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 .
Response to Applicants Arguments/Amendments
Applicant’s arguments, see page 1, filed 7/22/2026, with respect to double patenting have been fully considered and are persuasive. The double patenting rejections has all been withdrawn. Applicant has filed a terminal disclaimer to remove the rejection
Applicant's arguments filed 7/22/2026 with respect to 35 U.S.C. 101 have been fully considered but they are not persuasive.
Applicant argues “The claims cannot practically be performed in the human mind because of the arrangement of the operations they require. Claim 1 requires two separate operations performed upon the same image — operation b), inferring at least one classification based upon the at least one image, and operation c), performing optical character recognition on the at least one image — each producing its own result, followed by operation d), in which a SKU is associated with the package based upon the results of both. The Office Action maps these limitations to a series of discrete mental acts: a "mental model" inference, a separate act of "mentally performing character recognition on the object," and a mental association based upon the two. Office Action at 17–18. But the human mind cannot practically work that way. A person examining a package does not infer a classification of the package separately from reading the text appearing on the package, produce two distinct results, and then perform a further act of associating a SKU with the package based upon those two results; for a human observer, reading the text on a package is an integrated, inseparable part of recognizing the package. The Office Action's limitation-by-limitation mapping thus assumes a decomposition of human cognition that human cognition does not practically permit. At a minimum, a deliberately staged, multi-pass mental protocol in which an observer first classifies a package, then separately performs "character recognition" upon it as a distinct act with a distinct result, and then reconciles the two work products, is not a practical performance of the claimed operations in the human mind, and practical performance is the governing standard. MPEP § 2106.04(a)(2)(III).”
The examiner disagrees one of ordinary skill in the art could have easily performed image recognition and text recognition separately. Applicants assertion that humans do not typically perform mental classification and character recognition separately is mere allegation. Humans use various features including shape color ect to identify objects and these are not the same processes as reading text. For example a person in a could easily recognize the shape/color of an object then read the item to verify it’s the item they suspected the examiner believes this would not be an unusual way for a brain to operate. Further even if assuming applicant was correct (to which the examiner does not agree) that humans don’t typically operate this way there is nothing that would make it impossible for a person to perform these steps mentally.
Applicant further argues: As the specification explains, a machine-learning classifier operating alone can misidentify visually similar products. The specification describes, with reference to Figure 14A, an example in which the machine-learning model infers that a package face is a 32-pack of 16.9 oz bottles at 52% confidence and a 24-pack at only 33% confidence — but optical character recognition performed in parallel on the same package face detects the text "24," a keyword associated with the 24-pack, and the system therefore overrides the classification in favor of the 24-pack at high confidence. Figure 14C describes a corresponding example in which detected text ("GREEN") causes a lower-confidence brand inference to be augmented and selected over an incorrect higher-confidence inference. See also Figures 27A and 27B and the accompanying description in [00121-22], [00127-29], [00263-72]. The claimed combination — inferring a classification with a trained machine-learning model, performing optical character recognition on the same image, and making the association or determination based upon both — thus improves the accuracy of the automated identification itself. The improvement flows precisely from the separateness of the two claimed operations discussed above, which has no analogue in human cognition: because the optical character recognition supplies a result generated apart from the machine-learning inference, it is capable of correcting or augmenting that inference. That is an improvement in the functioning of the technology, not a use of a computer as a mere tool.
The Office Action's Prong Two analysis considers the additional elements only individually, characterizing the processor, media, machine-learning model, and optical character recognition each as generic. The eligibility inquiry, however, also requires consideration of the additional elements in ordered combination. BASCOM Global Internet Servs., Inc. v. AT&T Mobility LLC, 827 F.3d 1341, 1349–50 (Fed. Cir. 2016). The claimed arrangement — machine-learning inference and optical character recognition operating on the same image, with the final association based upon both — is precisely the non-conventional arrangement that the specification identifies as producing the accuracy improvement, and the Office Action does not address it.”
The examiner disagree applicant is merely using well known computer components as a tool to perform the abstract idea. The idea of recognizing and object via image features then using reding it to confirm is part of the abstract idea. Here applicant is using substantially the abstract idea as the “additional elements” which incorporate the abstract idea into. The additional elements amount to no more then generic computer components, combined with generic computer processes OCR and machine learning, which are used as tools to perform the abstract idea. The claims do not recite a specific computer implemented object recognition algorithm e.g. a specific computer implemented neural network improved with a specific OCR algorithm, applicant combines merely mental steps of classification and text recognition. A generic computer, OCR and machine learning are used as tools to implement the abstract idea.
Applicant's arguments filed 7/22/2026 with respect to 35 U.S.C. 102 have been fully considered but they are not persuasive.
Applicant argues that “For operation d), the Office Action relies on paragraph [0209] of Voegele. Office Action at 38. Paragraph [0209] describes a "second image processing operation" in a warehouse pallet-profiling system, and states in relevant part:
The second image processing operation can include, for example, identifying details on the contents and cases included on the pallet, such as text, markings, codes, and/or other labeling on the cases. The second image processing operations can aim to identify, specifically, what is included in the pallet, such as the specific skus that are contained in the pallet, the number of cases of each sku, date information associated with each case, and/or other salient information . . . . The second image processing operation can process all images captured of the pallet for a second time, but with using differing image processing techniques, such as using OCR and/or machine learning models, and/or other text/object detection algorithms.
Applicant does not dispute that the phrase "OCR and/or machine learning models" encompasses, as one alternative, the use of both OCR and machine learning models somewhere within the second image processing operation. However, the claims require more. The claims require that the association of the SKU (claim 1) or the determination of the classification (claims 18 and 33) be made based upon both the machine-learning inference and the optical character recognition. Paragraph [0209] discloses, at most, a collection of alternative image-processing techniques that "can" be employed to identify several different kinds of information — SKUs, case counts, date information, and "other salient information." Voegele does not disclose that any single identification, much less the identification of a SKU, is made based upon both a classification inferred by a machine learning model and the results of optical character recognition. Nothing in Voegele describes combining the output of a machine-learning inference with the output of optical character recognition to perform an identification or a classification.
Paragraph [0178] of Voegele, also cited by the Office Action, describes an image analysis module that "can be trained using one or more machine learning models to identify different types of labels from the image data" and that "can also be configured to perform object detection techniques and optical character recognition (OCR)." These are parallel capabilities of the module. Voegele never discloses that any particular determination is made using both capabilities together, arranged as required by operation d).”
The examiner disagrees the examiner notes that both machine learning and OCR are used to perform “identify, specifically, what is included in the pallet, such as the specific skus that are contained in the pallet” “ with using differing image processing techniques such as using OCR and/or machine learning models, and/or other text/object detection algorithms”. Specification OCR and machine learning are used to perform text detection and object detection [i.e. object classification] to determine the SKU of produces on the pallet. Further paragraph 178 describes operations of the “image analysis module” which is part of system 100 which performs the processes described in paragraph 209.
Applicant's arguments filed 7/22/2026 with respect to Claims 3, 7, 8, 11, 15, 17, 20, 21, 25, 28, and 31 rejected under 35 U.S.C. § 103 as obvious over Voegele in view of Martin Jr have been fully considered but they are not persuasive. Applicants arguments/amendments filed rely on applicant arguments with respect to 35 U.S.C. 102 which were found not persuasive. Therefore these arguments are also not persuasive.
Applicant's arguments filed 7/22/2026 with respect to 35 U.S.C. § 103 as obvious over Voegele in view of Martin Jr., Jindal (U.S. 2022/0261579), and Hogg (U.S. 2022/0318773) have been fully considered but they are not persuasive.
Applicant argues “the extracted text from the identified objects in the captured scene is compared to the inputted name of the target object to determine if any of the identified objects are a match. . . . In some other embodiments, the extracted text is used from only those identified objects having sufficiently matching label vectors where one or more classification labels match to one or more classification labels associated with the target object.
Jindal is an augmented-reality shopping application in which a user types the name of a product the user wishes to locate on a store shelf. A neural network identifies objects in the captured video scene and outputs, for each identified object, a "label vector" — a set of classification labels, inferred by the network, that describe the object (e.g., "jar," "purple," "jelly" for grape jelly). See Jindal at ¶ [0026]. The cited passage thus describes two comparisons, and neither is the comparison recited in operation g). The second sentence describes a filtering step in which the classification labels inferred for the identified objects are compared to classification labels associated with the target object, i.e. a comparison of classifications with classifications, involving no optical character recognition results. This is performed so that, as Jindal explains, "textual comparison is not needed for those objects that are clearly different from the target object." The first sentence describes the textual comparison itself, in which the extracted text is compared to "the inputted name of the target object" (the user's external query) involving no classification. At no point does Jindal compare the extracted text with the classification inferred for the object from which the text was extracted, or with any inferred classification at all.
Operation g) of claim 16, by contrast, requires comparing the results of the optical character recognition of operation c) with "the inferred at least one classification" (the classification inferred in operation b) using the at least one machine learning model from the at least one image of the package). That comparison is not disclosed in Jindal. Nor does the Office Action's gloss that "text associated with a classification is compared with the text of the OCR" (Office Action at 52) bridge the gap: the inputted name of the target object is the user's query, and it is neither the classification inferred for any identified object nor text associated with that inferred classification. Jindal therefore does not teach or suggest operation g) of claim 16 or step g) of claim 32.”
The examiner disagrees with applicants’ characterization of Jindal and the combination. The examiner note that “the extracted text is used from only those identified objects having sufficiently matching label vectors where one or more classification labels match to one or more classification labels associated with the target object.” The examiner notes that the inputted text is text associated with the inferred classification. Before matching with the text the Jindal determines which products are a match to the target object represented by the inputted text. Then compare text of the objects inferred to possible be target object and matches it to input text of the target object.
