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 .
This action is in response to the application and claims filed 11/22/2023. Claims 1-12 are pending and have been examined. Claims 1-12 are rejected.
Priority
Applicant’s claim for the benefit of a prior-filed application under 35 U.S.C. 119(e) or under 35 U.S.C. 120, 121, 365(c), or 386(c) is acknowledged. The present application is a continuation of Application No. 17/849,292, filed 6/24/2022 (now U.S. patent number 11,853,905 B2), which is a continuation of Application No. 17/361,798, filed 6/29/2021 (now U.S. patent number 11,416,753 B1).
Specification
The disclosure is objected to because of the following informalities:
The use of the term Excel which is a trade name or mark used in commerce, has been noted in this application. It should be capitalized wherever it appears and be accompanied by the generic terminology. For instance, the term Excel appears in paragraph 15 of the specification.
Although the use of trade names and marks used in commerce (i.e., trademarks, service marks, certification marks, and collective marks) are permissible in patent applications, the proprietary nature of the marks should be respected and every effort made to prevent their use in any manner which might adversely affect their validity as commercial marks. Appropriate correction is required.
Claim Rejections - 35 USC § 112
The following is a quotation of 35 U.S.C. 112(b):
(b) CONCLUSION.—The specification shall conclude with one or more claims particularly pointing out and distinctly claiming the subject matter which the inventor or a joint inventor regards as the invention.
Claims 1-12 are rejected under 35 U.S.C. 112(b) as being indefinite for failing to particularly point out and distinctly claim the subject matter which the inventor or a joint inventor regards as the invention.
Independent claims 1 and 7 both recite “comparisons of information based on the page-specific feature values of adjacent pages of the training document bundles” (see, the last limitation of claims 1 and 7). Applicant previously introduced “training information”, “page-specific feature information”, “first page-specific feature information … and second page-specific feature information” in these claims (see, e.g., lines 7, 14 and 17-18 of claim 1). As such, it is unclear if the subsequently-recited “comparisons of information based on the page-specific feature values of adjacent pages of the training document bundles” refers to comparing one or more of the previously-introduced types of “information” to other “information based on the page-specific feature values of adjacent pages of the training document bundles”, to comparing “information based on the page-specific feature values of adjacent pages of the training document bundles” (i.e., excluding the previously-introduced types of “information”), or to some other information comparison. For examination purposes, recitations of “comparisons of information based on the page-specific feature values of adjacent pages of the training document bundles” in claims 1 and 7 have been interpreted as any “comparisons of information” where the information being compared is “based on the page-specific feature values of adjacent pages of the training document bundles”. Appropriate correction is required.
Claims 2 and 8 both recite “the page-specific feature vectors” (see, lines 3-4 of claim 2 and lines 2-3 of claim 8). These recitations lack antecedent basis. No “page-specific feature vectors” were previously introduced in these claims, or in their respective base claims, independent claims 1 and 7. For examination purposes, recitations of “the page-specific feature vectors” in claims 5 and 11 have been interpreted as any “page-specific feature vectors”. Appropriate correction is required.
Claims 5 and 11 both recite “the individual page-specific feature vectors” (see, lines 1 of claims 5 and 11). These recitations lack antecedent basis. No “individual page-specific feature vectors” were previously introduced in these claims, or in their respective base claims, independent claims 1 and 7. Claims 2 and 8 recite “the page-specific feature vectors”. However, claims 5 and 11 depend directly from claims 1 and 7, not claims 2 and 8. Further, as discussed above, there is insufficient antecedent basis for “the page-specific feature vectors” recited in claims 2 and 8. For examination purposes, recitations of “the individual page-specific feature vectors” in claims 5 and 11 have been interpreted as any “individual page-specific feature vectors”. Appropriate correction is required.
Claims 6 and 12, which depend directly from claims 2 and 8, respectively are rejected under 35 U.S.C. 112(b) as being indefinite under the same rationale as claims 2 and 8.
