Data feedback interface
In an embodiment, a first level of confidence corresponding to a first data set presented in a pre-populated form is computed. A visualization suggesting a need for user review in association with the first data set is displayed when the first level of confidence is determined to not meet a first threshold value. In addition, a second level of confidence corresponding to a second data set presented in the pre-populated form is computed. No visualization is presented when the second level of confidence is determined to meet the second threshold value. In an embodiment, an impact associated with an academic course modification is determined and identified according to a user selection from a displayed set of scheduled courses. The impact may include a financial impact, a graduation timeline impact, or a workload impact associated with the modification.
1. One or more non-transitory machine-readable media storing instructions which, when executed by one or more processors, cause performance of operations comprising:
presenting a form pre-populated with a plurality of data sets;
computing a first level of confidence corresponding to a first data set, in the plurality of data sets;
determining that the first level of confidence corresponding to the first data set does not meet a first threshold value;
responsive to determining that the first level of confidence corresponding to the first data set does not meet the first threshold value: displaying a textual message that suggests a need for user review associated with the first data set and indicates a reason underlying the first level of confidence determined for the first data set, wherein the textual message is displayed in association with the first data set in the form;
computing a second level of confidence corresponding to a second data set, in the plurality of data sets;
determining that the second level of confidence corresponding to the second data set, in the plurality of data sets, meets a second threshold value; and
responsive to determining that the second level of confidence corresponding to the second data set meets the second threshold value: refraining from displaying any visualization, that suggests a need for user review associated with the second data set, in association with the second data set in the form;
wherein:
the first data set is obtained from a first source, of a plurality of sources;
the second data set is obtained from a second source, of the plurality of sources; and
the textual message further indicates that the first data set is obtained from the first source.
2. The one or more non-transitory machine-readable media of claim 1 , wherein the first level of confidence corresponding to the first data set is computed based on a date associated with the first data set.
3. The one or more non-transitory machine-readable media of claim 1 , wherein the first level of confidence corresponding to the first data set is computed based on identification of multiple data sets corresponding to a same form field that is associated with the first data set.
4. The one or more non-transitory machine-readable media of claim 1 , wherein the first level of confidence corresponding to the first data set is computed based on the first source of the first data set.
5. The one or more non-transitory machine-readable media of claim 1 , wherein the first level of confidence corresponding to the first data set is computed based on a machine-learning model.
6. The one or more non-transitory machine-readable media of claim 1 , wherein the operations further comprise pre-populating the form with the first data set at least by:
executing optical character recognition on an image to identify the plurality of data sets; and
assigning each of the plurality of data sets to a respective field based on a template associated with the image, wherein the template defines a location, of a value corresponding to each respective field, in the image.
7. The one or more non-transitory machine-readable media of claim 6 , wherein the template is selected based on a machine-learning model.
8. The one or more non-transitory machine-readable media of claim 1 , wherein the first level of confidence corresponding to the first data set is based on a correlation between (a) a document from which the first data set was extracted and (b) a template used for identification of any data stored in the document.
9. The one or more non-transitory machine-readable media of claim 1 , wherein the operations further comprise:
executing optical character recognition on an image, to identify a data element; and
using the data element, at least in part, to pre-populate the form.
10. The one or more non-transitory machine-readable media of claim 1 , wherein the operations further comprise:
determining that the first source, of the plurality of sources, includes the first data set, of the plurality of data sets, for populating a first field of the form;
determining that the second source, of the plurality of sources, includes a third data set, of the plurality of data sets, for populating the first field of the form;
wherein the first level of confidence corresponds to populating the first field with the first data set and is determined based at least on a conflict between the first data set and the third data set.
11. The one or more non-transitory machine-readable media of claim 10 , wherein the operations further comprise:
displaying one or more interface elements for receiving user input that selects at least one of the first data set from the first source and the third data set from the third source for populating the first field.
12. The one or more non-transitory machine-readable media of claim 1 , wherein:
the first level of confidence corresponds to populating a first field of the form with a first data set and is determined based at least on a comparison between (a) a first position associated with the first data set in a document from which the first data set was extracted and (b) a second position associated with the first field in a template associated with the form.
13. A method comprising:
presenting a form pre-populated with a plurality of data sets;
computing a first level of confidence corresponding to a first data set, in the plurality of data sets;
determining that the first level of confidence corresponding to the first data set does not meet a first threshold value;
responsive to determining that the first level of confidence corresponding to the first data set does not meet the first threshold value: displaying a textual message that suggests a need for user review associated with the first data set and indicates a reason underlying the first level of confidence determined for the first data set, wherein the textual message is displayed in association with the first data set in the form;
computing a second level of confidence corresponding to a second data set, in the plurality of data sets;
determining that the second level of confidence corresponding to the second data set, in the plurality of data sets, meets a second threshold value; and
responsive to determining that the second level of confidence corresponding to the second data set meets the second threshold value: refraining from displaying any visualization, that suggests a need for user review associated with the second data set, in association with the second data set in the form;
wherein:
the first data set is obtained from a first source, of a plurality of sources;
the second data set is obtained from a second source, of the plurality of sources; and
the textual message further indicates that the first data set is obtained from the first source.
14. The method of claim 13 , wherein the first level of confidence corresponding to the first data set is computed based on at least one of a date associated with the first data set, identification of multiple data sets corresponding to a same form field that is associated with the first data set, the first source of the first data set, or a machine-learning model.
15. The method of claim 13 , further comprising pre-populating the form with the first data set at least by:
executing optical character recognition on an image to identify the plurality of data sets; and
assigning each of the plurality of data sets to a respective field based on a template associated with the image, wherein the template defines a location, of a value corresponding to each respective field, in the image.
16. The method of claim 15 , wherein the template is selected based on a machine-learning model.
17. The method of claim 13 , wherein the first level of confidence corresponding to the first data set is based on a correlation between (a) a document from which the first data set was extracted and (b) a template used for identification of any data stored in the document.
18. The method of claim 13 , further comprising:
executing optical character recognition on an image, to identify a data element; and
using the data element, at least in part, to pre-populate the form.
19. One or more non-transitory machine-readable media storing instructions which, when executed by one or more processors, cause performance of operations comprising:
presenting a form pre-populated with a plurality of data sets comprising a first data set obtained from a first source and a second data set obtained from a second source;
computing a first level of confidence corresponding to the first data set;
determining that the first level of confidence corresponding to the first data set does not meet a first threshold value;
responsive to determining that the first level of confidence corresponding to the first data set does not meet the first threshold value: displaying a textual message that suggests a need for user review associated with the first data set and indicates that the first data set is obtained from the first source, wherein the textual message is displayed in association with the first data set in the form;
computing a second level of confidence corresponding to a second data set, in the plurality of data sets;
determining that the second level of confidence corresponding to the second data set, in the plurality of data sets, meets a second threshold value; and
responsive to determining that the second level of confidence corresponding to the second data set meets the second threshold value: refraining from displaying any visualization, that suggests a need for user review associated with the second data set, in association with the second data set in the form.
20. The one or more non-transitory machine-readable media of claim 19 , wherein:
the first level of confidence corresponds to populating a first field of the form with a first data set and is determined based at least on a comparison between (a) a first position associated with the first data set in a document from which the first data set was extracted and (b) a second position associated with the first field in a template associated with the form.