Applicant further argues:
Claim 16 further recites, “h) comparing the results of operation c) with the expected SKU" (the particular expected SKU received in operation e) of claim 15, against which the associated SKU is compared in operation f)). Claim 32 recites a similar step with respect to an expected classification. For this limitation, the Office Action relies on paragraph [0048] of Hogg, asserting that "OCR is compared to known structures of SKU." Office Action at 52. Paragraph [0048] of Hogg states in relevant part:
For example, the image files may be subjected to an OCR operation to identify the various strings present in the image file. The strings may then be compared to either known structures of SKUs (or UPCs, GTINs, etc) or to known product names used by the retailer at which the transaction was conducted, in order to collect the set of strings identifying items (operation 480).
Hogg describes performing optical character recognition on an image of a consumer's purchase receipt and comparing the extracted strings to "known structures of SKUs,” i.e., to generic SKU formats, in order to sort which strings on the receipt identify items at all, and to discard strings (dates, addresses, marketing text) that do not. Comparing extracted text against a generic identifier format to parse a receipt is not comparing the optical character recognition results with "the expected SKU," a specific, previously received value expected for the package. Hogg's cited disclosure involves no expected SKU for any package, and indeed no package at all. The Office Action's interpretation that "the two pieces of information are compared" reads the words "the expected SKU" out of the claim.
The examiner disagrees with applicant characterizations of the combination. The examiner notes that the expected SKU corresponds known SKU structure used by the retailer at which the transaction was conducted, which are compared to the OCR present in an image. The examiner note that expected SKU is a very broad term which could encompass a known structure used by a retailer. The examiner further notes that Martain JR already disclosed the expected SKU. Hogg discloses OCR data to expected SKU data.
Applicant further argues “A reference qualifies as prior art for an obviousness determination only when it is analogous to the claimed invention — that is, when the reference is from the same field of endeavor as the claimed invention, or, if not, when the reference is reasonably pertinent to the particular problem with which the inventor is involved. In re Bigio, 381 F.3d 1320, 1325 (Fed. Cir. 2004); In re Klein, 647 F.3d 1343, 1348 (Fed. Cir. 2011). Hogg is neither. Hogg is directed to a "System and Method for a Payment Card-Based Execution of a Multiparty Transaction Involving Electronic Funds Disbursement," a platform by which a lease-to-own or subscription company reconciles a consumer's payment-card checkout against the items covered by the consumer's arrangement, using a photograph of the store receipt. That is not the field of computer-vision identification of packages, and a payment-reconciliation platform that parses shopping receipts is not reasonably pertinent to the problem confronting the present inventors: accurately identifying the SKU of a physical package from images of the package. A person of ordinary skill seeking to improve machine-vision package identification would have had no reason to look to a lease-to-own payment-processing system.”
The examiner disagrees Hogg solves a similar problem of extracting SKU data as Vogels and Martin Jr. and is therefore analogous art. Further they are in the same field of optical character recognition. One of ordinary skill in the art
Applicant’s arguments with respect to claim(s) new claim 34 have been considered but are moot because the new ground of rejection does not rely on any reference applied in the prior rejection of record for any teaching or matter specifically challenged in the argument. Applicant merely states that these new claims are allowable over the prior art. Applicant’s arguments do not address the new grounds of rejection applied to the new claims nor do they argue and specific references.
Applicant further argues:
Finally, the rejection does not articulate a reason, supported by rational underpinning, why a person of ordinary skill in the art would have combined the four cited references. KSR Int'l Co. v. Teleflex Inc., 550 U.S. 398, 418 (2007); MPEP § 2143. "[O]bviousness concerns whether a skilled artisan not only could have made but would have been motivated to make the combinations or modifications of prior art to arrive at the claimed invention." Belden Inc. v. Berk-Tek LLC, 805 F.3d 1064, 1073 (Fed. Cir. 2015) (emphasis in original); see also ActiveVideo Networks, Inc. v. Verizon Commc'ns, Inc., 694 F.3d 1312, 1328 (Fed. Cir. 2012) (rejecting conclusory motivation reasoning).
As to Jindal, the Office Action reasons that one of ordinary skill "could have easily modified the combination of Voegele and Martin Jr with teaching of Jindal," that the results "would have been predictable," and that "[t]hese elements perform the same function in combination as they do separately as the combination on[ly] requires an additional comparison of data." Office Action at 51–52. That is not articulated reasoning. It is just a statement that the modification was possible and would not have broken anything. No reason to make the modification is identified.
Jindal is a consumer augmented-reality shopping application whose comparisons exist to answer a shopper's query. The user inputs the name of a desired product, and Jindal compares text extracted from objects on a store shelf to that inputted name, which is filtered by classification labels so that "textual comparison is not needed for those objects that are clearly different from the target object," in order to locate the target for the shopper. Jindal's technique, as disclosed, is thus structured entirely around an externally supplied target query. Voegele is an industrial warehouse system that profiles arriving pallets of goods. There is no consumer, there is no inputted target name, and there is no query to answer. The Office Action does not explain what, in Voegele's pallet-profiling operation, would play the role of Jindal's inputted target name; what problem, need, or design incentive in the Voegele/Martin system the modification would address; or why a person of ordinary skill designing a warehouse receiving system would look to a consumer shelf-search application at all. The observation that the combination merely "requires an additional comparison of data" identifies no reason to perform that additional comparison.
As to Hogg, the Office Action reasons only that "[o]ne of ordinary skill in the art could have easily compared OCR data to a expected SKU and the results (i.e. the two pieces of information are compared) would have been predictable." Office Action at 52. The same deficiency applies: possibility and predictability are not motivation. The Office Action identifies no problem, need, or design incentive that would have led the skilled artisan to assemble a warehouse pallet-profiling system (Voegele), a beverage-distribution validation system (Martin), an augmented-reality retail shopping application (Jindal), and a consumer payment-reconciliation platform (Hogg).
The examiner notes that “Teaching suggestion motivation“ rational cited by applicant is only one of the rationales available to demonstrate obviousness. Not every rational requires a motivation as describe by applicant.
See MPEP 2143: The Supreme Court in KSR Int'l Co. v. Teleflex Inc., 550 U.S. 398, 415-421, 82 USPQ2d 1385, 1395-97 (2007) identified a number of rationales to support a conclusion of obviousness which are consistent with the proper "functional approach" to the determination of obviousness as laid down in Graham. The key to supporting any rejection under 35 U.S.C. 103 is the clear articulation of the reason(s) why the claimed invention would have been obvious. The Supreme Court in KSR noted that the analysis supporting a rejection under 35 U.S.C. 103 should be made explicit. In Ball Aerosol v. Ltd. Brands, 555 F.3d 984, 89 USPQ2d 1870 (Fed. Cir. 2009), the Federal Circuit offered additional instruction as to the need for an explicit analysis. The Federal Circuit explained that the Supreme Court’s requirement for an explicit analysis does not require record evidence of an explicit teaching of a motivation to combine in the prior art.
The examiner was using the rational “Combining prior art elements according to known methods to yield predictable results rational” See MPEP 2143.
Further the examiner notes in the Jindal combination the examiner is merely combining the notion of comparing extracted text of a product to expected text based on classification. This is a simple concept that could easily be combined with Vogel to compare the extracted text of Vogel with expected text based on classification. Jindal and Vogels and Martin Jr and are all related to identifying products in an image.
Terminal Disclaimer
The terminal disclaimer filed on 8/14/2026 disclaiming the terminal portion of any patent granted on this application which would extend beyond the expiration date of 11783606 11972624 has been reviewed and is accepted. The terminal disclaimer has been recorded.
Claim Rejections - 35 USC § 101
35 U.S.C. 101 reads as follows:
Whoever invents or discovers any new and useful process, machine, manufacture, or composition of matter, or any new and useful improvement thereof, may obtain a patent therefor, subject to the conditions and requirements of this title.
Claim 1-47 are rejected under 35 U.S.C. 101 because the claimed invention is directed to an abstract idea without significantly more.
Re claim 1
The limitation at least one model that has been trained with a plurality of images of packages, as drafted, is a process that, under its broadest reasonable interpretation, covers performance of the limitation in the mind. For example, a trained model in the context of this claim encompasses the user having a mental model trained on packages.
The limitation receiving at least one image of the package, as drafted, is a process that, under its broadest reasonable interpretation, covers performance of the limitation in the mind. For example, receiving and image in the context of this claim encompasses the user mentally looking at an image to receive it in the brain.
The limitation using the at least one model, inferring at least one classification based upon the at least one image, as drafted, is a process that, under its broadest reasonable interpretation, covers performance of the limitation in the mind. For example, using a model to infer in the context of this claim encompasses the user mentally inferring based on a mental model.
The limitation performing character recognition on the at least one image, as drafted, is a process that, under its broadest reasonable interpretation, covers performance of the limitation in the mind. For example, performing character recognition in the context of this claim encompasses the user mentally performing character recognition on the object.
The limitation associating one of a plurality of SKUs with the package based upon operations b) and c), as drafted, is a process that, under its broadest reasonable interpretation, covers performance of the limitation in the mind. For example, associated in the context of this claim encompasses the user mentally making the association
If a claim limitation, under its broadest reasonable interpretation, covers performance of the limitation in the mind but for the recitation of generic computer components, then it falls within the “Mental Processes” grouping of abstract ideas. Accordingly, the claim recites an abstract idea.
This judicial exception is not integrated into a practical application. In particular, the claim only recites additional elements –
at least one processor; and at least one non-transitory computer-readable media storing at least one processor; and at least one non-transitory computer-readable media storing: at least one machine learning model at least one processor; and at least one non-transitory computer-readable media storing: at least one machine learning model; and instructions that, when executed by the at least one processor, cause the computing system to perform the method; and Optical Character recognition.
