Download presentation
Presentation is loading. Please wait.
Published byErnest Audley Modified over 9 years ago
1
T.Sharon-A.Frank 1 Internet Resources Discovery (IRD) Shopping Agents
2
2 T.Sharon-A.Frank ShopBot ShopBot is a softbot that carries out comparison shopping at Web vendors on a person’s behalf. It autonomously learns to extract product information from the Web vendors. ShopBot learns how to query a store’s searchable product catalog.
3
3 T.Sharon-A.Frank Example Search Form
4
4 T.Sharon-A.Frank Shopbot Assumptions Navigation simplicity –virtual stores have simple - user-friendly interfaces. Uniformity –product lists have similar structure. Separation tenure –description fields in a list of products will be separated –every product will have a separate line.
5
5 T.Sharon-A.Frank ShopBot Implementation ShopBot consists of two major components: –Learner: Gets as input the domain description and site URL. Creates the vendor description for use by Shopper. Moderately time-consuming; works off-line. –Shopper: On-line agent, shops for requested products using vendors descriptions created by Learner.
6
6 T.Sharon-A.Frank ShopBot Learner Domain Description URLs of possible vendors ShopBot Learner Online vendors Vendor Description for each vendor search for indices for each potential index for each sample product query on attributes accumulate responses analyze
7
7 T.Sharon-A.Frank Learner Domain Description Example products: P1, P2, …, Pn Attributes of the products: manufacturer(P1) = “Digital Village”, name(P1) = “Starship Titanic”, etc… »Shopbot learner uses domain-specific heuristics.
8
8 T.Sharon-A.Frank Learner Vendor Description URL of a searchable index form. A function that maps product attributes to the form fields. Functions for extracting data from pages returned: –A function that recognizes failure pages (“product not found”). –A function that strips header and trailer from successful pages. –A function that extracts a set of product descriptions from the remaining text on a successful page.
9
9 T.Sharon-A.Frank Learner Strategy Identify an appropriate search form. –Finds all forms, discards inappropriate forms using simple heuristics. Determine how to fill in the forms. Identify product description formats: –Fills in the form with dummy product to identify failure page. –Identifies header, trailer and the body for success page. –Parse body to a number of product descriptions using domain-specific heuristics.
10
10 T.Sharon-A.Frank ShopBot Buyer Domain Description Vendor Description ShopBot Buyer Online Vendors get user request for each vendor go to index fill in form parse results sort display GUI
11
11 T.Sharon-A.Frank 3. Multiple Sources Queried Simultaneously --Amazon.com, --American Library Association... 2. Jango Server : --interprets query 1. The Client : --Submits “ that book by Bill Gates ” 4. The Client : --Queries sources --Filters results --Presents reports Client Netbot Server http://www.jango.com The Jango Architecture
12
12 T.Sharon-A.Frank Jango - Example
13
13 T.Sharon-A.Frank Jango -- example
14
14 T.Sharon-A.Frank Jango -- example
15
15 T.Sharon-A.Frank Jango Shopping Agent
16
16 T.Sharon-A.Frank Shopping Results
17
17 T.Sharon-A.Frank Another Shopping Example
18
18 T.Sharon-A.Frank Softbots - Summary 1. A meta-service that leverages existing services and collates their results. 2. It enables a human user to state what he or she wants to accomplish. 3. It attempts to disambiguate the request and to dynamically determine how and where to satisfy it. 4. It utilizes automatic planning technology to dynamically generate the results
Similar presentations
© 2024 SlidePlayer.com Inc.
All rights reserved.