Also, claims 2-7 and 8-12, which depend directly or indirectly from claims 1 and 7, respectively are rejected under 35 U.S.C. 112(b) as being indefinite under the same rationale as claims 1 and 7.
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 1-12 are rejected on the ground of nonstatutory double patenting as being unpatentable over claims 1-2 and 5-6 of U.S. Patent No. 11,416,753 B1. Although the claims at issue are not identical, they are not patentably distinct from each other because all of the limitations of claims 1-12 in the present application are covered by claims 1-2 and 5-6 of U.S. Patent No. 11,416,753 B1 (please see the table below).
Regarding independent claims 1 and 7, claims 1 and 5 of U.S. Patent No. 11,416,753 B1 teach the claimed invention as shown in the table below.
Instant Application No. 18/517,849
(as filed 11/22/2023)
U.S. Patent No. 11,416,753 B1
1. A system configured to identify page breaks between adjacent documents within document bundles, wherein a document bundle is a combination of two or more separate documents, and wherein the document bundle is stored in a single electronic file, the system comprising:
one or more hardware processors configured by machine-readable instructions to:
obtain training information, wherein the training information includes training document bundles and corresponding document separation markers, wherein the training document bundles include a first training bundle combining at least a first document and a second document, wherein a document separation marker indicates a page break in the first training bundle between the first document and the second document, wherein the first document includes a first page, and wherein the second document includes a second page;
determine page-specific feature information pertaining to individual pages of the first training bundle, wherein the page-specific information pertaining to an individual page characterizes features of the individual page, and wherein the page-specific feature information includes first page-specific feature information pertaining to the first page and second page-specific feature information pertaining to the second page;
determine, based on the page-specific feature information, page-specific feature values for individual features of the individual pages of the first training bundle, wherein the page-specific feature values numerically represent the individual features of the individual pages, and wherein first page-specific feature values are determined for the first page based on the first page-specific feature information, and wherein second page-specific feature values are determined for the second page based on the second page-specific feature information; and
train a model through machine learning techniques, using the training document bundles, to make a determination whether the first page and the second page are part of different documents, wherein training the model includes comparisons of information based on the page-specific feature values of adjacent pages of the training document bundles1, and wherein training the model includes comparing the determination with the corresponding document separation markers.
1. A system configured to identify document transitions between adjacent documents within document bundles, wherein a document bundle is a combination of two or more separate documents, and wherein the document bundle is stored in a single electronic file, the system comprising:
one or more hardware processors configured by machine-readable instructions to:
obtain training information, wherein the training information includes training document bundles and corresponding document separation markers, wherein the training document bundles include a first training bundle combining at least a first document and a second document, wherein a document separation marker indicates where a document transition occurs, wherein a document transition is a page break in the first training bundle where the first document ends and the second document begins, wherein the first document includes a first page, and wherein the second document includes a second page;
determine page-specific feature information pertaining to individual pages of the first training bundle, wherein the page-specific information pertaining to an individual page characterizes features of the individual page for which feature information is obtained, and wherein the page-specific feature information includes first page-specific feature information pertaining to the first page and second page-specific feature information pertaining to the second page;
determine, based on the obtained page-specific feature information, page-specific feature values for individual features of the individual pages of the first training bundle, wherein the page-specific feature values numerically represent the individual features of the individual pages, and wherein first page-specific feature values are determined for the first page, based on the first page-specific feature information, and wherein second page-specific feature values are determined for the second page, based on the second page-specific feature information;
generate, for the individual pages of the first training bundle, a page-specific feature vector, such that a first page-specific feature vector pertaining to the first page is generated and is based on the first page-specific feature values, and a second page-specific feature vector pertaining to the second page is generated and is based on the second page-specific feature values, and wherein the individual page-specific feature vectors have a fixed dimension; and
train a model, using the training document bundles, to determine whether the first page and the second page are part of different documents, wherein training the model includes construction of a decision tree, wherein the decision tree is constructed based on comparisons of page pairs of the training document bundles, and wherein individual page pairs include a first page and a second page of the training document bundles, wherein the model makes a determination based on comparing the first page-specific feature vector and the second page-specific feature vector, wherein the first page-specific feature vector and the second page-specific feature vector have the same dimension, wherein a first set of bits at a given index of the first page-specific feature vector represents the same feature as a second set of bits at the given index of the second page-specific feature vector, and wherein the first set of bits and the second set of bits have the same bit length, and wherein training the model includes comparing the determination with the obtained corresponding document separation markers.
