IP Library › Granted Patent US 12705078
Granted Patent B2
US 12705078 · App. 18/481,910 · Granted Aug 11, 2026

Form field recommendation management

Inventors: Subash Bhamidipati (Issaquah, WA); Kuldip Oberoi (Milpitas, CA); Karan Nayyar (Foster City, CA); John Ray Thomas (Aptos, CA); Blake Thomas Sullivan (San Francisco, CA); Raj Karpana Alagumalai (Redmond, WA); Van Hieu Tran (Pflugerville, TX); Kevin Ng (Hampshire, GB)
Assignee: Oracle International Corporation
G06F9/453G06F16/215G06F40/174
View Patent ↗
Loading inventors, assignments & file history…
Monitor This Case
Get email alerts when status or documents change.
Order Certified Copies
Most orders are placed with the USPTO same day — all within 24 business hours.
Order via The Patent Place →
Pre-filled with this patent's details
Quick Facts
Patent No.
US 12705078
App. No.
18/481,910
Granted
Aug 11, 2026
Kind
B2
Abstract

Techniques for generating recommendations for form fields are disclosed. A system obtains user interaction data based on a user's interaction with a digital form. The digital form includes form fields mapped to attribute fields of data object resources. The data object resources specify criteria for when recommendations should be permitted or prohibited for the attribute fields of the business objects. The system obtains the criteria from the data object resources corresponding to the form fields in the digital form. The system compares the user interaction data with the recommendation enablement criteria to determine whether to allow the generation and presentation of recommendations for respective form fields. If the recommendation enablement criteria are met, the system applies a recommendation-type machine learning model to a set of input data including the user interaction data to generate a set of recommendations for a form field.

Claims (80)

1 . A non-transitory computer readable medium comprising instructions which, when executed by one or more hardware processors, causes performance of operations comprising:

displaying, in a Graphical User Interface (GUI), a plurality of data entry fields associated with a first data object resource, wherein the plurality of data entry fields are displayed in a data entry mode that allows a user to submit values in relation to the plurality of data entry fields;

subsequent to displaying the plurality of data entry fields in the GUI, monitoring user interaction with a first data entry field of the plurality of data entry fields to generate a first set of user interaction data indicating a first amount of time that the user has spent interacting with the first data entry field to submit user input in relation to the first data entry field;

determining that the first set of user interaction data meets a first set of recommendation enablement criteria at least by determining that the first amount of time the user has spent interacting with the first data entry field exceeds a first threshold time duration, wherein the first set of recommendation enablement criteria are stored in the first data object resource; and

responsive to determining that the first amount of time the user has spent interacting with the first data entry field exceeds the first threshold time duration:

displaying a recommended value for the first data entry field of the plurality of data entry fields,

wherein the first data object resource stores information identifying a set of records, and

wherein the recommended value is accessed from among a set of fields included in the set of records identified in the first data object resource.

2 . The non-transitory computer readable medium of claim 1 , wherein the operations further comprise:

generating a second set of user interaction data indicating a second amount of time that the user has spent interacting with a second data entry field;

determining whether the second set of user interaction data meets a second set of recommendation enablement criteria at least by determining that the second amount of time the user has spent interacting with the second data entry field does not meet a second threshold time duration; and

responsive to determining that the second amount of time the user has spent interacting with the second data entry field does not meet the second threshold time duration:

refraining from displaying any recommended value for the second data entry field of the plurality of data entry fields.

3 . The non-transitory computer readable medium of claim 2 , wherein the operations further comprise:

determining the first set of recommendation enablement criteria based on a first set of metadata stored in association with the first data entry field; and

determining the second set of recommendation enablement criteria based on a second set of metadata stored in association with the second data entry field.

4 . The non-transitory computer readable medium of claim 1 ,

wherein the first set of user interaction data indicates a second amount of time that has passed since user input was received from the user,

wherein the first set of recommendation enablement criteria specifies a second threshold time duration, and

wherein determining that the first set of user interaction data meets the first set of recommendation enablement criteria comprises determining that the second amount of time that has passed exceeds the second threshold time duration.

5 . The non-transitory computer readable medium of claim 1 ,

wherein the first set of user interaction data comprises information regarding an acceptance rate and/or rejection rate associated with previously presented recommended values, and

wherein the first set of recommendation enablement criteria specifies a threshold to be compared to the acceptance rate and/or the rejection rate to determine whether to present the recommended value for the first data entry field.

6 . The non-transitory computer readable medium of claim 1 , wherein the operations further comprise:

training a machine learning model based on training data sets, a first training data set of the training data sets comprising:

a particular set of user interaction data; and

a label indicating whether recommendations are to be enabled or disabled based on the particular set of user interaction data, and

wherein determining whether the first set of user interaction data meets the first set of recommendation enablement criteria comprises applying the trained machine learning model to the first set of user interaction data to determine whether to enable or disable recommendations for the first data entry field.

7 . The non-transitory computer readable medium of claim 1 ,

wherein the user interaction with the first data entry field comprises an attempt to submit a user-determined value for the first data entry field,

wherein the user interaction does not include any command to enable or disable value recommendations for the first data entry field.

8 . The non-transitory computer readable medium of claim 1 , wherein the operations further comprise:

determining the first set of recommendation enablement criteria based on a set of form-specific metadata stored in association with a form comprising the plurality of data entry fields.

9 . The non-transitory computer readable medium of claim 1 , wherein the first set of user interaction data indicates a second amount of time taken by the user to complete a second data entry field of the plurality of data entry fields.