The processor and non-transitory computer-readable media are recited at a high-level of generality (i.e., as a generic processor performing a generic computer function and a generic computer readable medium storing instructions for performing generic processing functions)) such that it amounts no more than mere instructions to apply the exception using generic computer components. The machine learning model is merely a generic learning model that only limits the judicial exception to the field of machine learning. Optical character recognition is a well-known function of using a computer to recognize text in images simply used as a tool to perform the abstract idea. Accordingly, this additional element does not integrate the abstract idea into a practical application because it does not impose any meaningful limits on practicing the abstract idea. The claim is directed to an abstract idea.
The claim does not include additional elements that are sufficient to amount to significantly more than the judicial exception. As discussed above with respect to integration of the abstract idea into a practical application, the additional element of using a processor and non-transitory computer readable media to perform steps amounts to no more than mere instructions to apply the exception using a generic computer component. The machine learning model is merely a generic learning model that only limits the judicial exception to the field of machine learning. Optical character recognition is a well-known function of using a computer to recognize text in images simply used as a tool to perform the abstract idea. Mere instructions to apply an exception using generic computer components combined with the generic concepts of OCR and machine learning cannot provide an inventive concept. The claim is not patent eligible.
Re claim 2 the limitation “wherein the at least one image of the package includes a plurality of images of the package, each of a different one of a plurality of package faces of the package”, as drafted, is a process that, under its broadest reasonable interpretation, covers performance of the limitation in the mind. For example, received images in the context of this claim encompasses the user mentally receiving a plurality of images by looking at them.
The analysis for this claim with respect to integration into an abstract idea and significantly more are not meaningfully different from the claim from which this claim depends.
Re claim 3 the limitation” wherein operation b) includes inferring at least one of a plurality of brands independently for each of the plurality of package faces”, as drafted, is a process that, under its broadest reasonable interpretation, covers performance of the limitation in the mind. For example, inferring in the context of this claim encompasses the user mentally making an inference.
The analysis for this claim with respect to integration into an abstract idea and significantly more are not meaningfully different from the claim from which this claim depends.
Re claim 4 the limitation “wherein the plurality of package faces includes a first package face and a second package face, wherein operation b) includes inferring a first plurality of brands based upon the first package face and inferring a second plurality of brands based upon the second package face, wherein the inference based upon the first package face is performed independently of the inference of the second package face.”, as drafted, is a process that, under its broadest reasonable interpretation, covers performance of the limitation in the mind. For example, inferring in the context of this claim encompasses the user mentally making the inferences.
The analysis for this claim with respect to integration into an abstract idea and significantly more are not meaningfully different from the claim from which this claim depends.
Re claim 5 the limitation wherein operation b) includes inferring at least one of a plurality of package types independently for each of the plurality of package faces, as drafted, is a process that, under its broadest reasonable interpretation, covers performance of the limitation in the mind. For example, inferring in the context of this claim encompasses the user mentally making the inferences.
The analysis for this claim with respect to integration into an abstract idea and significantly more are not meaningfully different from the claim from which this claim depends.
Re claim 6 the limitation of the limitation wherein operation b) includes inferring a first plurality of package types based upon the first package face and inferring a second plurality of package types based upon the second package face, wherein the inference of the first plurality of package types is performed independently of the inference of the second plurality of package types, as drafted, is a process that, under its broadest reasonable interpretation, covers performance of the limitation in the mind. For example, inferring in the context of this claim encompasses the user mentally making the inferences.
The analysis for this claim with respect to integration into an abstract idea and significantly more are not meaningfully different from the claim from which this claim depends.
Re claim 7 the limitation wherein operation b) includes inferring the at least one classification for each of the plurality of images of the packages independently of one another, as drafted, is a process that, under its broadest reasonable interpretation, covers performance of the limitation in the mind. For example, inferring in the context of this claim encompasses the user mentally making the inferences.
The analysis for this claim with respect to integration into an abstract idea and significantly more are not meaningfully different from the claim from which this claim depends.
Re claim 8 the limitation wherein the package contains a plurality of beverage containers and wherein the at least one model is trained on a plurality of images of packages of beverage containers., as drafted, is a process that, under its broadest reasonable interpretation, covers performance of the limitation in the mind. For example, training a model in the context of this claim encompasses the user mentally training a mental model using the images.
The analysis for this claim with respect to integration into an abstract idea and significantly more are not meaningfully different from the claim from which this claim depends.
Re claim 9 the limitation determining a best classification independently for each of the plurality of images based upon the inference of the at least one classification and the optical character recognition of the image, as drafted, is a process that, under its broadest reasonable interpretation, covers performance of the limitation in the mind. For example, determining a classification in the context of this claim encompasses the user mentally determining the best classification.
The analysis for this claim with respect to integration into an abstract idea and significantly more are not meaningfully different from the claim from which this claim depends.
Re claim 10 the limitation wherein operation d) is performed based upon the best classifications of the plurality of images, as drafted, is a process that, under its broadest reasonable interpretation, covers performance of the limitation in the mind. For example, performing operation d in the context of this claim encompasses the user mentally associating a SKU with the package.
The analysis for this claim with respect to integration into an abstract idea and significantly more are not meaningfully different from the claim from which this claim depends.
Re claim 11 the limitation wherein operation b) includes inferring at least one of a plurality of package types independently for each of the plurality of package faces, as drafted, is a process that, under its broadest reasonable interpretation, covers performance of the limitation in the mind. For example, inferring package types in the context of this claim encompasses the user mentally making inferences.
The analysis for this claim with respect to integration into an abstract idea and significantly more are not meaningfully different from the claim from which this claim depends.
Re claim 12 the limitation wherein the plurality of package faces includes a first package face and a second package face, wherein operation b) includes inferring a first plurality of package types based upon the first package face and inferring a second plurality of package types based upon the second package face, wherein the inference based upon the first package face is performed independently of the inference of the second package face, as drafted, is a process that, under its broadest reasonable interpretation, covers performance of the limitation in the mind. For example, inferring in the context of this claim encompasses the user mentally making inferences.
The analysis for this claim with respect to integration into an abstract idea and significantly more are not meaningfully different from the claim from which this claim depends.
Re claim 13 the limitation wherein the at least one classification is a plurality of classifications and wherein operation b) includes inferring each of the plurality of classifications at a confidence level, and wherein the operations further include augmenting at least one of the confidence levels associated with the plurality of classifications based upon operation c) and wherein operation d) is performed based upon the at least one augmented confidence level, as drafted, is a process that, under its broadest reasonable interpretation, covers performance of the limitation in the mind. For example, inferring classification, augmenting classification and associating an SKU in the context of this claim encompasses the user mentally inferring a classification mentally changing a classification and mentally determining an SKU.
The analysis for this claim with respect to integration into an abstract idea and significantly more are not meaningfully different from the claim from which this claim depends.
Re claim 14 the limitation wherein the package contains a plurality of beverage containers and wherein the at least one machine model is trained on a plurality of images of packages of beverage containers, as drafted, is a process that, under its broadest reasonable interpretation, covers performance of the limitation in the mind. For example, training a model in the context of this claim encompasses the user mentally training a mentally model based on the claimed images.
The analysis for this claim with respect to integration into an abstract idea and significantly more are not meaningfully different from the claim from which this claim depends.
Re claim 15 the limitation e) receiving an expected SKU; and f) comparing the associated one of the plurality of SKUs with the expected SKU., as drafted, is a process that, under its broadest reasonable interpretation, covers performance of the limitation in the mind. For example, receiving a expected SKU and comparing it in the context of this claim encompasses the user mentally learning of an expected SKU and comparing it to the inferred one.
The analysis for this claim with respect to integration into an abstract idea and significantly more are not meaningfully different from the claim from which this claim depends.
Re claim 16 the limitation wherein the operations further include: g) comparing results of operation c) with the inferred at least one classification; and h) comparing the results of operation c) with the expected SKU., as drafted, is a process that, under its broadest reasonable interpretation, covers performance of the limitation in the mind. For example, comparing in the context of this claim encompasses the user mentally making comparisons.
The analysis for this claim with respect to integration into an abstract idea and significantly more are not meaningfully different from the claim from which this claim depends.
Re claim 17 the limitation wherein the package contains a plurality of beverage containers and wherein the at least one model is trained on a plurality of images of packages of beverage containers., as drafted, is a process that, under its broadest reasonable interpretation, covers performance of the limitation in the mind. For example, training a model in the context of this claim encompasses the user mentally training a mental model using the claimed images.
The analysis for this claim with respect to integration into an abstract idea and significantly more are not meaningfully different from the claim from which this claim depends.
Re claim 18
the limitation “a) receiving in at least one computer at least one image of the package”, as drafted, is a process that, under its broadest reasonable interpretation, covers performance of the limitation in the mind. For example, receiving and image in the context of this claim encompasses the user mentally looking at an image to receive it in the brain.
The limitation using at least one learning model to infer at least one inferred classification based upon each of the at least one image, as drafted, is a process that, under its broadest reasonable interpretation, covers performance of the limitation in the mind. For example, using a model to infer in the context of this claim encompasses the user mentally inferring based on a mental model.
The limitation performing optical character recognition on the at least one image, as drafted, is a process that, under its broadest reasonable interpretation, covers performance of the limitation in the mind. For example, performing character recognition in the context of this claim encompasses the user mentally performing character recognition on the object.
The limitation determining the classification of the package based upon steps b) and c), as drafted, is a process that, under its broadest reasonable interpretation, covers performance of the limitation in the mind. For example, associated in the context of this claim encompasses the user mentally making classification.
If a claim limitation, under its broadest reasonable interpretation, covers performance of the limitation in the mind but for the recitation of generic computer components, then it falls within the “Mental Processes” grouping of abstract ideas. Accordingly, the claim recites an abstract idea.
