The present invention, in some embodiments thereof, relates to a system and a method for advertising and, more particularly, but not exclusively, to a system and a method for advertising according to characteristics provided by an advertiser.
Internet based advertising is an important mechanism that enterprises use to communicate with customers. With the introduction of the Internet, new advertising and communication possibilities with customers have been created, which offer the potential of greatly enhanced and more effective advertising techniques for businesses. Online visitors to web documents on the Internet may be directed to a company's web document in several ways including, for example, paid-for advertisements that link to a merchant's web document or links presented in the natural search results presented by a search engine, such as Yahoo!™, MSN™, or Google™ in response to a visitor's language query.
Consumers are showing an increasing preference for using the Internet when searching for purchases, as compared to traditional media outlets. These conclusions are supported by the increasing demand for, and proliferation of, high-speed Internet connections throughout the United States and worldwide. As the Internet grows in popularity and felt necessity, the volume of businesses advertising and communicating over the Internet promises to increase in a corresponding manner.
In light of this progression, a number of systems and methods have been developed for enhancing the Internet based advertising and to match advertisements to the viewer.
For example, U.S. Pat. No. 7,136,871, filed on Nov. 21, 2001, describes a system, including a planning module, a control module, and a receiver module, configured to schedule display of one or more advertising impressions of available advertising inventory. The planning module enables scheduling a requested quantity of advertising impressions in accordance with target criteria. Further, the planning module enables selecting an advertising impression goal for advertisement, assigning an advertising type and defining a weight for the advertisements. The control module receives the schedule, the advertising type and the defined weights and generates one or more metadata files that contain target criteria, advertising type and weights for the advertisements. The one or more metadata files, with the advertisements, are delivered to the receiver module that is configured to define a display frequency for the advertisements which based upon one or more of the metadata files. The receiver module selectively displays advertisement content associated with the advertisements to achieve the advertising impression goal.
According to some embodiments of the present invention there is provided a method for identifying web documents for presenting an advertisement, comprises receiving an advertisement for members of at least one demographic segment, identifying at least one web document with an editing style indicative of a creator of the at least one demographic segment, and allowing a presentation of the advertisement to at least one visitor of the at least one identified web document.
Optionally, the web documents comprises at least one member of a group consisting of: a blog, a micro-blogging page, a social network page, a webpage, a video blog, an audio blog, a podcast, a WORD document, a portable document format (PDF) document, an excel spreadsheet document, an extensible markup language (XML) page, a hypertext markup language (HTML) page, and an Internet page.
Optionally, each the demographic segment defines a member of a group consisting of: a gender, a social class, a socio economic class, a native language, a personality characteristic, an education level, an income level, and sociability.
Optionally, the identifying comprises identifying at least one demographic profiling marker indicative of the at least demographic segment in respective the web document.
More optionally, the at least one demographic profiling marker is a textual feature from the textual content of the at least one web document.
More optionally, the identifying comprises estimating the frequency of the textual feature in the textual content of the at least one web document.
According to some embodiments of the present invention there is provided a method for selecting web documents for presenting an advertisement. The method comprises identifying, for each of a plurality of web documents, a relation to at least one of a plurality of demographic segments, providing an advertisement for a target audience selected from the plurality of demographic segments, selecting at least one of the plurality of web documents according to a match between respective the at least one demographic segment and the target audience, and allowing a presentation of the advertisement to at least one visitor of the at least one selected web document.
Optionally, the relation is a relation to an author of a respective the web document.
Optionally, the plurality of demographic segments are based on a characteristic of a group consisting of: a gender, a social class, a socio economic class, a native language, a personality characteristic, an education level, an income level, and sociability.
Optionally, the identifying comprises identifying at least one demographic profiling marker indicative of the relation in respective the web document.
More optionally, at least one demographic profiling marker comprises at least one textual feature from the textual content of the respective web document.
More optionally, the at least one textual feature comprises a member of a group consisting of: a grammatical error, an orthographic error, morphological language feature, a lexical word selection, a syntactic wording selection, a prosodic wording selection, and a vocabulary.
More optionally, at least one demographic profiling marker comprises at least one visual feature from the visual content of the respective web document.
More optionally, at least one demographic profiling marker comprises at least one audible feature from the audible content of the respective web document.
More optionally, at least one demographic profiling marker comprises the source of respective the web document.
More optionally, at least one demographic profiling marker comprises at least one editorial feature from the respective web document.
More optionally, the demographic profiling marker is a combination of at least two of a group consisting of: a textual feature, visual feature, editorial feature, audible feature, and a contextual feature.
According to some embodiments of the present invention there is provided a system for selecting advertisement spots. The system comprises a content analysis module configured for identifying, for each of a plurality of web documents, a relation to at least one of a plurality of demographic segments and a receiving unit configured for receiving an advertisement for a target audience selected from the plurality of demographic segments. The system further comprises an advertisement spot selector configured for selecting at least one of the plurality of web documents according to a match between respective the at least one demographic segment and the target audience. The selection allows a presentation of the advertisement to at least one visitor of the at least one selected web document.
