Automatic hyperlinking of documents
US-2020410157-A1 · Dec 31, 2020 · US
US11734374B2 · US · B2
| Field | Value |
|---|---|
| Publication number | US-11734374-B2 |
| Application number | US-202117163490-A |
| Country | US |
| Kind code | B2 |
| Filing date | Jan 31, 2021 |
| Priority date | Jan 31, 2021 |
| Publication date | Aug 22, 2023 |
| Grant date | Aug 22, 2023 |
A practical reading order for non-experts. Skip the full description unless you need deep technical detail.
What the patent document calls the invention.
A short plain-language summary of the technical disclosure.
Who owns or filed the patent and who is credited as inventor.
Filing, priority, publication, and grant dates set the timeline.
The legal scope of protection — read this for what is actually claimed.
Technology tags used to group this patent with similar filings.
Prior art links and similar publications in this corpus.
Official abstract text for this publication.
Systems and methods including one or more processors and one or more non-transitory storage devices storing computing instructions configured to run on the one or more processors and perform: determining one or more similarity scores between at least two of: a first item in a hierarchical categorization containing items; a category in the hierarchical categorization; or a topic; filtering out at least one potential match from one or more potential matches using the one or more similarity scores; ranking the one or more potential matches, as filtered, using the one or more similarity scores; re-ranking the one or more potential matches, as filtered, using additional data about at least one of: the first item in the hierarchical categorization containing the items; the category in the hierarchical categorization; or the topic; and inserting one or more hyperlinks into an anchor webpage, the one or more hyperlinks configured to navigate a user from an anchor webpage to one or more potential match webpages associated with the one or more potential matches, as filtered and re-ranked. Other embodiments are disclosed herein.
Opening claim text (preview).
What is claimed is: 1. A system comprising: one or more processors; and one or more non-transitory computer-readable storage devices storing computing instructions, when executed on the one or more processors, cause the one or more processors to perform functions comprising: determining one or more similarity scores between at least two or more items, wherein: a similarity score pair comprises an anchor item and one or more respective potential matches, in at least one of: a first item in a hierarchical categorization containing items, wherein the hierarchical categorization comprises levels of item taxonomies, wherein the levels of the item taxonomies are configured to classify the items based on respective properties of each item of the items, and wherein deeper levels of an item taxonomy go deeper into respective sub-categories of each category in the item taxonomy; or a keyword; and determining the one or more similarity scores comprises: determining, using a piecewise function, a page number similarity score between each item and one or more of its respective sub-categories of the respective sub-categories in the item taxonomy; filtering out, by a number of co-views between the anchor item and each one of the one or more respective potential matches, at least one potential match from the one or more respective potential matches using the one or more similarity scores, and removing each of the one or more respective potential matches that do not exceed a threshold number of co-views, wherein a co-view comprises pairs of items viewed in a browsing session on a website; ranking the one or more respective potential matches, as filtered and removed, using the one or more similarity scores; re-ranking the one or more respective potential matches, as filtered and removed, using additional data comprising search engine optimization data; and inserting one or more hyperlinks into an anchor webpage, the one or more hyperlinks configured to navigate a user from the anchor webpage to one or more potential match webpages associated with the one or more respective potential matches, as filtered and removed and re-ranked. 2. The system of claim 1 , wherein determining the one or more similarity scores further comprises: determining one or more cosine similarities between the at least two or more items in at least two of: the first item in the hierarchical categorization containing the items; the first item's respective sub-categories of the respective sub-categories in the hierarchical categorization; or the keyword. 3. The system of claim 1 , wherein determining the page number similarity score of between each item and its respective sub-categories of the respective sub-categories in the item taxonomy comprises: assigning a hierarchical page number similarity score to each page of a respective website comprising each item. 4. The system of claim 1 , wherein: filtering out the at least one potential match from the one or more respective potential matches comprises: removing potential matches previously linked with the anchor item. 5. The system of claim 1 , wherein the search engine optimization data comprises at least one of: the first item in the hierarchical categorization containing the items; the first item's respective sub-categories of the sub-categories in the hierarchical categorization; or the keyword. 6. The system of claim 1 , wherein the one or more computing instructions, when executed on the one or more processors, further cause the one or more processors to perform functions comprising: before re-ranking the one or more respective potential matches, using a predictive algorithm trained on natural language data to determine one or more new respective potential matches; and combining the one or more new respective potential matches with a list of the one or more respective potential matches ranked by the one or more similarity scores. 7. The system of claim 6 , wherein the predictive algorithm comprises a natural language processing algorithm. 8. The system of claim 1 , wherein the one or more hyperlinks are configured to be read by one or more web scrapers. 9. The system of claim 1 , wherein the one or more computing instructions, when executed on the one or more processors, further cause the one or more processors to perform an additional function comprising: adding one or more new respective potential matches to a list of the one or more respective potential matches ranked by the one or more similarity scores. 10. The system of claim 1 , wherein the one or more hyperlinks comprise two or more hyperlinks configured to navigate a user between the anchor webpage and the one or more potential match webpages, wherein the anchor webpage comprises: a view item page when the anchor webpage is for the anchor item; a view-browse category page when the anchor webpage is for the respective sub-categories of the anchor item; or a view topic page when the anchor webpage is for the keyword. 11. A method being implemented via execution of computing instructions configured to run on one or more processors and stored at non-transitory computer-readable media, the method comprising: determining one or more similarity scores between at least two or more items, wherein: a similarity score pair comprises an anchor item and one or more respective potential matches, in at least one of: a first item in a hierarchical categorization containing items, wherein the hierarchical categorization comprises levels of item taxonomies, wherein the levels of the item taxonomies are configured to classify the items based on respective properties of each item of the items, and wherein deeper levels of an item taxonomy go deeper into respective sub-categories of each category in the item taxonomy; or a keyword; and determining the one or more similarity scores comprises: determining, using a piecewise function, a page number similarity score between each item and one or more of its respective sub-categories of the respective sub-categories in the item taxonomy; filtering out, by a number of co-views between the anchor item and each one of the one or more respective potential matches, at least one potential match from the one or more respective potential matches using the one or more similarity scores, and removing each of the one or more respective potential matches that do not exceed a threshold number of co-views, wherein a co-view comprises pairs of items viewed in a browsing session on a web site; ranking the one or more respective potential matches, as filtered and removed, using the one or more similarity scores; re-ranking the one or more respective potential matches, as filtered and removed, using additional data comprising search engine optimization data; and inserting one or more hyperlinks into an anchor webpage, the one or more hyperlinks configured to navigate a user from the anchor webpage to one or more potential match webpages associated with the one or more respective potential matches, as filtered and removed and re-ranked. 12. The method of claim 11 , wherein determining the one or more similarity scores further comprises: determining one or more cosine similarities between the at least two or more items in at least two of: the first item in the hierarchical categorization containing the items; the first item's respective sub-categories of the respective sub-categories in the hierarchical categorization; or the keyword. 13. The method of claim 11 , wherein determining the page number similarity score of between each item and its respective sub-categories of the respective sub-categories in the it
Navigation, e.g. using categorised browsing · CPC title
Filtering based on additional data, e.g. user or group profiles · CPC title
Natural language query formulation or dialogue systems · CPC title
Details of hyperlinks; Management of linked annotations · CPC title
Processing or translation of natural language (natural language analysis G06F40/20; semantic analysis G06F40/30) · CPC title
Related publications grouped by family.
Answers are generated from the same data shown on this page.