# US 2024/0202061 A1 · Machine-Learning Based Similarity Engine > Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt - Number: US 2024/0202061 A1 - Document ID: US20240202061A1 - Status: Published application - Kind: A1 - Application number: 18/594,906 - Filed: 2024-03-04 - Published: 2024-06-20 - Earliest claimed: 2021-01-06 - Assignees: ServiceNow, Inc. - Applicants: ServiceNow, Inc. - Inventors: Hari Krishna Vutukuru; Purvanshi Yadav; Anushree Randad; Ajesh Sasidharan; Payal Roy; Ankit Kumar Das - Web page: https://patentgrep.com/patent/US20240202061A1 ## CPC - G06F 11/0787: {Storage of error reports, e.g. persistent data storage, storage using memory protection} - G06F 11/0769: {Readable error formats, e.g. cross-platform generic formats, human understandable formats} - G06N 3/088: Non-supervised learning, e.g. competitive learning - G06N 20/00: Machine learning - G06N 20/10: using kernel methods, e.g. support vector machines [SVM] - G06F: ELECTRIC DIGITAL DATA PROCESSING (computer systems based on specific computational models G06N) - G06N: COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS ## Abstract An embodiment may involve storage containing incident logs and mappings between incident logs and vector representations generated by a machine learning (ML) model. The embodiment may further involve one or more processors configured to: receive, from a client device, a classification request corresponding to an additional incident log; transmit, to the ML model, additional values as appearing in the additional incident log, wherein reception of the additional values causes the ML model to generate an additional vector representation of the additional incident log; obtain confidence measurements respectively representing similarities between the additional vector representation and each of the vector representations corresponding to the incident logs; determine, based on the confidence measurements, a set of one or more incident logs that are semantically relevant to the additional incident log; and transmit, to the client device, representations of the one or more incident logs and their corresponding confidence measurements. ## Claims ### Claim 1 A method comprising receiving first data indicating a classification request that is directed to a graphical user interface (GUI), wherein the classification request is based on a first incident log; generating, via a machine learning model, a first vector representation of the first incident log; identifying a second incident log of a plurality of incident logs according to a comparison between the first vector representation and respective vector representations of the plurality of incident logs; and transmitting second data to update the GUI to display a visual representation of the second incident log. ### Claim 2 (depends on 1) The method of claim 1, wherein identifying the second incident log includes comparing the first vector representation with each of the respective vector representations of the plurality of incident logs. ### Claim 3 (depends on 1) The method of claim 1, wherein the first data is received from a client device, and wherein the second data is transmitted to the client device. ### Claim 4 (depends on 1) The method of claim 1, wherein the visual representation of the second incident log is selectable for grouping with a visual representation of the first incident log. ### Claim 5 (depends on 4) The method of claim 4, further comprising: receiving a selection of the second incident log; and storing a group association between the first incident log and the second incident log. ### Claim 6 (depends on 5) The method of claim 5, wherein the group association is a parent-child relationship or a sibling relationship. ### Claim 7 (depends on 1) The method of claim 1, wherein identifying the second incident log comprises: determining, based on similarity values between the first vector representation and the respective vector representations of the plurality of incident logs, the second incident log as being above a threshold similarity with the first incident log. ### Claim 8 (depends on 1) The method of claim 1, wherein the GUI includes an identifier for the first incident log and a description of the first incident log. ### Claim 9 (depends on 1) The method of claim 1, wherein the GUI includes a list-based view of the plurality of incident logs, and wherein the list-based view respectively specifies in line items for each of the plurality of incident logs: (i) an identifier and (ii) a description. ### Claim 10 (depends on 1) The method of claim 1, further comprising: determining, based on the plurality of incident logs, a set of one or more incident solutions associated with one or more of the plurality of incident logs, wherein each of the incident solutions includes a further set of fields that respectively define a solution to a problem expressed in the one or more of the plurality of incident logs. ### Claim 11 (depends on 1) The method of claim 1, wherein the first vector representation was generated by the machine learning model based on respective values in one or more fields of the first incident log, and wherein a second vector representation was generated by the machine learning model based on respective values in one or more fields of the second incident log. ### Claim 12 (depends on 11) The method of claim 11, wherein the machine learning model is based on a word vector model or a paragraph vector model, and wherein training the machine learning model comprises mapping text within a pre-determined set of fields for a set of training incident logs into an n-dimensional semantic space related to content of the text. ### Claim 13 A non-transitory computer-readable medium, having stored thereon program instructions that, upon execution by a computing system, cause the computing system to perform operations comprising: receiving first data indicating a classification request that is directed to a graphical user interface (GUI), wherein the classification request is based on a first incident log; generating, via a machine learning model, a first vector representation of the first incident log; identifying a second incident log of a plurality of incident logs according to a comparison between the first vector representation and respective vector representations of the plurality of incident logs; and transmitting second data to update the GUI to display a visual representation of the second incident log. ### Claim 14 (depends on 13) The non-transitory computer-readable medium of claim 13, wherein the visual representation of the second incident log is selectable for grouping with a visual representation of the first incident log. ### Claim 15 (depends on 14) The non-transitory computer-readable medium of claim 14, the operations further comprising: receiving a selection of the second incident log; and storing a group association between the first incident log and the second incident log. ### Claim 16 (depends on 15) The non-transitory computer-readable medium of claim 15, wherein the group association is a parent-child relationship or a sibling relationship. ### Claim 17 (depends on 13) The non-transitory computer-readable medium of claim 13, the operations further comprising: determining, based on the plurality of incident logs, a set of one or more incident solutions associated with one or more of the plurality of incident logs, wherein each of the incident solutions includes a further set of fields that respectively define a solution to a problem expressed in the one or more of the plurality of incident logs. ### Claim 18 (depends on 13) The non-transitory computer-readable medium of claim 13, wherein the first vector representation was generated by the machine learning model based on respective values in one or more fields of the first incident log, and wherein a second vector representation was generated by the machine learning model based on respective values in one or more fields of the second incident log. ### Claim 19 (depends on 18) The non-transitory computer-readable medium of claim 18, wherein the machine learning model is based on a word vector model or a paragraph vector model, and wherein training the machine learning model comprises mapping text within a pre-determined set of fields for a set of training incident logs into an n-dimensional semantic space related to content of the text. ### Claim 20 A system comprising: persistent storage containing a plurality of incident logs; and one or more processors configured to: receive first data indicating a classification request that is directed to a graphical user interface (GUI), wherein the classification request is based on a first incident log; generate, via a machine learning model, a first vector representation of the first incident log; identify a second incident log of the plurality of incident logs according to a comparison between the first vector representation and respective vector representations of the plurality of incident logs; and transmit second data to update the GUI to display a visual representation of the second incident log.