Optionally, the content analysis module is configured for identifying at least one demographic profiling marker indicative of the relation in respective the web document.
Optionally, the system further comprises a repository comprises a dataset mapping the relation between a plurality of demographic profiling markers and a plurality of editing styles each associated with at least one of the plurality of demographic segments, the content analysis module being configured for performing the identification using the map.
Optionally, an author of the at least one selected web document and the target audience are from a common of the plurality of demographic segments.
Optionally, the plurality of demographic segments are based on a characteristic of a group consisting of: a gender, a social class, a socio economic class, income level, income level, a native language, a personality characteristic, an education level, an income level, and sociability.
According to some embodiments of the present invention there is provided a method for identifying web documents for presenting an advertisement. The method comprises receiving an advertisement for members of at least one demographic segment, identifying at least one web document with an editing style intended to members of the at least one demographic segment, and allowing a presentation of the advertisement to at least one visitor of the at least one identified web document.
Unless otherwise defined, all technical and/or scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which the invention pertains. Although methods and materials similar or equivalent to those described herein can be used in the practice or testing of embodiments of the invention, exemplary methods and/or materials are described below. In case of conflict, the patent specification, including definitions, will control. In addition, the materials, methods, and examples are illustrative only and are not intended to be necessarily limiting.
Implementation of the method and/or system of embodiments of the invention can involve performing or completing selected tasks manually, automatically, or a combination thereof. Moreover, according to actual instrumentation and equipment of embodiments of the method and/or system of the invention, several selected tasks could be implemented by hardware, by software or by firmware or by a combination thereof using an operating system.
For example, hardware for performing selected tasks according to embodiments of the invention could be implemented as a chip or a circuit. As software, selected tasks according to embodiments of the invention could be implemented as a plurality of software instructions being executed by a computer using any suitable operating system. In an exemplary embodiment of the invention, one or more tasks according to exemplary embodiments of method and/or system as described herein are performed by a data processor, such as a computing platform for executing a plurality of instructions. Optionally, the data processor includes a volatile memory for storing instructions and/or data and/or a non-volatile storage, for example, a magnetic hard-disk and/or removable media, for storing instructions and/or data. Optionally, a network connection is provided as well. A display and/or a user input device such as a keyboard or mouse are optionally provided as well.
Some embodiments of the invention are herein described, by way of example only, with reference to the accompanying drawings. With specific reference now to the drawings in detail, it is stressed that the particulars shown are by way of example and for purposes of illustrative discussion of embodiments of the invention. In this regard, the description taken with the drawings makes apparent to those skilled in the art how embodiments of the invention may be practiced.
In the drawings:
The present invention, in some embodiments thereof, relates to a system and a method for advertising and, more particularly, but not exclusively, to a system and a method for advertising according to characteristics provided by an advertiser.
According to an aspect of some embodiments of the present invention there is provided a method and a system for identifying web documents, such as blogs, profile pages in social networks, such as FaceBook™ and MySpace™, editorials and/or comments in online newspapers and/or websites, talkbacks webpages, paid content articles, for example as provided at www.associatedcontent.com, blogs in blogging services, and micro-blogging pages of micro-blogging service, such as Twitter™, for presenting an advertisement. The method allows matching an advertisement that is targeted for members of a known demographic segment, such as age, gender, social class, social economic class and/or income level, to web documents which are relatively frequently accessed by members of this known demographic segment. The method is based on receiving the advertisement and identifying one or more web documents which have been created, for example written, kept, managed, and/or edited, with an editing style that is indicative for a target audience of the targeted demographic segment, for example, an editing style of a creator from the targeted demographic segment, as further described below. Web documents of a certain editing style are characterized by similar writing patterns, layout design, editing pattern and the like. The matching allows the presentation of the advertisement to visitors of the identified web documents.
Optionally, each one of the identified web documents is characterized by one or more demographic profiling markers which are indicative of a relation to a target audience of one or more demographic segments, for example to a relation of the creator of the website to one or more demographic segments. An demographic profiling marker may be a textual feature, a visual feature, an editorial feature, an audible feature, a contextual feature and/or a combination thereof, for example as described below.
According to other embodiments of the present invention a system for selecting web documents for advertisement is provided. The system comprises a content analysis module for analyzing web documents and identifying the demographic segments to which the creator and/or the target audience of each one of them is related. The system further comprises a receiving unit for receiving an advertisement for a certain demographic segment and an advertisement spot selector configured for selecting, from the at least one of the web documents. The selected websites having an editing style which is common in web documents indented to certain the demographic segment to which the received advertisement is intended. For example, the receiving unit may select the web sites by identifying creators which are related to the demographic segment to which the received advertisement is intended. Such a selection allows the presentation of the advertisement to visitors of the selected web documents.
