Patent Application
20190279274
The present invention relates generally to user providing recommendations for product purchases based on previous product purchases or other behavior by a customer.
Neonics, Inc. U.S. Pat. No. 4,996,642, describes selectively recommending to a user items such as movies sampled by other users. The recommendations are weighted, based on scalar ratings of the user being close to scalar ratings of other users for some product both have reviewed.
MNI Interactive U.S. Pat. No. 5,583,763 describes a user designating his or her preferred selections as entries in a user's preference list. Entries in the user's list are compared with entries in the other users' lists. When a significant number of matches have been found between two lists, the unmatched entries of the other user's preference list are extracted. Those unmatched entries with a high correlation to the user's preference list are presented to the user as selections in which the user is likely to be interested.
Cendant Publishing U.S. Pat. No. 6,782,370 describes allowing customers to submit goods or services to be used as filter data when providing recommendations based on customer buying hi story.
Amazon.com U.S. Pat. No. 6,266,649 describes a recommendations service that recommends items to individual users based on a set of items that are known to be of interest to the user, such as a set of items previously purchased by the user. In the disclosed embodiments, the service is used to recommend products to users of a merchant's Web site. The real-time service generates the recommendations using a previously-generated (off-line) table which maps items to lists of “similar” items. The similarities reflected by the table are based on the collective interests of the community of users.
Amazon.com U.S. Pat. No. 6,912,505 describes determining relationships between products by identifying products that are frequently viewed by users within the same browsing session (e.g., products A and Bare related because a significant portion of those who viewed A also viewed B). The resulting item relatedness data is stored in a table that maps items to sets of related items. The table may be used to provide personalized product recommendations to users.
Amazon.com U.S. Pat. No. 7,113,917 is similar, relating to items actually selected (e.g., in a shopping cart).
The present invention provides the ability to make recommendations to customers based on a variety of tracked customer behaviors. In one embodiment, behavior by a customer can be tracked across a session, and across multiple sessions, including Lifetime Individual Visitor Experience Profiles (LIVE Profiles). The system can track browsing, buying and abandoning actions. By correlating these to behaviors of other customers, recommendations of affinity products can be made. For example, the following correlations can be used for recommendations: buy-to-buy (cross-session), view-to-view (same-session), view-to-buy (same-session), and abandon-to-buy (same-session) actions.
In one embodiment, a merchant is provided with a preview display. The preview display shows the actual recommendations that would be made based on the weightings applied to different correlations in an algorithm. The merchant can thus adjust the weightings, create exceptions or overrides, or take other action to get the desired results. After such adjustments, the merchant can export the results and affinity product data to the merchant's web site for actual usage.
In another embodiment, a closed-loop system is provided. The merchant is provided with a display providing real-time feedback on the performance of the recommendation algorithm. The real-time feedback shows the correlated products, and tracks the actual sales, browsing and abandoning. The merchant can thus instantly see the results of changes (different weightings, etc.) in the recommendation algorithm.
In one embodiment, the feedback is provided in real time by aggregating the monitored data by the web analytics server into aggregate groups. The aggregate data is then stored in a hierarchical structure in a RAM in the analytics server system. The data is then provided from said RAM to a client at a client computer.
In one embodiment, the recommendations can be based on different segments of users. For example, the segment of users whose behavior is used to generate the recommendations could be users of the merchants' website, users of all merchants in a particular market segment, user characteristics, users using the same search engine, vertical or horizontal market segments, etc.
The foregoing has outlined rather generally the features and technical advantages of one or more embodiments of the present invention in order that the detailed description of the present invention that follows may be better understood. Additional features and advantages of the present invention will be described hereinafter which may form the subject of the claims of the present invention.
A better understanding of the present invention can be obtained when the following detailed description is considered in conjunction with the following drawings, in which:
Overall System
Traffic to the merchant web site is monitored by web analytics server system 16. System 16 provides data over the Internet to a merchant web site monitoring computer and a merchant FTP (File Transfer Protocol) site 19.
Data on user traffic is stored in a database of database engine 20 in web analytics server system 16. A sessionizer 17 organizes the data into user sessions, as described in co-pending application Ser. No. 11/546,923, filed Oct. 11, 2006. The system also includes a web reporter 125 and a real-time analytics application 136. Merchant computer 18 includes a preview client module 22 that interacts with web reporter 125, and a real-time reporter client that interacts with real-time analytics application 136.
