# US 10,769,359 B1 · Dynamic determination of missing fields > Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt - Number: US 10,769,359 B1 - Document ID: US10769359B1 - Status: Granted - Kind: B1 - Application number: 16/212,253 - Filed: 2018-12-06 - Granted: 2020-09-08 - Earliest claimed: 2018-12-06 - Assignees: Intuit Inc. - Applicants: Intuit Inc. - Inventors: Pradeep Kurunimakki Laxminarayana; John Samuel; Arun Satyarth - Web page: https://patentgrep.com/patent/US10769359B1 ## CPC - G06F 40/174: Form filling; Merging - G06N 3/09: Supervised learning - G06N 5/025: Extracting rules from data - G06N 20/00: Machine learning - G06F: ELECTRIC DIGITAL DATA PROCESSING (computer systems based on specific computational models G06N) - G06N: COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS ## Abstract A processor may receive a data submission made through the UI. The data submission may lack data in at least one blank field provided in the UI for entering information in which no information has been entered. The processor may classify the data submission as having at least one data submission type using at least one machine learning (ML) process. The processor may determine at least one required field for the at least one data submission type. The at least one required field may require information to be entered therein. The processor may determine that the at least one blank field is also the at least one required field. The processor may cause the UI to indicate that the at least one blank field is also the at least one required field. ## Claims ### Claim 1 A method of automatically determining at least one required field in a user interface (UI), comprising: receiving, at a processor, a data submission made through the UI, the data submission including a plurality of fields used to complete a document, wherein the data submission lacks data in at least one blank field provided in the UI for entering information in which no information has been entered; classifying, by the processor, the data submission as having at least one data submission type using at least one machine learning (ML) process that evaluates the data submission against training data including a plurality of sample data submissions having one or more filled in fields that include similar information to data input into at least one field of the data submission; determining, by the processor, at least one required field for the at least one data submission type based on patterns, indicated in the training data, of observed fields that are usually filled in for sample data submissions of the at least one data submission type, wherein the at least one required field requiring information to be entered therein; determining, by the processor, that the at least one blank field is also the at least one required field; and causing, by the processor, the UI to indicate that the at least one blank field is also the at least one required field. ### Claim 2 (depends on 1) The method of claim 1, wherein the classifying further comprises cleaning the data submission before using the at least one ML process. ### Claim 3 (depends on 2) The method of claim 2, wherein the cleaning comprises at least one of: discarding a portion of the data submission that is not relevant to the at least one ML process; and formatting the data submission to have a same format as training data used by the at least one ML process. ### Claim 4 (depends on 1) The method of claim 1, wherein the at least one ML process uses at least one of a neural network algorithm, a random forest algorithm, and a k-nearest neighbor algorithm. ### Claim 5 (depends on 1) The method of claim 1, wherein the determining of the at least one required field is based at least in part on a local rule applied to the data submission, wherein the local rule does not apply to at least a portion of training data used by the at least one ML process. ### Claim 6 (depends on 1) The method of claim 1, further comprising: receiving, by the processor, training data including the plurality of sample data submissions; classifying, by the processor, the training data using the at least one ML process; and storing, by the processor, a result of the classifying as trained data, wherein the classifying of the data submission is based on the trained data. ### Claim 7 (depends on 6) The method of claim 6, further comprising cleaning, by the processor, at least one of the sample data submissions prior to the classifying. ### Claim 8 (depends on 7) The method of claim 7, wherein the cleaning comprises at least one of: discarding a portion of the at least one of the sample data submissions that is not relevant to the at least one ML process; and collapsing a portion of the at least one of the sample data submissions into a description of the portion and a count of occurrences of the portion within the total sample data submissions. ### Claim 9 A system configured to automatically determine at least one required field in a user interface (UI), comprising: a processor; and a non-transitory memory in communication with the processor and configured to store instructions that, when executed by the processor, cause the processor to perform processing comprising: receiving a data submission made through the UI, the data submission including a plurality of fields used to complete a document, wherein the data submission lacks data in at least one blank field provided in the UI for entering information in