# US 2017/0286377 A1 · Narrative generation using pattern recognition > Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt - Number: US 2017/0286377 A1 - Document ID: US20170286377A1 - Status: Published application - Kind: A1 - Application number: 15/085,226 - Filed: 2016-03-30 - Published: 2017-10-05 - Earliest claimed: 2016-03-30 - Assignees: International Business Machines Corporation - Applicants: International Business Machines Corporation - Inventors: Al Chakra; Jonathan Dunne; Liam Harpur; Eduardo A. Patrocinio - Web page: https://patentgrep.com/patent/US20170286377A1 ## CPC - G06F 40/166: Editing, e.g. inserting or deleting - G06F 16/345: {Summarisation for human users} - G06F 40/279: Recognition of textual entities - G06F 40/40: Processing or translation of natural language (natural language analysis G06F40/20; semantic analysis G06F40/30) - G06F 40/56: Natural language generation - G06F: ELECTRIC DIGITAL DATA PROCESSING (computer systems based on specific computational models G06N) ## Abstract Embodiments include method, systems and computer program products for narrative generation using pattern recognition by topic. In some embodiments, a topic may include identified from content. Events associated with the topic may be obtained from one or more sources. The events may be processed. A narrative of the topic may be generated using pattern recognition on the events. The narrative may be transmitted for presentation to a user. ## Claims ### Claim 1 A computer-implemented method comprising: identifying a topic from content; obtaining events associated with the topic from one or more sources; processing the events; generating a narrative of the topic using pattern recognition on the events; and transmitting the narrative for presentation to a user. ### Claim 2 (depends on 1) The computer-implemented method of claim 1, further comprising: retrieving the events from a repository; and generating the narrative of the topic using the events retrieved from the repository. ### Claim 3 (depends on 1) The computer-implemented method of claim 1, wherein processing the events further comprises: normalizing the events using timestamps and natural language processing. ### Claim 4 (depends on 1) The computer-implemented method of claim 1, further comprising: determining a time threshold has not been exceeded; receiving additional events; processing the additional events; and updating the narrative using the additional events. ### Claim 5 (depends on 1) The computer-implemented method of claim 1, wherein the time threshold is a first time threshold and the method further comprises: receiving an update event associated with the topic; determining that the first time threshold has been exceeded; determining a second time threshold has not been exceeded; updating the narrative using the update event; and transmitting a notification and the narrative to the user, wherein the notification is indicative that the narrative has been updated. ### Claim 6 (depends on 1) The computer-implemented method of claim 1, wherein the one or more sources were previously selected by the user. ### Claim 7 (depends on 1) The computer-implemented method of claim 1, wherein the content is one of an email, a blog post, a social media post, a website, or text message. ### Claim 8 A computer program product comprising a non-transitory storage medium readable by a processing circuit and storing instructions for execution by the processing circuit for performing a method comprising: identifying a topic from content; obtaining events associated with the topic from one or more sources; processing the events; generating a narrative of the topic using pattern recognition on the events; and transmitting the narrative for presentation to a user. ### Claim 9 (depends on 8) The computer program product of claim 8, wherein the method further comprises: retrieving the events from a repository; and generating the narrative of the topic using the events retrieved from the repository. ### Claim 10 (depends on 8) The computer program product of claim 8, wherein processing the events further comprises: normalizing the events using timestamps and natural language processing. ### Claim 11 (depends on 8) The computer program product of claim 8, wherein the method further comprises: determining a time threshold has not been exceeded; receiving additional events; processing the additional events; and updating the narrative using the additional events. ### Claim 12 (depends on 8) The computer program product of claim 8, wherein the time threshold is a first time threshold and the method further comprises: receiving an update event associated with the topic; determining that the first time threshold has been exceeded; determining a second time threshold has not been exceeded; updating the narrative using the update event; and transmitting a notification and the narrative to the user, wherein the notification is indicative that the narrative has been updated. ### Claim 13 (depends on 1) The computer-implemented method of claim 1, wherein the one or more sources were previously selected by the user. ### Claim 14 (depends on 1) The computer-implemented method of claim 1, wherein the content is one of an email, a blog post, a social media post, a website, or text message. ### Claim 15 A system, comprising: a processor in communication with one or more types of memory, the processor configured to: identify a topic from content; obtain events associated with the topic from one or more sources; process the events; generate a narrative of the topic using pattern recognition on the events; and transmit the narrative for presentation to a user. ### Claim 16 (depends on 15) The system of claim 15, wherein the processor is further configured to: retrieve the events from a repository; and generate the narrative of the topic using the events retrieved from the repository. ### Claim 17 (depends on 15) The system of claim 15, wherein, to process the events, the processor is further configured to: normalize the events using timestamps and natural language processing. ### Claim 18 (depends on 15) The system of claim 15, wherein the processor is further configured to: determine a time threshold has not been exceeded; receive additional events; process the additional events; and update the narrative using the additional events. ### Claim 19 (depends on 15) The system of claim 15, wherein the time threshold is a first time threshold and wherein the processor is further configured to: receive an update event associated with the topic; determine that the first time threshold has been exceeded; determine a second time threshold has not been exceeded; update the narrative using the update event; and transmit a notification and the narrative to the user, wherein the notification is indicative that the narrative has been updated. ### Claim 20 (depends on 1) The computer-implemented method of claim 1, wherein the one or more sources were previously selected by the user.