Before explaining at least one embodiment of the invention in detail, it is to be understood that the invention is not necessarily limited in its application to the details of construction and the arrangement of the components and/or methods set forth in the following description and/or illustrated in the drawings and/or the Examples. The invention is capable of other embodiments or of being practiced or carried out in various ways.
Reference is now made to
As further described below, the method allows matching an advertisement that is targeted for members of a known demographic segment to web documents which are relatively frequently accessed by members of this known demographic segment. First, as shown at 51, an advertisement, which may be represented by a generic definition defining an advertised product or a family of products, is provided. Optionally, the advertisement is provided from a remote advertisement server, such as shown at numeral 111 in
Reference is now made to
Reference is now also made to
First, as shown at 201, references to one or more web documents are provided, optionally as records in a database, for example as shown at 104. Additionally or alternatively references to web documents are provided by using the aforementioned search engine that is designed to retrieve references to web documents, for example that web documents that fulfill one or more criterions, such as blogs, frequently changing websites, and the like.
Now, as shown at 202, the demographic segment in each one of the web documents which are referred to in the provided references is identified. Optionally, one or more demographic profiling markers which are indicative of the demographic segment are identified and used to classify web documents, for example as described below.
For example, the content of one or more posts of a blog and/or pages of a social network profile is analyzed to extract one or more demographic profiling markers. As used herein, an demographic profiling marker is a textual feature, visual feature, editorial feature, audible feature, contextual feature and/or a combination thereof that is presented and/or available for presentation to users accessing a textual, visual, and/or audible post of a blog. For clarity, these features are exemplified below. The existence of a certain demographic profiling marker in a certain web document characterizes it as a web document intended for a certain demographic segment, for example a web document kept, edited and/or written by an author characterized by being part of the certain demographic segment.
In some embodiments of the present invention, the demographic profiling markers are textual features, such as content-based features and style-based features; see Campbell, R. S. & Pennebaker, J. W. (2003), The secret life of pronouns: Flexibility in writing style and physical health, Psychological Science, 14, 60-65, which is incorporated herein by reference. In such an embodiment, the textual feature is marked as a demographic profiling marker if the frequency of the occurrence thereof in the text of the website, optionally normalized by the number of words in the text, exceeds a predefined threshold. The style-based features may include lexical, syntactic, and/or vocabulary features and associated errors, such as grammatical or orthographic errors. The content-based features may include words and/or phrases which have a distinguishing nature, such as words and/or phrases which are used by authors of a certain country, culture, sex, personality, discipline or a combination thereof, or by authors which are creating content for these demographic segments.
Optionally, a feature set that naturally subsumes both function words and parts-of-speech is created for each website in a manner that allows classifying some textual features which are used as demographic profiling markers. Optionally, the feature set is arranged as trees, for example as depicted in
Reference is now also made to
As depicted in the table, other exemplary writing patterns which are indicative of other demographic segments, such as writing patterns of different age groups, different mother tongue and/or different personalities are characterized by a high prevalence of different textual features.
In some embodiments of the present invention, the demographic profiling markers includes visual and/or audible features, such as video clips, audio files, images, and/or graphic objects which are embedded into the analyzed web document. Such visual and/or audible features may be used, separately or in combination with other demographic profiling markers, to classify the demographic segments of the author of the web document or to classify the demographic segments of indented target audience of the web document.
Optionally, known audio, video and/or image analysis may be used for identifying and mapping these features, see for example, Durrell, Kevan, Pornographic image detection with Gabor filters, Proc. SPIE Vol. 4668, p. 1-9, Applications of Artificial Neural Networks in Image Processing VII, Nasser M. Nasrabadi; Aggelos K. Katsaggelos; N. Rea, Eds, Multimodal Periodicity Analysis for Illicit Content Detection in Videos, Visual Media Production, 2006. CVMP 2006. 3rd European Conference on Volume, Issue, 2006 Page(s): 106-114, and Forsyth, David A. et al., “Finding Pictures of Objects in Large Collections of Images,” Proceedings, International Workshop on Object Recognition, Cambridge, 1996, which are incorporated herein by reference.
In some embodiments of the present invention, the demographic profiling markers includes source features, such as the uniform resource locator (URL) of the website, the common search term which is used for addressing the respective web document, the description and all tags of the web document and/or the posts thereof, the web document name, the titles in the virtual root, the deployment path, links from the web document, link to the web document and/or any combination thereof.
In some embodiments of the present invention, the demographic profiling markers of one or more of the analyzed web document includes editorial features. As used herein, an editorial feature is a feature that has an effect on the look and feel of the analyzed web document, such as a selected template and/or any object arrangement and/or prevalence in a document. Optionally, the editorial feature is identified by analyzing the graphical elements the graphical user interfaces (GUIs) and/or textual command language which is used to control and/or navigate in the web document. Optionally, the editorial feature is identified according to the opening webpage or post, the arrangement of video files and/or images in the webpage, the prevalence of video files and/or images in the webpage, the icons used to represent certain functions such as opening and closing files, directories and application programs, the size and position of windows; conventions for the meaning of different buttons on a mouse and keys on the keyboard, and/or the appearance and operation of menus. As the aforementioned demographic profiling markers, these demographic profiling markers may be used for identifying a writing pattern that is identified with one or more demographic segments. For example, a web document that includes a large number of graphic objects on a colorful background and or short text segments with variable fonts and/or embedded emoticons, may identified as a document created by a teenager.