Weighted Algorithm
In one embodiment, analytics system 16 tracks lifetime user behavior. The same user can be tracked over multiple sessions, and also may be tracked at different merchant sites (of merchants subscribing to the web analytics system). For example, when user A browses a product, the system can determine the group of other users who browsed the same product. Other products bought by those other users can be determined, and the most common product bought (and not bought by user A) can be provided as a recommendation to user A. Alternately, the recommendation could be the next most common product bought if, for example, the most common product is already being discounted and the merchant wants to promote another product. Alternately, the most common product browsed can be recommended to user A. A variety of affiliations are possible based on different user actions. These affiliations are described in an algorithm, with different weightings applied by the merchant.
In one embodiment, four kinds of weights to specify different probabilities to inter-relate various actions performed by the customer across sessions while visiting the e-commerce website. These weights combine the most common affiliated product in buy-to-buy (BB, cross-session), view-to-view (VV, same-session), view-to-buy (VB, same-session), and abandon-to-buy (AB, same-session) actions. These weights can be interactively adjusted for providing flexibility for users to control their recommendations. Other embodiments use more scores, consisting of these 3 attributes and add-to-carts. In one example, the merchant can select the variables a, b, c and d between O and 100% to select a recommended product according to the formula: Recommendation=(a×BB)+(b×VV)+(c×VB)+(d×AB). The formula can further compare the recommendation to products already viewed or bought by a particular user, and can change to a next most common affiliated product if the user has already viewed or bought the first choice for a recommendation. Alternate formulas could be used, such as including the second or third most common affiliated product in each category (BB, VV, VB, AB).
Preview
Window 26 includes a weighting for each of the four categories. These are shown as rating from 0 to 100 in the example. The merchant can adjust these weighting, and see the effect in preview window 28. The recommendation preview window 28 shows a Target Product Name in the first column (such as a Model X laptop computer A which can be browsed by user 1) and one or more affinity products that will be recommended according to the formula and weightings chosen. Three affinity products are shown in the example of
The merchant can also exclude certain products or categories of products from being recommended by entering them in exclusion window 30. For example, the merchant may not want to recommend products that are already selling well and are the most popular, or products that are discounted or otherwise being marketed by different means. This eliminates any bias towards new products or popular products associated with events happening across the World.
In one embodiment, additional options allow customizing the number of recommendations according to e-commerce merchant needs. This can be done with an Export Settings window as shown in
In another embodiment of the invention, recommendation preview window 28 is used to show a preview of recommendations based on keywords. This can be used for words searched by the user either on the merchant's site, or on the search engine which led to the merchant's site. The recommendations can be displayed to the user on the merchant's web site. Alternately, if the merchant has an advertising arrangement with a search engine, the recommendations could be displayed along with the search results when the user enters the key words in the search engine.
An alternate view of window 26 can be provided with different keyword affinities. For example, keyword-browse, keyword-abandon, keyword-buy. Further gradations can be specified, such as whether the keyword or affinity product is on the merchant site, the search engine, or any merchant site in a category. In one embodiment, a weighting algorithm can combine both keywords and products browsed, bought, etc.
Real-Time Monitor
In one embodiment, the feedback is provided in real time by aggregating the monitored data by the web analytics server into aggregate groups. The aggregate data is then stored in a hierarchical structure in a RAM in the analytics server system. The data is then provided from said RAM to a client at a client computer.
Data is initially provided to a group of web servers, or pixel servers, 123 as a log of click stream data. Multiple collectors 126 pull the data, sort the data by session (using the session ID), and provide the data in multiple messaging queues to the sessionizers (transformers) 128. The data for the same session is sent to the same sessionizer based on a hash ID algorithm. The sessionizers organize the collected data as discussed below, then provide it in different formats and based on various business and statistical logic through a variety of different messaging systems 130 to different targets that include but are not limited to: 1-real time in-memory streaming for real time in-memory analytics; 2-real time in memory streaming through a variety of application APIs for other applications; 3-used for long term database loading or other storage media.
Any of these messaging systems 130 can pass on any number of well-defined alerts coming from any external sources to the RAM 135. RAM 135 may also directly receive an RSS feed through the internet. Thus, data from different sources including the session data from the sessionizer, the alerts or other data types from other external sources can be combined and processed, using any business logic or statistical data analysis in the RAM and made available for real time viewing to any target. Examples include, for the same client, not only web data, but call center data, bricks and mortar store data, giving a complete overview of business models defined and represented using the data.
