DETAILED ACTION
Notice of Pre-AIA or AIA Status
The present application, filed on or after March 16, 2013, is being examined under the first inventor to file provisions of the AIA .
Double Patenting
The nonstatutory double patenting rejection is based on a judicially created doctrine grounded in public policy (a policy reflected in the statute) so as to prevent the unjustified or improper timewise extension of the “right to exclude” granted by a patent and to prevent possible harassment by multiple assignees. A nonstatutory double patenting rejection is appropriate where the conflicting claims are not identical, but at least one examined application claim is not patentably distinct from the reference claim(s) because the examined application claim is either anticipated by, or would have been obvious over, the reference claim(s). See, e.g., In re Berg, 140 F.3d 1428, 46 USPQ2d 1226 (Fed. Cir. 1998); In re Goodman, 11 F.3d 1046, 29 USPQ2d 2010 (Fed. Cir. 1993); In re Longi, 759 F.2d 887, 225 USPQ 645 (Fed. Cir. 1985); In re Van Ornum, 686 F.2d 937, 214 USPQ 761 (CCPA 1982); In re Vogel, 422 F.2d 438, 164 USPQ 619 (CCPA 1970); In re Thorington, 418 F.2d 528, 163 USPQ 644 (CCPA 1969).
A timely filed terminal disclaimer in compliance with 37 CFR 1.321(c) or 1.321(d) may be used to overcome an actual or provisional rejection based on nonstatutory double patenting provided the reference application or patent either is shown to be commonly owned with the examined application, or claims an invention made as a result of activities undertaken within the scope of a joint research agreement. See MPEP § 717.02 for applications subject to examination under the first inventor to file provisions of the AIA as explained in MPEP § 2159. See MPEP § 2146 et seq. for applications not subject to examination under the first inventor to file provisions of the AIA . A terminal disclaimer must be signed in compliance with 37 CFR 1.321(b).
The filing of a terminal disclaimer by itself is not a complete reply to a nonstatutory double patenting (NSDP) rejection. A complete reply requires that the terminal disclaimer be accompanied by a reply requesting reconsideration of the prior Office action. Even where the NSDP rejection is provisional the reply must be complete. See MPEP § 804, subsection I.B.1. For a reply to a non-final Office action, see 37 CFR 1.111(a). For a reply to final Office action, see 37 CFR 1.113(c). A request for reconsideration while not provided for in 37 CFR 1.113(c) may be filed after final for consideration. See MPEP §§ 706.07(e) and 714.13.
The USPTO Internet website contains terminal disclaimer forms which may be used. Please visit www.uspto.gov/patent/patents-forms. The actual filing date of the application in which the form is filed determines what form (e.g., PTO/SB/25, PTO/SB/26, PTO/AIA /25, or PTO/AIA /26) should be used. A web-based eTerminal Disclaimer may be filled out completely online using web-screens. An eTerminal Disclaimer that meets all requirements is auto-processed and approved immediately upon submission. For more information about eTerminal Disclaimers, refer to www.uspto.gov/patents/apply/applying-online/eterminal-disclaimer.
Claims 1-20 are rejected on the ground of nonstatutory double patenting as being unpatentable over claims 1-18 of U.S. Patent No. 11,837,002. Although the claims at issue are not identical, they are not patentably distinct from each other because instant set of claims are generally broader than that of the patent as provided below:
Instant application
Patent 11,837,002
1. A method, comprising: receiving, by a processor of a computer system, a text stream of data derived by an optical character recognition process from an image of a piece of content; detecting, by the processor of the computer system, a plurality of pieces of spatial information associated with the piece of content and
indicating a location of an empty table cell with missing text following an associated non-empty table cell having a particular word;
encoding, by the processor of the computer system, the plurality of pieces of spatial information into respective tokens comprising a first token containing the particular word and
associated pieces of spatial information separated by a delimiter and a second token containing a placeholder text for the missing text of the empty table cell and associated pieces of spatial information separated by the delimiter; and
using, by the processor of the computer system, the tokens on a machine learning model.