This judicial exception is not integrated into a practical application. In particular, the claim only recites additional elements –
A computer to perform the method; at least one machine learning model and Optical Character recognition.
The computer is recited at a high-level of generality (i.e., a generic computer performing generic processing functions)) such that it amounts no more than mere instructions to apply the exception using generic computer components. The machine learning model is merely a generic learning model that only limits the judicial exception to the field of machine learning. Optical character recognition is a well-known function of using a computer to recognize text in images simply used as a tool to perform the abstract idea. Accordingly, this additional element does not integrate the abstract idea into a practical application because it does not impose any meaningful limits on practicing the abstract idea. The claim is directed to an abstract idea.
The claim does not include additional elements that are sufficient to amount to significantly more than the judicial exception. As discussed above with respect to integration of the abstract idea into a practical application, the additional element of using a computer to perform steps amounts to no more than mere instructions to apply the exception using a generic computer component. The machine learning model is merely a generic learning model that only limits the judicial exception to the field of machine learning. Optical character recognition is a well-known function of using a computer to recognize text in images simply used as a tool to perform the abstract idea. Mere instructions to apply an exception using generic computer components combined with the generic concepts of OCR and machine learning cannot provide an inventive concept. The claim is not patent eligible.
Re claim 19 the limitation “wherein the at least one image of the package includes a plurality of images of the package, each of a different one of a plurality of package faces of the package”, as drafted, is a process that, under its broadest reasonable interpretation, covers performance of the limitation in the mind. For example, received images in the context of this claim encompasses the user mentally receiving a plurality of images by looking at them.
The analysis for this claim with respect to integration into an abstract idea and significantly more are not meaningfully different from the claim from which this claim depends.
Re claim 20 the limitation wherein the package contains a plurality of beverage containers and wherein the at least one model is trained on a plurality of images of packages of beverage containers., as drafted, is a process that, under its broadest reasonable interpretation, covers performance of the limitation in the mind. For example, training a model in the context of this claim encompasses the user mentally training a mental model using the images.
The analysis for this claim with respect to integration into an abstract idea and significantly more are not meaningfully different from the claim from which this claim depends.
Re claim 21 the limitation” wherein operation b) includes inferring at least one of a plurality of brands independently for each of the plurality of package faces”, as drafted, is a process that, under its broadest reasonable interpretation, covers performance of the limitation in the mind. For example, inferring in the context of this claim encompasses the user mentally making an inference.
The analysis for this claim with respect to integration into an abstract idea and significantly more are not meaningfully different from the claim from which this claim depends.
Re claim 22 the limitation “wherein the plurality of package faces includes a first package face and a second package face, wherein step b) includes inferring a first plurality of brands based upon the first package face and inferring a second plurality of brands based upon the second package face, wherein the inference based upon the first package face is performed independently of the inference of the second package face.”, as drafted, is a process that, under its broadest reasonable interpretation, covers performance of the limitation in the mind. For example, inferring in the context of this claim encompasses the user mentally making the inferences.
The analysis for this claim with respect to integration into an abstract idea and significantly more are not meaningfully different from the claim from which this claim depends.
Re claim 23 the limitation wherein step b) includes inferring at least one of a plurality of package types independently for each of the plurality of package faces, as drafted, is a process that, under its broadest reasonable interpretation, covers performance of the limitation in the mind. For example, inferring in the context of this claim encompasses the user mentally making the inferences.
The analysis for this claim with respect to integration into an abstract idea and significantly more are not meaningfully different from the claim from which this claim depends.
Re claim 24 the limitation of the limitation wherein step b) includes inferring a first plurality of package types based upon the first package face and inferring a second plurality of package types based upon the second package face, wherein the inference of the first plurality of package types is performed independently of the inference of the second plurality of package types, as drafted, is a process that, under its broadest reasonable interpretation, covers performance of the limitation in the mind. For example, inferring in the context of this claim encompasses the user mentally making the inferences.
The analysis for this claim with respect to integration into an abstract idea and significantly more are not meaningfully different from the claim from which this claim depends.
Re claim 25 the limitation wherein step b) includes inferring the at least one classification for each of the plurality of images of the packages independently of one another, as drafted, is a process that, under its broadest reasonable interpretation, covers performance of the limitation in the mind. For example, inferring in the context of this claim encompasses the user mentally making the inferences.
The analysis for this claim with respect to integration into an abstract idea and significantly more are not meaningfully different from the claim from which this claim depends.
Re claim 26 the limitation determining a best classification independently for each of the plurality of images based upon the inference of the at least one classification and the optical character recognition of the image, as drafted, is a process that, under its broadest reasonable interpretation, covers performance of the limitation in the mind. For example, determining a classification in the context of this claim encompasses the user mentally determining the best classification.
The analysis for this claim with respect to integration into an abstract idea and significantly more are not meaningfully different from the claim from which this claim depends.
Re claim 27 the limitation wherein step d) is performed based upon the best classifications of the plurality of images, as drafted, is a process that, under its broadest reasonable interpretation, covers performance of the limitation in the mind. For example, performing operation d in the context of this claim encompasses the user mentally associating a SKU with the package.
The analysis for this claim with respect to integration into an abstract idea and significantly more are not meaningfully different from the claim from which this claim depends.
Re claim 28 the limitation wherein step b) includes inferring at least one of a plurality of package types independently for each of the plurality of package faces, as drafted, is a process that, under its broadest reasonable interpretation, covers performance of the limitation in the mind. For example, inferring package types in the context of this claim encompasses the user mentally making inferences.
The analysis for this claim with respect to integration into an abstract idea and significantly more are not meaningfully different from the claim from which this claim depends.
Re claim 29 the limitation wherein the plurality of package faces includes a first package face and a second package face, wherein step b) includes inferring a first plurality of package types based upon the first package face and inferring a second plurality of package types based upon the second package face, wherein the inference based upon the first package face is performed independently of the inference of the second package face, as drafted, is a process that, under its broadest reasonable interpretation, covers performance of the limitation in the mind. For example, inferring in the context of this claim encompasses the user mentally making inferences.
The analysis for this claim with respect to integration into an abstract idea and significantly more are not meaningfully different from the claim from which this claim depends.
Re claim 30 the limitation wherein the at least one classification is a plurality of classifications and wherein step b) includes inferring each of the plurality of classifications at a confidence level, and wherein the method further include augmenting at least one of the confidence levels associated with the plurality of classifications based upon step c) and wherein step d) is performed based upon the at least one augmented confidence level, as drafted, is a process that, under its broadest reasonable interpretation, covers performance of the limitation in the mind. For example, inferring classification, augmenting classification and associating an SKU in the context of this claim encompasses the user mentally inferring a classification mentally changing a classification and mentally determining an SKU.
The analysis for this claim with respect to integration into an abstract idea and significantly more are not meaningfully different from the claim from which this claim depends.
Re claim 31 e) receiving an expected classification; and f) comparing the classification of the package determined in step d) with the expected classification, as drafted, is a process that, under its broadest reasonable interpretation, covers performance of the limitation in the mind. For example, receiving a expected classification and comparing it in the context of this claim encompasses the user mentally learning of an expected classification and comparing it to the inferred one.
Re claim 32 the limitation including: g) comparing results of step c) with the inferred at least one classification; and h) comparing the results of step c) with the expected classification, as drafted, is a process that, under its broadest reasonable interpretation, covers performance of the limitation in the mind. For example, comparing in the context of this claim encompasses the user mentally making comparisons.
The analysis for this claim with respect to integration into an abstract idea and significantly more are not meaningfully different from the claim from which this claim depends.
Re claim 33
The limitation at least one model that has been trained with a plurality of images of packages, as drafted, is a process that, under its broadest reasonable interpretation, covers performance of the limitation in the mind. For example, a trained model in the context of this claim encompasses the user having a mental model trained on packages.
The limitation receiving at least one image of the package, as drafted, is a process that, under its broadest reasonable interpretation, covers performance of the limitation in the mind. For example, receiving and image in the context of this claim encompasses the user mentally looking at an image to receive it in the brain.
The limitation using the at least one model, inferring at least one classification based upon the at least one image, as drafted, is a process that, under its broadest reasonable interpretation, covers performance of the limitation in the mind. For example, using a model to infer in the context of this claim encompasses the user mentally inferring based on a mental model.
The limitation performing character recognition on the at least one image, as drafted, is a process that, under its broadest reasonable interpretation, covers performance of the limitation in the mind. For example, performing character recognition in the context of this claim encompasses the user mentally performing character recognition on the object.
The limitation determining the classification of the package based upon operations b) and c), as drafted, is a process that, under its broadest reasonable interpretation, covers performance of the limitation in the mind. For example, associated in the context of this claim encompasses the user mentally making the association
If a claim limitation, under its broadest reasonable interpretation, covers performance of the limitation in the mind but for the recitation of generic computer components, then it falls within the “Mental Processes” grouping of abstract ideas. Accordingly, the claim recites an abstract idea.
This judicial exception is not integrated into a practical application. In particular, the claim only recites additional elements –
at least one processor; and at least one non-transitory computer-readable media storing at least one processor; and at least one non-transitory computer-readable media storing: at least one machine learning model at least one processor; and at least one non-transitory computer-readable media storing: at least one machine learning model; and instructions that, when executed by the at least one processor, cause the computing system to perform the method; and Optical Character recognition.
The processor and non-transitory computer-readable media are recited at a high-level of generality (i.e., as a generic processor performing a generic computer function and a generic computer readable medium storing instructions for performing generic processing functions)) such that it amounts no more than mere instructions to apply the exception using generic computer components. The machine learning model is merely a generic learning model that only limits the judicial exception to the field of machine learning. Optical character recognition is a well-known function of using a computer to recognize text in images simply used as a tool to perform the abstract idea. Accordingly, this additional element does not integrate the abstract idea into a practical application because it does not impose any meaningful limits on practicing the abstract idea. The claim is directed to an abstract idea.