2. The system of claim 1, wherein the one or more hardware processors are further configured to:
generate, for the individual pages of the first training bundle, the page-specific feature vectors2, such that a first page-specific feature vector pertaining to the first page is generated and is based on the first page-specific feature values, and a second page-specific feature vector pertaining to the second page is generated and is based on the second page-specific feature values, wherein a first set of bits at a given index of the first page-specific feature vector represents the same feature as a second set of bits at the given index of the second page-specific feature vector,
wherein the information based on the page-specific feature values includes the page-specific feature vectors.
1. A system … comprising: one or more hardware processors configured by machine-readable instructions to: …
generate, for the individual pages of the first training bundle, a page-specific feature vector, such that a first page-specific feature vector pertaining to the first page is generated and is based on the first page-specific feature values, and a second page-specific feature vector pertaining to the second page is generated and is based on the second page-specific feature values, and wherein the individual page-specific feature vectors have a fixed dimension; …
determine, based on the obtained page-specific feature information, page-specific feature values for individual features of the individual pages, …
and wherein first page-specific feature values are determined for the first page, based on the first page-specific feature information, and wherein second page-specific feature values are determined for the second page, based on the second page-specific feature information;
wherein the first page-specific feature vector and the second page-specific feature vector have the same dimension, wherein a first set of bits at a given index of the first page-specific feature vector represents the same feature as a second set of bits at the given index of the second page-specific feature vector
3. The system of claim 1, wherein training the model includes construction of a decision tree based on the page-specific feature values.
1. A system … wherein training the model includes construction of a decision tree, wherein the decision tree is constructed based on comparisons of page pairs of the training document bundles, and wherein individual page pairs include a first page and a second page of the training document bundles, wherein the model makes a determination based on comparing the first page-specific feature vector and the second page-specific feature vector.
4. The system of claim 3, wherein the decision tree includes one or more nodes, wherein the nodes are separated into one or more tree levels, and wherein the comparisons of the information include traversing through the one or more tree levels of the decision tree.
2. The system of claim 1, wherein the decision tree includes one or more nodes, wherein the nodes are separated into one or more tree levels, and wherein comparisons between the first page-specific feature vector and the second page-specific feature vector include traversing through the one or more tree levels of the decision tree.
5. The system of claim 1, wherein the individual page-specific feature vectors have a fixed dimension.
1. A system configured to identify document transitions between adjacent documents … wherein the individual page-specific feature vectors have a fixed dimension
6. The system of claim 2, wherein the first set of bits and the second set of bits have the same bit length.
1. A system configured to identify document transitions between adjacent documents … wherein the first set of bits and the second set of bits have the same bit length
7. A method for identifying page breaks between adjacent documents within document bundles, wherein a document bundle is a combination of two or more separate documents, and wherein the document bundle is stored in a single electronic file, the method comprising:
obtaining training information, wherein the training information includes training document bundles and corresponding document separation markers, wherein the training document bundles include a first training bundle combining at least a first document and a second document, wherein a document separation marker indicates a page break in the first training bundle between the first document and the second document, wherein the first document includes a first page, and wherein the second document includes a second page;
determining page-specific feature information pertaining to individual pages of the first training bundle, wherein the page-specific information pertaining to an individual page characterizes features of the individual page, and wherein the page-specific feature information includes first page-specific feature information pertaining to the first page and second page-specific feature information pertaining to the second page;
determining, based on the page-specific feature information, page-specific feature values for individual features of the individual pages of the first training bundle, wherein the page-specific feature values numerically represent the individual features of the individual pages, and wherein first page-specific feature values are determined for the first page based on the first page-specific feature information, and wherein second page-specific feature values are determined for the second page based on the second page-specific feature information; and
training a model through machine learning techniques, using the training document bundles, to make a determination whether the first page and the second page are part of different documents, wherein training the model includes comparisons of information based on the page-specific feature values of adjacent pages of the training document bundles3, and wherein training the model includes comparing the determination with the corresponding document separation markers.
