Database query generation and automated sequencing of query results

Patent metadata

Field	Value
Publication number	US-12579134-B2
Application number	US-202318101935-A
Country	US
Kind code	B2
Filing date	Jan 26, 2023
Priority date	Jan 26, 2022
Publication date	Mar 17, 2026
Grant date	Mar 17, 2026

Abstract

A system includes memory hardware configured to store instructions and processor hardware configured to execute the instructions. The instructions include generating an interactive graphical user interface including a first user interface element. The instructions include, in response to a user entering a text string into the first user interface element: generating a second user interface element, generating predictive elements based on the text string, and populating the second user interface element with the predictive elements. The instructions include, in response to the user selecting one of the predictive elements: adding the predictive element to a fourth user interface element, querying a database based on the predictive element, and populating a fifth user interface element with results of the query.

First claim

The invention claimed is:

1 . A system comprising:
memory hardware configured to store instructions, and processor hardware configured to execute the instructions, wherein the instructions include:
generating an interactive graphical user interface including a first user interface element,
in response to receiving a first text string at the first user interface element, automatically generating a second user interface element,
generating a set of attributes associated with the first text string,
generating a first set of predictive filters based on the generated set of attributes,
populating the second user interface element with the first set of predictive filters,
in response to a selection of a first predictive filter of the first set of predictive filters, automatically adding the first predictive filter to a third user interface element,
generating a second set of attributes associated with a second text string different than the first input string and input at the third user interface element,
generating a second set of predictive filters based on the second set of attributes and the first predictive filter, and
in response to a selection of a second predictive filter of the second set of predictive filters:
querying a database based on the first predictive filter and the second predictive filter, and
populating a fifth user interface element with results of the query.

2 . The system of claim 1 wherein the first text string is converted to an input vector and passed to a trained machine learning model to generate the first set of predictive filters.

3 . The system of claim 2 wherein the trained machine learning model includes a trained neural network.

4 . The system of claim 3 wherein the trained neural network includes:
an input layer having a plurality of nodes;
one or more hidden layers having a plurality of nodes; and
an output layer having a plurality of nodes.

5 . The system of claim 4 wherein:
each node of the input layer is connected to at least one node of the one or more hidden layers;
each node of the input layer represents a numerical value; and
the at least one node of the one or more hidden layers receives the numerical value multiplied by a weight as an input.

6 . The system of claim 5 wherein the at least one node of the one or more hidden layers receives the numerical value multiplied by the weight and offset by a bias as the input.

7 . The system of claim 6 wherein the at least one node of the one or more hidden layers is configured to:
sum inputs received from nodes of the input layer;
provide the summed inputs to an activation function; and
provide an output of the activation function to one or more nodes of a next layer.

8 . The system of claim 7 wherein the first set of predictive filters includes at least one of:
a first data structure associated with one or more medications;
a second data structure associated with one or more laboratory tests; and
a third data structure associated with one or more medical conditions.

9 . The system of claim 8 wherein the fifth user interface element displays the results of the query in an interactive table.

10 . A computer-implemented method comprising:
generating an interactive graphical user interface including a first user interface element, in response to receiving a first text string into the first user interface element, automatically generating a second user interface element, generating a set of attributes associated with the first text string, generating a first set of predictive filters corresponding to the set of attributes, populating the second user interface element with the first set of predictive filters, in response to a selection of a first predictive filter of the first set of predictive filters, automatically adding the first predictive filter to a third user interface element, generating a second set of attributes associated with a second text string different than the first input string and input at the third user interface, generating a second set of predictive filters based on the second set of attributes and the first predictive filter, and in response to a selection of a second predictive filter of the second set of predictive filters:
querying a database based on the first predictive filter and the second predictive filter, and
populating a fifth user interface element with results of the query.

11 . The computer-implemented method of claim 10 wherein the first text string is converted to an input vector and passed to a trained machine learning model to generate the first set of predictive filters.

12 . The computer-implemented method of claim 11 wherein the trained machine learning model includes a trained neural network.

13 . The computer-implemented method of claim 12 wherein the trained neural network includes:
an input layer having a plurality of nodes;
one or more hidden layers having a plurality of nodes; and
an output layer having a plurality of nodes.

14 . The computer-implemented method of claim 13 wherein:
each node of the input layer is connected to at least one node of the one or more hidden layers;
each node of the input layer represents a numerical value; and
the at least one node of the one or more hidden layers receives the numerical value multiplied by a weight as an input.

15 . The computer-implemented method of claim 14 wherein the at least one node of the one or more hidden layers receives the numerical value multiplied by the weight and offset by a bias as the input.

16 . The computer-implemented method of claim 15 wherein the at least one node of the one or more hidden layers is configured to:
sum inputs received from nodes of the input layer;
provide the summed inputs to an activation function; and
provide an output of the activation function to one or more nodes of a next layer.

17 . The computer-implemented method of claim 16 wherein the first set of predictive filters includes at least one of:
a first data structure associated with one or more medications;
a second data structure associated with one or more laboratory tests; and
a third data structure associated with one or more medical conditions.

18 . A computerized method comprising:
in response to receiving a first text string, presenting a first plurality of data filters to a user in a graphical user interface based on the first text string; in response to a selection of a first data filter of the first plurality of data filters, presenting a plurality of value choices to the user in the graphical user interface; in response to a selection of a first value choice of the plurality of value choices, performing a first query on a database, wherein the first query is based on the first value choice; based on results of the first query and a second text string different than the first input string and input at the third user interface, determining a second plurality of data filter elements; presenting the second plurality of data filter elements to the user in the graphical user interface; in response to a selection of values for multiple data filter elements of the first plurality of data filter elements and the second plurality of data filter elements, presenting a graphical representation of a subset of records from the database, wherein the subset of records is determined by the selected values for the multiple data filter elements; and in response to receiving a request, queuing a set of channel-specific communications for the subset of records.

Assignees

• Evernorth Strategic Dev Inc

Inventors

• Wong Mark D

Classifications

• G06N3/04

  Architecture, e.g. interconnection topology · CPC title

• G06F9/451

  Execution arrangements for user interfaces · CPC title

• G06F16/248

  Presentation of query results · CPC title

• G06N3/063

  using electronic means · CPC title

• G06F16/2425 Primary

  Iterative querying; Query formulation based on the results of a preceding query · CPC title