claim 1, the acts further comprising: caching generative language model responses for retrieval in response to similar queries. ### Claim 8 A computing device comprising: a processor; and memory storing instructions that, when executed by the processor, cause the processor to perform acts comprising: transmitting a user query to a search system; receiving conversational output from a generative language model, where the generative language model generated the conversational output based upon a prompt comprising the query; and streaming the conversational output on a search engine results page (SERP) in a chat window, such that the conversational output is presented to a user as though it is being typed in real time in the chat window; receiving an indication that a search result in the SERP has been selected by the user; and causing a webpage corresponding to the selected search result to be displayed, wherein the chat window is caused to be maintained on the webpage. ### Claim 9 (depends on 8) The computing device of claim 8, wherein the conversational output comprises information related to search results responsive to the query. ### Claim 10 (depends on 8) The computing device of claim 8, wherein the acts further include: transmitting an indication of user interaction with the SERP responsive to the conversational output; receiving updated search results and updated conversational output in response to the user interaction. ### Claim 11 (depends on 10) The computing device of claim 10, the acts further comprising: displaying streamed updated search results and updated conversational output on the SERP. ### Claim 12 (depends on 8) The computing device of claim 8, the acts further comprising: receiving and displaying supplemental content related to the conversational output on a dynamically updatable display pane on the SERP; and receiving and displaying updated supplemental content responsive to at least one of additional user interaction and updated conversational output. ### Claim 13 (depends on 12) The computing device of claim 12, the acts further comprising: synchronizing streaming of the supplemental content to the conversational output by comparing metadata associated with the conversational output and the supplemental content. ### Claim 14 (depends on 8) The computing device of claim 8, the acts further comprising; identifying offensive content in at least one of the conversational output and the supplemental content; and prior to rendering, at least one of: removing the offensive content; and removing the source of the offensive content. ### Claim 15 A method that facilitates providing conversational interaction on search engine results page presented on an interface of a computing device, the method comprising: receiving a query provided by a user; generating a prompt that is to be input to a generative language model, where the prompt includes an instruction for the generative language model to generate conversational output based upon the query; providing the prompt as input to the generative language model, wherein the generative language model generates conversational output based upon the prompt; streaming the conversational output to ene of a search engine results page (SERP) in a chat window, such that the conversational output appears to the user as though it is being typed in real time in the chat window; receiving an indication that a search result in the SERP has been selected by the user; and causing a webpage corresponding to the selected search result to be displayed, wherein the chat window is caused to be maintained on the webpage. ### Claim 16 (depends on 15) The method of claim 15, wherein generating the prompt further includes providing a search system with the query, wherein the search system identifies search results based upon the query and includes a portion of the search results in the prompt. ### Claim 17 (depends on 16) The method of claim 16, wherein the acts further include: receiving an indication of user interaction with the SERP responsive to the conversational output; retrieving additional search results in response to the user interaction; generating and transmitting to the generative language model an updated prompt based on a portion of the additional search results and the user interaction; receiving updated conversational output from the generative language model; and streaming the updated search results and updated conversational output to the SERP on the computing device. ### Claim 18 (depends on 15) The method of claim 15, the acts further comprising: providing supplemental content related to the conversational output for display on a dynamically updatable display pane on the computing device; and updating the supplemental content responsive to at least one of additional user interaction and updated conversational output. ### Claim 19 (depends on 18) The method of claim 18, the acts further comprising: synchronizing streaming of the supplemental content to the conversational output by comparing metadata associated with the conversational output and the supplemental content. ### Claim 20 (depends on 15) The method of claim 15, the acts further comprising; identifying offensive content in at least one of the conversational output and the supplemental content; and prior to rendering, at least one of: removing the offensive content; and removing the source of the offensive content.