1. A method, comprising: receiving, by a processor of a computer system, a text stream of data derived by an optical character recognition process from an image of a piece of content; detecting, by the processor of the computer system, a plurality of pieces of spatial information associated with the piece of content, wherein the plurality of pieces of spatial information represents hierarchical spatial information indicative of relative locations of respective particular words within the piece of content, and wherein the hierarchical spatial information is further indicative of a location of an empty table cell, with missing text, following an associated non-empty table cell having a corresponding particular word;
encoding, by the processor of the computer system, each of the plurality of pieces of spatial information into a respective token associated with a respective particular word, each respective token containing the respective particular word,
or a placeholder text for the missing text of the empty table cell, and associated hierarchical spatial information, each piece of the associated hierarchical spatial information being separated by a delimiter; generating, by the processor of the computer system, a plurality of numerical spatial features based on the encoded plurality of pieces of spatial information, wherein the plurality of numerical spatial features includes a plurality of numerical values representing the respective particular words and the empty table cell; inputting, by the processor of the computer system, the plurality of numerical spatial features into a machine learning model; and performing, by the processor of the computer system, the machine learning model using the plurality of numerical spatial features.
Claim Rejections - 35 USC § 103
The following is a quotation of 35 U.S.C. 103 which forms the basis for all obviousness rejections set forth in this Office action:
A patent for a claimed invention may not be obtained, notwithstanding that the claimed invention is not identically disclosed as set forth in section 102, if the differences between the claimed invention and the prior art are such that the claimed invention as a whole would have been obvious before the effective filing date of the claimed invention to a person having ordinary skill in the art to which the claimed invention pertains. Patentability shall not be negated by the manner in which the invention was made.
Claims 1-20 are rejected under 35 U.S.C. 103 as being unpatentable over Calapodescu et al. (US 2017/0300565) in view of Dejean et al. (US 2015/0169510).
Claim 1
Calapodescu teaches a method, comprising: receiving, by a processor of a computer system, a text stream of data derived by an optical character recognition process from an image of a piece of content ([0040] The system 30 receives as input a text document 10, such as a resume, for processing. The resume may be an electronic document such as a Word document, or a scanned paper document. In the case of a scanned document, the document may be preprocessed, either by the system or elsewhere, using optical character recognition to extract the text content.);
detecting, by the processor of the computer system, a plurality of pieces of spatial information associated with the piece of content ([0042] The segmentation component 50 (optional) segments the document 10 into sections 18, e.g., based on document structure, such as lines between rows of text, section titles, paragraph breaks, combinations thereof, and the like. In one embodiment, the section starts are identified using a categorizer which is applied on each line of text. The categorizer may be, for example, a Probabilistic latent semantic analysis (PLSA) model trained on a set of section classes, such as the five classes: experience, education, skills, other, and none). In one embodiment the categorizer is trained to detect the beginning of each section, for example, by classifying each line as being a title or not.) and
indicating a location of an empty table cell with missing text following an associated non-empty table cell having a particular word ([0052] incomplete clusters Ci; For example, Citigroup is not detected in window 96 of Fig. 7, following the group chunk “Financial Analysis Dept” of the window 96 and following the window 94. [0104], The first example 94 is the search window of a complete sample and the second one 96 is the search window of an incomplete one (missing organization); [0127] trained CRF model is used to label chunks of the text windows corresponding to the incomplete clusters. Examiner notes this indicates ORGM chunk of trained CRF model is used to label corresponding text window where “Citigroup” would be in the incomplete clusters. [0128] For example, in the case of FIG. 8, the CRF model 78 may learn a pattern that includes the features JOB DATE NL UPP GRP NL UPP ORGM NL from complete clusters and thus is able to predict that the uppercase chunk Citigroup on the third line of the incomplete cluster window 96 is an organization-type entity.);
encoding, by the processor of the computer system, the plurality of pieces of spatial information into respective tokens comprising a first token containing the particular word and associated pieces of spatial information separated by a delimiter ([0043], Component 52 may be a conventional entity extraction component which has been trained to label entities 12, 14, 16, etc., in the text that fall within one of a predefined set of entity classes, such as at least two or at least three or at least four entity classes. The entity extraction component 50 may be a rule based extraction system or based on a probabilistic model, such as a Conditional Random Field (CRF) system, or a combination thereof. A suitable rule-based system 52 includes a parser which applies rules for tokenizing the text to form a sequence of tokens (generally, words), applying morphological tags (in particular, parts of speech, such as noun, verb, adjective, etc.), identifying noun clusters, and labeling the nouns/noun clusters with entity tags using, for example, an entity resource, such as a lexicon 60 of entities, in which the entities may each be labeled according to one of a predefined set of entity classes. In this case, the extraction of the first set of entities may include accessing the lexicon of entities and identifying text sequences (one or more tokens) in the section which each match a respective entity in the lexicon; Notes as provided above [0019] Entities 12, 14, 16, etc., to be extracted,…tend to be grouped or clustered together (location wise) and that each entity/word is tokenized with label/tag/location indicator; [0048]-[0052], [0048] The first entity extraction component 52 also identifies a location of each of the extracted entities, e.g., with offset precision or other location indicator. For example, each character (including spaces between tokens) is indexed in sequence. Each entity can then be located by its first index and its length. For example, entity 14, classed as City/State, may have the location: index 19, length 13. The output of the first entity extraction component 52 is a list 61 of extracted entities and respective entity classes and associated location information. Examiner notes each entity corresponds to a token with spatial features such as location indicators. See also [0107]-[0113], [0107] The chunker component 65 may employ tokenization and syntactic and semantic features provided by a syntactic parser 52, such as the Xerox Incremental Parser (XIP), in addition to the results of the first extraction component 52 to split the text into chunks. In the exemplary embodiment, a chunk can be:… [0111], separators may be used for chunking: [0112] (period, comma, parenthesis, quotes, etc.)); and
using, by the processor of the computer system, the tokens on a machine learning model ([0057], [0154]-[0155]; S128 of Fig. 3; [0154] The entities extracted from the resumes can be used to learn a classifier model, e.g., a binary classifier, for distinguishing between good and bad resumes.).
