# US 2021/0241235 A1 · System for scheduling account contact

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

- Number: US 2021/0241235 A1
- Document ID: US20210241235A1
- Status: Published application
- Kind: A1
- Application number: 17/164,664
- Filed: 2021-02-01
- Published: 2021-08-05
- Earliest claimed: 2020-01-31
- Assignees: Attunely Inc.
- Applicants: Attunely Inc.
- Inventors: Ryan Kosai; Adam J. Profitt; Carl Toews
- Web page: https://patentgrep.com/patent/US20210241235A1

## CPC

- G06Q 10/1093: Calendar-based scheduling for persons or groups
- G06N 7/01: Probabilistic graphical models, e.g. probabilistic networks
- G06N 20/00: Machine learning
- G06N 20/20: Ensemble learning
- H04M 3/51: Centralised call answering arrangements requiring operator intervention {, e.g. call or contact centers for telemarketing}
- H04M 2203/402: Agent or workforce management
- H04M 2203/403: Agent or workforce training
- 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
- G06N: COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- H04M: TELEPHONIC COMMUNICATION (circuits for controlling other apparatus via a telephone cable and not involving telephone switching apparatus G08)

## Abstract

Disclosed is a system to determine a first contact probability for each of a plurality of time slots for each of a plurality of first accounts using a trained machine learning model based on a first set of account information and first contact attempt logs, determine a first prioritization for each of a plurality of first accounts based on a second set of account information, and generate a contact schedule based on the first contact probability for each of the plurality of time slots and the first prioritization. The trained machine learning model is trained based on training accounts.

## Claims

### Claim 1

A system, comprising:
a memory storing computer readable instructions; and
a processor configured to execute the computer readable instructions to:
determine a first contact probability for each of a plurality of time slots for each of a plurality of first accounts based on a first set of account information and first contact attempt logs for each of the plurality of first accounts, wherein the first contact probability is determined using a trained machine learning model, wherein the trained machine learning model is trained based on training accounts;
determine a first prioritization for each of a plurality of first accounts based on a second set of account information;
generate a contact schedule based on the first contact probability for each of the plurality of time slots for each of the plurality of first accounts and the first prioritization for each of the plurality of first accounts, wherein the contact schedule includes the time slots and wherein the plurality of first accounts are each assigned to one of the time slots.

### Claim 2 (depends on 1)

The system recited in claim 1, wherein the first set of account information includes first location information and a first contact attempt log including first results for previous contact attempts for respective first accounts.

### Claim 3 (depends on 2)

The system recited in claim 2, wherein each of the training accounts includes training location information and a training contact attempt log including training results for contact attempts for respective training accounts, and further wherein the trained machine learning model is trained based on snapshots of the training results for the contact attempts and training location information.

### Claim 4 (depends on 3)

The system recited in claim 3, wherein
if a number of first results for previous contact attempts for a first account is equal to or above a threshold value, the first contact probability for the first account is determined based on the first location information and a snapshot of the results for the contact attempts, and
if the number of first results for the previous contact attempts for the first account is below the threshold value, the first contact probability for the first account is determined based on the first location information.

### Claim 5 (depends on 1)

The system recited in claim 1, wherein the second set of account information includes an account age for each of the first accounts and the first prioritization is generated based on the account age.

### Claim 6 (depends on 1)

The system recited in claim 1, wherein the first set of account information includes an account value and the first prioritization is generated based on the account value.

### Claim 7 (depends on 6)

The system recited in claim 6, wherein the second set of account information includes the first contact probability for each of a plurality of time slots and the first prioritization is generated based on the first contact probability.

### Claim 8 (depends on 1)

The system recited in claim 1, wherein the processor is further configured to execute the computer readable instructions to determine eligible time slots among the plurality of time slots for each of the plurality of first accounts.

### Claim 9 (depends on 8)

The system recited in claim 8, wherein the contact schedule is further generated based on the determined eligible time slots for each of the plurality of first accounts.

### Claim 10

A system, comprising:
a memory storing computer readable instructions; and
a processor configured to execute the computer readable instructions to perform the following:
determine a first contact probability for each of a plurality of time slots for each of a plurality of first accounts based on a first set of account information and first contact attempt logs for each of the plurality of first accounts, wherein the first contact probability is determined using a trained machine learning model, wherein the trained machine learning model is trained based on training accounts;
determine a first prioritization for each of a plurality of first accounts based on a second set of account information;
generate a contact schedule for a first time slot of the plurality of time slots based on the first contact probability for each of the plurality of time slots for each of the plurality of accounts and the first prioritization for the plurality of accounts;
update the first contact probability for the remaining time slots based on call attempts in the first time slot;
generate a contact schedule for a second time slot of the plurality of time slots based on the updated first contact probability for each remaining timeslot of the plurality of time slots for each of the plurality of accounts and the first prioritization for the plurality of accounts.

### Claim 11 (depends on 10)

The system recited in claim 10, wherein the first set of account information includes first location information and a first contact attempt log including first results for previous contact attempts for respective first accounts.

### Claim 12 (depends on 11)

The system recited in claim 11, wherein each of the training accounts includes training location information and a training contact attempt log including training results for contact attempts for respective training accounts, wherein the trained machine learning model is trained based on snapshots of the training results for the contact attempts and training location information.

### Claim 13 (depends on 12)

The system recited in claim 12, wherein
if a number of first results for previous contact attempts for a first account is equal to or above a threshold value, the first contact probability for the first account is determined based on the first location information and a snapshot of the results for the contact attempts, and
if the number of first results for the previous contact attempts for the first account is below the threshold value, the first contact probability for the first account is determined based on the first location information.

### Claim 14 (depends on 10)

The system recited in claim 10, wherein the second set of account information includes an account age for each of the first accounts and the first prioritization is generated based on the account age.

### Claim 15 (depends on 10)

The system recited in claim 10, wherein the first set of account information includes an account value and the first prioritization is generated based on the account value.

### Claim 16 (depends on 15)

The system recited in claim 15, wherein the second set of account information includes the first contact probability for each of a plurality of time slots and the first prioritization is generated based on the first contact probability.

### Claim 17 (depends on 10)

The system recited in claim 10, wherein the processor is further configured to execute the computer readable instructions to determine eligible time slots among the plurality of time slots for each of the plurality of first accounts.

### Claim 18 (depends on 17)

The system recited in claim 17, wherein the contact schedule is further generated based on the determined eligible time slots for each of the plurality of first accounts.