# US 2022/0277355 A1 · Systems and methods for health care provider engagement

> Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt

- Number: US 2022/0277355 A1
- Document ID: US20220277355A1
- Status: Published application
- Kind: A1
- Application number: 17/568,522
- Filed: 2022-01-04
- Published: 2022-09-01
- Earliest claimed: 2019-07-08
- Assignees: Aktana, Inc.
- Applicants: Aktana, Inc.
- Inventors: Gil Blustein; Jin Huang; Marc Cohen; Wendong Zhu
- Web page: https://patentgrep.com/patent/US20220277355A1

## CPC

- G06N 20/20: Ensemble learning
- G06Q 30/0276: {Advertisement creation}
- G06N 3/084: Backpropagation, e.g. using gradient descent
- G06N 3/09: Supervised learning
- G06N 5/01: Dynamic search techniques; Heuristics; Dynamic trees; Branch-and-bound
- G06Q 30/0244: {Optimization}
- G06Q 30/0254: {based on statistics}
- G06Q 30/0255: {based on user history}
- G06Q 30/0264: {based upon schedule}
- G06Q 30/0272: Period of advertisement exposure
- G06Q 30/0631: {Recommending goods or services}
- G06N 3/044: Recurrent networks, e.g. Hopfield networks
- G06N 3/045: Combinations of networks
- G06N 20/00: Machine learning
- G06N: COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06Q: INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR

## Abstract

A health care provider (HCP) engagement engine is disclosed. The HCP engagement engine facilitates effective communication between pharmaceutical sales representatives (medical reps) and HCPs by generating, using machine learning algorithms, messages for the medical reps to send to HCPs. The recommended messages may be sent over a network and may include email messages, text messages, or online chat messages. The recommended messages may be drafted entirely by the engagement engine or may be drafted as addenda to messages already used by the medical reps. The HCP engagement engine uses historical data on actions performed by the HCPs and medical reps, as well as data collected from historical message recommendation events, in order to produce message recommendations.

## Claims

### Claim 1

A computer-implemented method for enhancing a user's engagement or action with a target customer to increase marketing effectiveness, the method comprising:
receiving customer data from one or more devices associated with the target customer, wherein the customer data comprises information pertaining to one or more actions taken by the target customer in response to at least one message sent by the user to the target customer, wherein the message is associated with marketing or sales of a pharmaceutical product;
aggregating the customer data from the one or more devices over a plurality of different time periods; and
analyzing the aggregated customer data with aid of a machine learning algorithm to determine one or more recommendations to the user for enhancing the user's engagement or action with the target customer, wherein the one or more recommendations comprise (1) temporal insights and (2) contextual insights for increasing a likelihood of the user effectively engaging or interacting with the target customer relating to the marketing or sales of the pharmaceutical product.

### Claim 2

(canceled)

### Claim 3 (depends on 1)

The method of claim 1, wherein the one or more actions taken by the target customer comprise: (a) opening the message, (b) clicking on content or a hyperlink within the message, (c) replying to the message, (d) forwarding the message to one or more other parties, (e) deleting the message, (f) archiving the message, (g) posting or sharing the message on social media or a website, or (h) inaction or lack of action taken with respect to the message.

### Claim 4

(canceled)

### Claim 5 (depends on 1)

The method of claim 1, wherein the aggregated customer data comprises time series data including timestamps associated with one or more of the following events or actions: (1) a time instant t1 at which the message is transmitted to the target customer's device(s); (2) a time instant t2 at which the message is received by the target customer's device(s); (3) a time duration t3 for which the message has yet to be opened by the target customer; (4) a time instant t4 at which the target customer opens the message; (5) a time duration t5 for which the message is being opened; (6) a time instant t6 at which the target customer clicks on content or a hyperlink within the message; (7) a time instant t7 at which the target customer closes the message; (8) a time instant t8 at which the target customer replies to the user's message; (9) a time duration t9 for which the target customer spends replying to the user's message; (10) a time instant t10 at which the target customer forwards the user's message to one or more other parties; (11) a time instant t11 at which the target customer archives the message; or (12) a time instant t12 at which the target customer deletes the message.

### Claim 6 (depends on 1)

The method of claim 1, wherein the plurality of different time periods is defined in different time intervals on the order of hours, days, weeks, or months.

### Claim 7

(canceled)

### Claim 8 (depends on 1)

The method of claim 1, wherein the temporal insights in the one or more recommendations comprise a suggested timing for the user to deliver a follow-on message to the target customer, and wherein the suggested timing comprises a specific time or timeslot on a specific day(s) of a week or month.

### Claim 9 (depends on 1)

The method of claim 1, wherein the contextual insights in the one or more recommendations comprise a suggested follow-on message for the user to deliver to the target customer, and wherein the suggested follow-on message comprises topics, subjects or keywords relating to the pharmaceutical product that are determined to be of interest or relevance to the target customer.

