# US 2014/0006861 A1 · Problem inference from support tickets > Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt - Number: US 2014/0006861 A1 - Document ID: US20140006861A1 - Status: Published application - Kind: A1 - Application number: 13/535,366 - Filed: 2012-06-28 - Published: 2014-01-02 - Earliest claimed: 2012-06-28 - Assignees: Microsoft Corporation - Inventors: Navendu Jain; Rahul Potharaju - Web page: https://patentgrep.com/patent/US20140006861A1 ## CPC - G06F 11/079: {Root cause analysis, i.e. error or fault diagnosis (in a hardware test environment G06F11/22; in a software test environment G06F11/36)} - G06F 11/0709: {in a distributed system consisting of a plurality of standalone computer nodes, e.g. clusters, client-server systems} - G06F 40/289: Phrasal analysis, e.g. finite state techniques or chunking - G06F 40/30: Semantic analysis - G06N 5/022: Knowledge engineering; Knowledge acquisition - G06N 20/00: Machine learning - H04L 41/069: using logs of notifications; Post-processing of notifications - H04L 41/16: using machine learning or artificial intelligence - H04L 41/5074: Handling of user complaints or trouble tickets - H04L 43/045: for graphical visualisation of monitoring data - G06F: ELECTRIC DIGITAL DATA PROCESSING (computer systems based on specific computational models G06N) - G06N: COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS - H04L: TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION (arrangements common to telegraphic and telephonic communication H04M) ## Abstract The described implementations relate to processing of electronic data. One implementation is manifested as a system that can include an inference engine and at least one processing device configured to execute the inference engine. The inference engine can be configured to perform automated detection of concepts expressed in failure logs that include unstructured data. For example, the inference engine can analyze text of support tickets or diary entries relating to troubleshooting of an electronic network to obtain concepts identifying problems, actions, or activities. The inference engine can also be configured to generate output that reflects the identified concepts, e.g., via a visualization or queryable programming interface. ## Claims ### Claim 1 A method comprising: obtaining a plurality of documents, the plurality of documents having corresponding text; performing phrase extraction on the text to obtain a plurality of phrases that appear in the text; filtering out some phrases from the plurality of phrases based on one or more criteria to obtain a subset of the plurality of phrases; mapping individual phrases from the subset of phrases to classes of an ontology model and storing the individual phrases in a knowledge base; analyzing an individual document by applying the classes of the ontology model to occurrences of the phrases in the individual document to infer at least one concept expressed by the individual document; generating output reflecting the at least one concept expressed by the individual document; and performing incremental learning by updating the knowledge base with a new phrase identified in the individual document, wherein at least the phrase extraction is performed using a computing device. ### Claim 2 (depends on 1) The method according to claim 1, wherein the plurality of documents comprise support tickets and associated diary entries reflecting troubleshooting of problems on an electronic network. ### Claim 3 (depends on 2) The method according to claim 2, wherein the analyzing is also performed on structured data in the individual document or other data that is external to the plurality of documents. ### Claim 4 (depends on 1) The method according to claim 1, wherein the performing phrase extraction comprises employing a compression algorithm to build a dictionary of phrases. ### Claim 5 (depends on 4) The method according to claim 4, wherein the performing phrase extraction comprises performing a frequency estimation of a number of times the plurality of phrases appear in the plurality of documents. ### Claim 6 (depends on 1) The method according to claim 1, wherein the filtering comprises part-of-speech filtering, length and frequency filtering, and information theoretic filtering. ### Claim 7 (depends on 1) The method according to claim 1, wherein the classes of the ontology model include an action class, a negation class, a sentiment class, a quantity class, an entity class, an incident class, and a condition class. ### Claim 8 (depends on 1) The method according to claim 1, further comprising matching the occurrences of the phrases in the individual document to a grammar pattern to identify the at least one concept, wherein the grammar pattern is built using one or more of the classes of the ontology model or one or more subclasses of the ontology model. ### Claim 9 (depends on 8) The method according to claim 8, wherein the generating the output includes creating a concept tree representing the at least one concept expressed by the individual document. ### Claim 10 (depends on 1) The method according to claim 1, wherein the output is a visualization that identifies at least one action concept expressed in multiple documents for devices of a particular device type. ### Claim 11 One or more computer-readable storage devices or memory devices comprising device-readable instructions which, when executed by one or more processing devices, cause the one or more processing devices to perform acts comprising: identifying occurrences of phrases in a support ticket, wherein the support ticket includes text describing troubleshooting steps taken by one or more network engineers to resolve one or more network problems; and inferring, from the occurrences, one or more concepts expressed by the text of the support ticket. ### Claim 12 (depends on 11) The one or more computer-readable storage devices or memory devices according to claim 11, wherein an individual concept identifies at least one of an individual network problem, an action taken to resolve the individual network problem, or an activity performed during troubleshooting of the individual network problem. ### Claim 13 (depends on 12) The one or more computer-readable storage devices or memory devices according to claim 12, wherein the acts further comprise tagging the occurrences of the phrases in the support ticket with classes or subclasses of an ontology model. ### Claim 14 (depends on 11) The one or more computer-readable storage devices or memory devices according to claim 11, wherein the identifying and the inferring are performed for multiple support tickets to identify a trend across the multiple support tickets. ### Claim 15 (depends on 14) The one or more computer-readable storage devices or memory devices according to claim 14, wherein the trend is grouped by a device type that includes multiple device models. ### Claim 16 A system comprising: an inference engine configured to perform automated detection of concepts expressed in failure logs, the failure logs comprising unstructured data; and at least one processing device configured to execute the inference engine. ### Claim 17 (depends on 16) The system according to claim 16, wherein the unstructured data comprises freeform text. ### Claim 18 (depends on 16) The system according to claim 16, wherein the failure logs comprise support tickets, network event logs, traffic logs, configuration files, or system logs. ### Claim 19 (depends on 16) The system according to claim 16, further comprising: a knowledge base configured to store phrases that are mapped to classes of an ontology, wherein the inference engine is further configured to perform the automated detection using the phrases stored in the knowledge base. ### Claim 20 (depends on 16) The system according to claim 16, embodied as at least one server computer.