5. A method for identifying document transitions between adjacent documents within document bundles, wherein a document bundle is a combination of two or more separate documents, and wherein the document bundle is stored in a single electronic file, the method comprising:
obtaining training information, wherein the training information includes training document bundles and corresponding document separation markers, wherein the training document bundles include a first training bundle combining at least a first document and a second document, wherein a document separation marker indicates where a document transition occurs, wherein a document transition is a page break in the first training bundle where the first document ends and the second document begins, wherein the first document includes a first page, and wherein the second document includes a second page;
determining page-specific feature information pertaining to individual pages of the first training bundle, wherein the page-specific information pertaining to an individual page characterizes features of the individual page for which feature information is obtained, and wherein the page-specific feature information includes first page-specific feature information pertaining to the first page and second page-specific feature information pertaining to the second page;
determining, based on the obtained page-specific feature information, page-specific feature values for individual features of the individual pages of the first training bundle, wherein the page-specific feature values numerically represent the individual features of the individual pages, and wherein first page-specific feature values are determined for the first page, based on the first page-specific feature information, and wherein second page-specific feature values are determined for the second page, based on the second page-specific feature information;
generating, for the individual pages of the first training bundle, a page-specific feature vector, such that a first page-specific feature vector pertaining to the first page is generated based on the first page-specific feature values, and a second page-specific feature vector pertaining to the second page is generated based on the second page-specific feature values, and wherein the individual page-specific feature vectors have a fixed dimension; and
training a model, using the training document bundles, to determine whether the first page and the second page are part of different documents, wherein training the model includes construction of a decision tree, wherein the decision tree is constructed based on comparisons of page pairs of the training document bundles, wherein individual page pairs include a first page and a second page of the training document bundles, wherein the model makes a determination based on comparing the first page-specific feature vector and the second page-specific feature vector, wherein the first page-specific feature vector and the second page-specific feature vector have the same dimension, wherein a first set of bits at a given index of the first page-specific feature vector represents the same feature as a second set of bits at the given index of the second page-specific feature vector, and wherein the first set of bits and the second set of bits have the same bit length, and wherein training the model includes comparing the determination with the obtained corresponding document separation markers.
8. The method of claim 7, further comprising:
generating, for the individual pages of the first training bundle, the page-specific feature vectors4, such that a first page-specific feature vector pertaining to the first page is generated and is based on the first page-specific feature values, and a second page-specific feature vector pertaining to the second page is generated and is based on the second page-specific feature values, wherein a first set of bits at a given index of the first page-specific feature vector represents the same feature as a second set of bits at the given index of the second page-specific feature vector,
wherein the information based on the page-specific feature values includes the page-specific feature vectors.
5. A method for identifying document transitions … comprising: …
generating, for the individual pages of the first training bundle, a page-specific feature vector, such that a first page-specific feature vector pertaining to the first page is generated based on the first page-specific feature values, and a second page-specific feature vector pertaining to the second page is generated based on the second page-specific feature values, and wherein the individual page-specific feature vectors have a fixed dimension …
determine, based on the obtained page-specific feature information, page-specific feature values for individual features of the individual pages …
and wherein first page-specific feature values are determined for the first page, based on the first page-specific feature information, and wherein second page-specific feature values are determined for the second page, based on the second page-specific feature information; wherein the first page-specific feature vector and the second page-specific feature vector have the same dimension, wherein a first set of bits at a given index of the first page-specific feature vector represents the same feature as a second set of bits at the given index of the second page-specific feature vector
9. The method of claim 7, wherein training the model includes construction of a decision tree based on the page-specific feature values.
