Patents by Inventor Michael Kraley
Michael Kraley has filed for patents to protect the following inventions. This listing includes patent applications that are pending as well as patents that have already been granted by the United States Patent and Trademark Office (USPTO).
-
Publication number: 20230336532Abstract: Systems and techniques for privacy preserving document analysis are described that derive insights pertaining to a digital document without communication of the content of the digital document. To do so, the privacy preserving document analysis techniques described herein capture visual or contextual features of the digital document and creates a stamp representation that represents these features without included the content of the digital document. The stamp representation is projected into a stamp embedding space based on a stamp encoding model generated through machine learning techniques capturing feature patterns and interaction in the stamp representations. The stamp encoding model exploits these feature interactions to define similarity of source documents based on location within the stamp embedding space. Accordingly, the techniques described herein can determine a similarity of documents without having access to the documents themselves.Type: ApplicationFiled: May 15, 2023Publication date: October 19, 2023Applicant: Adobe Inc.Inventors: Nikolaos Barmpalios, Ruchi Rajiv Deshpande, Randy Lee Swineford, Nargol Rezvani, Andrew Marc Greene, Shawn Alan Gaither, Michael Kraley
-
Patent number: 11769072Abstract: The structure of an untagged document can be derived using a predictive model that is trained in a supervised learning framework based on a corpus of tagged training documents. Analyzing the training documents results in a plurality of document part feature vectors, each of which correlates a category defining a document part (for example, “title” or “body paragraph”) with one or more feature-value pairs (for example, “font=Arial” or “alignment=centered”). Any suitable machine learning algorithm can be used to train the predictive model based on the document part feature vectors extracted from the training documents. Once the predictive model has been trained, it can receive feature-value pairs corresponding to a portion of an untagged document and make predictions with respect to the how that document part should be categorized. The predictive model can therefore generate tag metadata that defines a structure of the untagged document in an automated fashion.Type: GrantFiled: August 8, 2016Date of Patent: September 26, 2023Assignee: Adobe Inc.Inventor: Michael Kraley
-
Patent number: 11689507Abstract: Systems and techniques for privacy preserving document analysis are described that derive insights pertaining to a digital document without communication of the content of the digital document. To do so, the privacy preserving document analysis techniques described herein capture visual or contextual features of the digital document and creates a stamp representation that represents these features without included the content of the digital document. The stamp representation is projected into a stamp embedding space based on a stamp encoding model generated through machine learning techniques capturing feature patterns and interaction in the stamp representations. The stamp encoding model exploits these feature interactions to define similarity of source documents based on location within the stamp embedding space. Accordingly, the techniques described herein can determine a similarity of documents without having access to the documents themselves.Type: GrantFiled: November 26, 2019Date of Patent: June 27, 2023Assignee: Adobe Inc.Inventors: Nikolaos Barmpalios, Ruchi Rajiv Deshpande, Randy Lee Swineford, Nargol Rezvani, Andrew Marc Greene, Shawn Alan Gaither, Michael Kraley
-
Patent number: 11238312Abstract: The present disclosure relates to systems, methods, and non-transitory computer readable media for generating diverse and realistic synthetic documents using deep learning. In particular, the disclosed systems can utilize a trained neural network to generate realistic image layouts comprising page elements that comply with layout parameters. The disclosed systems can also generate synthetic content corresponding to the page elements within the image layouts. The disclosed systems insert the synthetic content into the corresponding page elements of documents based on the image layouts to generate synthetic documents.Type: GrantFiled: November 21, 2019Date of Patent: February 1, 2022Assignee: Adobe Inc.Inventors: Verena Kaynig-Fittkau, Sruthi Madapoosi Ravi, Richard Cohn, Nikolaos Barmpalios, Michael Kraley, Kanchana Sethu
-
Publication number: 20210158093Abstract: The present disclosure relates to systems, methods, and non-transitory computer readable media for generating diverse and realistic synthetic documents using deep learning. In particular, the disclosed systems can utilize a trained neural network to generate realistic image layouts comprising page elements that comply with layout parameters. The disclosed systems can also generate synthetic content corresponding to the page elements within the image layouts. The disclosed systems insert the synthetic content into the corresponding page elements of documents based on the image layouts to generate synthetic documents.Type: ApplicationFiled: November 21, 2019Publication date: May 27, 2021Inventors: Verena Kaynig-Fittkau, Sruthi Madapoosi Ravi, Richard Cohn, Nikolaos Barmpalios, Michael Kraley, Kanchana Sethu
-
Publication number: 20210160221Abstract: Systems and techniques for privacy preserving document analysis are described that derive insights pertaining to a digital document without communication of the content of the digital document. To do so, the privacy preserving document analysis techniques described herein capture visual or contextual features of the digital document and creates a stamp representation that represents these features without included the content of the digital document. The stamp representation is projected into a stamp embedding space based on a stamp encoding model generated through machine learning techniques capturing feature patterns and interaction in the stamp representations. The stamp encoding model exploits these feature interactions to define similarity of source documents based on location within the stamp embedding space. Accordingly, the techniques described herein can determine a similarity of documents without having access to the documents themselves.Type: ApplicationFiled: November 26, 2019Publication date: May 27, 2021Applicant: Adobe Inc.Inventors: Nikolaos Barmpalios, Ruchi Rajiv Deshpande, Randy Lee Swineford, Nargol Rezvani, Andrew Marc Greene, Shawn Alan Gaither, Michael Kraley