The claim does not include additional elements that are sufficient to amount to significantly more than the judicial exception. As discussed above with respect to integration of the abstract idea into a practical application, the additional element of using a processor and non-transitory computer readable media to perform steps amounts to no more than mere instructions to apply the exception using a generic computer component. The machine learning model is merely a generic learning model that only limits the judicial exception to the field of machine learning. Optical character recognition is a well-known function of using a computer to recognize text in images simply used as a tool to perform the abstract idea. Mere instructions to apply an exception using generic computer components combined with the generic concepts of OCR and machine learning cannot provide an inventive concept. The claim is not patent eligible.
Re claim 34
The limitation at least one model that has been trained with a plurality of images of packages, as drafted, is a process that, under its broadest reasonable interpretation, covers performance of the limitation in the mind. For example, a trained model in the context of this claim encompasses the user having a mental model trained on packages.
The limitation receiving at least one image of the package, as drafted, is a process that, under its broadest reasonable interpretation, covers performance of the limitation in the mind. For example, receiving and image in the context of this claim encompasses the user mentally looking at an image to receive it in the brain.
The limitation applying the at least one image to the at least one learning model, as drafted, is a process that, under its broadest reasonable interpretation, covers performance of the limitation in the mind. For example, applying a model in the context of this claim encompasses the user having a mental model and applying it.
The limitation identifying a plurality of classifications based upon a result of operation, as drafted, is a process that, under its broadest reasonable interpretation, covers performance of the limitation in the mind. For example, identifying in the context of this claim encompasses the user mentally identifying classifications
The limitation performing character recognition on the at least one image, as drafted, is a process that, under its broadest reasonable interpretation, covers performance of the limitation in the mind. For example, performing character recognition in the context of this claim encompasses the user mentally performing character recognition on the object.
The limitation selecting one of the plurality of classifications as the classification associated with the package based at least in part upon operation d), as drafted, is a process that, under its broadest reasonable interpretation, covers performance of the limitation in the mind. For example, selection in the context of this claim encompasses the user mentally making the association by selecting.
If a claim limitation, under its broadest reasonable interpretation, covers performance of the limitation in the mind but for the recitation of generic computer components, then it falls within the “Mental Processes” grouping of abstract ideas. Accordingly, the claim recites an abstract idea.
This judicial exception is not integrated into a practical application. In particular, the claim only recites additional elements –
at least one processor; and at least one non-transitory computer-readable media storing at least one processor; and at least one non-transitory computer-readable media storing: at least one machine learning model at least one processor; and at least one non-transitory computer-readable media storing: applying a machine learning model and instructions that, when executed by the at least one processor, cause the computing system to perform the method; and Optical Character recognition.
The processor and non-transitory computer-readable media are recited at a high-level of generality (i.e., as a generic processor performing a generic computer function and a generic computer readable medium storing instructions for performing generic processing functions)) such that it amounts no more than mere instructions to apply the exception using generic computer components. The machine learning model is merely a generic learning model that only limits the judicial exception to the field of machine learning. Optical character recognition is a well-known function of using a computer to recognize text in images simply used as a tool to perform the abstract idea. Accordingly, this additional element does not integrate the abstract idea into a practical application because it does not impose any meaningful limits on practicing the abstract idea. The claim is directed to an abstract idea.
The claim does not include additional elements that are sufficient to amount to significantly more than the judicial exception. As discussed above with respect to integration of the abstract idea into a practical application, the additional element of using a processor and non-transitory computer readable media to perform steps amounts to no more than mere instructions to apply the exception using a generic computer component. The machine learning model is merely a generic learning model that only limits the judicial exception to the field of machine learning. Optical character recognition is a well-known function of using a computer to recognize text in images simply used as a tool to perform the abstract idea. Mere instructions to apply an exception using generic computer components combined with the generic concepts of OCR and machine learning cannot provide an inventive concept. The claim is not patent eligible.
Re claim 35 The limitation wherein the at least one image of the package includes a plurality of images, each of the plurality of images being of a different one of a plurality of package faces of the package, as drafted, is a process that, under its broadest reasonable interpretation, covers performance of the limitation in the mind. For example, the limitation in the context of this claim encompasses the user mentally looking at image of various package faces.
The analysis for this claim with respect to integration into an abstract idea and significantly more are not meaningfully different from the claim from which this claim depends.
Re claim 36 The limitation wherein operations b) and c) are performed independently for each of the plurality of images, as drafted, is a process that, under its broadest reasonable interpretation, covers performance of the limitation in the mind. For example, the limitation in the context of this claim encompasses the user mentally evaluating a plurality of images independently to generate a plurality of classifications.
The analysis for this claim with respect to integration into an abstract idea and significantly more are not meaningfully different from the claim from which this claim depends.
Re claim 37 The limitation includes comparing text identified in operation d) to a plurality of keywords, each of the plurality of keywords being associated with at least one of the plurality of classifications, and augmenting a confidence level associated with each classification for which the text matches or partially matches an associated keyword, as drafted, is a process that, under its broadest reasonable interpretation, covers performance of the limitation in the mind. For example, the limitation in the context of this claim encompasses the user mentally performing the comparisons with keywords.
The analysis for this claim with respect to integration into an abstract idea and significantly more are not meaningfully different from the claim from which this claim depends.
Re claim 38 The limitation wherein the at least one image of the package includes a plurality of images, each of the plurality of images being of a different one of a plurality of package faces of the package, wherein operations b), c), and d) are performed for each of the plurality of images, and wherein operation e) includes comparing confidence levels, including the at least one augmented confidence level, of the classifications identified for the plurality of package faces and selecting the one of the plurality of classifications having a highest confidence level, as drafted, is a process that, under its broadest reasonable interpretation, covers performance of the limitation in the mind. For example, the limitation in the context of this claim encompasses the user mentally evaluating a plurality of images and comparing confidence levels.
The analysis for this claim with respect to integration into an abstract idea and significantly more are not meaningfully different from the claim from which this claim depends.
Re claim 39 The limitation wherein of) receiving an expected classification of the package; and g) comparing text identified in operation d) to at least one keyword associated with the expected classification, as drafted, is a process that, under its broadest reasonable interpretation, covers performance of the limitation in the mind. For example, the limitation in the context of this claim encompasses the user mentally evaluating a plurality of images independently to generate a plurality of classifications.
The analysis for this claim with respect to integration into an abstract idea and significantly more are not meaningfully different from the claim from which this claim depends.
Re claim 40 The limitation associating the expected classification with the package based upon operation g)., as drafted, is a process that, under its broadest reasonable interpretation, covers performance of the limitation in the mind. For example, the limitation in the context of this claim encompasses the user mentally performing an association.
The analysis for this claim with respect to integration into an abstract idea and significantly more are not meaningfully different from the claim from which this claim depends.
Re claim 41 The limitation wherein the operations further include associating one of a plurality of SKUs with the package based upon the classification selected in operation e)., as drafted, is a process that, under its broadest reasonable interpretation, covers performance of the limitation in the mind. For example, the limitation in the context of this claim encompasses the user mentally performing an association.
The analysis for this claim with respect to integration into an abstract idea and significantly more are not meaningfully different from the claim from which this claim depends.
Re claim 42
The limitation at least one model that has been trained with a plurality of images of packages, as drafted, is a process that, under its broadest reasonable interpretation, covers performance of the limitation in the mind. For example, a trained model in the context of this claim encompasses the user having a mental model trained on packages.
The limitation receiving a plurality of images of the package, each of the plurality of images being of a different one of a plurality of package faces of the package, as drafted, is a process that, under its broadest reasonable interpretation, covers performance of the limitation in the mind. For example, receiving and image in the context of this claim encompasses the user mentally looking at an image to receive it in the brain.
The limitation applying each of the plurality of images to the at least one learning model, as drafted, is a process that, under its broadest reasonable interpretation, covers performance of the limitation in the mind. For example, applying a model in the context of this claim encompasses the user having a mental model and applying it.
The limitation identifying, for each of the plurality of images, a plurality of classifications based upon a result of operation b) each of the plurality of classifications having an associated confidence level, as drafted, is a process that, under its broadest reasonable interpretation, covers performance of the limitation in the mind. For example, identifying in the context of this claim encompasses the user mentally making the identification and mentally determining a confidence level.
The limitation d) performing character recognition on each of the plurality of images, as drafted, is a process that, under its broadest reasonable interpretation, covers performance of the limitation in the mind. For example, performing character recognition in the context of this claim encompasses the user mentally performing character recognition on the object.
The limitation determining a best classification independently for each of the plurality of images based upon the plurality of classifications identified for the image in operation c) and the optical character recognition of the image in operation d), as drafted, is a process that, under its broadest reasonable interpretation, covers performance of the limitation in the mind. For example, determining in the context of this claim encompasses the user mentally determining a best classification.
The limitation determining the classification associated with the package based upon the best classifications determined for the plurality of images, as drafted, is a process that, under its broadest reasonable interpretation, covers performance of the limitation in the mind. For example, determining in the context of this claim encompasses the user mentally determining the associated classification.
If a claim limitation, under its broadest reasonable interpretation, covers performance of the limitation in the mind but for the recitation of generic computer components, then it falls within the “Mental Processes” grouping of abstract ideas. Accordingly, the claim recites an abstract idea.
This judicial exception is not integrated into a practical application. In particular, the claim only recites additional elements –
at least one processor; and at least one non-transitory computer-readable media storing at least one processor; and at least one non-transitory computer-readable media storing: at least one machine learning model at least one processor; and at least one non-transitory computer-readable media storing: applying a machine learning model and instructions that, when executed by the at least one processor, cause the computing system to perform the method; and Optical Character recognition.