5. A method for identifying document transitions between adjacent documents: … wherein training the model includes construction of a decision tree, wherein the decision tree is constructed based on comparisons of page pairs of the training document bundles, wherein individual page pairs include a first page and a second page of the training document bundles, wherein the model makes a determination based on comparing the first page-specific feature vector and the second page-specific feature vector.
10. The method of claim 9, wherein the decision tree includes one or more nodes, wherein the nodes are separated into one or more tree levels, and wherein the comparisons of the information include traversing through the one or more tree levels of the decision tree.
6. The method of claim 5, wherein the decision tree includes one or more nodes, wherein the nodes are separated into one or more tree levels, and wherein comparisons between the first page-specific feature vector and the second page-specific feature vector include traversing through the one or more tree levels of the decision tree.
11. The method of claim 7, wherein the individual page-specific feature vectors have a fixed dimension.
5. A method for identifying document transitions between adjacent documents … wherein the individual page-specific feature vectors have a fixed dimension
12. The method of claim 7, wherein the first set of bits and the second set of bits
have the same bit length.
5. A method for identifying document transitions between adjacent documents … wherein the first set of bits and the second set of bits have the same bit length
As shown in the table above, claim 1 of U.S. Patent No. 11,416,753 encompasses the same subject matter as independent claim 1 of the instant application.
The table above uses the underlined text to highlight the similarities between the two applications and claims within, while the non-underlined text signifies the difference between the claim sets. Upon review of the non-underlined text, a person of ordinary skill in the art would concluded that the scope of the claim inventions are obvious variants of each other. To further expand on the above table, each claim listed above is either directly from the reference patent and/or obvious as explained below. Claims not directly referenced in the explanation below are believed to be adequately explained by the comparison chart above.
Regarding independent claims 1 and 7 of the instant application, the claim languages and scope are similar to one another aside from being directed to different statutory categories. The examiner points out the similarities between claim 1 of this application and claim 1 of the reference patent 11,416,753 in this office action for clarity but the reasoning, motivation(s), and rationale apply for claim 7 as well.
Regarding instant claim 1, the instant claim is substantially identical to claim 1 of the reference patent 11,416,753, except the instant claim 1 recites “A system configured to identify page breaks between adjacent documents within document bundles” and claim 1 of the reference patent 11,416,753 recites “A system configured to identify document transitions between adjacent documents within document bundles”. However, as shown in the table above, claim 1 of the reference patent 11,416,753 recites “wherein a document transition is a page break”. That is, the “page break” recited in instant claim 1 is an obvious variant of the “document transition” recited in claim 1 of the reference patent 11,416,753.
As further shown in the table above, the recited system components and limitations of instant claim 1 are largely identical to the components and limitations recited in system claim 1 of the reference patent 11,416,753 except that claim 1 of the reference patent additionally recites “generate, for the individual pages of the first training bundle, a page-specific feature vector, such that a first page-specific feature vector pertaining to the first page is generated and is based on the first page-specific feature values, and a second page-specific feature vector pertaining to the second page is generated and is based on the second page-specific feature values, and wherein the individual page-specific feature vectors have a fixed dimension; and … wherein training the model includes construction of a decision tree, … wherein the model makes a determination based on comparing the first page-specific feature vector and the second page-specific feature vector, wherein the first page-specific feature vector and the second page-specific feature vector have the same dimension, wherein a first set of bits at a given index of the first page-specific feature vector represents the same feature as a second set of bits at the given index of the second page-specific feature vector, and wherein the first set of bits and the second set of bits have the same bit length”. That is, instant claim 1 is a broader version of claim 1 of the reference patent and claim 1 of the reference patent encompasses the same subject matter as instant claim 1. As such, instant claim 1 is an obvious variation of claim 1 of the reference patent 11,416,753.
Similarly, regarding instant claim 7, this independent claim encompasses the claimed invention of independent claim 5 in the reference patent. As shown in the table above, the method steps of instant claim 7 are largely identical to the method steps of claim 5 of patent 11,416,753. As such, instant claim 7 is an obvious variation of claim 5 of the reference patent 11,416,753 because claim 5 of patent 11,416,753 is substantially identical to instant application claim 7 (please see the table above).