-
Patent number: 10372821Abstract: Certain embodiments identify a correct structured reading-order sequence of text segments extracted from a file. A probabilistic language model is generated from a large text corpus to comprise observed word sequence patterns for a given language. The language model measures whether splicing together a first text segment with another continuation text segment results in a phrase that is more likely than a phrase resulting from splicing together the first text segment with other continuation text segments. Sets of text segments, which include a first set with a first text segment and a first continuation text segment as well as a second set with the first text segment and a second continuation text segment, are provided to the probabilistic model. A score indicative of a likelihood of the set providing a correct structured reading-order sequence is obtained for each set of text segments.Type: GrantFiled: March 17, 2017Date of Patent: August 6, 2019Assignee: Adobe Inc.Inventors: Walter Chang, Trung Bui, Pranjal Daga, Michael Kraley, Hung Bui
-
Publication number: 20180267956Abstract: A computer implemented method and system identifies correct structured reading-order sequence of text segments that are extracted from a file structured in a portable document format. A probabilistic language model is generated from a large text corpus to comprise observed word sequence patterns for a given language. The language model measures whether splicing together a first text segment with another continuation text segment results in a phrase that is more likely than a phrase resulting from splicing together the first text segment with other continuation text segments. Sets of text segments are provided to the probabilistic model, where the sets of text segments comprise a first set including the first text segment and a first continuation text segment. A second set includes the first text segment and a second continuation text segment. A score is obtained for each set of text segments. The score is indicative of a likelihood of the set providing a correct structured reading-order sequence.Type: ApplicationFiled: March 17, 2017Publication date: September 20, 2018Applicant: Adobe Systems IncorporatedInventors: Walter Chang, Trung Bui, Pranjal Daga, Michael Kraley, Hung Bui
-
Publication number: 20180039907Abstract: The structure of an untagged document can be derived using a predictive model that is trained in a supervised learning framework based on a corpus of tagged training documents. Analyzing the training documents results in a plurality of document part feature vectors, each of which correlates a category defining a document part (for example, “title” or “body paragraph”) with one or more feature-value pairs (for example, “font=Arial” or “alignment=centered”). Any suitable machine learning algorithm can be used to train the predictive model based on the document part feature vectors extracted from the training documents. Once the predictive model has been trained, it can receive feature-value pairs corresponding to a portion of an untagged document and make predictions with respect to the how that document part should be categorized. The predictive model can therefore generate tag metadata that defines a structure of the untagged document in an automated fashion.Type: ApplicationFiled: August 8, 2016Publication date: February 8, 2018Applicant: Adobe Systems IncorporatedInventor: Michael Kraley
-
Patent number: 9547712Abstract: Techniques are disclosed for efficiently and automatically classifying textual documents or files. In some embodiments, the classification process is integrated into or otherwise made part of the storage function, such that when the user initiates a save process for a given file, the file is processed through a classifier prior to (or contemporaneously with) completing the save function. In some such embodiments, textual content of the file is analyzed using natural language processing to identify a main or substantial concept discussed in the file, and one or more corresponding tags are then assigned to that file. Subsequently, the user can access that file based on the one or more tags, for instance, through a user interface that allows the user to select one or more content categories associated with the assigned tags. The files can be text-based, but may include other content as well, such as images, video, and audio.Type: GrantFiled: February 25, 2016Date of Patent: January 17, 2017Assignee: Adobe Systems IncorporatedInventor: Michael Kraley
-
Publication number: 20160171084Abstract: Techniques are disclosed for efficiently and automatically classifying textual documents or files. In some embodiments, the classification process is integrated into or otherwise made part of the storage function, such that when the user initiates a save process for a given file, the file is processed through a classifier prior to (or contemporaneously with) completing the save function. In some such embodiments, textual content of the file is analyzed using natural language processing to identify a main or substantial concept discussed in the file, and one or more corresponding tags are then assigned to that file. Subsequently, the user can access that file based on the one or more tags, for instance, through a user interface that allows the user to select one or more content categories associated with the assigned tags. The files can be text-based, but may include other content as well, such as images, video, and audio.Type: ApplicationFiled: February 25, 2016Publication date: June 16, 2016Applicant: Adobe Systems IncorporatedInventor: Michael Kraley
-
