# US 2019/0318199 A1 · Classification and comparison of event related data objects > Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt - Number: US 2019/0318199 A1 - Document ID: US20190318199A1 - Status: Published application - Kind: A1 - Application number: 16/387,362 - Filed: 2019-04-17 - Published: 2019-10-17 - Earliest claimed: 2018-04-17 - Assignees: Primer Technologies, Inc. - Applicants: Primer Technologies, Inc. - Inventors: John Neil Bohannon; Leonard Apeltsin; Raine Morgan Hoover; Wei Gong - Web page: https://patentgrep.com/patent/US20190318199A1 ## CPC - G06F 16/345: {Summarisation for human users} - G06F 9/542: {Event management; Broadcasting; Multicasting; Notifications} - G06F 16/9038: Presentation of query results - G06F 18/21: Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation - G06F 18/2115: by evaluating different subsets according to an optimisation criterion, e.g. class separability, forward selection or backward elimination - G06F 18/22: Matching criteria, e.g. proximity measures - G06F 18/2431: Multiple classes - G06F 18/256: {of results relating to different input data, e.g. multimodal recognition} - G06V 10/70: using pattern recognition or machine learning (optical pattern recognition or electronic computations therefor G06V10/88) - G06V 10/764: using classification, e.g. of video objects - G06V 10/811: {the classifiers operating on different input data, e.g. multi-modal recognition} - G06V 20/41: {Higher-level, semantic clustering, classification or understanding of video scenes, e.g. detection, labelling or Markovian modelling of sport events or news items (segmenting video sequences G06V20/49)} - G06F: ELECTRIC DIGITAL DATA PROCESSING (computer systems based on specific computational models G06N) - G06V: IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING ## Abstract Systems, methods, and software described herein provide enhancements of managing summaries provided to end users. In one implementation, a summary service identifies data objects that correspond to an event and classifies each of the data objects into classifications of interest. Once classified, data objects are compared between the different classifications to identify information differences, and the information differences are used to generate a summary for an end user of the summary service. ## Claims ### Claim 1 A method of operating a summary service to provide event summarization, the method comprising: identifying data objects that qualify for an event from a plurality of data objects obtained from a plurality of information sources; identifying two or more classifications of interest for the event; for each data object in the data objects that qualify for the event, determining whether the data object qualifies for a classification of interest of the two or more classifications of interest; when the data object qualifies for a classification of interest of the two or more classifications of interest, classifying the data object as part of the classification of interest; determining information differences between data objects in different classifications of the two or more classifications; and generating a summary based on the information differences. ### Claim 2 (depends on 1) The method of claim 1, wherein the data objects comprise documents, social media posts, videos, and/or audio files. ### Claim 3 (depends on 1) The method of claim 1, wherein the information sources comprise webpages and/or feeds. ### Claim 4 (depends on 1) The method of claim 1, wherein the two or more classifications of interest comprise two or more geographic regions. ### Claim 5 (depends on 1) The method of claim 1, wherein the two or more classifications of interest comprise two or more languages. ### Claim 6 (depends on 1) The method of claim 1 further comprising receiving a request for the summary from an end user, and wherein generating the summary based on the information differences comprises generating the summary based on the information differences and summary preferences of the end user. ### Claim 7 (depends on 6) The method of claim 6, wherein the summary preferences of the end user comprise learned preferences identified from previous summary requests and responses for the end user. ### Claim 8 (depends on 1) The method of claim 1, wherein determining information differences between data objects in different classifications of the two or more classifications comprises determining numerical value differences between data objects in different classifications of the two or more classifications. ### Claim 9 A computing apparatus comprising: one or more non-transitory computer readable storage media; a processing system operatively coupled to the one or more non-transitory computer readable storage media; and program instructions stored on the one or more non-transitory computer readable storage media to provide event summarization that, when read and executed by the processing system, direct the processing system to at least: identify data objects that qualify for an event from a plurality of data objects obtained from a plurality of information sources; identify two or more classifications of interest for the event; for each data object in the data objects that qualify for the event, determine whether the data object qualifies for a classification of interest of the two or more classifications of interest; when the data object qualifies for a classification of interest of the two or more classifications of interest, classify the data object as part of the classification of interest; determine information differences between data objects in different classifications of the two or more classifications; and generate a summary based on the information differences. ### Claim 10 (depends on 9) The computer apparatus of claim 9, wherein the data objects comprise documents, social media posts, videos, and/or audio files. ### Claim 11 (depends on 9) The computer apparatus of claim 9, wherein the information sources comprise webpages and/or feeds. ### Claim 12 (depends on 9) The computer apparatus of claim 9, wherein the two or more classifications of interest comprise two or more geographic regions. ### Claim 13 (depends on 9) The computer apparatus of claim 9, wherein the two or more classifications of interest comprise two or more languages. ### Claim 14 (depends on 9) The computer apparatus of claim 9, wherein the program instructions further direct the processing system to receive a request for the summary from an end user, and wherein generating the summary based on the information differences comprises generating the summary based on the information differences and summary preferences of the end user. ### Claim 15 (depends on 13) The computer apparatus of claim 13, wherein the summary preferences of the end user comprise learned preferences identified from previous summary requests and responses for the end user. ### Claim 16 (depends on 9) The computer apparatus of claim 9, wherein determining information differences between data objects in different classifications of the two or more classifications comprises determining numerical value differences between data objects in different classifications of the two or more classifications. ### Claim 17 (depends on 9) The computer apparatus of claim 9, wherein determining information differences between data objects in different classifications of the two or more classifications comprises: for each classification, generating a summary of data values from data objects that classify for the classification; and determining the information differences between the summaries for each of the classifications. ### Claim 18 (depends on 9) The computer apparatus of claim 9, wherein generating the summary based on the information differences comprises generating a text summary or graph-based summary based on the information differences. ### Claim 19 A method of operating a summary service to provide a summary of an event, the method comprising: for each data object in a plurality of data objects that provide information for the event, determine whether the data object qualifies for a classification of interest of two or more classifications of interest; when the data object qualifies for a classification of interest of the two or more classifications of interest, classifying the data object as part of the classification of interest; determining information differences between data objects in different classifications of the two or more classifications; scoring each information difference of the information differences based at least on a relevance of the information difference to an event type for the event; and generating a summary based on the scores for each information difference of the information differences. ### Claim 20 (depends on 19) The method of claim 19, wherein generating the summary based on the scores for each information difference of the information differences comprises generating the summary based on the scores for each information difference of the information differences, wherein each information difference is prioritized in the summary based on the scores.