Therefore, instant application claims 1 and 7 are taught by claims 1 and 5, respectively, of U.S. Patent No. 11,416,753.
Regarding dependent claims 2-6, which each depend directly or indirectly from independent claim 1, claim 1 of U.S. Patent No. 11,416,753 teaches the limitations of claim 1 as described in the table above. Claims 1 and 2 of U.S. Patent No. 11,416,753 further teach the limitations of dependent claims 2-6 of the instant application (please see the table above).
Further regarding instant dependent claims 8-12, the instant claims 8-12 encompass the claimed invention of claims 5 and 6 in the reference patent. As such, instant claims 8-12 are obvious variations of claims 5 and 6 of patent 11,416,753 because claims 5 and 6 of patent 11,416,753 are substantially identical to instant application claims 8-12 (please see the table above).
Claims 1-12 are rejected on the ground of nonstatutory double patenting as being unpatentable over claims 1-2, 5-8 and 11-12 of U.S. Patent No. 11,853,905 B2. Although the claims at issue are not identical, they are not patentably distinct from each other because all of the limitations of claims 1-12 in the present application are covered by claims 1-2, 5-8 and 11-12 of U.S. Patent No. 11,853,905 B2 (please see the table below).
Regarding independent claims 1 and 7, claims 1 and 7 of U.S. Patent No. 11,853,905 B2 teach the claimed invention as shown in the table below.
Instant Application No. 18/517,849
(as filed 11/22/2023)
U.S. Patent No. 11,853,905 B2
1. A system configured to identify page breaks between adjacent documents within document bundles, wherein a document bundle is a combination of two or more separate documents, and wherein the document bundle is stored in a single electronic file, the system comprising:
one or more hardware processors configured by machine-readable instructions to:
obtain training information, wherein the training information includes training document bundles and corresponding document separation markers, wherein the training document bundles include a first training bundle combining at least a first document and a second document, wherein a document separation marker indicates a page break in the first training bundle between the first document and the second document, wherein the first document includes a first page, and wherein the second document includes a second page;
determine page-specific feature information pertaining to individual pages of the first training bundle, wherein the page-specific information pertaining to an individual page characterizes features of the individual page, and wherein the page-specific feature information includes first page-specific feature information pertaining to the first page and second page-specific feature information pertaining to the second page;
determine, based on the page-specific feature information, page-specific feature values for individual features of the individual pages of the first training bundle, wherein the page-specific feature values numerically represent the individual features of the individual pages, and wherein first page-specific feature values are determined for the first page based on the first page-specific feature information, and wherein second page-specific feature values are determined for the second page based on the second page-specific feature information; and
train a model through machine learning techniques, using the training document bundles, to make a determination whether the first page and the second page are part of different documents, wherein training the model includes comparisons of information based on the page-specific feature values of adjacent pages of the training document bundles5, and wherein training the model includes comparing the determination with the corresponding document separation markers.
1. A system configured to identify page breaks between adjacent documents within document bundles, wherein a document bundle is a combination of two or more separate documents, and wherein the document bundle is stored in a single electronic file, the system comprising:
one or more hardware processors configured by machine-readable instructions to:
obtain training information, wherein the training information includes training document bundles and corresponding document separation markers, wherein the training document bundles include a first training bundle combining at least a first document and a second document, wherein a document separation marker indicates a page break in the first training bundle between the first document and the second document, wherein the first document includes a first page, and wherein the second document includes a second page;
determine page-specific feature information pertaining to individual pages of the first training bundle, wherein the page-specific information pertaining to an individual page characterizes features of the individual page, and wherein the page-specific feature information includes first page-specific feature information pertaining to the first page and second page-specific feature information pertaining to the second page;
determine, based on the page-specific feature information, page-specific feature values for individual features of the individual pages of the first training bundle, wherein the page-specific feature values numerically represent the individual features of the individual pages, and wherein first page-specific feature values are determined for the first page based on the first page-specific feature information, and wherein second page-specific feature values are determined for the second page based on the second page-specific feature information;
generate, for the individual pages of the first training bundle, page-specific feature vectors, such that a first page-specific feature vector pertaining to the first page is generated and is based on the first page-specific feature values, and a second page-specific feature vector pertaining to the second page is generated and is based on the second page-specific feature values, wherein a first set of bits at a given index of the first page-specific feature vector represents the same feature as a second set of bits at the given index of the second page-specific feature vector; and
train a model, using the training document bundles, to determine whether the first page and the second page are part of different documents, wherein training the model includes construction of a decision tree, wherein the decision tree is constructed based on comparisons of the page-specific feature vectors of adjacent pages of the training document bundles, and wherein training the model includes comparing the determination with the corresponding document separation markers.