In some embodiments of the present invention, the demographic profiling markers of one or more of the analyzed web document includes contextual features. In such an embodiment, a predefined combination of textual features, visual, editorial, and/or audible features is identified as demographic profiling markers. Optionally, the plurality of features, optionally weighted, are arranged in a vector and summed and/or matched with a predefined value and/or vector. For example, the presence of the word “love” in combination with a heart shaped emoticon may indicate that the author or the target audience of the webpage is related to one demographic segment while the presence of the word “love” in combination with a graph may indicate that the author or the target audience of the webpage is related to another demographic segment.
In some embodiments of the present invention, the plurality of web documents are clustered according to different editing styles which are associated with different demographic segments. In such embodiments, each cluster includes websites having similar demographic profiling markers and/or demographic profiling markers which are related to the same editing style. Optionally, some web documents are clustered to a number of different clusters. For example, the same website may be clustered as a member of a cluster identified by an editing style of author from the demographic segment of people between 20 and 30 and with as a member of a cluster identified by an editing style of an author from the demographic segment of women.
The demographic profiling markers, which are optionally prevailing textual features in the web document, as described above, characterize the editing style of the author and therefore may be used for determining whether the web document is suitable for an advertisement that is indented for a target audience which is associated, optionally positively intrigued, by documents having a similar editing style. Optionally, the editing style is an editing style authors from a common demographic segment. Examples for editing styles are writing patterns of authors which are related to a certain segment of the population, such as woman authors, male authors, neurotic authors, authors of certain proficiency, low social economic level authors, high social economic level authors, and paranoiac authors.
Optionally, a combination of demographic profiling markers is associated with one or more demographic segments and used for classifying the author or the target audience of the webpage as a member of a certain social economic class and/or any other classification that may be used for segmenting a group of potential customers as a targeted audience.
As described above, some or all of the analyzed web documents are tagged as matching to one or more editing styles, according to the demographic profiling markers which have been identified therein. Optionally, known learning machines and/or methods are used for identifying demographic profiling markers and mapping between them and editing styles. Such learning machines and/or methods are known in the art, and therefore not discussed herein in great detail, see S. Argamon, M. Koppel, J. Pennebaker and J. Schler (2007), Automatically Profiling the Author of an Anonymous Text, Communications of the ACM, published in http://www.cs.biu.ac.il/˜koppel/papers/AuthorshipProfiling-cacm-final.pdf and incorporated herein by reference.
In some embodiment of the present invention, the learning is performed as follows: features are identified in each one of a plurality of exemplary web documents and arranged in a numerical vector X=(x1, . . . , xi, . . . , xn), where n denotes the number of features and xi denotes the relative frequency of feature i in the document. Such a vector allows the applying of machine-learning algorithms that identify classifiers, tag them as demographic profiling markers, and optionally use them for assigning the related documents to one or more demographic segments. Optionally, the classifiers are identified by generating a weight vector Wj=(w1j, . . . , wij, . . . , wnj) for each demographic segments cj and then assign a document, X, to the demographic segment for which the inner product Wj·X is maximal. There are a number of effective algorithms for learning the weight vectors, such as a Bayesian multi-class regression to (BMR) algorithm, for example see Crammer, K. and Singer, Y. (2003), Ultraconservative Online Algorithms for Multiclass Problems, Journal of Machine Learning Research, 3:951-991, Genkin, A., Lewis, D. D., and Madigan, D. (2006), Large-scale Bayesian logistic regression for text categorization, Technimetrics, and Koppel, M., Schler, J., Argamon, S., and Pennebaker, J. W. (2006), Effects of age and gender on blogging, Presented at AAAI 2006 Spring Symposium on Computational Approaches to Analyzing Weblogs, Stanford, Calif., March 2006 which are incorporated herein by reference.
As shown at 203, one or more advertisements which are designed to be presented in relation and/or in certain web documents are received and/or tagged. Each advertisement may be a targeted advertisement designed to address a certain target audience that has been identified for the advertised product. For example, an advertisement for premium shaving cream may be targeted advertisement designed for a group of individuals having a customer prototype of a male, between 30 and 50 of a high social economy class, and an average yearly income of $120,000.
As shown at 204, each one of the received advertisements is tagged with a specific target audience of a predefined demographic segment that has been identified for the advertised product. Optionally, the target audience is associated with requested editing styles of authors from the predefined demographic segment. Optionally, the system 100 comprises and/or connected to a map, such as a list, that describes connections between target audiences and editing styles. Such a map may be used for identifying which editing styles should be associated with an advertisement that is targeted for a certain audience. It should be noted that such an association may be done manually, automatically, and/or semi manually.