which no information has been entered; classifying the data submission as having at least one data submission type using at least one machine learning (ML) process that evaluates the data submission against training data including a plurality of sample data submissions having one or more filled in fields that include similar information to data input into at least one field of the data submission; determining at least one required field for the at least one data submission type based on patterns, indicated in the training data, of observed fields that are usually filled in for sample data submissions of the at least one data submission type, wherein the at least one required field requiring information to be entered therein; determining that the at least one blank field is also the at least one required field; and causing the UI to indicate that the at least one blank field is also the at least one required field. ### Claim 10 (depends on 9) The system of claim 9, wherein the classifying further comprises cleaning the data submission before using the at least one ML process. ### Claim 11 (depends on 10) The system of claim 10, wherein the cleaning comprises at least one of: discarding a portion of the data submission that is not relevant to the at least one ML process; and formatting the data submission to have a same format as training data used by the at least one ML process. ### Claim 12 (depends on 9) The system of claim 9, wherein the at least one ML process uses at least one of a neural network algorithm, a random forest algorithm, and a k-nearest neighbor algorithm. ### Claim 13 (depends on 9) The system of claim 9, wherein the determining of the at least one required field is based at least in part on a local rule applied to the data submission, wherein the local rule does not apply to at least a portion of training data used by the at least one ML process. ### Claim 14 (depends on 9) The system of claim 9, wherein the instructions further cause the processor to perform processing comprising: receiving, by the processor, training data including the plurality of sample data submissions; classifying, by the processor, the training data using the at least one ML process; and storing, by the processor, a result of the classifying as trained data, wherein the classifying of the data submission is based on the trained data. ### Claim 15 (depends on 14) The system of claim 14, wherein the instructions further cause the processor to perform processing comprising cleaning at least one of the sample data submissions prior to the training. ### Claim 16 (depends on 15) The system of claim 15, wherein the cleaning comprises at least one of: discarding a portion of the at least one of the sample data submissions that is not relevant to the at least one ML process; and collapsing a portion of the at least one of the sample data submissions into a description of the portion and a count of occurrences of the portion within the total sample data submissions. ### Claim 17 A method of automatically determining at least one required field in a user interface (UI), comprising: receiving, at a processor the processor, training data including a plurality of sample data submissions; classifying, by the processor, the training data using at least one machine learning (ML) process; storing, by the processor, a result of the classifying as trained data; receiving, at the processor, a data submission made through the UI, the data submission including a plurality of fields used to complete a document, wherein the data submission lacks data in at least one blank field provided in the UI for entering information in which no information has been entered; classifying, by the processor, the data submission as having at least one data submission type using the at least one ML process that evaluates the data submission against the trained data, wherein the trained data includes a plurality of sample data submissions having one or more filled in fields that include similar information to data input into at least one field of the data submission; determining, by the processor, at least one required field for the at least one data submission type based on patterns, indicated in the training data, of observed fields that are usually filled in for sample data submissions of the at least one data submission type, wherein the at least one required field requiring information to be entered therein; determining, by the processor, that the at least one blank field is also the at least one required field; and causing, by the processor, the UI to indicate that the at least one blank field is also the at least one required field. ### Claim 18 (depends on 17) The method of claim 17, wherein the at least one ML process uses at least one of a neural network algorithm, a random forest algorithm, and a k-nearest neighbor algorithm. ### Claim 19 (depends on 1) The method of claim 1, wherein the training data includes behavior data generated during one or more user sessions, wherein the behavior data comprises records of filled in fields and not filled in fields for a plurality of sample data submissions previously received by the UI. ### Claim 20 (depends on 9) The system of claim 9, wherein the training data includes behavior data generated during one or more user sessions, wherein the behavior data comprises records of filled in fields and not filled in fields for a plurality of sample data submissions previously received by the UI.