US-12626053-B2 - System, method, and computer program for user input fields auto-completion using machine learning model selection with dynamic threshold mechanism

Abstract

As described herein, a system, method, and computer program are provided for using a dynamic threshold mechanism that is utilizing a set of machine learning models to auto-complete user input fields. User access to a form having a plurality of user input fields is detected. One or more of the plurality of user input fields are auto-completed over a sequence of stages, utilizing at least one machine learning model.

Inventors

• Lior Turgeman
• Ravit Fireberger
• Taima Abu Saleh

Assignees

• AMDOCS DEVELOPMENT LIMITED

Dates

Publication Date

20260512

Application Date

20240122

Claims (19)

1. 1 . A non-transitory computer-readable media storing computer instructions which when executed by one or more processors of a device cause the device to: detect user access to a form having a plurality of user input fields; and auto-complete one or more of the plurality of user input fields over a sequence of stages, utilizing at least one machine learning model, wherein a classification threshold used by the at least one machine learning model for each stage in the sequence of stages is adjusted as a function of a current stage in the sequence of stages and F1 scores computed from prior stages in the sequence of stages.
2. 2 . The non-transitory computer-readable media of claim 1 , wherein the device is further caused to: detect at least one initial user input to at least one user input field of the plurality of user input fields.
3. 3 . The non-transitory computer-readable media of claim 2 , wherein the auto-completing is initiated based on the at least one initial user input to the at least one user input field.
4. 4 . The non-transitory computer-readable media of claim 1 , wherein auto-completing one or more of the plurality of user input fields includes presenting an input suggestion in each of the one or more of the plurality of user input fields.
5. 5 . The non-transitory computer-readable media of claim 4 , wherein the input suggestion is capable of being accepted or rejected by a user.
6. 6 . The non-transitory computer-readable media of claim 5 , wherein acceptance or rejection of the input suggestion affects the auto-completing in at least one subsequent stage in the sequence of stages.
7. 7 . The non-transitory computer-readable media of claim 5 , wherein rejection of the input suggestion presented in a user input field of the plurality of user input fields includes user entry of a new input to the user input field.
8. 8 . The non-transitory computer-readable media of claim 7 , wherein user entry of the new input to the user input field causes the at least one machine learning model to be updated.
9. 9 . The non-transitory computer-readable media of claim 8 , wherein the at least one machine learning model is updated by revising a hierarchy of user input field dependencies.
10. 10 . The non-transitory computer-readable media of claim 1 , wherein auto-completing one or more of the plurality of user input fields over a sequence of stages, utilizing the at least one machine learning model, includes for each stage in the sequence of stages: processing existing input in the plurality of user input fields, utilizing the at least one machine learning model, to predict additional input for at least one empty user input field of the plurality of user input fields, auto-completing the at least one empty user input field with the additional input.
11. 11 . The non-transitory computer-readable media of claim 1 , wherein a weight of precision is increased for each subsequent stage in the sequence of stages to increasingly prioritize precision over recall across the sequence of stages.
12. 12 . The non-transitory computer-readable media of claim 1 , wherein the auto-completing is performed utilizing a plurality of machine learning models.
13. 13 . The non-transitory computer-readable media of claim 12 , wherein for each dependent user input field, the plurality of machine learning models are trained using different combinations of independent fields.
14. 14 . The non-transitory computer-readable media of claim 1 , wherein the at least one machine learning model is trained on labeled historical data using supervised learning.
15. 15 . The non-transitory computer-readable media of claim 1 , wherein at least one accuracy metric is calculated for the at least one machine learning model on a validation set.
16. 16 . The non-transitory computer-readable media of claim 15 , wherein the at least one accuracy metric includes one or more of precision, recall, or F1 scores.
17. 17 . The non-transitory computer-readable media of claim 15 , wherein an optimal machine learning model of the at least one machine learning model is selected for each combination of user input fields, based on the at least one accuracy metric, and wherein the optimal machine learning model is utilized for auto-completion involving the associated combination of user input fields.
18. 18 . A method, comprising: at a computer system: detecting user access to a form having a plurality of user input fields; and auto-completing one or more of the plurality of user input fields over a sequence of stages, utilizing at least one machine learning model, wherein a classification threshold used by the at least one machine learning model for each stage in the sequence of stages is adjusted as a function of a current stage in the sequence of stages and F1 scores computed from prior stages in the sequence of stages.
19. 19 . A system, comprising: a non-transitory memory storing instructions; and one or more processors in communication with the non-transitory memory that execute the instructions to: detect user access to a form having a plurality of user input fields; and auto-complete one or more of the plurality of user input fields over a sequence of stages, utilizing at least one machine learning model, wherein a classification threshold used by the at least one machine learning model for each stage in the sequence of stages is adjusted as a function of a current stage in the sequence of stages and F1 scores computed from prior stages in the sequence of stages.