For example, a target audience of middle class women in the age between 30 and 50 is mapped, by the map, to editing style of web document authors having a writing style and/or reputation which are most likely to attract such middle class women. Optionally, the map is defined in a manner that a target audience is associated with editing styles, such as writing patterns, of web document authors having similar, or substantially similar, characteristics to its member. For example, a target audience of a low class man in the age between 15 and 20 is mapped to one or more editing styles of web document authors in the same social economic class, income level, sex and/or age.
Now, as shown at 205, one or more matching web documents are identified according to a match between the target audience and the demographic segment of the authors of the web documents. As described above, one or more exemplary demographic profiling markers are identified in each one of the web documents in a manner that allows identifying the demographic segment of the author thereof. By identifying a match between the target audience and the demographic segment of the authors of the web documents, advertisement in proximity to content that is most likely to have the target audience that has been identified for the advertised product may be found.
As described above, one or more demographic profiling markers are identified in each web document. These demographic profiling markers may be used for classifying a web document of the plurality of web documents as created by an author of a certain demographic segment. In such an embodiment, the target audience of the received advertisement is matched with one or more of clusters having an association with respective demographic segments. In such a manner, one or more clusters may be identified as including web documents which are suitable for the received advertisement. For example, an advertisement that has been associated with a target audience of the demographic segment of people between 20 and 30 years old from a high social economic class may be matched with web documents clustered in a cluster of similar demographic segments, such as a demographic segment of people between 20 and 30 years old, a demographic segment of high social economic class, a union of the members of the groups, and/or intersection of the members of the groups.
Now, as shown at 206, the matched web documents are associated with the received advertisement. In such a manner, the received advertisement is presented and/or otherwise provided to visitors of the matched web documents. As the matched web documents have been identified as web documents which are accessed by member of a demographic segment that has been identified by the providers of the advertisement as suitable for the promotion of the advertised product, the advertisement exposure is relativity efficient. For example, when the received advertisement are associated with a demographic segment of an author from a high socio-economic class, the identified web documents are created, for example managed, kept, and/or written, by an author having of an editing style which presumably has a target audience that includes members of the high socio-economic class.
It is expected that during the life of a patent maturing from this application many relevant methods and systems will be developed and the scope of the term network, web document, and/or client terminal is intended to include all such new technologies a priori.
As used herein the term “about” refers to ±10%.
The terms “comprises”, “comprising”, “includes”, “including”, “having” and their conjugates mean “including but not limited to”.
The term “consisting of means “including and limited to”.
The term “consisting essentially of” means that the composition, method or structure may include additional ingredients, steps and/or parts, but only if the additional ingredients, steps and/or parts do not materially alter the basic and novel characteristics of the claimed composition, method or structure.
As used herein, the singular form “a”, “an” and “the” include plural references unless the context clearly dictates otherwise. For example, the term “a compound” or “at least one compound” may include a plurality of compounds, including mixtures thereof.
Throughout this application, various embodiments of this invention may be presented in a range format. It should be understood that the description in range format is merely for convenience and brevity and should not be construed as an inflexible limitation on the scope of the invention. Accordingly, the description of a range should be considered to have specifically disclosed all the possible subranges as well as individual numerical values within that range. For example, description of a range such as from 1 to 6 should be considered to have specifically disclosed subranges such as from 1 to 3, from 1 to 4, from 1 to 5, from 2 to 4, from 2 to 6, from 3 to 6 etc., as well as individual numbers within that range, for example, 1, 2, 3, 4, 5, and 6. This applies regardless of the breadth of the range.
Whenever a numerical range is indicated herein, it is meant to include any cited numeral (fractional or integral) within the indicated range. The phrases “ranging/ranges between” a first indicate number and a second indicate number and “ranging/ranges from” a first indicate number “to” a second indicate number are used herein interchangeably and are meant to include the first and second indicated numbers and all the fractional and integral numerals therebetween.
It is appreciated that certain features of the invention, which are, for clarity, described in the context of separate embodiments, may also be provided in combination in a single embodiment. Conversely, various features of the invention, which are, for brevity, described in the context of a single embodiment, may also be provided separately or in any suitable subcombination or as suitable in any other described embodiment of the invention. Certain features described in the context of various embodiments are not to be considered essential features of those embodiments, unless the embodiment is inoperative without those elements.
Although the invention has been described in conjunction with specific embodiments thereof, it is evident that many alternatives, modifications and variations will be apparent to those skilled in the art. Accordingly, it is intended to embrace all such alternatives, modifications and variations that fall within the spirit and broad scope of the appended claims.
