# US 11,443,214 B2 · Moderation of user-generated content > Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt - Number: US 11,443,214 B2 - Document ID: US11443214B2 - Status: Granted - Kind: B2 - Application number: 16/154,377 - Filed: 2018-10-08 - Published: 2019-08-08 - Granted: 2022-09-13 - Earliest claimed: 2011-04-29 - Assignees: Google Inc. - Applicants: Google LLC - Inventors: Ashutosh Kulshreshtha; Luca de Alfaro; Mitchell Slep; Nicu Daniel Cornea; Sowmya Subramanian; Ethan G. Russell - Web page: https://patentgrep.com/patent/US11443214B2 ## CPC - G06N 5/048: Fuzzy inferencing - G06F 16/00: Information retrieval; Database structures therefor; File system structures therefor - G09B 29/106: {using electronic means} - H04W 12/40: Security arrangements using identity modules - G06N: COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS - G06F: ELECTRIC DIGITAL DATA PROCESSING (computer systems based on specific computational models G06N) - G09B: EDUCATIONAL OR DEMONSTRATION APPLIANCES; APPLIANCES FOR TEACHING, OR COMMUNICATING WITH, THE BLIND, DEAF OR MUTE; MODELS; PLANETARIA; GLOBES; MAPS; DIAGRAMS (devices for psychotechnics or for testing reaction times A61B5/16; games, sports, amusements A63; projectors, projector screens G03B) - H04W: WIRELESS COMMUNICATION NETWORKS (broadcast communication H04H; communication systems using wireless links for non-selective communication, e.g. wireless extensions H04M1/72) ## Abstract A system and method for updating and correcting facts that receives proposed values for facts from users and determines a correctness score which is used to automatically accept or reject the proposed values. ## Claims ### Claim 1 A computer-implemented method for moderating user-generated content within a web-based application, comprising: obtaining, by a computing system comprising one or more computing devices, a proposed user-generated value associated with a feature for inclusion in an online database of features that are accessed from a web-based application; obtaining, by the computing system, metadata associated with a user providing the proposed user-generated value; accessing a reliability engine comprising at least one machine-learned model configured to determine a score indicative of a probability that unreliable information has been provided; providing, by the computing system, the proposed user-generated value and the metadata associated with the user to the at least one machine-learned model of the reliability engine; receiving, by the computing system, as an output of the at least one machine-learned model of the reliability engine, and in response to receipt of the proposed user-generated value and the metadata associated with the user, an unreliability score indicative of a probability that the user having proposed the user-generated value has provided unreliable information; and determining, by the computing system, to implement an action on the proposed user-generated value based on the unreliability score as compared to one or more thresholds. ### Claim 2 (depends on 1) The computer-implemented method of claim 1, wherein the metadata associated with the user providing the proposed user-generated value comprises data from edit logs that contain information about user interactions with the online database of features, each log entry of the edit logs comprising one or more of a timestamp, user ID, and type of interaction. ### Claim 3 (depends on 1) The computer-implemented method of claim 1, wherein edit sessions of unreliable users are used as a training set for training the at least one machine-learned model of the reliability engine. ### Claim 4 (depends on 3) The computer-implemented method of claim 3, wherein the edit sessions comprise a plurality of different characteristics that are used to differentiate unreliable users from reliable users. ### Claim 5 (depends on 4) The computer-implemented method of claim 4, wherein the plurality of different characteristics of the edit sessions comprise indications associated with one or more of a frequency of the edit sessions, an average time between the edit sessions, a number of edits made per edit session, or a time of day of each edit session. ### Claim 6 (depends on 1) The computer-implemented method of claim 1, wherein determining to implement an action on the proposed user-generated value based on the unreliability score as compared to one or more thresholds comprises automatically accepting or rejecting the user-generated value as part of the online database of features. ### Claim 7 (depends on 1) The computer-implemented method of claim 1, wherein determining to implement an action on the proposed user-generated value based on the unreliability score as compared to one or more thresholds comprises flagging the user-generated value for manual review. ### Claim 8 (depends on 1) The computer-implemented method of claim 1, wherein the proposed value associated with the feature for inclusion in the online database of features comprises a new feature to be added to the online database. ### Claim 9 (depends on 1) The computer-implemented method of claim 1, wherein the proposed value associated with the feature for inclusion in the online database of features comprises an updated attribute associated with an existing feature already stored in the online database. ### Claim 10 (depends on 1) The computer-implemented method of claim 1, wherein the proposed value associated with a feature for inclusion on the online database of features is obtained from a client device. ### Claim 11 (depends on 1) The computer-implemented method of claim 1, wherein the online database of features comprises an online map comprising a plurality of map features. ### Claim 12 (depends on 1) The computer-implemented method of claim 1, wherein the online database of features comprises an online database of community pages. ### Claim 13 A system for moderating user-generated content within a web-based application, comprising: a network interface configured to receive a proposed user-generated value from a client device that is adapted to access the web-based application, the proposed user-generated value being associated with a feature for inclusion in an online database of features that are accessed from the web-based application; a database containing user metadata that is accessed to determine metadata associated with a user providing the proposed user-generated value; and a reliability engine comprising at least one machine-learned model configured to determine a score indicative of a probability that unreliable information has been provided; wherein the system is configured to provide the proposed user-generated value and the metadata associated with the user to the at least one machine-learned model of the reliability engine, and to receive as an output of the at least one machine-learned model of the reliability engine, and in response to receipt of the proposed user-generated value and the metadata associated with the user, an unreliability score indicative of a probability that the user having proposed the user-generated value has provided unreliable information; and wherein the system is configured to implement an action on the proposed user-generated value based on the unreliability score as compared to one or more thresholds. ### Claim 14 (depends on 13) The system of claim 13, wherein the database containing user metadata comprises data from edit logs that contain information about user interactions with the online database of features, each log entry of the edit logs comprising one or more of a timestamp, user ID, and type of interaction. ### Claim 15 (depends on 13) The system of claim 13, wherein edit sessions of unreliable users are used as a training set for training the at least one machine-learned model of the reliability engine. ### Claim 16 (depends on 15) The system of claim 15, wherein the edit sessions comprise a plurality of different characteristics that are used to differentiate unreliable users from reliable users, the plurality of different characteristics of the edit sessions comprising indications associated with one or more of a frequency of the edit sessions, an average time between the edit sessions, a number of edits made per edit session, or a time of day of each edit session. ### Claim 17 (depends on 13) The system of claim 13, wherein the system is configured to automatically accept or reject the user-generated value as part of the online database of features based on the unreliability score as compared to one or more thresholds. ### Claim 18 (depends on 13) The system of claim 13, wherein the system is configured to flag the user-generated value for manual review based on the unreliability score as compared to one or more thresholds. ### Claim 19 (depends on 13) The system of claim 13, wherein the proposed value associated with the feature for inclusion in the online database of features comprises a new feature to be added to the online database. ### Claim 20 (depends on 13) The system of claim 13, wherein the proposed value associated with the feature for inclusion in the online database of features comprises an updated attribute associated with an existing feature already stored in the online database.