The processor and non-transitory computer-readable media are recited at a high-level of generality (i.e., as a generic processor performing a generic computer function and a generic computer readable medium storing instructions for performing generic processing functions)) such that it amounts no more than mere instructions to apply the exception using generic computer components. The machine learning model is merely a generic learning model that only limits the judicial exception to the field of machine learning. Optical character recognition is a well-known function of using a computer to recognize text in images simply used as a tool to perform the abstract idea. Accordingly, this additional element does not integrate the abstract idea into a practical application because it does not impose any meaningful limits on practicing the abstract idea. The claim is directed to an abstract idea.
The claim does not include additional elements that are sufficient to amount to significantly more than the judicial exception. As discussed above with respect to integration of the abstract idea into a practical application, the additional element of using a processor and non-transitory computer readable media to perform steps amounts to no more than mere instructions to apply the exception using a generic computer component. The machine learning model is merely a generic learning model that only limits the judicial exception to the field of machine learning. Optical character recognition is a well-known function of using a computer to recognize text in images simply used as a tool to perform the abstract idea. Mere instructions to apply an exception using generic computer components combined with the generic concepts of OCR and machine learning cannot provide an inventive concept. The claim is not patent eligible.
Re claim 43 The limitation wherein each of the best classifications has an associated confidence level, and wherein operation f) includes comparing the confidence levels of the best classifications and selecting the best classification having a highest confidence level as the classification associated with the package, as drafted, is a process that, under its broadest reasonable interpretation, covers performance of the limitation in the mind. For example, the limitation in the context of this claim encompasses the user mentally performing the comparison and selection.
The analysis for this claim with respect to integration into an abstract idea and significantly more are not meaningfully different from the claim from which this claim depends.
Re claim 44 The limitation, wherein operation e) includes augmenting the confidence level associated with at least one of the plurality of classifications identified for at least one of the plurality of images based upon text identified in operation d) matching or partially matching a keyword associated with the at least one of the plurality of classifications as drafted, is a process that, under its broadest reasonable interpretation, covers performance of the limitation in the mind. For example, the limitation in the context of this claim encompasses the user mentally augmenting a confidence level and mentally matching a keyword.
The analysis for this claim with respect to integration into an abstract idea and significantly more are not meaningfully different from the claim from which this claim depends.
Re claim 45 The limitation wherein operation c) is performed for each of the plurality of images independently of the others of the plurality of image, as drafted, is a process that, under its broadest reasonable interpretation, covers performance of the limitation in the mind. For example, the limitation in the context of this claim encompasses the user mentally performing identification for each image independently.
The analysis for this claim with respect to integration into an abstract idea and significantly more are not meaningfully different from the claim from which this claim depends.
Re claim 46 The limitation wherein the operations further include: g) receiving an expected classification of the package; and h) comparing the classification associated with the package determined in operation f) with the expected classification, as drafted, is a process that, under its broadest reasonable interpretation, covers performance of the limitation in the mind. For example, the limitation in the context of this claim encompasses the user mentally receiving an expected classification.
The analysis for this claim with respect to integration into an abstract idea and significantly more are not meaningfully different from the claim from which this claim depends.
Re claim 47 The limitation wherein the operations further include associating one of a plurality of SKUs with the package based upon the classification determined in operation f), as drafted, is a process that, under its broadest reasonable interpretation, covers performance of the limitation in the mind. For example, the limitation in the context of this claim encompasses the user mentally performing the association.
The analysis for this claim with respect to integration into an abstract idea and significantly more are not meaningfully different from the claim from which this claim depends.
Claim Rejections - 35 USC § 102
The following is a quotation of the appropriate paragraphs of 35 U.S.C. 102 that form the basis for the rejections under this section made in this Office action:
A person shall be entitled to a patent unless –
(a)(1) the claimed invention was patented, described in a printed publication, or in public use, on sale, or otherwise available to the public before the effective filing date of the claimed invention.
(a)(2) the claimed invention was described in a patent issued under section 151, or in an application for patent published or deemed published under section 122(b), in which the patent or application, as the case may be, names another inventor and was effectively filed before the effective filing date of the claimed invention.
Claim(s) 1,2,18,19 and 33 is/are rejected under 35 U.S.C. 102(a)(2) as being anticipated by Voegele US 2022/0332504.
Re claim 1 Voegele discloses
A computing system for identifying a SKU associated with a package comprising:
at least one processor (see paragraph 215 note that the device is implemented by a memory and a processor); and at least one non-transitory computer-readable media storing (see paragraph 215 note that the device is implemented by a memory and a processor): at least one machine learning model (see paragraph 215 note that memory stores the computer instructions see paragraph 209 note that different types of label are detected from a machine learning model) that has been trained with a plurality of images of packages (see paragraph 145 note that machine learning is trained using images of pallets see paragraph 74 note that the pallets contain cases corresponding to the packages); and instructions that, when executed by the at least one processor, cause the computing system to perform the following operations (see paragraph 215 note that memory stores the computer instructions):
a) receiving at least one image of the package (see paragraph 209 and abstract note that images of the pallet are captured which include cases [i.e. packages]);
b) using the at least one machine learning model, inferring at least one classification based upon the at least one image (see paragraph 178 and 209 note that details such as labels on the cases may be determined using machine learning);
c) performing optical character recognition on the at least one image (see paragraph 209 text comprising OCR may by used to identify information on the packaging);
and d) associating one of a plurality of SKUs with the package based upon operations b) and c) (see paragraph 209 “The second image processing operation can include, for example, identifying details on the contents and cases included on the pallet, such as text, markings, codes, and/or other labeling on the cases. The second image processing operations can aim to identify, specifically, what is included in the pallet, such as the specific sku’s that are contained in the pallet” note that the second processing operations including label detection and text detection are used to determine an SKU of the package).
Re claim 2 Voegele discloses wherein the at least one image of the package includes a plurality of images of the package, each of a different one of a plurality of package faces of the package. (see claim 26 “Images can also be captured of every side of the pallet, thereby providing a more complete view of the pallet for profiling via image analysis techniques.” See paragraph 26 note that a complete view of the pallet will include images of multiple sides of some packages see for example figure 1 b note that in this scenario a picture of each side of the pallet will include multiple faces of the packages depicted).
Re claim 18 Vogel discloses
A computer method for determining a classification of a plurality of classifications of a package including:
a) receiving in at least one computer at least one image of the package; (see paragraph 209 and abstract note that images of the pallet are captured which include cases [i.e. packages]);
b) the at least one computer using at least one machine learning model to infer at least one inferred classification based upon each of the at least one image; (see paragraph 178 and 209 note that details such as labels on the cases may be determined using machine learning);
c) the at least one computer performing optical character recognition on the at least one image; (see paragraph 209 text comprising OCR maybe used to identify information on the packaging);
and d) the at least one computer determining the classification of the package based upon steps b) and c). (See paragraph 209 “The second image processing operation can include, for example, identifying details on the contents and cases included on the pallet, such as text, markings, codes, and/or other labeling on the cases. The second image processing operations can aim to identify, specifically, what is included in the pallet, such as the specific sku’s that are contained in the pallet” note that the second processing operations including label detection and text detection are used to determine an SKU of the package which could be considered a class).
Re claim 19 Voegele discloses wherein the at least one image of the package includes a plurality of images of the package, each of a different one of a plurality of package faces of the package. (See claim 26 “Images can also be captured of every side of the pallet, thereby providing a more complete view of the pallet for profiling via image analysis techniques.” See paragraph 26 note that a complete view of the pallet will include images of multiple sides of some packages see for example figure 1 b note that in this scenario a picture of each side of the pallet will include multiple faces of the packages depicted).
Re claim 33 Voegele discloses
A computing system for identifying a classification associated with a package comprising, wherein the classification is one of a plurality of classifications:
at least one processor (see paragraph 215 note that the device is implemented by a memory and a processor); and at least one non-transitory computer-readable media storing (see paragraph 215 note that the device is implemented by a memory and a processor): at least one machine learning model (see paragraph 215 note that memory stores the computer instructions see paragraph 209 note that different types of label are detected from a machine learning model) that has been trained with a plurality of images of packages (see paragraph 145 note that machine learning is trained using images of pallets see paragraph 74 note that the pallets contain cases corresponding to the packages); and instructions that, when executed by the at least one processor, cause the computing system to perform the following operations (see paragraph 215 note that memory stores the computer instructions):
a) receiving at least one image of the package (see paragraph 209 and abstract note that images of the pallet are captured which include cases[i.e packages]);
b) using the at least one machine learning model, inferring at least one inferred classification based upon the at least one image (see paragraph 178 and 209 note that details such as labels on the cases may be determined using machine learning );
c) performing optical character recognition on the at least one image (see paragraph 209 text comprising OCR may be used to identify information on the packaging);
and d) determining the classification of the package based upon operations b) and c) (see paragraph 209 “The second image processing operation can include, for example, identifying details on the contents and cases included on the pallet, such as text, markings, codes, and/or other labeling on the cases. The second image processing operations can aim to identify, specifically, what is included in the pallet, such as the specific skus that are contained in the pallet” note that the second processing operations including label detection and text detection are used to determine an SKU of the package, note that a SKU could be considered a classification of the package).
Claim(s) 34, 39 and 40 is/are rejected under 35 U.S.C. 102(a)(1) as being anticipated by Adato US 20190149725 A1.