All publications, patents and patent applications mentioned in this specification are herein incorporated in their entirety by reference into the specification, to the same extent as if each individual publication, patent or patent application was specifically and individually indicated to be incorporated herein by reference. In addition, citation or identification of any reference in this application shall not be construed as an admission that such reference is available as prior art to the present invention. To the extent that section headings are used, they should not be construed as necessarily limiting.
This application claims the benefit of priority of U.S. Provisional Patent Application No. 61/115,564, filed on Nov. 18, 2008 and U.S. Provisional Patent Application No. 61/115,562, filed on Nov. 18, 2008. The contents of the above Applications are incorporated herein by reference. The teachings of U.S. Provisional Patent Application No. 61/071,707, filed on May 14, 2008, are also incorporated herein by reference.
Number | Name | Date | Kind |
---|---|---|---|
4994966 | Hutchins | Feb 1991 | A |
5537586 | Amram | Jul 1996 | A |
5819260 | Lu | Oct 1998 | A |
5930788 | Wical | Jul 1999 | A |
6014651 | Crawford | Jan 2000 | A |
6144991 | England | Nov 2000 | A |
6714975 | Aggarwal | Mar 2004 | B1 |
6826559 | Ponte | Nov 2004 | B1 |
6892354 | Servan-Schreiber et al. | May 2005 | B1 |
7047404 | Doonan et al. | May 2006 | B1 |
7124093 | Graham | Oct 2006 | B1 |
7228493 | Kosak | Jun 2007 | B2 |
7296064 | Yoon | Nov 2007 | B2 |
7302404 | Solomon | Nov 2007 | B2 |
7320031 | Konig et al. | Jan 2008 | B2 |
7346606 | Bharat | Mar 2008 | B2 |
7483891 | Liu et al. | Jan 2009 | B2 |
7493553 | Vora et al. | Feb 2009 | B1 |
7580926 | Kapur et al. | Aug 2009 | B2 |
7647299 | Harik | Jan 2010 | B2 |
7653627 | Li et al. | Jan 2010 | B2 |
7680796 | Yeh et al. | Mar 2010 | B2 |
7693830 | Guha | Apr 2010 | B2 |
7711743 | Cavagnaro et al. | May 2010 | B2 |
7716199 | Guha | May 2010 | B2 |
7725464 | Grubb et al. | May 2010 | B2 |
7734624 | Anderson et al. | Jun 2010 | B2 |
7788132 | Desikan et al. | Aug 2010 | B2 |
7827060 | Wright et al. | Nov 2010 | B2 |
7827158 | Hayakawa | Nov 2010 | B2 |
7831586 | Reitter et al. | Nov 2010 | B2 |
7987194 | Walker | Jul 2011 | B1 |
7991806 | Broder | Aug 2011 | B2 |
7996282 | Scott et al. | Aug 2011 | B1 |
8001105 | Bolivar et al. | Aug 2011 | B2 |
8140515 | Pradhan | Mar 2012 | B2 |
8150679 | Wick | Apr 2012 | B2 |
8156002 | van Zwol | Apr 2012 | B2 |
8296335 | Bouve | Oct 2012 | B2 |
8311997 | Kauchak | Nov 2012 | B1 |
8326686 | Datar | Dec 2012 | B2 |
8412650 | Takamatsu | Apr 2013 | B2 |
8538836 | Scott et al. | Sep 2013 | B1 |
8645817 | Fisher | Feb 2014 | B1 |
8726278 | Shawver | May 2014 | B1 |
8732605 | Falaki | May 2014 | B1 |
8837835 | Samwel, III | Sep 2014 | B1 |
9043333 | Look | May 2015 | B1 |
9117219 | Solomon | Aug 2015 | B2 |
20010043364 | Messner | Nov 2001 | A1 |
20010049620 | Blasko | Dec 2001 | A1 |
20020010681 | Hillegass | Jan 2002 | A1 |
20020023042 | Solomon | Feb 2002 | A1 |
20020042870 | Rocray | Apr 2002 | A1 |
20020065857 | Michalewicz | May 2002 | A1 |
20020065958 | Rocray | May 2002 | A1 |
20020083123 | Freedman | Jun 2002 | A1 |
20020129063 | Kosak | Sep 2002 | A1 |
20020138331 | Hosea | Sep 2002 | A1 |
20030101024 | Adar | May 2003 | A1 |
20030140311 | Lemon | Jul 2003 | A1 |
20030172005 | Hellal et al. | Sep 2003 | A1 |
20040039916 | Aldis | Feb 2004 | A1 |
20040054589 | Nicholas | Mar 2004 | A1 |
20040059708 | Dean | Mar 2004 | A1 |
20040093327 | Anderson et al. | May 2004 | A1 |
20050033641 | Jha et al. | Feb 2005 | A1 |
20050114198 | Koningstein | May 2005 | A1 |
20050120390 | Nonoyama | Jun 2005 | A1 |
20050132347 | Harper | Jun 2005 | A1 |