2. The system of claim 1, wherein the one or more hardware processors are further configured to:
generate, for the individual pages of the first training bundle, the page-specific feature vectors6, such that a first page-specific feature vector pertaining to the first page is generated and is based on the first page-specific feature values, and a second page-specific feature vector pertaining to the second page is generated and is based on the second page-specific feature values, wherein a first set of bits at a given index of the first page-specific feature vector represents the same feature as a second set of bits at the given index of the second page-specific feature vector,
wherein the information based on the page-specific feature values includes the page-specific feature vectors.
1. A system … comprising: one or more hardware processors configured by machine-readable instructions to: …
generate, for the individual pages of the first training bundle, page-specific feature vectors, such that a first page-specific feature vector pertaining to the first page is generated and is based on the first page-specific feature values, and a second page-specific feature vector pertaining to the second page is generated and is based on the second page-specific feature values, wherein a first set of bits at a given index of the first page-specific feature vector represents the same feature as a second set of bits at the given index of the second page-specific feature vector … and wherein first page-specific feature values are determined for the first page based on the first page-specific feature information, and wherein second page-specific feature values are determined for the second page based on the second page-specific feature information
3. The system of claim 1, wherein training the model includes construction of a decision tree based on the page-specific feature values.
1. A system … wherein training the model includes construction of a decision tree, wherein the decision tree is constructed based on comparisons of the page-specific feature vectors of adjacent pages of the training document bundles
4. The system of claim 3, wherein the decision tree includes one or more nodes, wherein the nodes are separated into one or more tree levels, and wherein the comparisons of the information include traversing through the one or more tree levels of the decision tree.
2. The system of claim 1, wherein the decision tree includes one or more nodes, wherein the nodes are separated into one or more tree levels, and wherein the comparisons of the page-specific feature vectors include traversing through the one or more tree levels of the decision tree.
5. The system of claim 1, wherein the individual page-specific feature vectors7 have a fixed dimension.
5. The system of claim 1, wherein the individual page-specific feature vectors have a fixed dimension.
6. The system of claim 2, wherein the first set of bits and the second set of bits have the same bit length.
6. The system of claim 1, wherein the first set of bits and the second set of bits have the same bit length.
7. A method for identifying page breaks between adjacent documents within document bundles, wherein a document bundle is a combination of two or more separate documents, and wherein the document bundle is stored in a single electronic file, the method comprising:
obtaining training information, wherein the training information includes training document bundles and corresponding document separation markers, wherein the training document bundles include a first training bundle combining at least a first document and a second document, wherein a document separation marker indicates a page break in the first training bundle between the first document and the second document, wherein the first document includes a first page, and wherein the second document includes a second page;
determining page-specific feature information pertaining to individual pages of the first training bundle, wherein the page-specific information pertaining to an individual page characterizes features of the individual page, and wherein the page-specific feature information includes first page-specific feature information pertaining to the first page and second page-specific feature information pertaining to the second page;
determining, based on the page-specific feature information, page-specific feature values for individual features of the individual pages of the first training bundle, wherein the page-specific feature values numerically represent the individual features of the individual pages, and wherein first page-specific feature values are determined for the first page based on the first page-specific feature information, and wherein second page-specific feature values are determined for the second page based on the second page-specific feature information; and
training a model through machine learning techniques, using the training document bundles, to make a determination whether the first page and the second page are part of different documents, wherein training the model includes comparisons of information based on the page-specific feature values of adjacent pages of the training document bundles8, and wherein training the model includes comparing the determination with the corresponding document separation markers.