Calapodescu teaches utilization of delimiters as provided above ([0111], separators may be used for chunking: [0112] (period, comma, parenthesis, quotes, etc.)). Still Calapodescu may not clearly detail a second token containing a placeholder text for the missing text of the empty table cell.
Dejean teaches a second token containing a placeholder text for the missing text of the empty table cell ([0120] the clayout model is used to provide one or more missing elements of the structure and/or correct improper tagging of one or more elements. The clayout model is used to process all sdata and missing tags are added to lines which were not tagged. [0129], incomplete sdata elements are selected and the method attempts to complete the sdata elements using neighbor elements while using the generated layout structure to determine the neighborhood. Focusing on the top, bottom, left, and right of the layout structure, missing fields may be captured.)
Thus it would have been obvious to one of ordinary skill in the art before the effective filing date of the invention to incorporate placeholder for missing text of the empty table cell as taught by Dejean with the entity extraction method of Calapodescu, because doing so would have provided combining the layout structures and the tagged elements, so that layout models for representing the structured data are inferred for the current page. These models are used to correct or tag some elements missed by the tagging step. Finally a set of structured data is extracted ([0038] of Dejean).
Claim 2
The combination teaches the method of claim 1, the detecting of the plurality of pieces of spatial information further comprising: detecting, by the processor of the computer system, the empty table cell in the piece of content ([0127] of Calapodescu, incomplete clusters).
Claim 3
The combination teaches the method of claim 2, further comprising: inserting, by the processor of the computer system, the placeholder text into the detected empty table cell in place of the missing text ([0095] of Dejean, some elements may have no features, such as element 7 (table cell 7 of multiple table cells 1-8 of Fig. 10); See Table 1, element/cell 7 ‘[]’).
Claim 4
The combination teaches the method of claim 1, the using of the tokens on the machine learning model comprising: performing, by the processor of the computer system, an information extraction machine learning process to extract data from the piece of content (abstract of Calapodescu, Patterns for extracting new entities are learned based on the complete clusters. New entities are extracted from incomplete clusters based on the learned patterns.).
Claim 5
The combination teaches the method of claim 4, the performing of the information extraction machine learning process further comprising: receiving, by the processor of the computer system, another text stream from the optical character recognition process of a form; and extracting, by the processor of the computer system, words from the form using the information extraction machine learning process ([0003] of Calapodescu, the content of the sections may have many different forms (list of structured paragraphs, tables, full sentences or list of words).).
Claim 6
The combination teaches the method of claim 1, the using of the tokens on the machine learning model comprising: performing, by the processor of the computer system, an information extraction using a bidirectional long short term memory machine learning model process to extract data from a form ([0004] of Calapodescu, The UIMA Ruta rule-based system for information extraction and general natural language processing is described as well as machine learning techniques based on Conditional Random Fields (CRF) and extensions. [0131] of Calapodescu, As an alternative to a CRF model 78, a deep-neural network architecture can be used for extraction of features, such as a Recurrent Neural Network (RNN) using a Long Short Term Memory (LSTM) architecture.).
Claim 7
The combination teaches the method of claim 1, the using of the tokens on the machine learning model comprising: performing, by the processor of the computer system, an information extraction using a conditional random field machine learning model process to extract data from a form ([0004] of Calapodescu, The UIMA Ruta rule-based system for information extraction and general natural language processing is described as well as machine learning techniques based on Conditional Random Fields (CRF) and extensions.).