10 . The non-transitory computer readable medium of claim 1 , wherein the first set of user interaction data comprises a second amount of time that has passed between receiving second data in a second form field and receiving the user input in relation to the first data entry field.

11 . The non-transitory computer readable medium of claim 1 , wherein determining that the first amount of time the user has spent interacting with the first data entry field exceeds the first threshold time duration comprises determining a particular amount of time that the first data entry field has been selected for receiving user input.

12 . The non-transitory computer readable medium of claim 1 , wherein the first set of recommendation enablement criteria further comprise at least one of:

an authorization level of the user; and

a position of the user in a company.

13 . The non-transitory computer readable medium of claim 1 , wherein the first set of recommendation enablement criteria include a binary value representing whether recommendations are enabled or disabled for the first data entry field among the plurality of data entry fields, and

wherein determining whether the first set of user interaction data meets the first set of recommendation enablement criteria is based at least on determining the binary value specifies recommendations are enabled for the first data entry field.

14 . A method, comprising:

displaying, in a Graphical User Interface (GUI), a plurality of data entry fields associated with a first data object resource, wherein the plurality of data entry fields are displayed in a data entry mode that allows a user to submit values in relation to the plurality of data entry fields;

subsequent to displaying the plurality of data entry fields in the GUI, monitoring user interaction with a first data entry field of the plurality of data entry fields to generate a first set of user interaction data indicating a first amount of time that the user has spent interacting with the first data entry field to submit user input in relation to the first data entry field;

determining that the first set of user interaction data meets a first set of recommendation enablement criteria at least by determining that the first amount of time the user has spent interacting with the first data entry field exceeds a first threshold time duration, wherein the first set of recommendation enablement criteria are stored in the first data object resource; and

responsive to determining that the first amount of time the user has spent interacting with the first data entry field exceeds the first threshold time duration:

displaying a recommended value for the first data entry field of the plurality of data entry fields,

wherein the first data object resource stores information identifying a set of records, and

wherein the recommended value is accessed from among a set of fields included in the set of records identified in the first data object resource.

15 . The method of claim 14 , further comprising:

generating a second set of user interaction data indicating a second amount of time that the user has spent interacting with a second data entry field to submit user input in relation to the second data entry field;

determining whether the second set of user interaction data meets a second set of recommendation enablement criteria at least by determining that the second amount of time the user has spent interacting with the second data entry field does not meet a second threshold time duration; and

responsive to determining that the second amount of time the user has spent interacting with the second data entry field does not meet the second threshold time duration:

refraining from displaying any recommended value for the second data entry field of the plurality of data entry fields.

16 . The method of claim 15 , further comprising:

determining the first set of recommendation enablement criteria based on a first set of metadata stored in association with the first data entry field; and

determining the second set of recommendation enablement criteria based on a second set of metadata stored in association with the second data entry field.

17 . The method of claim 14 , wherein the first set of user interaction data indicates a second amount of time that has passed since user input was received from the user,

wherein the first set of recommendation enablement criteria specifies a second threshold time duration, and

wherein determining that the first set of user interaction data meets the first set of recommendation enablement criteria comprises determining that the second amount of time that has passed exceeds the second threshold time duration.

18 . The method of claim 14 , wherein the first set of user interaction data comprises information regarding an acceptance rate and/or rejection rate associated with previously presented recommended values, and

wherein the first set of recommendation enablement criteria specifies a threshold to be compared to the acceptance rate and/or the rejection rate to determine whether to present the recommended value for the first data entry field.

19 . The method of claim 14 , further comprising:

training a machine learning model based on training data sets, a first training data set of the training data sets comprising:

a particular set of user interaction data; and

a label indicating whether recommendations are to be enabled or disabled based on the particular set of user interaction data,

wherein determining whether the first set of user interaction data meets the first set of recommendation enablement criteria comprises applying the trained machine learning model to the first set of user interaction data to determine whether to enable or disable recommendations for the first data entry field.

20 . The method of claim 14 , wherein the user interaction with the first data entry field comprises an attempt to submit a user-determined value for the first data entry field,

wherein the user interaction does not include any command to enable or disable value recommendations for the first data entry field.

21 . The method of claim 14 , further comprising:

determining the first set of recommendation enablement criteria based on a set of form-specific metadata stored in association with a form comprising the plurality of data entry fields.

22 . A system, comprising:

one or more processors; and

memory storing instructions that, when executed by the one or more processors, cause the system to perform:

displaying, in a Graphical User Interface (GUI), a plurality of data entry fields associated with a first data object resource, wherein the plurality of data entry fields are displayed in a data entry mode that allows a user to submit values in relation to the plurality of data entry fields;

subsequent to displaying the plurality of data entry fields in the GUI, monitoring user interaction with a first data entry field of the plurality of data entry fields to generate a first set of user interaction data indicating a first amount of time that the user has spent interacting with the first data entry field to submit user input in relation to the first data entry field;

determining that the first set of user interaction data meets a first set of recommendation enablement criteria at least by determining that the first amount of time the user has spent interacting with the first data entry field exceeds a first threshold time duration, wherein the first set of recommendation enablement criteria are stored in the first data object resource; and

responsive to determining that the first amount of time the user has spent interacting with the first data entry field exceeds the first threshold time duration:

displaying a recommended value for the first data entry field of the plurality of data entry fields, wherein the first data object resource stores information identifying a set of records, and

wherein the recommended value is accessed from among a set of fields included in the set of records identified in the first data object resource.