The data in RAM 135 is provided to a variety of web services platforms 142, which are available for external vendors to pull through any APIs for export streaming. Also, the data from RAM 135 is accessed by a real time browser based application 144. Real-Time Analytics Application 136 includes RAM for storage 135 and RAM based services 137. RAM based services 137 are programs stored in the main memory of a server which controls the storing, processing, aggregating, accessing, authenticating, authorizing, etc. of data in the RAM. Such services include a de-serializing service, an aggregator service, a localizer service, a security service, a messaging service, a recovery service, and/or any other service defined on the data in RAM.
Real time reporter 144 may reside on a client computer or may be downloaded from a web analytic server, and can use Flash, Ajax, a local application or other methods for requesting and rendering reports. The data for the reports is requested from Web Analytics Server 16 across the Internet 14. Independent modules within the real time reporter program 144 will retrieve data in RAM 135 from real time analytics application 136 asynchronously using interface module 140, through different protocols (HTTPs, Flash, Ajax, etc.) for the real time interactions.
The system of
In one embodiment, the real-time monitor can be used to provide the last 7 days of data on the top 100 products of a merchant. The merchant could vary the recommendations daily, based on browsing of the top 100 products. Alternately, other numbers of products or time periods could be used. The real-time monitor will show the actual sales being made based on the recommendations soon after they occur, allowing the merchant to adjust quickly to changing conditions.
LIVE Profile Segmentation
In one embodiment, the recommendations can be based on different segments of users. For example, the segment of users whose behavior is used to generate the recommendations could be users of the merchant's website. Alternately, because the web analytics is typically provided by a third party to multiple merchants, the segment can be users of all merchants in a particular market segment. For example, if the merchant is a shoe store, the segment could be all shoe stores, all clothing stores, all women's shoe and/or clothing stores, all users in a particular geographic area, or any combination. The recommendations can also be segmented by any other information available, such as the net worth of the users, the purchase volume or average price per product bought by the users (e.g., high end users), users browsing at the same time of day or seasons, users using the same search engine, vertical or horizontal market segments, etc.
In one embodiment, behavior by a customer can be tracked across a session, and across multiple sessions, including Lifetime Individual Visitor Experience Profiles (LIVE Profiles) of Coremetrics. The system can track browsing, buying and abandoning actions for each user over the online lifetime of that user.
Search Engine Source
In one embodiment, the search engine used by customers to reach the merchant's site is tracked. This can form the basis of another segmentation, with recommendations being drawn from the group of users that came to the merchant's site using the same search engine. Additionally, based on this information, recommendations can be made to the customers by providing the recommendation before the customer even reaches the merchant's web site, by providing a recommendation upon entry of certain key words in the search engine. The merchant can accomplish this through an advertising arrangement with the search engine provider. Alternately, the recommendation can be made on the basis of the keywords used to reach the merchant site, and displayed on the merchant site.
Embodiments of the present invention thus provide a system that offers and algorithm using conditional probability to calculate the recommendations based on past history of product page views and purchases by online customers. The system is generic enough that it can be applied across any kind of retail ecommerce site. It provides an interactive mechanism to fine tune the recommendations at any time according to merchant's requirements. The system can adaptively increase the efficiency of the recommendations by tracking the effectiveness of the recommendations presented. This information can be used in the subsequent calculations of recommendations. The effectiveness can be improved using real-time feedback.
It will be understood that modifications and variations may be effected without departing from the scope of the novel concepts of the present invention. For example, other actions of users could be track and correlated or segmented, such as particular browsing actions including dwell time on a particular web page, viewing of particular news stories, amount of time spent surfing, etc. Alternately, physical characteristics can be correlated or segmented, such as those inferred from product purchases (shoe size, dress size), etc. Also, although the term “products” has been used herein, it is understood to include services, categories or groupings of products and categories or groupings of services. Additionally, the recommendations can include any sort of qualification or terms, such as a discount for buying in the next hour. Accordingly, the foregoing description is intended to be illustrative, but not limiting, of the scope of the invention which is set forth in the following claims.
The present invention may be a system, a method, and/or a computer program product at any possible technical detail level of integration. The computer program product may include a computer readable storage medium (or media) having computer readable program instructions thereon for causing a processor to carry out aspects of the present invention.