Re claim 34 Adato discloses
A computing system for identifying a classification associated with a package, the classification being one of a plurality of classifications, the computing system comprising:
at least one processor; and at least one non-transitory computer-readable media storing: at least one machine learning model that has been trained with a plurality of images of packages; and
instructions that, when executed by the at least one processor, cause the computing system to perform the following operations: a) receiving at least one image of the package;
b) applying the at least one image to the at least one machine learning model (see claim 127 “. In some embodiments, image processing unit 130 may utilize suitably trained machine learning algorithms and models to perform the product identification” note that machine learning may be used to perform product identification);
c) identifying a plurality of classifications based upon a result of operation b); (see paragraph 17 “The method may also include analyzing the at least one image to detect the product represented in the at least one image. The method may further include determining that the detected product is either a first type of product or a second type of product.” note that the product is analyzed to determine if it is either the first type or the second type see paragraph 258 note that a result may include a plurality of suggested product identities)
d) performing optical character recognition on the at least one image (see paragraph 357 n accordance with the present invention, the at least one image may be further analyzed to identify text associated with the bottle, and the identified text may be used in the identification of the type of the product (“for example by processing the image of the text using OCR algorithm, and using the resulting textual information in the identification of the type of the product). In accordance with the present invention, the at least one image may be further analyzed to identify a price associated with the bottle, and the identified price may be used in the identification of the type of the product (for example as described below). In accordance with the present invention, the at least one image may be further analyzed to detect a label associated with the bottle, and the detected label may be used in the identification of the type of the product (for example by identifying text on the label using OCR and using the resulting textual information in the identification of the type of the product,” note that optical character recognition ,may be used to determine for example a prices of the product );
e) selecting one of the plurality of classifications as the classification associated with the package based at least in part upon operation d). (see paragraph 410 ” Further, according to the present disclosure the method for processing images captured in a retail store may include determining that the detected product is either a first type of product or a second type of product, wherein the first type of products and the second type of products may have similar visual appearances. Each of the first type of product and the second type of product may be associated with a different price range. For example, method 2100 may contain step 2116 of determining that the product is of a first type or a second type based on the price falling within a first or second price range. In some examples, the type of a detect product may be determined to be of a plurality of alternative types of products (for example, of two alternative types of products, of three alternative types of products, of four alternative types of products, of more than four alternative types of products, and so forth).” Note that whether the product is first type or second type is based on the prices of the product)
Re claim 37 Adato further discloses e) includes comparing text identified in operation d) to a plurality of keywords, each of the plurality of keywords being associated with at least one of the plurality of classifications, and augmenting a confidence level associated with each classification for which the text matches or partially matches an associated keyword (see paragraph 276 “Using OCR and other image analysis method described above, server 135 may identify “displayed in the personal product section,” “conditioner is displayed on the same shelf,” and “$15 on the price tag,” which again may be all characteristics for “Head & Shoulders Shampoo.” Image processing unit 130 may assign 105 points to the confidence level for “Head & Shoulders Shampoo” being the candidate type of the products, that is, 5 points for having “white container,” 5 points for having “blue cap,” 50 points for “Head & Shoulders logo,” 30 points for having “text Anti-Dandruff,” 5 points for having “displayed in the personal product section,” 5 points for having “conditioner is displayed on the same shelf,” and 5 points for having “$15 on the price tag.” The confidence level of 105 points may be above the threshold, and image processing unit 130 may store the received image to “Head & Shoulders Shampoo” product models.” Note that OCR information like text “Anti dandruff” or the prices may bye used to augment the confidence value of the classification).
Re claim 39 Adato discloses all the elements of claim 1 and f) receiving an expected classification of the package; (see paragraph 306 “For example, when the shelf in the image is determined to be for displaying soft drinks (for example according to a planogram, to a store map, etc.), image processing unit 130 may select the product models that contains the expected product types, such as, “Coca-Cola Zero,” “Sprite,” and “Fanta,” etc., to be included in the subset of product models” )
and g) comparing text identified in operation d) to at least one keyword associated with the expected classification (see paragraph 124 “determining at least one characteristic of the product for determining the type of the product. As used herein, the term “characteristic of the product” refers to one or more visually discernable features attributed to the product. Consistent with the present disclosure, the characteristic of the product may assist in classifying and identifying the product. For example, the characteristic of the product may be associated with the ornamental design of the product, the size of the product, the shape of the product, the colors of the product, the brand of the product, a logo or text associated with the product (e.g., on a product label)” see also 131 “Consistent with the present embodiment, the term “product model” refers to any type of algorithm or stored product data that a processor may access or execute to enable the identification of a particular product associated with the product model. For example, the product model may include a description of visual and contextual properties of the particular product (e.g., the shape, the size, the colors, the texture, the brand name, the price, the logo, text appearing on the particular product, the shelf associated with the particular product, adjacent products in a planogram, the location within the retail store” note that text may be used to determine if it contains words associated with a particular product ).
Re claim 40 Adato discloses associating the expected classification with the package based upon operation (see paragraph 131 “Consistent with the present embodiment, the term “product model” refers to any type of algorithm or stored product data that a processor may access or execute to enable the identification of a particular product associated with the product model. For example, the product model may include a description of visual and contextual properties of the particular product (e.g., the shape, the size, the colors, the texture, the brand name, the price, the logo, text appearing on the particular product, the shelf associated with the particular product, adjacent products in a planogram” note that a particular product model may use text to assist in recognizing the product).
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.
Claim(s) 3, 7, 8, 11, 15, 17, 20, 21, 25, 28 and 31 is/are rejected under 35 U.S.C. 103 as being unpatentable over Voegele US 2022/0332504 in view of Martin Jr US 2020/0273131.
Re claim 3 Voegele discloses all of the features of claim 2 Voegele does not expressly disclose wherein operation b) includes inferring at least one of a plurality of brands independently for each of the plurality of package faces. Martin Jr discloses wherein operation b) includes inferring at least one of a plurality of brands independently for each of the plurality of package faces (see paragraph 60-63 “The package type of each item 20 is identified by the computer, such as reusable beverage crate, corrugated tray with translucent plastic wrap, or fully enclosed cardboard or paperboard box. The branding of each item 20 is also identified by the computer (e.g. a specific flavor from a specific manufacturer), such as by reading the images/text on the packaging” “After individual items 20 are identified on each of the four sides of the loaded pallet 22, based upon the known dimensions of the items 20 and pallet 22, duplicates are removed, i.e. it is determined which items are visible from more than one side and appear in more than one image. If some items are identified with less confidence from one side, but appear in another image where they are identified with more confidence, the identification with more confidence is used” note that brands are determined for each pack in each image and each side, subsequently if the item is identified on multiple sides the highest confidence side is used. The examiner notes that these operations are performed separately i.e. independently as they are generated with different confidences). The motivation to combine is “The individual items 20 are then identified on each of the four sides of the loaded pallet 22.” See paragraph 60 and “If some items are identified with less confidence from one side, but appear in another image where they are identified with more confidence, the identification with more confidence is used.” (see paragraph 62). One of ordinary skill in the art could have easily used the method of Martin Jr to modify the teachings of Voegele to determine brands of multiple faces as part of the recognition process. Therefore, it would have been obvious to one of ordinary skill in the art before the effective filing dates of the claimed invention to combine Voegele and Martin Jr. to reach the aforementioned advantage.
Re claim 7 Voegele discloses all of the features of claim 2 Voegele does not expressly disclose wherein operation b) includes inferring the at least one classification for each of the plurality of images of the packages independently of one another. Martin Jr discloses wherein operation b) includes inferring the at least one classification for each of the plurality of images of the packages independently of one another (see paragraph 60-63 “The package type of each item 20 is identified by the computer, such as reusable beverage crate, corrugated tray with translucent plastic wrap, or fully enclosed cardboard or paperboard box. The branding of each item 20 is also identified by the computer (e.g. a specific flavor from a specific manufacturer), such as by reading the images/text on the packaging” “After individual items 20 are identified on each of the four sides of the loaded pallet 22, based upon the known dimensions of the items 20 and pallet 22, duplicates are removed, i.e. it is determined which items are visible from more than one side and appear in more than one image. If some items are identified with less confidence from one side, but appear in another image where they are identified with more confidence, the identification with more confidence is used” note that brands are determined for each pack in each image and each side, subsequently if the item is identified on multiple sides the highest confidence side is used. The examiner notes that these operations are performed separately i.e. independently as they are generated with different confidences). The motivation to combine is “The individual items 20 are then identified on each of the four sides of the loaded pallet 22.” See paragraph 60 and “If some items are identified with less confidence from one side, but appear in another image where they are identified with more confidence, the identification with more confidence is used.” (see paragraph 62). One of ordinary skill in the art could have easily used the method of Martin Jr to modify the teachings of Voegele to determine brands of multiple faces as part of the recognition process. Therefore, it would have been obvious to one of ordinary skill in the art before the effective filing dates of the claimed invention to combine Voegele and Martin Jr. to reach the aforementioned advantage.
Re claim 8 Voegele discloses and wherein the at least one machine learning model is trained on a plurality of images of packages. (see paragraph 145 note that machine learning models are trained using images of pallets see paragraph 74 note that the pallets contain cases corresponding to the packages). Voegele does not expressly disclose wherein the package contains a plurality of beverage containers. Martin Jr discloses wherein the package contains a plurality of beverage containers (See paragraph 2 “for example, the products may be cases of beverage containers (e.g. cartons of cans and beverage crates containing bottles or cans, etc). There are many different permutations of flavors, sizes, and types of beverage containers delivered to each store.” The motivation to combine is “The improved delivery system facilitates order accuracy from the warehouse to the store by combining machine learning and computer vision software” of the beverage containers of paragraph 2. One of ordinary skill in the art could have easily applied the method of Voegele to the beverage containers of Martin Jr to recognize cases of beverages. Therefore, it would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to combine Voegele and Martin Jr. to reach the aforementioned advantage.