Description

FIELD OF THE INVENTION The present invention relates to auto-complete processes for user input fields. BACKGROUND Data entry is a tedious task that requires a considerable amount of time and effort. The traditional approach to data entry involves manual data entry into a system, which is time-consuming and prone to errors. Automating data entry can greatly improve efficiency and reduce errors. One way to achieve this is by developing a system that can autocomplete fields as the user fills in a form. Autocomplete systems are common in many applications such as search engines, address books, and email systems. These systems are designed to save time and improve user experience by suggesting the most likely completions for the user's input. In the context of data entry, an autocomplete system can help users fill out a form more quickly and accurately by suggesting the most likely values for each field. There are several challenges in developing an autocomplete system for data entry. One challenge is determining the relationships between the fields in the form. For example, if the user enters a value in one field, how likely is it that the user will enter a particular value in another field? Another challenge is ensuring the accuracy of the suggested completions. The system must be able to accurately predict the most likely values for each field based on the user's input. There is thus a need for addressing these and/or other issues associated with the prior art. For example, there is a need to use machine learning to auto-complete user input fields. SUMMARY As described herein, a system, method, and computer program are provided for using a dynamic threshold mechanism that is utilizing a set of machine learning models to auto-complete user input fields. User access to a form having a plurality of user input fields is detected. One or more of the plurality of user input fields are auto-completed over a sequence of stages, utilizing at least one machine learning model. BRIEF DESCRIPTION OF THE DRAWINGS FIG. 1 illustrates a method for using machine learning to auto-complete user input fields, in accordance with one embodiment. FIG. 2 illustrates a method for training a machine learning model to auto-complete user input fields, in accordance with one embodiment. FIG. 3 illustrates a method for training a plurality of machine learning models to auto-complete user input fields, in accordance with one embodiment. FIG. 4 illustrates a method for auto-completing a plurality of user input fields over a sequence of stages, utilizing at least one machine learning model, in accordance with one embodiment. FIG. 5 illustrates a method for dynamically updating a classification threshold used by a machine learning model to auto-complete user input fields, in accordance with one embodiment. FIG. 6 illustrates a method for updating a machine learning model used to auto-complete user input fields, in accordance with one embodiment. FIG. 7 illustrates a network architecture, in accordance with one possible embodiment. FIG. 8 illustrates an exemplary system, in accordance with one embodiment. DETAILED DESCRIPTION FIG. 1 illustrates a method 100 for using machine learning to auto-complete user input fields, in accordance with one embodiment. The method 100 may be carried out by a computer system, such as that described below with respect to FIGS. 7 and/or 8. In operation 102, user access to a form having a plurality of user input fields is detected. The form refers to any user interface having a plurality of user input fields in which a user can enter input (e.g. values, text, etc.). In an embodiment, the form may be a web-based user interface. As mentioned, the form has a plurality of user input fields. The user input fields may be text boxes, drop-down menus, or any other types of input fields in which a user can enter input. The form may be a user interface to an application or service. In an embodiment, the form may be a user interface to a service request system. For example, the form may be used by a user to request a service. The user access to the form that is detected may include a user opening the form in a web browser, for example. In an embodiment, at least one initial user input to at least one of the user input fields may also be detected. For example, the initial user input may be detected for the purpose of initiating an auto-completion for one or more other user input fields of the form, as described below. In operation 104, one or more of the plurality of user input fields are auto-completed over a sequence of stages, utilizing at least one machine learning model. The machine learning model refers to a model that has been trained using machine learning to predict input for user input fields. Auto-completion refers to automatically providing input to user input fields. As mentioned, the auto-completing may be initiated based on at least one initial user input to at least one of the user input fields. In an embodimen