The computer readable storage medium can be a tangible device that can retain and store instructions for use by an instruction execution device. The computer readable storage medium may be, for example, but is not limited to, an electronic storage device, a magnetic storage device, an optical storage device, an electromagnetic storage device, a semiconductor storage device, or any suitable combination of the foregoing. A non-exhaustive list of more specific examples of the computer readable storage medium includes the following: a portable computer diskette, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or Flash memory), a static random access memory (SRAM), a portable compact disc read-only memory (CD-ROM), a digital versatile disk (DVD), a memory stick, a floppy disk, a mechanically encoded device such as punch-cards or raised structures in a groove having instructions recorded thereon, and any suitable combination of the foregoing. A computer readable storage medium, as used herein, is not to be construed as being transitory signals per se, such as radio waves or other freely propagating electromagnetic waves, electromagnetic waves propagating through a waveguide or other transmission media (e.g., light pulses passing through a fiber-optic cable), or electrical signals transmitted through a wire.
Computer readable program instructions described herein can be downloaded to respective computing/processing devices from a computer readable storage medium or to an external computer or external storage device via a network, for example, the Internet, a local area network, a wide area network and/or a wireless network. The network may comprise copper transmission cables, optical transmission fibers, wireless transmission, routers, firewalls, switches, gateway computers and/or edge servers. A network adapter card or network interface in each computing/processing device receives computer readable program instructions from the network and forwards the computer readable program instructions for storage in a computer readable storage medium within the respective computing/processing device.
Computer readable program instructions for carrying out operations of the present invention may be assembler instructions, instruction-set-architecture (ISA) instructions, machine instructions, machine dependent instructions, microcode, firmware instructions, state-setting data, configuration data for integrated circuitry, or either source code or object code written in any combination of one or more programming languages, including an object oriented programming language such as Smalltalk, C++, or the like, and procedural programming languages, such as the “C” programming language or similar programming languages. The computer readable program instructions may execute entirely on the user's computer, partly on the user's computer, as a stand-alone software package, partly on the user's computer and partly on a remote computer or entirely on the remote computer or server. In the latter scenario, the remote computer may be connected to the user's computer through any type of network, including a local area network (LAN) or a wide area network (WAN), or the connection may be made to an external computer (for example, through the Internet using an Internet Service Provider). In some embodiments, electronic circuitry including, for example, programmable logic circuitry, field-programmable gate arrays (FPGA), or programmable logic arrays (PLA) may execute the computer readable program instructions by utilizing state information of the computer readable program instructions to personalize the electronic circuitry, in order to perform aspects of the present invention.
Aspects of the present invention are described herein with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the invention. It will be understood that each block of the flowchart illustrations and/or block diagrams, and combinations of blocks in the flowchart illustrations and/or block diagrams, can be implemented by computer readable program instructions.
These computer readable program instructions may be provided to a processor of a computer, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions/acts specified in the flowchart and/or block diagram block or blocks. These computer readable program instructions may also be stored in a computer readable storage medium that can direct a computer, a programmable data processing apparatus, and/or other devices to function in a particular manner, such that the computer readable storage medium having instructions stored therein comprises an article of manufacture including instructions which implement aspects of the function/act specified in the flowchart and/or block diagram block or blocks.
The computer readable program instructions may also be loaded onto a computer, other programmable data processing apparatus, or other device to cause a series of operational steps to be performed on the computer, other programmable apparatus or other device to produce a computer implemented process, such that the instructions which execute on the computer, other programmable apparatus, or other device implement the functions/acts specified in the flowchart and/or block diagram block or blocks.
The flowchart and block diagrams in the Figures illustrate the architecture, functionality, and operation of possible implementations of systems, methods, and computer program products according to various embodiments of the present invention. In this regard, each block in the flowchart or block diagrams may represent a module, segment, or portion of instructions, which comprises one or more executable instructions for implementing the specified logical function(s). In some alternative implementations, the functions noted in the blocks may occur out of the order noted in the Figures. For example, two blocks shown in succession may, in fact, be accomplished as one step, executed concurrently, substantially concurrently, in a partially or wholly temporally overlapping manner, or the blocks may sometimes be executed in the reverse order, depending upon the functionality involved. It will also be noted that each block of the block diagrams and/or flowchart illustration, and combinations of blocks in the block diagrams and/or flowchart illustration, can be implemented by special purpose hardware-based systems that perform the specified functions or acts or carry out combinations of special purpose hardware and computer instructions.
| Number | Date | Country | |
|---|---|---|---|
| Parent | 12615476 | Nov 2009 | US |
| Child | 16422605 | US | |
| Parent | 11748391 | May 2007 | US |
| Child | 12615476 | US |
