# US 11,443,004 B1 · Data extraction and optimization using artificial intelligence models > Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt - Number: US 11,443,004 B1 - Document ID: US11443004B1 - Status: Granted - Kind: B1 - Application number: 16/732,916 - Filed: 2020-01-02 - Granted: 2022-09-13 - Earliest claimed: 2019-01-02 - Assignees: Foundrydc, LLC - Applicants: Foundrydc, LLC - Inventors: Ned Brody; James Manzi - Web page: https://patentgrep.com/patent/US11443004B1 ## CPC - G06F 16/951: Indexing; Web crawling techniques - G06F 16/9538: Presentation of query results - G06F 16/9566: {URL specific, e.g. using aliases, detecting broken or misspelled links} - G06F 16/958: Organisation or management of web site content, e.g. publishing, maintaining pages or automatic linking - G06N 3/0442: characterised by memory or gating, e.g. long short-term memory [LSTM] or gated recurrent units [GRU] - G06N 3/09: Supervised learning - G06N 20/00: Machine learning - G06N 3/044: Recurrent networks, e.g. Hopfield networks - G06F: ELECTRIC DIGITAL DATA PROCESSING (computer systems based on specific computational models G06N) - G06N: COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS ## Abstract Disclosed herein are embodiments of systems, methods, and products comprises a server, which identifies optimized potential suppliers based on the client's request. The request comprises search specification and preselected bidders. The server extracts a first set of keywords from the search specification and finds web pages of potential suppliers based on the first set of keywords. The server identifies the websites of the preselected bidders, extracts a second set of keywords from the websites, and finds web pages of more potential suppliers based on the second set of keywords. The server determines the web pages are associated with real suppliers by excluding non-supplier web pages. The server determines a similarity score for each potential supplier by vectorizing keywords extracted from the supplier's web pages. The server determines a risk score for each potential supplier. The server generates a GUI comprising a list of suppliers ranked based on the similarity scores. ## Claims ### Claim 1 A computer-implemented method comprising: retrieving, by a server, a set of web documents in response to a plurality of search attribute inputs; generating, by the server, a set of vectors representing n-gram values corresponding to a plurality of terms within each web document; executing, by the server, a first artificial intelligence model configured to receive the set of vectors for each web document and generate an importance score for each web document, the importance score indicating a likelihood that the web document corresponds to a supplier rather than a non-supplier; executing, by the server, a second artificial intelligence model configured to: receive a first set of vectors corresponding to a first subset of the set of web documents satisfying an importance value threshold and generate a similarity score associated with each web document within the first subset of the set of web documents, the similarity score corresponding to a similarity between the plurality of search attribute inputs and the web document; selecting, by the server, a second subset of the set of web documents satisfying a similarity score threshold; selecting, by the server, a third subset of the set of web documents satisfying a pre-determined blacklisting criteria; generating, by the server, a graphical user interface configured to present a listing of each web document within the third subset of the set of web documents; and upon receiving a selection on the graphical user interface, generating, by the server, an electronic message directed to an address associated with at least one search attribute and containing a predetermined text string. ### Claim 2 (depends on 1) The method of claim 1, further comprising: identifying, by the server, a fourth subset of web documents based on executing a whitelisting protocol on the third subset of the set of web documents. ### Claim 3 A computer-implemented method comprising: retrieving, by a server, a set of web documents in response to a plurality of search attributes input on a graphical user interface, wherein each web document within the set of web documents comprises at least one text string corresponding to at least one search attribute; extracting, by the server, a set of terms from each web document; generating, by the server, a set of vectors representing an n-gram value corresponding to a plurality of terms within the set of terms; executing, by the server, a first artificial intelligence model configured to receive the set of vectors for each web document and generate an importance score associated with each web document, the importance score indicating a likelihood that the web document corresponds to a supplier; executing, by the server, a second artificial intelligence model configured to: receive a first set of vectors corresponding to a first subset of the set of web documents satisfying an importance score threshold, and generate a similarity score associated with each web document within the first subset of the set of web documents, the similarity score corresponding to a similarity between the plurality of search attributes and the web document; executing, by the server, a blacklisting protocol configured to receive a second subset of the set of web documents that satisfy a similarity score threshold, and determine whether the second subset of the set of web documents satisfy a pre-determined blacklisting criteria; identifying, by the server, a third subset of web documents based upon a combined value from the importance score, the similarity score, and the pre-determined blacklisting criteria; generating, by the server, a second graphical user interface configured to present a listing of each web document within the third subset of the set of web documents; and upon receiving a selection on the second graphical user interface, generating, by the server, an electronic message directed to an address associated with at least one search attribute and containing a predetermined text string. ### Claim 4 (depends