# US 2022/0044115 A1 · Systems and methods for managing interaction invitations

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

- Number: US 2022/0044115 A1
- Document ID: US20220044115A1
- Status: Published application
- Kind: A1
- Application number: 17/351,336
- Filed: 2021-06-18
- Published: 2022-02-10
- Earliest claimed: 2019-08-14
- Assignees: Liveperson, Inc.
- Applicants: Liveperson, Inc.
- Inventors: Vadim Milman; Itamar Keller; Shachar Hendel; Tomer Ben-David; Amihay Zer-Kavod; Yariv Lukach; Leor Gruendlinger; Ofer Ron; Shlomo Lahav
- Web page: https://patentgrep.com/patent/US20220044115A1

## CPC

- G06N 3/08: Learning methods
- H04M 3/5158: {in combination with automated outdialling systems (devices for signalling identity of wanted subscriber H04M1/26)}
- G06N 3/045: Combinations of networks
- G06N 3/0464: Convolutional networks [CNN, ConvNet]
- G06N 3/09: Supervised learning
- G06Q 30/016: After-sales
- H04L 51/02: using automatic reactions or user delegation, e.g. automatic replies or chatbot-generated messages
- H04L 51/216: Handling conversation history, e.g. grouping of messages in sessions or threads
- G06N 3/044: Recurrent networks, e.g. Hopfield networks
- G06N 7/01: Probabilistic graphical models, e.g. probabilistic networks
- G06N 20/10: using kernel methods, e.g. support vector machines [SVM]
- H04M 2203/551: Call history
- H04M 2203/556: Statistical analysis and interpretation
- 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)
- 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
- H04L: TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION (arrangements common to telegraphic and telephonic communication H04M)

## Abstract

The present disclosure relates generally to facilitating routing of communications. One example includes a communication server determining capacities associated with a terminal devices based on workloads for agents associated with the terminal devices. Historical acceptance data is accessed for past interaction invitations to user devices associated with one or more criteria. Current data is then used to determine available interactions and to facilitate interactions using interaction invitations based on the historical data and the current number of available interactions.

## Claims

### Claim 1

(canceled)

### Claim 2

A computer-implemented method comprising:
determining capacities associated with a plurality of terminal devices, wherein the capacities are based on workloads for agents associated with the plurality of terminal devices;
accessing current data for current user devices which are currently active in a network to determine a current number of available interactions, wherein the current data includes associations between the current user devices and one or more criteria associated with an acceptance rate;
modeling the acceptance rate based on a historical rejection rate, the one or more criteria, and expected delays in response times;
dynamically determining that the current number of available interactions is less than a number of the current user devices;
selecting a subset of the current user devices based on modeling of the acceptance rate; and
transmitting interaction requests to the subset of the current user devices.

### Claim 3 (depends on 2)

The computer-implemented method of claim 2, further comprising transmitting additional interaction requests to additional devices of the current user devices not selected in the subset of the current user devices as one or more of the subset of the current user devices fails to respond to an associated interaction request within a delay time threshold.

### Claim 4 (depends on 2)

The computer-implemented method of claim 2, further comprising:
determining that one or more of the interaction requests are associated with corresponding delays larger than a delay threshold;
generating updated current data for an updated set of user devices;
selecting a subset of the updated set of user devices, wherein the subset of the updated set of user devices includes one or more of the current user devices not included in the subset of the current user devices; and
transmitting second interaction requests to the subset of the updated set of user devices.

### Claim 5 (depends on 2)

The computer-implemented method of claim 2, further comprising:
determining that one or more of the interaction requests are associated with corresponding delays larger than a delay threshold;
determining updated capacities for the plurality of terminal devices;
generating updated current data for an updated set of user devices; and
modelling an updated acceptance rate based on the one or more of the interaction requests associated with the corresponding delays larger than the delay threshold.

### Claim 6 (depends on 2)

The computer-implemented method of claim 2, wherein determining the current number of available interactions includes:
providing the capacities for the agents and the current data for the current user devices to a machine learning system trained using historical acceptance data including the one or more criteria; and
receiving a value for the current number of available interactions from the machine learning system.

### Claim 7 (depends on 2)

The computer-implemented method of claim 2, wherein the current data includes real-time data gathered via the network for the current user devices in the network available to receive a targeted interaction invitation.

### Claim 8 (depends on 2)

The computer-implemented method of claim 2, wherein determining the current number of available interactions comprises:
providing the capacities for the agents and the current data for the current user devices to a machine learning system trained using historical acceptance data including the one or more criteria, wherein the machine learning system includes a first neural network trained to determine a value for the current number of available interactions using the historical acceptance data and a second neural network trained to determine a likelihood of acceptance for each device of the current user devices using the historical acceptance data.

### Claim 9

A device comprising:
a memory; and
one or more processors coupled to the memory, the one or more processors configured to perform operations comprising:
determining capacities associated with a plurality of terminal devices, wherein the capacities are based on workloads for agents associated with the plurality of terminal devices;
accessing current data for current user devices which are currently active in a network to determine a current number of available interactions, wherein the current data includes associations between the current user devices and one or more criteria associated with an acceptance rate;
modeling the acceptance rate based on a historical rejection rate, the one or more criteria, and expected delays in response times;
dynamically determining that the current number of available interactions is less than a number of the current user devices;
selecting a subset of the current user devices based on modeling of the acceptance rate; and
transmitting interaction requests to the subset of the current user devices.