Claim 8
The combination teaches the method of claim 1, the detecting of the plurality of pieces of spatial information comprising: detecting, by the processor of the computer system, the plurality of pieces of spatial information as hierarchical spatial information ([0019] of Calapodescu, In accordance with another aspect of the exemplary embodiment, a method for extracting entities from a resume includes segmenting the resume into sections. A first set of entities and respective entity class labels is extracted from the section with at least one of grammar rules, a probabilistic model, and a lexicon. At least a subset of the extracted entities in the first set is clustered into clusters, based on locations of the entities in the resume. [0036] FIG. 1 illustrates part of a loosely-structured document 10, such as a resume. Entities 12, 14, 16, etc., to be extracted,…tend to be grouped or clustered together (location wise). In this example, four clusters 20, 22, 24, 26 of entities are seen and, in each entity cluster, the entities are semantically related (i.e., the date corresponds to the job title and to the company name of the cluster).).
Claim 9
The combination teaches the method of claim 1, the detecting of the plurality of pieces of spatial information comprising: detecting, by the processor of the computer system, the plurality of pieces of spatial information as hierarchical spatial information comprising spatial information about a page of the piece of content, spatial information about a table cell in the page of the piece of content, spatial information about a paragraph in the table cell of the piece of content, spatial information about a line in the paragraph of the piece of content and spatial information about a word in the line of the piece of content ([0003] of Calapodescu, While a resume is a well-defined document, with fairly standard sections (personal information, education, experience, etc.), the format and presentation may vary widely. Also, multiple file formats are possible (PDF, Microsoft Office Word document, text file, html, etc.), the order of the sections may vary (e.g., the education section may be at the beginning or at the end), and the content of the sections may have many different forms (list of structured paragraphs, tables, full sentences or list of words). [0042] The segmentation component 50 (optional) segments the document 10 into sections 18, e.g., based on document structure, such as lines between rows of text, section titles, paragraph breaks).
Claim 10
The combination teaches the method of claim 1, the encoding of the plurality of pieces of spatial information comprising: generating, by the processor of the computer system, the first token as a spatial object token ([0019] of Calapodescu, In accordance with another aspect of the exemplary embodiment, a method for extracting entities from a resume includes segmenting the resume into sections. A first set of entities and respective entity class labels is extracted from the section with at least one of grammar rules, a probabilistic model, and a lexicon. At least a subset of the extracted entities in the first set is clustered into clusters, based on locations of the entities in the resume. [0043] of Calapodescu, A suitable rule-based system 52 includes a parser which applies rules for tokenizing the text to form a sequence of tokens (generally, words), applying morphological tags (in particular, parts of speech, such as noun, verb, adjective, etc.), identifying noun clusters, and labeling the nouns/noun clusters with entity tags using, for example, an entity resource, such as a lexicon 60 of entities, in which the entities may each be labeled according to one of a predefined set of entity classes. In this case, the extraction of the first set of entities may include accessing the lexicon of entities and identifying text sequences (one or more tokens) in the section which each match a respective entity in the lexicon.)
Claims 11-20
These claims recite substantially the same limitations as those provided in claims 1-10 respectively, and therefore they are rejected for the same reasons.
Conclusion
Any inquiry concerning this communication or earlier communications from the examiner should be directed to THOMAS H MAUNG whose telephone number is (571)270-5690. The examiner can normally be reached Monday-Friday, 9am-6pm, EST.
Examiner interviews are available via telephone, in-person, and video conferencing using a USPTO supplied web-based collaboration tool. To schedule an interview, applicant is encouraged to use the USPTO Automated Interview Request (AIR) at http://www.uspto.gov/interviewpractice.
If attempts to reach the examiner by telephone are unsuccessful, the examiner’s supervisor, Carolyn R. Edwards can be reached at 1-(571) 2707136. The fax phone number for the organization where this application or proceeding is assigned is 571-273-8300.
Information regarding the status of published or unpublished applications may be obtained from Patent Center. Unpublished application information in Patent Center is available to registered users. To file and manage patent submissions in Patent Center, visit: https://patentcenter.uspto.gov. Visit https://www.uspto.gov/patents/apply/patent-center for more information about Patent Center and https://www.uspto.gov/patents/docx for information about filing in DOCX format. For additional questions, contact the Electronic Business Center (EBC) at 866-217-9197 (toll-free). If you would like assistance from a USPTO Customer Service Representative, call 800-786-9199 (IN USA OR CANADA) or 571-272-1000.
/THOMAS H MAUNG/Primary Examiner, Art Unit 2692
/CAROLYN R EDWARDS/Supervisory Patent Examiner, Art Unit 2692