Publication number: 20160098483Abstract: Techniques are disclosed for efficiently and automatically classifying textual documents or files. In some embodiments, the classification process is integrated into or otherwise made part of the storage function, such that when the user initiates a save process for a given file, the file is processed through a classifier prior to (or contemporaneously with) completing the save function. In some such embodiments, textual content of the file is analyzed using natural language processing to identify a main or substantial concept discussed in the file, and one or more corresponding tags are then assigned to that file. Subsequently, the user can access that file based on the one or more tags, for instance, through a user interface that allows the user to select one or more content categories associated with the assigned tags. The files can be text-based, but may include other content as well, such as images, video, and audio.Type: ApplicationFiled: December 11, 2015Publication date: April 7, 2016Applicant: Adobe Systems IncorporatedInventor: Michael Kraley
-
Patent number: 9298813Abstract: Techniques are disclosed for efficiently and automatically classifying textual documents or files. In some embodiments, the classification process is integrated into or otherwise made part of the storage function, such that when the user initiates a save process for a given file, the file is processed through a classifier prior to (or contemporaneously with) completing the save function. In some such embodiments, textual content of the file is analyzed using natural language processing to identify a main or substantial concept discussed in the file, and one or more corresponding tags are then assigned to that file. Subsequently, the user can access that file based on the one or more tags, for instance, through a user interface that allows the user to select one or more content categories associated with the assigned tags. The files can be text-based, but may include other content as well, such as images, video, and audio.Type: GrantFiled: December 11, 2015Date of Patent: March 29, 2016Assignee: Adobe Systems IncorporatedInventor: Michael Kraley
-
Patent number: 9239876Abstract: Techniques are disclosed for efficiently and automatically classifying textual documents or files. In some embodiments, the classification process is integrated into or otherwise made part of the storage function, such that when the user initiates a save process for a given file, the file is processed through a classifier prior to (or contemporaneously with) completing the save function. In some such embodiments, textual content of the file is analyzed using natural language processing to identify a main or substantial concept discussed in the file, and one or more corresponding tags are then assigned to that file. Subsequently, the user can access that file based on the one or more tags, for instance, through a user interface that allows the user to select one or more content categories associated with the assigned tags. The files can be text-based, but may include other content as well, such as images, video, and audio.Type: GrantFiled: December 3, 2012Date of Patent: January 19, 2016Assignee: ADOBE SYSTEMS INCORPORATEDInventor: Michael Kraley
-
Patent number: 8849869Abstract: In various embodiments, a computerized method includes creating a first item of a list having at least two items that form a portion of electronic content. The computerized method can include creating a second item of the list within the electronic content, as well as converting the second item to a separate paragraph below the first item, wherein the separate paragraph is part of the first item. The computerized method may include creating another item of the list below the separate paragraph, wherein a continuity is maintained between the first item and the another item of the list. The computerized method includes storing the electronic content in a machine-readable medium.Type: GrantFiled: March 11, 2013Date of Patent: September 30, 2014Assignee: Adobe Systems IncorporatedInventor: Michael Kraley
-
Publication number: 20140156665Abstract: Techniques are disclosed for efficiently and automatically classifying textual documents or files. In some embodiments, the classification process is integrated into or otherwise made part of the storage function, such that when the user initiates a save process for a given file, the file is processed through a classifier prior to (or contemporaneously with) completing the save function. In some such embodiments, textual content of the file is analyzed using natural language processing to identify a main or substantial concept discussed in the file, and one or more corresponding tags are then assigned to that file. Subsequently, the user can access that file based on the one or more tags, for instance, through a user interface that allows the user to select one or more content categories associated with the assigned tags. The files can be text-based, but may include other content as well, such as images, video, and audio.Type: ApplicationFiled: December 3, 2012Publication date: June 5, 2014Applicant: ADOBE SYSTEMS INCORPORATEDInventor: Michael Kraley
-
Publication number: 20130198622Abstract: In various embodiments, a computerized method includes creating a first item of a list having at least two items that form a portion of electronic content. The computerized method can include creating a second item of the list within the electronic content, as well as converting the second item to a separate paragraph below the first item, wherein the separate paragraph is part of the first item. The computerized method may include creating another item of the list below the separate paragraph, wherein a continuity is maintained between the first item and the another item of the list. The computerized method includes storing the electronic content in a machine-readable medium.Type: ApplicationFiled: March 11, 2013Publication date: August 1, 2013Applicant: Adobe System IncorporatedInventor: Michael Kraley
-
Patent number: 8396900Abstract: In various embodiments, a computerized method includes creating a first item of a list having at least two items that form a portion of electronic content. The computerized method can include creating a second item of the list within the electronic content, as well as converting the second item to a separate paragraph below the first item, wherein the separate paragraph is part of the first item. The computerized method may include creating another item of the list below the separate paragraph, wherein a continuity is maintained between the first item and the another item of the list. The computerized method includes storing the electronic content in a machine-readable medium.Type: GrantFiled: April 6, 2011Date of Patent: March 12, 2013Assignee: Adobe Systems IncorporatedInventor: Michael Kraley