Claims:We Claim:
1. A system for inferring intent of visitors to a Website comprising:
a. a visitor-tracking application executing from a digital medium coupled to a server hosting the Website; and
b. an inference engine for processing the data to infer the intent of visitors;
2. The system of claim 1 wherein the Website consists of one or more Web pages.
3. The system of claim 2 wherein the one or more Web pages include one or more blogs, news articles, or ecommerce pages.
4. The system of claim 1 wherein the visitor behavior recorded includes mouseover or clicking on a link with anchor text.
5. 5. The system of claim 1 wherein visitor behavior that includes mousing over and clicking on hypertext.
, Description:Technical Field of the Invention
The present invention is in the field of ecommerce and pertains particularly to methods and apparatus for inferring intent of Web visitors and generating leads based on the inferred intent other information about visitors and Website visits.
Background of the Invention
In the field of ecommerce, it is desired that information about visitors to ecommerce pages be made available to site owners for the purpose of leveraging information captured about the visitors to the site to increase sales revenue of the site through proactive contact with those potential customers.
It is known that servers track Website visitors by recording their browser behavior at the site especially the sequence of URLs clicked on by the visitor during site navigation. Information about each visitor to the site is collected where information is available and recorded so that owners/operators of the site may utilize the information in an attempt to reach potential new customers who have visited the site but who had not become customers of the site. Tracking cookies are one method that is used to track browser navigation and search behavior of online visitors to determine what the visitors are interested in.
In many cases custom advertisements in the form of banner ads and other types of advertising are pushed to visitor's Internet appliances where the visitors exhibited some definitive pattern in Web navigation and/or some pattern in searching the Internet. An advertiser seeks to deliver advertising that might be relevant to what the visitor may be interested in at the time. Gathering data about online activity of persons is often used in addition to profile data, survey data, etc. to attempt to determine what interest patterns exist for the user and therefore what products and services that user might be interested in.
Much of this kind of visitor monitoring and data gathering is semi-automated at best and much manual work is required in order to determine interests of a user to any degree of authenticity. Moreover, much visitor behavior online may not be simpatico to visitor behaviors offline such as store purchase histories, hobbies, work patterns, spending patterns, and general demographics. Another challenge is categorizing visitors into one or more groups having the same general product or service interest that would serve as a potential marketing base for a proactive campaign to offer products or services to those visitors. Therefore, what is clearly needed is a system for monitoring and recording visitor behavior and for inferring intent of visitors to a Web interactive or Website in a manner that correlates the inference data with other data gathered using more traditional techniques that would result in better granularity of visitor intent at the site and in general would provide more robust information for group categorization and generation of better qualified leads.
Object of the Invention
The object of the present invention is a system for inferring intent of visitors to a Website is provided, comprising a visitor-tracking application executing from a digital medium coupled to a server hosting the Website,
Summary of The Invention
The server connected to a repository adapted to store data about visitor behavior, and an inference engine for processing the data to infer the intent of visitors. In this system visitor behavior relative to links is tracked, and intent of a visitor is inferred from one or both, or a combination of analysis of the behavior and deducing meaning for anchor text of links selected.
In one embodiment the Website consists of one or more Web pages. Also, in one embodiment the one or more Web pages include one or more blogs, news articles, or ecommerce pages. The visitor behavior recorded may include mouseover or clicking on a link with anchor text. The visitor behavior tracked may also mousing over and clicking on hypertext wherein such recorded behavior and time associated therewith is used to fine tune the level of visitor intent.
In some embodiments there may be one or more application program interfaces (APIs) to one or more third-party data-gathering and holding services and wherein such data if discovered is used to fine tune level of intent of the visitor and to identify the visitor without ambiguity. Also, in some embodiments one or more of the anchor text instances may point to a multimedia presentation, an interactive form, or a data download or upload interface.
In some embodiments the system may include a data mining application for navigating to external data sources and acquiring data from those external data sources and wherein that data, if discovered, is used to fine tune the level of visitor intent and to identify the visitor without ambiguity. In some cases, the data miner is enabled to mine data from a visitor-subscribed Website using a login token.