7. A method for identifying page breaks between adjacent documents within document bundles, wherein a document bundle is a combination of two or more separate documents, and wherein the document bundle is stored in a single electronic file, the method comprising:
obtaining training information, wherein the training information includes training document bundles and corresponding document separation markers, wherein the training document bundles include a first training bundle combining at least a first document and a second document, wherein a document separation marker indicates a page break in the first training bundle between the first document and the second document, wherein the first document includes a first page, and wherein the second document includes a second page;
determining page-specific feature information pertaining to individual pages of the first training bundle, wherein the page-specific information pertaining to an individual page characterizes features of the individual page, and wherein the page-specific feature information includes first page-specific feature information pertaining to the first page and second page-specific feature information pertaining to the second page;
determining, based on the page-specific feature information, page-specific feature values for individual features of the individual pages of the first training bundle, wherein the page-specific feature values numerically represent the individual features of the individual pages, and wherein first page-specific feature values are determined for the first page based on the first page-specific feature information, and wherein second page-specific feature values are determined for the second page based on the second page-specific feature information;
generating, for the individual pages of the first training bundle, page-specific feature vectors, such that a first page-specific feature vector pertaining to the first page is generated based on the first page-specific feature values, and a second page-specific feature vector pertaining to the second page is generated based on the second page-specific feature values, wherein a first set of bits at a given index of the first page-specific feature vector represents the same feature as a second set of bits at the given index of the second page-specific feature vector; and
training a model, using the training document bundles, to determine whether the first page and the second page are part of different documents, wherein training the model includes construction of a decision tree, wherein the decision tree is constructed based on comparisons of the page-specific feature vectors of adjacent pages of the training document bundles, and wherein training the model includes comparing the determination with the corresponding document separation markers.
8. The method of claim 7, further comprising:
generating, for the individual pages of the first training bundle, the page-specific feature vectors9, such that a first page-specific feature vector pertaining to the first page is generated and is based on the first page-specific feature values, and a second page-specific feature vector pertaining to the second page is generated and is based on the second page-specific feature values, wherein a first set of bits at a given index of the first page-specific feature vector represents the same feature as a second set of bits at the given index of the second page-specific feature vector,
wherein the information based on the page-specific feature values includes the page-specific feature vectors.
7. A method for identifying page breaks … comprising: …
generating, for the individual pages of the first training bundle, page-specific feature vectors, such that a first page-specific feature vector pertaining to the first page is generated based on the first page-specific feature values, and a second page-specific feature vector pertaining to the second page is generated based on the second page-specific feature values, wherein a first set of bits at a given index of the first page-specific feature vector represents the same feature as a second set of bits at the given index of the second page-specific feature vector; and
… and wherein first page-specific feature values are determined for the first page based on the first page-specific feature information, and wherein second page-specific feature values are determined for the second page based on the second page-specific feature information
9. The method of claim 7, wherein training the model includes construction of a decision tree based on the page-specific feature values.
7. A method for identifying page breaks … wherein training the model includes construction of a decision tree, wherein the decision tree is constructed based on comparisons of the page-specific feature vectors of adjacent pages of the training document bundles
10. The method of claim 9, wherein the decision tree includes one or more nodes, wherein the nodes are separated into one or more tree levels, and wherein the comparisons of the information include traversing through the one or more tree levels of the decision tree.
8. The method of claim 7, wherein the decision tree includes one or more nodes, wherein the nodes are separated into one or more tree levels, and wherein the comparisons of the page-specific feature vectors include traversing through the one or more tree levels of the decision tree.
11. The method of claim 7, wherein the individual page-specific feature vectors10 have a fixed dimension.
11. The method of claim 7, wherein the individual page-specific feature vectors have a fixed dimension.
12. The method of claim 7, wherein the first set of bits and the second set of bits
have the same bit length