# US 2021/0241297 A1 · Artificial Intelligence Sales Technology Stack Prospecting

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

- Number: US 2021/0241297 A1
- Document ID: US20210241297A1
- Status: Published application
- Kind: A1
- Application number: 16/780,276
- Filed: 2020-02-03
- Published: 2021-08-05
- Earliest claimed: 2020-02-03
- Assignees: Dell Products L.P.
- Applicants: Dell Products L.P.
- Inventors: Venkata Chandra Sekar Rao
- Web page: https://patentgrep.com/patent/US20210241297A1

## CPC

- G06Q 30/0204: Market segmentation
- G06N 3/044: Recurrent networks, e.g. Hopfield networks
- G06N 3/0442: characterised by memory or gating, e.g. long short-term memory [LSTM] or gated recurrent units [GRU]
- G06N 3/045: Combinations of networks
- G06N 3/09: Supervised learning
- G06N 3/08: Learning methods
- 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

## Abstract

A system, method, and computer-readable medium for performing artificial intelligence (AI) to enhance productivity and efficiency of a sales process by identifying prospective customers by a proactive approach. Stacked recurring neural networks are implemented to classify existing and prospective customers, and to learn and determine sales processes and sales pipelines. Sales patterns of existing customers are identified. Based on the sales patterns, classification is performed as to customers. Prospective customers are identified based on the sales patterns. A recommendation is made as to which prospective customers to target. Sales process and sales pipeline of prospective customers are determined to allow for proactive actions to be performed in the sales process and sales pipeline.

## Claims

### Claim 1

A computer-implementable method for sales prospecting, comprising:
identifying sales patterns of existing customers;
classifying the existing customers based on the sales patterns;
identifying prospective customers based on the classifying;
recommending prospective customers based on the identifying; and
determining sales processes and sales pipelines of recommended prospective customers.

### Claim 2 (depends on 1)

The method of claim 1, wherein a recurring neural network (RNN) performs the identifying by learning the sales patterns of existing customers.

### Claim 3 (depends on 1)

The method of claim 1, wherein a recurring neural network (RNN) performs the classification based on expected time to convert a prospective customer to an actual customer.

### Claim 4 (depends on 1)

The method of claim 1, wherein the identifying is based on sales patterns received by a recurring neural network (RNN).

### Claim 5 (depends on 1)

The method of claim 1, wherein recommending is performed by recommendation generator.

### Claim 6 (depends on 1)

The method of claim 1, wherein the recommending prioritizes prospective customers that are most likely to convert to actual customers.

### Claim 7 (depends on 1)

The method of claim 1, wherein the determining sales processes and sales pipelines is performed by a long short term memory recurring neural network (LSTM RNN).

### Claim 8

A system comprising:
a processor;
a data bus coupled to the processor; and
a non-transitory, computer-readable storage medium embodying computer program code, the non-transitory, computer-readable storage medium being coupled to the data bus, the computer program code interacting with a plurality of computer operations for improving sales prospecting executable by the processor and configured for:
identifying sales patterns of existing customers;
classifying the existing customers based on the sales patterns;
identifying prospective customers based on the classifying;
recommending prospective customers based on the identifying; and
determining sales processes and sales pipelines of recommended prospective customers.

### Claim 9 (depends on 8)

The system of claim 8, wherein a recurring neural network (RNN) performs the identifying by learning the sales patterns of existing customers.

### Claim 10 (depends on 8)

The system of claim 8, wherein a recurring neural network (RNN) performs the classification based on expected time to convert a prospective customer to an actual customer.

### Claim 11 (depends on 8)

The system of claim 8, wherein the identifying is based on sales patterns received by a recurring neural network (RNN).

### Claim 12 (depends on 8)

The system of claim 8, wherein recommending is performed by recommendation generator.

### Claim 13 (depends on 8)

The system of claim 8, wherein the recommending prioritizes prospective customers that are most likely to convert to actual customers.

### Claim 14 (depends on 8)

The system of claim 8, wherein the determining sales processes and sales pipelines is performed by a long short term memory recurring neural network (LSTM RNN).

### Claim 15

A non-transitory, computer-readable storage medium embodying computer program code, the computer program code comprising computer executable instructions configured for:
identifying sales patterns of existing customers;
classifying the existing customers based on the sales patterns;
identifying prospective customers based on the classifying;
recommending prospective customers based on the identifying; and
determining sales processes and sales pipelines of recommended prospective customers.

### Claim 16 (depends on 14)

The non-transitory, computer-readable storage medium of claim 14, wherein a recurring neural network (RNN) performs the identifying by learning the sales patterns of existing customers.

### Claim 17 (depends on 14)

The non-transitory, computer-readable storage medium of claim 14, wherein a recurring neural network (RNN) performs the classification based on expected time to convert a prospective customer to an actual customer.

### Claim 18 (depends on 14)

The non-transitory, computer-readable storage medium of claim 14, wherein the identifying is based a sales patterns received by a recurring neural network (RNN).

### Claim 19 (depends on 14)

The non-transitory, computer-readable storage medium of claim 14, wherein the recommending prioritizes prospective customers that are most likely to convert to actual customers.

### Claim 20 (depends on 14)

The non-transitory, computer-readable storage medium of claim 14, wherein the determining sales processes and sales pipelines is performed by a long short term memory recurring neural network (LSTM RNN).