Visitor behavior in some cases may include acts of screen capture and or highlighting or download of text or images. The recorded behavior and the time associated therewith is used to fine tune the level of visitor intent. In some embodiments the data about one or more visitors and about visitor behavior including intent is packaged as one or more sales leads presented in a sales information capsule to potential buyers.
In another aspect of the invention a method for inferring intent of visitors to a Website includes the steps of (a) tracking visitor behavior by a visitor-tracking application executing from a digital medium coupled to a server hosting the Website, the server connected to a repository adapted to store data about visitor behavior; and (b) inferring intent of visitors from the data by an inference engine deducing meaning of anchor text of links selected by a visitor, and/or visitor behavior relative to the links. In one embodiment the Website consists of one or more Web pages. Also, in one embodiment the one or more Web pages may include one or more blogs, news articles, or ecommerce pages. Visitor behavior recorded may include mouseover or clicking on a link with anchor text, and such recorded behavior and time associated therewith is used to fine tune the level of visitor intent.
n some embodiments there may be one or more application program interfaces (APIs) to one or more third-party data-gathering and holding services and wherein such data if discovered is used to fine tune level of intent of the visitor and to identify the visitor without ambiguity. Also, in some embodiments one or more of the anchor text instances may point to a multimedia presentation, an interactive form, or a data download or upload interface.
In some embodiments there may be a data mining application for navigating to external data sources and acquiring data from those external data sources and wherein that data, if discovered, is used to fine tune the level of visitor intent and to identify the visitor without ambiguity. The data miner may be enabled to mine data from a visitor-subscribed Website using a login token.
In various embodiments visitor behavior include acts of screen capture and or highlighting or download of text or images and wherein that recorded behavior and the time associated therewith is used to fine tune the level of visitor intent. Further, the data about one or more visitors and about visitor behavior including intent is packaged as one or more sales leads presented in a sales information capsule to potential buyers.
Brief Description of Drawings
FIG. 1 is a process flow chart illustrating steps for generating leads and packaging the leads into one or more lead capsules according to an embodiment of the present invention.
Detailed Description of Invention
The inventors provide in one embodiment a system for inferring the intent of online visitors and for automatically generating leads based on the inferences wherein such leads may be categorized by similar intent into groups or clusters and wherein such leads may be packaged interactively for sale to organizations willing to purchase them for proactive engagement purposes. The system and methods of the present invention are described in enabling detail using the following examples, which may describe more than one embodiment of the invention.
FIG. 1 is a process flow chart illustrating steps for generating leads and packaging the leads into one or more lead capsules according to an embodiment of the present invention. Steps illustrate a process that may be an extension of the process; At step 1 the raw data sets and data found during look up operations if performed is sent to an inference engine analogous to the inference engine to determine intent of each visitor. At step 2 the inference engine processes each data to infer intent of the visitors. This step is performed after monitoring and data capture tasks are completed for the visitors. In one aspect the inference engine may be enabled to determine if visitor data sets input into the engine are those of new and fresh visitors or customers who have come back to the Website after already being processed as a lead. At step 3 the system decides of whether there are any new visitors to the site. If there were no new or fresh visitors detected in step 3, the system may update a lead database (LDB) at step 4 with any new data discovered about the existing leads. Such data may affect the intent classification or intent level of a lead, the cluster assignment for the lead or other attributes of the lead such as pricing for the lead. If at step 3 there are fresh visitors detected, the lead generator generates new leads from those visitor data sets at step 5. At step 6 these new leads may be correlated with one another to form one or more new lead clusters at step 7 based on shared attributes of the generated leads. In one aspect the new leads are added to existing lead clusters based on similar attributes rather than forming many new lead clusters. Having too many narrowly defined lead clusters is not desirable. Forming a few lead clusters that remain relevant to the proactive designs of a buyer enterprise is more desirable.