on 3) The method of claim 3, further comprising: identifying, by the server, a fourth subset of web documents based on executing a whitelisting protocol on the third subset of the set of web documents. ### Claim 5 (depends on 3) The method of claim 3, wherein the server retrieves the set of web documents by at least one of searching a web, querying a database, and utilizing a web search application programming interface. ### Claim 6 (depends on 3) The method of claim 3, wherein the server identifies the plurality of terms within the set of terms. ### Claim 7 (depends on 3) The method of claim 3, further comprising: displaying, by the server, the listing of each web document in the second graphical user interface based on a ranking of the similarity scores. ### Claim 8 (depends on 3) The method of claim 3, further comprising: retrieving and aggregating, by the server, internal and external information regarding each entity corresponding to each web document within the third subset of the set of web documents; and determining, by the server, a risk score for each entity based on the internal and external information by executing another artificial intelligence model. ### Claim 9 (depends on 3) The method of claim 3, further comprising: receiving, by the server, a request comprising a search specification; and extracting the plurality of search attributes from the search specification. ### Claim 10 (depends on 3) The method of claim 3, further comprising: receiving, by the server, a request comprising preselected entities; identifying, by the server, web documents of the preselected entities; and extracting, by the server, the plurality of search attributes from the web documents of the preselected entities. ### Claim 11 (depends on 3) The method of claim 3, further comprising: displaying, by the server, web documents of preselected entities followed by web documents of other entities whose web documents have similarity scores satisfying the threshold. ### Claim 12 A computer system comprising: a client device configured to display at least one graphical user interface generated by a server; and a server in communication with the client device, the server configured to: retrieve a set of web documents in response to a plurality of search attributes input on a graphical user interface displayed on the client device, wherein each web document within the set of web documents comprises at least one text string corresponding to at least one search attribute; extract a set of terms from each web document; generate a set of vectors representing an n-gram value corresponding to a plurality of terms within the set of terms; execute a first artificial intelligence model configured to receive the set of vectors for each web document and generate an importance score associated with each web document, the importance score indicating a likelihood that the web document corresponds to a supplier rather than a non-supplier; execute a second artificial intelligence model configured to receive a first set of vectors corresponding to a first subset of the set of web documents satisfying an importance score threshold, and generate a similarity score associated with each web document within the first subset of the set of web documents, the similarity score corresponding to a similarity between the plurality of search attributes and the web document; execute a blacklisting protocol configured to receive a second subset of the set of web documents that satisfy a similarity score threshold, and determine whether the second subset of the set of web documents satisfy a pre-determined blacklisting criteria; identify a third subset of web documents based upon a combined value from the importance score, the similarity score, and the pre-determined blacklisting criteria; generate a second graphical user interface configured to present a listing of each web document within the third subset of the set of web documents; and upon receiving a selection on the second graphical user interface, generate an electronic message directed to an address associated with at least one search attribute and containing a predetermined text string. ### Claim 13 (depends on 12) The computer system of claim 12, wherein the server is further configured to: identify a fourth subset of web documents based on executing a whitelisting protocol on the third subset of the set of web documents. ### Claim 14 (depends on 13) The computer system of claim 13, wherein the server is further configured to: display the listing of each web document in the second graphical user interface based on a ranking of the similarity scores. ### Claim 15 (depends on 12) The computer system of claim 12, wherein the server retrieves the set of web documents by at least one of searching a web, querying a database, and utilizing a web search application programming interface. ### Claim 16 (depends on 12) The computer system of claim 12, wherein the server identifies the plurality of terms within the set of terms. ### Claim 17 (depends on 12) The computer system of claim 12, wherein the server is further configured to: retrieve and aggregate internal and external information regarding each entity corresponding to each web document within the third subset of the set of web documents; and determine a risk score for each entity based on the internal and external information by executing another artificial intelligence model. ### Claim 18 (depends on 12) The computer system of claim 12, wherein the server is further configured to: receive a request comprising a search specification; and extract the plurality of search attributes from the search specification. ### Claim 19 (depends on 12) The computer system of claim 12, wherein the server is further configured to: receive a request comprising preselected entities; identify web documents of the preselected entities; and extract the plurality of search attributes from the web documents of the preselected entities. ### Claim 20 (depends on 12) The computer system of claim 12, wherein the server is further configured to: display web documents of preselected entities followed by web documents of other entities whose web documents have similarity scores satisfying the threshold.