# US 2019/0356643 A1 · Predicting input locations for data aggregation using machine learning > Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt - Number: US 2019/0356643 A1 - Document ID: US20190356643A1 - Status: Published application - Kind: A1 - Application number: 16/525,536 - Filed: 2019-07-29 - Published: 2019-11-21 - Earliest claimed: 2015-11-12 - Assignees: Mx Technologies, Inc. - Applicants: MX Technologies, Inc. - Inventors: John Ryan Caldwell - Web page: https://patentgrep.com/patent/US20190356643A1 ## CPC - H04L 63/08: {for authentication of entities (cryptographic mechanisms or cryptographic arrangements for entity authentication H04L9/32)} - G06F 21/6218: {to a system of files or objects, e.g. local or distributed file system or database} - H04L 43/0852: Delays - H04L 47/82: {Miscellaneous aspects} - H04L 63/0428: {wherein the data content is protected, e.g. by encrypting or encapsulating the payload} - H04L 63/083: {using passwords (cryptographic mechanisms or cryptographic arrangements for entity authentication using a predetermined code H04L9/3226)} - H04L 63/10: {for controlling access to devices or network resources} - H04L 67/02: based on web technology, e.g. hypertext transfer protocol [HTTP] - H04L 67/10: in which an application is distributed across nodes in the network (software deployment G06F8/60; multiprogramming arrangements G06F9/46) - H04L 67/52: specially adapted for the location of the user terminal - H04L 67/53: using third party service providers - H04L 67/535: {Tracking the activity of the user (network monitoring arrangements H04L43/00; recording of computer activity G06F11/34)} - H04L 41/22: comprising specially adapted graphical user interfaces [GUI] - H04L: TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION (arrangements common to telegraphic and telephonic communication H04M) - G06F: ELECTRIC DIGITAL DATA PROCESSING (computer systems based on specific computational models G06N) ## Abstract Apparatuses, systems, methods, and computer program products are disclosed for distributed and/or decentralized data aggregation. A method includes determining a user's electronic credentials for a third party service provider. A method includes detecting that access to a third party service provider is unavailable. A method includes processing, using machine learning, a website of a third party service provider to determine a prediction of an input location for a user's electronic credentials. A method includes accessing a third party service provider using a predicted input location for a user's electronic credentials to download data associated with the user from the third party service provider. ## Claims ### Claim 1 A method comprising: determining a user's electronic credentials for a third party service provider; detecting that access to the third party service provider is unavailable; processing, using machine learning, a website of the third party service provider to determine a prediction of an input location for the user's electronic credentials; and accessing the third party service provider using the predicted input location for the user's electronic credentials to download data associated with the user from the third party service provider. ### Claim 2 (depends on 1) The method of claim 1, further comprising processing one or more web pages of the website of the third party service provider, using the machine learning, to determine the prediction of the input location for the user's electronic credentials. ### Claim 3 (depends on 2) The method of claim 2, wherein the machine learning processes one or more images of the one or more web pages of the website of the third party service provider to determine the prediction of the input location for the user's electronic credentials using image recognition. ### Claim 4 (depends on 2) The method of claim 2, further comprising: parsing the one or more web pages of the website of the third party service provider for information for the one or more web pages; and processing, using the machine learning, the parsed information for the one or more web pages to determine the prediction of the input location for the user's electronic credentials. ### Claim 5 (depends on 1) The method of claim 1, further comprising determining a prediction of an input location for the user's electronic credentials based on historical changes to one or more web pages of the website of the third party service provider. ### Claim 6 (depends on 1) The method of claim 1, further comprising determining a prediction of an input location for the user's electronic credentials based on input from other users accessing one or more web pages of the website of the third party service provider. ### Claim 7 (depends on 1) The method of claim 1, further comprising accessing one or more other locations of the third party service provider, with one or more artificially introduced delays between accessing the one or more other locations and downloading the data, thereby emulating a use pattern of the user for the third party service provider. ### Claim 8 (depends on 7) The method of claim 7, wherein the emulated use pattern is determined based on one or more of an average pattern identified in behavior of multiple other users accessing the third party service provider using a web browser and a pattern identified in behavior of the user accessing the third party service provider using a web browser. ### Claim 9 (depends on 1) The method of claim 1, further comprising displaying to a user in an interface the prediction of the input location for the user's electronic credentials on the website of the third party service provider. ### Claim 10 (depends on 1) The method of claim 1, wherein the third party service provider is one of a plurality of third party service providers where the user has data, the user's data downloaded and aggregated from each of the plurality of third party service providers using electronic credentials for each of the plurality of third party service providers. ### Claim 11 (depends on 1) The method of claim 1, further comprising: generating and managing one or more different, secure, electronic credentials for the user for the third party service provider; and securely storing the generated one or more different, secure, electronic credentials for the user on a hardware device associated with the user. ### Claim 12 An apparatus, comprising: means for determining a user's electronic credentials for a third party service provider; means for detecting that access to the third party service provider is unavailable; means for processing, using machine learning, a website of the third party service provider to determine a prediction of an input location for the user's electronic credentials; and means for accessing the third party service provider using the predicted input location for the user's electronic credentials to download data associated with the user from the third party service provider. ### Claim 13 (depends on 12) The apparatus of claim 12, further comprising means for processing one or more web pages of the website of the third party service provider, using the machine learning, to determine the prediction of the input location for the user's electronic credentials. ### Claim 14 (depends on 13) The apparatus of claim 13, wherein the machine learning processes one or more images of the one or more web pages of the website of the third party service provider to determine the prediction of the input location for the user's electronic credentials. ### Claim 15 (depends on 13) The apparatus of claim 13, further comprising: means for parsing the one or more web pages of the website of the third party service provider for information for the one or more web pages; and means for processing, using the machine learning, the parsed information for the one or more web pages to determine the prediction of the input location for the user's electronic credentials. ### Claim 16 (depends on 12) The apparatus of claim 12, further comprising means for determining a prediction of an input location for the user's electronic credentials based on historical changes to one or more web pages of the website of the third party service provider. ### Claim 17 (depends on 12) The apparatus of claim 12, further comprising means for determining a prediction of an input location for the user's electronic credentials based on input from other users accessing one or more web pages of the website of the third party service provider. ### Claim 18 (depends on 12) The apparatus of claim 12, further comprising means for accessing one or more other locations of the third party service provider, with one or more artificially introduced delays between accessing the one or more other locations and downloading the data, thereby emulating a use pattern of the user for the third party service provider. ### Claim 19 (depends on 18) The apparatus of claim 18, wherein the emulated use pattern is determined based on one or more of an average pattern identified in behavior of multiple other users accessing the third party service provider using a web browser and a pattern identified in behavior of the user accessing the third party service provider using a web browser. ### Claim 20 A computer program product comprising a non-transitory computer readable storage medium storing computer usable program code executable by a processor to perform operations, the operations comprising: determining a user's electronic credentials for a third party service provider; detecting that access to the third party service provider is unavailable; processing, using machine learning, a website of the third party service provider to determine a prediction of an input location for the user's electronic credentials; and accessing the third party service provider using the predicted input location for the user's electronic credentials to download data associated with the user from the third party service provider.