# US 2019/0378149 A1 · Predictive analytics for leads generation and engagement recommendations

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

- Number: US 2019/0378149 A1
- Document ID: US20190378149A1
- Status: Published application
- Kind: A1
- Application number: 16/528,246
- Filed: 2019-07-31
- Published: 2019-12-12
- Earliest claimed: 2015-02-10
- Assignees: Everstring Innovation Technology
- Applicants: EverString Innovation Technology
- Inventors: Hua Gao; Vincent Yang; Yi Jin; Amit Rai
- Web page: https://patentgrep.com/patent/US20190378149A1

## CPC

- G06Q 30/0201: Market modelling; Market analysis; Collecting market data
- G06F 16/951: Indexing; Web crawling techniques
- G06Q 10/0637: Strategic management or analysis, e.g. setting a goal or target of an organisation; Planning actions based on goals; Analysis or evaluation of effectiveness of goals
- G06Q 30/0204: Market segmentation
- G06Q 30/0631: {Recommending goods or services}
- G06Q 30/0641: {utilising user interfaces specially adapted for shopping}
- 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
- G06F: ELECTRIC DIGITAL DATA PROCESSING (computer systems based on specific computational models G06N)

## Abstract

An automated predictive analytics system disclosed herein provides for generating sales leads with lead engagement recommendations. In one implementation, the system determines similarities between fitness, engagement, and intent characteristics of a plurality of target clients and fitness, engagement, and intent characteristics of an entity's existing clients. Subsequently, the system generates recommendations for engagement with the plurality of target clients, wherein components of the recommendations for engagement are based on determined similarities between the fitness, engagement, and intent characteristics of the plurality of target clients and the fitness, engagement, and intent characteristics of the entity's existing clients. The system presents the plurality of leads with the recommendations of engagement to using a graphical user interface (GUI) at the application layer of the system.

## Claims

### Claim 1

A computer-implemented method, wherein one or more computing devices comprising storage and a processor are programmed to perform steps comprising:
generating recommendations for engagement with the plurality of target clients, wherein components of the recommendations for engagement are based on determined similarities between (a) a fitness, engagement, and intent characteristics of a plurality of target clients and (b) a fitness, engagement, and intent characteristics of an entity's existing clients;
categorizing a plurality of web pages, hyperlinks, and link structures located over the Internet using a trained classifier that uses features from content and code on web pages;
crawling, by a computer, the plurality of web pages, hyperlinks, and link structures based on the categorization of the plurality of web pages, hyperlinks, and link structures to collect third party unstructured text information; and
generating a feature matrix for the target client and comparing one or more value of the feature matrix of the target client with one or more values of a feature matrix for the entity's existing clients to generate the recommendations of engagement.

### Claim 2 (depends on 1)

The computer-implemented method of claim 1, further comprising:
analyzing the third party unstructured text information to generate the fitness characteristics of the plurality of target clients.

### Claim 3 (depends on 2)

The computer-implemented method of claim 2, wherein crawling the plurality of web pages, hyperlinks, and link structures further comprises:
traversing a target client website to collect target client unstructured text information;
categorizing the target company website pages into one or more categories; and
analyzing the target client unstructured text information per each of the one or more categories; and
extracting target company fitness information.

### Claim 4 (depends on 3)

The computer-implemented method of claim 3, further comprising adjusting parameters of the crawling based on automated machine learning of the target client unstructured text information.

### Claim 5 (depends on 4)

The computer-implemented method of claim 4, further comprising presenting a plurality of leads with the recommendations of engagement.

### Claim 6 (depends on 5)

The computer-implemented method of claim 5, further comprising:
determining predictive values of one more feature of the features matrix;
determining a regularization function based on the feature matrix;
adjusting feature weights based on the regularization function; and
applying the adjusted regularization function to an objective function to generate a new objective function.

### Claim 7 (depends on 6)

The computer-implemented method of claim 6, further comprising optimizing the new objective function.

### Claim 8 (depends on 1)

The computer-implemented method of claim 1, further comprising traversing, using one or more application programming interfaces, a plurality of the entity's internal data sources to generate the fitness characteristics of the entity's existing clients.

### Claim 9 (depends on 8)

The computer-implemented method of claim 8, further comprising:
determining various engagement characteristics of the plurality of the entity's existing clients based on analysis of data collected by the application programming interfaces.

### Claim 10 (depends on 1)

The computer-implemented method of claim 1, wherein presenting the plurality of leads with the recommendations of engagement further comprises presenting the plurality of leads with the recommendations of engagement using a graphical user interface (GUI) at an application layer of a leads management system.

### Claim 11 (depends on 10)

The computer-implemented method of claim 10, wherein the recommendations of engagement of the target client is an observed purchasing pattern of the target client determined based on analysis of the publicly available unstructured text related to the target client.

### Claim 12 (depends on 1)

The computer-implemented method of claim 1, wherein the intent characteristic of the target client is based on a publicly available browsing behavior of one or more employees of the target client.

### Claim 13

A physical article of manufacture including one or more devices encoding computer-executable instructions for executing on a computer system a computer process, the computer process comprising:
generating recommendations for engagement with a plurality of target clients, wherein components of the recommendations for engagement are based on determined similarities between (a) a fitness, engagement, and intent characteristics of the plurality of target clients and (b) a fitness, engagement, and intent characteristics of an entity's existing clients;
generating a feature matrix for the target client and comparing one or more value of the feature matrix of the target client with one or more values of a feature matrix for the entity's existing clients to generate the recommendations of engagement;
categorizing a plurality of web pages, hyperlinks, and link structures located over the Internet using a trained classifier that uses features from content and code on web pages;
crawling, by a computer, the plurality of web pages, hyperlinks, and link structures based on the categorization of the plurality of web pages, hyperlinks, and link structures to collect third party unstructured text information.

### Claim 14 (depends on 13)

The physical article of manufacture of claim 13, wherein the computer process further comprising analyzing the third party unstructured text information to generate the fitness characteristics of the plurality of target clients.

### Claim 15 (depends on 13)

The physical article of manufacture of claim 13, wherein the computer process further comprising:
traversing a target client website to collect target client unstructured text information;
categorizing target client website pages into one or more categories; and
analyzing the target client unstructured text information per each of the one or more categories; and
extracting target client fitness information.

### Claim 16 (depends on 13)

The physical article of manufacture of claim 13, wherein the computer process further comprising adjusting parameters of the crawling based on automated machine learning of the target client unstructured text information.

### Claim 17 (depends on 13)

The physical article of manufacture of claim 13, wherein the computer process further comprising presenting the plurality of leads with the recommendations of engagement.

### Claim 18 (depends on 13)

The physical article of manufacture of claim 13, wherein the computer process further comprising:
determining predictive values of one more feature of the feature matrix;
determining a regularization function based on the feature matrix; and
adjusting feature weights based on the regularization function.

### Claim 19 (depends on 18)

The physical article of manufacture of claim 18, wherein the computer process further comprising applying the adjusted regularization function to an objective function to generate a new objective function.

### Claim 20 (depends on 18)

The physical article of manufacture of claim 18, wherein the computer process further comprising optimizing the new objective function.