### Claim 10 (depends on 9)

The device of claim 9, wherein the one or more processors are further configured to perform operations comprising transmitting additional interaction requests to additional devices of the current user devices not selected in the subset of the current user devices as one or more of the subset of the current user devices fails to respond to an associated interaction request within a delay time threshold.

### Claim 11 (depends on 9)

The device of claim 9, wherein the one or more processors are further configured to perform operations comprising:
determining that one or more of the interaction requests are associated with corresponding delays larger than a delay threshold;
generating updated current data for an updated set of user devices;
selecting a subset of the updated set of user devices, wherein the subset of the updated set of user devices includes one or more of the current user devices not included in the subset of the current user devices; and
transmitting second interaction requests to the subset of the updated set of user devices.

### Claim 12 (depends on 9)

The device of claim 9, wherein the one or more processors are further configured to perform operations comprising:
determining that one or more of the interaction requests are associated with corresponding delays larger than a delay threshold;
determining updated capacities for the plurality of terminal devices;
generating updated current data for an updated set of user devices; and
modelling an updated acceptance rate based on the one or more of the interaction requests associated with the corresponding delays larger than the delay threshold.

### Claim 13 (depends on 9)

The device of claim 9, wherein determining the current number of available interactions includes:
providing the capacities for the agents and the current data for the current user devices to a machine learning system trained using historical acceptance data including the one or more criteria; and
receiving a value for the current number of available interactions from the machine learning system.

### Claim 14 (depends on 9)

The device of claim 9, wherein the current data includes real-time data gathered via the network for the current user devices in the network available to receive a targeted interaction invitation.

### Claim 15 (depends on 9)

The device of claim 9, wherein determining the current number of available interactions comprises:
providing the capacities for the agents and the current data for the current user devices to a machine learning system trained using historical acceptance data including the one or more criteria, wherein the machine learning system includes a first neural network trained to determine a value for the current number of available interactions using the historical acceptance data and a second neural network trained to determine a likelihood of acceptance for each device of the current user devices using the historical acceptance data.

### Claim 16

A non-transitory computer readable storage medium comprising instructions that, when executed by one or more processors of a device, cause the device to perform operations comprising:
determining capacities associated with a plurality of terminal devices, wherein the capacities are based on workloads for agents associated with the plurality of terminal devices;
accessing current data for current user devices which are currently active in a network to determine a current number of available interactions, wherein the current data includes associations between the current user devices and one or more criteria associated with an acceptance rate;
modeling the acceptance rate based on a historical rejection rate, the one or more criteria, and expected delays in response times;
dynamically determining that the current number of available interactions is less than a number of the current user devices;
selecting a subset of the current user devices based on modeling of the acceptance rate; and
transmitting interaction requests to the subset of the current user devices.

### Claim 17 (depends on 16)

The non-transitory computer readable storage medium of claim 16, wherein the instructions further cause the device to perform operations comprising transmitting additional interaction requests to additional devices of the current user devices not selected in the subset of the current user devices as one or more of the subset of the current user devices fails to respond to an associated interaction request within a delay time threshold.

### Claim 18 (depends on 16)

The non-transitory computer readable storage medium of claim 16, wherein the instructions further cause the device to perform operations comprising:
determining that one or more of the interaction requests are associated with corresponding delays larger than a delay threshold;
generating updated current data for an updated set of user devices;
selecting a subset of the updated set of user devices, wherein the subset of the updated set of user devices includes one or more of the current user devices not included in the subset of the current user devices; and
transmitting second interaction requests to the subset of the updated set of user devices.

### Claim 19 (depends on 16)

The non-transitory computer readable storage medium of claim 16, wherein the instructions further cause the device to perform operations comprising:
determining that one or more of the interaction requests are associated with corresponding delays larger than a delay threshold;
determining updated capacities for the plurality of terminal devices;
generating updated current data for an updated set of user devices; and
modelling an updated acceptance rate based on the one or more of the interaction requests associated with the corresponding delays larger than the delay threshold.

### Claim 20 (depends on 16)

The non-transitory computer readable storage medium of claim 16, wherein determining the current number of available interactions includes:
providing the capacities for the agents and the current data for the current user devices to a machine learning system trained using historical acceptance data including the one or more criteria; and
receiving a value for the current number of available interactions from the machine learning system.

### Claim 21 (depends on 16)

The non-transitory computer readable storage medium of claim 16, wherein the current data includes real-time data gathered via the network for the current user devices in the network available to receive a targeted interaction invitation.

### Claim 22 (depends on 16)

The non-transitory computer readable storage medium of claim 16, wherein determining the current number of available interactions comprises:
providing the capacities for the agents and the current data for the current user devices to a machine learning system trained using historical acceptance data including the one or more criteria, wherein the machine learning system includes a first neural network trained to determine a value for the current number of available interactions using the historical acceptance data and a second neural network trained to determine a likelihood of acceptance for each device of the current user devices using the historical acceptance data.