### Claim 10 (depends on 9)

The method of claim 9, wherein the topics, subjects or keywords are determined to be of interest or relevance to the target customer based on one or more of the following: (1) a profile of the target customer; (2) information about the target customer obtained directly or indirectly from a plurality of sources; (3) information about one or more conferences or events that the target customer has attended, is attending, or planning to attend; (4) articles written or published by the target customer; (5) talks or presentations given by the target customer; (6) online content posted by the target customer; (7) news, reviews, or articles about the target customer posted by third parties or individuals affiliated with the target customer; or (8) other pharmaceutical products that are currently being used or endorsed, or that had been previously used or endorsed by the target customer.

### Claim 11 (depends on 1)

The method of claim 1, wherein the one or more recommendations further comprise: (3) insights on modes or channels of communications for increasing the likelihood of the user effectively engaging or interacting with the target customer relating to the marketing or sales of the pharmaceutical product.

### Claim 12 (depends on 11)

The method of claim 11, wherein the modes or channels of communications comprise one or more of the following: (1) email communications; (2) mobile text messages; (3) social media websites; (4) mobile applications; (5) telephone calls; (6) in-person meetings; (7) video conferencing; (8) conferences or seminars; or (9) events conducted at the target customer's work facility.

### Claim 13 (depends on 1)

The method of claim 1, further comprising:
providing the one or more recommendations to one or more devices associated with the user; and
displaying the one or more recommendations as one or more visual graphical objects on the user's device(s).

### Claim 14 (depends on 13)

The method of claim 13, wherein the one or more visual graphical objects are configured to allow the user to perform one or more of the following actions: (1) accept the one or more recommendations; (2) reject the one or more recommendations; (3) mark the one or more recommendations with a status marker; or (4) provide feedback on the one or more recommendations.

### Claim 15

(canceled)

### Claim 16 (depends on 14)

The method of claim 14, further comprising:
receiving user data from the one or more devices associated with the user, wherein the user data comprises information pertaining to one or more actions taken by the user based on the one or more recommendations;
aggregating the user data over the plurality of different time periods; and
analyzing the aggregated user data and the aggregated customer data with aid of the machine learning algorithm to determine an effectiveness of the recommendation(s) and the user's action(s) in enhancing the user's engagement or action with the target customer.

### Claim 17 (depends on 16)

The method of claim 16, wherein the effectiveness of the one or more recommendations is provided as a score for each of the recommendation(s).

### Claim 18 (depends on 17)

The method of claim 17, further comprising:
modifying one or more subsequent recommendations to the user to improve their effectiveness, based on the scores of one or more previous recommendations to the user.

### Claim 19

(canceled)

### Claim 20

(canceled)

### Claim 21 (depends on 20)

The method of claim 20, wherein the machine learning algorithm is used to generate a decision model, wherein the decision model is used to determine the one or more recommendations, wherein the one or more recommendations are configured to maximize a likelihood of the target customer clicking or opening an existing message or a next message from the user.

### Claim 22

(canceled)

### Claim 23 (depends on 21)

The method of claim 21, wherein the decision model is based on (1) individual historical behavior of the target customer with respect to messages sent by the user and (2) aggregated historical behaviors of a population of different target customers with respect to messages sent by a plurality of different users.

### Claim 24 (depends on 1)

The method of claim 1, wherein the machine learning algorithm is selected from the group consisting of a boosted decision tree, a classification tree, a regression tree, a bagging tree, a random forest, a neural network, and a rotational forest.

### Claim 25 (depends on 21)

The method of claim 21, further comprising:
providing, to the decision model, new customer data associated with one or more new actions taken by the target customer in response to the at least one message sent by the user to the target customer; and
training the decision model by modifying the decision model to account for the relevance of the new customer data and new actions when determining the one or more recommendations for the user.

### Claim 26

A system for enhancing a user's engagement or action with a target customer to increase marketing effectiveness, the system comprising:
a server in communication with one or devices associated with the target customer; and
a memory storing instructions that, when executed by the server, cause the server to perform operations comprising:
receiving customer data from the one or more devices associated with the target customer,
wherein the customer data comprises information pertaining to one or more actions taken by the target customer in response to at least one message sent by the user to the target customer, wherein the message is associated with marketing or sales of a pharmaceutical product;
aggregating the customer data from the one or more devices over a plurality of different time periods; and
analyzing the aggregated customer data with aid of a machine learning algorithm to determine one or more recommendations to the user for enhancing the user's engagement or action with the target customer, wherein the one or more recommendations comprise (1) temporal insights and (2) contextual insights for increasing a likelihood of the user effectively engaging or interacting with the target customer relating to the marketing or sales of the pharmaceutical product.

### Claim 27

(canceled)

### Claim 28

A non-transitory computer-readable storage medium including instructions that, when executed by a server, cause the server to perform operations comprising:
receiving customer data from one or more devices associated with the target customer, wherein the customer data comprises information pertaining to one or more actions taken by the target customer in response to at least one message sent by the user to the target customer, wherein the message is associated with marketing or sales of a pharmaceutical product;
aggregating the customer data from the one or more devices over a plurality of different time periods; and
analyzing the aggregated customer data with aid of a machine learning algorithm to determine one or more recommendations to the user for enhancing the user's engagement or action with the target customer, wherein the one or more recommendations comprise (1) temporal insights and (2) contextual insights for increasing a likelihood of the user effectively engaging or interacting with the target customer relating to the marketing or sales of the pharmaceutical product.