20050262428 | Little | Nov 2005 | A1 |
20050278620 | Baldwin et al. | Dec 2005 | A1 |
20060010073 | Fisher et al. | Jan 2006 | A1 |
20060074748 | Kline et al. | Apr 2006 | A1 |
20060200420 | Osada | Sep 2006 | A1 |
20060242147 | Gehrking | Oct 2006 | A1 |
20060287920 | Perkins | Dec 2006 | A1 |
20060293951 | Patel et al. | Dec 2006 | A1 |
20070005417 | Desikan et al. | Jan 2007 | A1 |
20070016469 | Bae | Jan 2007 | A1 |
20070027772 | Chou | Feb 2007 | A1 |
20070033221 | Copperman | Feb 2007 | A1 |
20070038614 | Guha | Feb 2007 | A1 |
20070047817 | Abdulkader | Mar 2007 | A1 |
20070050389 | Kim et al. | Mar 2007 | A1 |
20070050393 | Vogel et al. | Mar 2007 | A1 |
20070061203 | Ellis et al. | Mar 2007 | A1 |
20070067304 | Ives | Mar 2007 | A1 |
20070079327 | Khoo et al. | Apr 2007 | A1 |
20070112629 | Solomon et al. | May 2007 | A1 |
20070136817 | Nguyen | Jun 2007 | A1 |
20070156520 | Sharma | Jul 2007 | A1 |
20070208621 | Park et al. | Sep 2007 | A1 |
20070208728 | Zhang | Sep 2007 | A1 |
20070214042 | Dominowska | Sep 2007 | A1 |
20070233556 | Koningstcin | Oct 2007 | A1 |
20070244750 | Grannan et al. | Oct 2007 | A1 |
20070260741 | Bezancon | Nov 2007 | A1 |
20070288431 | Reitter et al. | Dec 2007 | A1 |
20080028100 | Adelman | Jan 2008 | A1 |
20080086356 | Glassman et al. | Apr 2008 | A1 |
20080183742 | Kapur | Jul 2008 | A1 |
20080195461 | Li | Aug 2008 | A1 |
20080208754 | Zunke | Aug 2008 | A1 |
20080235085 | Kovinsky | Sep 2008 | A1 |
20080235187 | Gade et al. | Sep 2008 | A1 |
20080249855 | Collins et al. | Oct 2008 | A1 |
20080281705 | Solomon | Nov 2008 | A1 |
20080288341 | Garbe | Nov 2008 | A1 |
20080300971 | Zeng | Dec 2008 | A1 |
20090019008 | Moore et al. | Jan 2009 | A1 |
20090024718 | Anagnostopoulos | Jan 2009 | A1 |
20090063229 | Coladonato et al. | Mar 2009 | A1 |
20090063491 | Barclay et al. | Mar 2009 | A1 |
20090076886 | Dulitz et al. | Mar 2009 | A1 |
20090119218 | Ooki | May 2009 | A1 |
20090119779 | Dean | May 2009 | A1 |
20090132500 | Jones | May 2009 | A1 |
20090171948 | Solomon | Jul 2009 | A1 |
20090193249 | Conrado et al. | Jul 2009 | A1 |
20090228281 | Singleton | Sep 2009 | A1 |
20090235187 | Kim et al. | Sep 2009 | A1 |
20090265243 | Karassner et al. | Oct 2009 | A1 |
20090276208 | Pagan | Nov 2009 | A1 |
20100042504 | Shenfield et al. | Feb 2010 | A1 |
20100088321 | Solomon et al. | Apr 2010 | A1 |
20100114562 | Hutchinson et al. | May 2010 | A1 |
20100121790 | Klinkott | May 2010 | A1 |
20100125502 | Solomon | May 2010 | A1 |
20100145808 | Hilbert | Jun 2010 | A1 |
20100161385 | Karypis | Jun 2010 | A1 |
20100185513 | Anderson et al. | Jul 2010 | A1 |
20100191574 | Ziemann | Jul 2010 | A1 |
20100312469 | Chen | Dec 2010 | A1 |
20110055195 | Reitter et al. | Mar 2011 | A1 |
20110086331 | Karov Zangvil | Apr 2011 | A1 |
20120054053 | Cheek | Mar 2012 | A1 |
20120078715 | Li | Mar 2012 | A1 |
20120284119 | Hu | Nov 2012 | A1 |
20120303446 | Busch | Nov 2012 | A1 |
20130097166 | Fink | Apr 2013 | A1 |
20130125240 | Xu | May 2013 | A1 |
20130304572 | Axe et al. | Nov 2013 | A1 |
20140013449 | Vijay | Jan 2014 | A1 |
20140108145 | Patel | Apr 2014 | A1 |
20140129211 | Kimelfeld | May 2014 | A1 |
20160191540 | Fuka | Jun 2016 | A1 |
20160203301 | Ooki | Jul 2016 | A1 |
20160260127 | Bradley | Sep 2016 | A1 |
Number | Date | Country |
---|---|---|
WO-9829818 | Jul 1998 | WO |
Entry |
---|
Herring et al (“Bridging the Gap: A Genre Analysis of Weblogs”, Proceedings of the 37th Hawaii International Conference on System Sciences—2004). |
Huffaker, D. A. and Calvert, S. L. (2005), Gender, Identity, and Language Use in Teenage Blogs. Journal of Computer-Mediated Communication. |
Mei,et al (PageSense: Toward Stylewise Contextual Advertising via Visual Analysis of Web Pages) (Year: 2018). |
Response dated Jan. 3, 2012 to Official Action dated Aug. 5, 2011 From the US Patent and Trademark Office Re. U.S. Appl. No. 12/551,603. |
Official Action dated Mar. 15, 2011 From the US Patent and Trademark Office Re. U.S. Appl. No. 12/347,027. |
Official Action dated Mar. 9, 2012 From the US Patent and Trademark Office Re. U.S. Appl. No. 12/551,603. |
Abadpour et al. “Pixel-Based Skin Detection for Pornography Filtering”, Iranian Journal of Electrical & Electronic Engineering, 25 P., 2005. |
Argamon et al. “Automatically Profiling the Author of an Anonymous Text”, 13 P. |
Liang et al. “Detecting Pornographic Images”, Asia Pacific Institute of Information Technology, Kuala Lumpur, Malaysia, 6 P. |
Restriction Official Action dated Mar. 28, 2012 From the US Patent and Trademark Office Re. U.S. Appl. No. 12/615,279. |
Official Action dated Apr. 16, 2012 From the US Patent and Trademark Office Re. U.S. Appl. No. 12/347,027. |
Response dated Jun. 15, 2011 to Official Action dated Mar. 15, 2011 From the US Patent and Trademark Office Re. U.S. Appl. No. 12/347,027. |
Official Action dated Aug. 1, 2012 From the US Patent and Trademark Office Re. U.S. Appl. No. 12/615,279. |
Official Action dated Aug. 5, 2011 From the US Patent and Trademark Office Re. U.S. Appl. No. 12/551,603. |
Official Action dated Aug. 31, 2011 From the US Patent and Trademark Office Re. U.S. Appl. No. 12/347,027. |
Official Action dated Oct. 18, 2012 From the US Patent and Trademark Office Re. U.S. Appl. No. 12/347,027. |
Response dated Dec. 1, 2011 to Official Action dated Aug. 31, 2011 From the US Patent and Trademark Office Re. U.S. Appl. No. 12/347,027. |
Official Action dated May 29, 2013 From the US Patent and Trademark Office Re. U.S. Appl. No. 12/615,279. |
Applicant-Initiated Interview Summary dated Apr. 2, 2013 From the US Patent and Trademark Office Re. U.S. Appl. No. 12/347,027. |
Applicant-Initiated Interview Summary dated Jul. 7, 2014 From the US Patent and Trademark Office Re. U.S. Appl. No. 12/347,027. |
Official Action dated Aug. 21, 2014 From the US Patent and Trademark Office Re. U.S. Appl. No. 12/551,603. |
Official Action dated Jul. 15, 2014 From the US Patent and Trademark Office Re. U.S. Appl. No. 12/347,027. |
Advisory Action Before the Filing of an Appeal Brief dated Aug. 22, 2013 From the US Patent and Trademark Office Re. U.S. Appl. No. 12/615,279. |
Official Action dated Feb. 24, 2014 From the US Patent and Trademark Office Re. U.S. Appl. No. 12/347,027. |
Advisory Action Before the Filing of an Appeal Brief dated Oct. 30, 2014 From the US Patent and Trademark Office Re. U.S. Appl. No. 12/347,027. |
Official Action dated Dec. 19, 2014 From the US Patent and Trademark Office Re. U.S. Appl. No. 12/615,279. |
Official Action dated Jan. 13, 2015 From the US Patent and Trademark Office Re. U.S. Appl. No. 12/347,027. |
Advisory Action Before the Filing of an Appeal Brief dated Sep. 17, 2015 From the US Patent and Trademark Office Re. U.S. Appl. No. 12/551,603. |
Official Action dated Aug. 26, 2016 From the US Patent and Trademark Office Re. U.S. Appl. No. 12/615,279. |
Official Action dated Jul. 26, 2016 From the US Patent and Trademark Office Re. U.S. Appl. No. 12/551,603. |
Official Action dated Feb. 7, 2017 From the US Patent and Trademark Office Re. U.S. Appl. No. 12/615,279. (26 pages). |
Official Actiondated May 4, 2015 From the US Patent and Trademark Office Re. U.S. Appl. No. 12/551,603. |
Official Action dated Jun. 30, 2015 From the US Patent and Trademark Office Re. U.S. Appl. No. 12/615,279. |
Number | Date | Country | |
---|---|---|---|
20100125502 A1 | May 2010 | US |
Number | Date | Country | |
---|---|---|---|
61115562 | Nov 2008 | US | |
61115564 | Nov 2008 | US |