Re claim 11 Voegele discloses all of the features of claim 2 Voegele does not expressly disclose wherein operation b) includes inferring at least one of a plurality of package types independently for each of the plurality of package faces. Martin Jr discloses w wherein operation b) includes inferring at least one of a plurality of package types independently for each of the plurality of package faces. (see paragraph 60-63 “The package type of each item 20 is identified by the computer, such as reusable beverage crate, corrugated tray with translucent plastic wrap, or fully enclosed cardboard or paperboard box. The branding of each item 20 is also identified by the computer (e.g. a specific flavor from a specific manufacturer), such as by reading the images/text on the packaging” “After individual items 20 are identified on each of the four sides of the loaded pallet 22, based upon the known dimensions of the items 20 and pallet 22, duplicates are removed, i.e. it is determined which items are visible from more than one side and appear in more than one image. If some items are identified with less confidence from one side, but appear in another image where they are identified with more confidence, the identification with more confidence is used” note that brands are determined for each pack in each image and each side, subsequently if the item is identified on multiple sides the highest confidence side is used. The examiner notes that these operations are performed separately i.e. independently as they are generated with different confidences). The motivation to combine is “The individual items 20 are then identified on each of the four sides of the loaded pallet 22.” See paragraph 60 and “If some items are identified with less confidence from one side, but appear in another image where they are identified with more confidence, the identification with more confidence is used.” (see paragraph 62). One of ordinary skill in the art could have easily used the method of Martin Jr to modify the teachings of Voegele to determine brands of multiple faces as part of the recognition process. Therefore, it would have been obvious to one of ordinary skill in the art before the effective filing dates of the claimed invention to combine Voegele and Martin Jr. to reach the aforementioned advantage.
Re claim 15 Voegele discloses all the features of claim 1 Voegele does not expressly disclose wherein the operations further include: e) receiving an expected SKU; and f) comparing the associated one of the plurality of SKUs with the expected SKU. Martin Jr. discloses the operations further include: e) receiving an expected SKU; and f) comparing the associated one of the plurality of SKUs with the expected SKU (see paragraph 50 “The SKUs of the products 20 on the pallet 22 are compared to the pick sheet 64 by the DC computer 26 in step 160, to ensure that all the SKUs associated with the pallet id of the pallet 22 on the pick sheet 64 are present on the correct pallet 22”). The motivation to combine is to ensure that all the SKUs associated with the pallet id of the pallet 22 on the pick sheet 64 are present on the correct pallet 22”. One of ordinary skill in the art could have easily modified Vogele to compare the detected SKU to an expected listed as described in Martin Jr. Therefore, it would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to combine Vogele and Martin Jr to reach the aforementioned advantage.
Re claim 17 Voegele discloses and wherein the at least one machine learning model is trained on a plurality of images of packages. (see paragraph 145 note that machine learning models are trained using images of pallets see paragraph 74 note that the pallets contain cases corresponding to the packages). Voegele does not expressly disclose wherein the package contains a plurality of beverage containers. Martin Jr discloses wherein the package contains a plurality of beverage containers (See paragraph 2 “for example, the products may be cases of beverage containers (e.g. cartons of cans and beverage crates containing bottles or cans, etc). There are many different permutations of flavors, sizes, and types of beverage containers delivered to each store.” The motivation to combine is “The improved delivery system facilitates order accuracy from the warehouse to the store by combining machine learning and computer vision software” of the beverage containers of paragraph 2. One of ordinary skill in the art could have easily applied the method of Voegele to the beverage containers of Martin Jr to recognize cases of beverages. Therefore, it would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to combine Voegele and Martin Jr. to reach the aforementioned advantage.
Re claim 20 Voegele discloses and wherein the at least one machine learning model is trained on a plurality of images of packages. (see paragraph 145 note that machine learning models are trained using images of pallets see paragraph 74 note that the pallets contain cases corresponding to the packages). Voegele does not expressly disclose wherein the package contains a plurality of beverage containers. Martin Jr discloses wherein the package contains a plurality of beverage containers (See paragraph 2 “for example, the products may be cases of beverage containers (e.g. cartons of cans and beverage crates containing bottles or cans, etc). There are many different permutations of flavors, sizes, and types of beverage containers delivered to each store.” The motivation to combine is “The improved delivery system facilitates order accuracy from the warehouse to the store by combining machine learning and computer vision software” of the beverage containers of paragraph 2. One of ordinary skill in the art could have easily applied the method of Voegele to the beverage containers of Martin Jr to recognize cases of beverages. Therefore, it would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to combine Voegele and Martin Jr. to reach the aforementioned advantage.
Re claim 21 Voegele discloses all of the features of claim 20, Voegele does not expressly disclose wherein operation b) includes inferring at least one of a plurality of brands independently for each of the plurality of package faces. Martin Jr discloses wherein operation b) includes inferring at least one of a plurality of brands independently for each of the plurality of package faces (see paragraph 60-63 “The package type of each item 20 is identified by the computer, such as reusable beverage crate, corrugated tray with translucent plastic wrap, or fully enclosed cardboard or paperboard box. The branding of each item 20 is also identified by the computer (e.g. a specific flavor from a specific manufacturer), such as by reading the images/text on the packaging” “After individual items 20 are identified on each of the four sides of the loaded pallet 22, based upon the known dimensions of the items 20 and pallet 22, duplicates are removed, i.e. it is determined which items are visible from more than one side and appear in more than one image. If some items are identified with less confidence from one side, but appear in another image where they are identified with more confidence, the identification with more confidence is used” note that brands are determined for each pack in each image and each side, subsequently if the item is identified on multiple sides the highest confidence side is used. The examiner notes that these operations are performed separately i.e. independently as they are generated with different confidences). The motivation to combine is “The individual items 20 are then identified on each of the four sides of the loaded pallet 22.” See paragraph 60 and “If some items are identified with less confidence from one side, but appear in another image where they are identified with more confidence, the identification with more confidence is used.” (see paragraph 62). One of ordinary skill in the art could have easily used the method of Martin Jr to modify the teachings of Voegele to determine brands of multiple faces as part of the recognition process. Therefore, it would have been obvious to one of ordinary skill in the art before the effective filing dates of the claimed invention to combine Voegele and Martin Jr. to reach the aforementioned advantage.
Re claim 25 Voegele discloses all of the features of claim 20, Voegele does not expressly disclose wherein step b) includes inferring the at least one classification for each of the plurality of images of the packages independently of one another. Martin Jr discloses wherein step b) includes inferring the at least one classification for each of the plurality of images of the packages independently of one another (see paragraph 60-63 “The package type of each item 20 is identified by the computer, such as reusable beverage crate, corrugated tray with translucent plastic wrap, or fully enclosed cardboard or paperboard box. The branding of each item 20 is also identified by the computer (e.g. a specific flavor from a specific manufacturer), such as by reading the images/text on the packaging” “After individual items 20 are identified on each of the four sides of the loaded pallet 22, based upon the known dimensions of the items 20 and pallet 22, duplicates are removed, i.e. it is determined which items are visible from more than one side and appear in more than one image. If some items are identified with less confidence from one side, but appear in another image where they are identified with more confidence, the identification with more confidence is used” note that brands are determined for each pack in each image and each side, subsequently if the item is identified on multiple sides the highest confidence side is used. The examiner notes that these operations are performed separately i.e. independently as they are generated with different confidences). The motivation to combine is “The individual items 20 are then identified on each of the four sides of the loaded pallet 22.” See paragraph 60 and “If some items are identified with less confidence from one side, but appear in another image where they are identified with more confidence, the identification with more confidence is used.” (see paragraph 62). One of ordinary skill in the art could have easily used the method of Martin Jr to modify the teachings of Voegele to determine brands of multiple faces as part of the recognition process. Therefore, it would have been obvious to one of ordinary skill in the art before the effective filing dates of the claimed invention to combine Voegele and Martin Jr. to reach the aforementioned advantage.
Re claim 28 Voegele discloses all of the features of claim 20, Voegele does not expressly disclose wherein operation b) includes inferring at least one of a plurality of package types independently for each of the plurality of package faces. Martin Jr discloses w wherein operation b) includes inferring at least one of a plurality of package types independently for each of the plurality of package faces. (See paragraph 60-63 “The package type of each item 20 is identified by the computer, such as reusable beverage crate, corrugated tray with translucent plastic wrap, or fully enclosed cardboard or paperboard box. The branding of each item 20 is also identified by the computer (e.g. a specific flavor from a specific manufacturer), such as by reading the images/text on the packaging” “After individual items 20 are identified on each of the four sides of the loaded pallet 22, based upon the known dimensions of the items 20 and pallet 22, duplicates are removed, i.e. it is determined which items are visible from more than one side and appear in more than one image. If some items are identified with less confidence from one side, but appear in another image where they are identified with more confidence, the identification with more confidence is used” note that brands are determined for each pack in each image and each side, subsequently if the item is identified on multiple sides the highest confidence side is used. The examiner notes that these operations are performed separately i.e. independently as they are generated with different confidences). The motivation to combine is “The individual items 20 are then identified on each of the four sides of the loaded pallet 22.” See paragraph 60 and “If some items are identified with less confidence from one side, but appear in another image where they are identified with more confidence, the identification with more confidence is used.” (see paragraph 62). One of ordinary skill in the art could have easily used the method of Martin Jr to modify the teachings of Voegele to determine brands of multiple faces as part of the recognition process. Therefore, it would have been obvious to one of ordinary skill in the art before the effective filing dates of the claimed invention to combine Voegele and Martin Jr. to reach the aforementioned advantage.
Re claim 31 Voegele discloses all the features of claim 18 Voegele does not expressly disclose e) receiving an expected classification; and f) comparing the classification of the package determined in step d) with the expected classification. Martin Jr. d e) receiving an expected classification; and f) comparing the classification of the package determined in step d) with the expected classification (see paragraph 50 “The SKUs of the products 20 on the pallet 22 are compared to the pick sheet 64 by the DC computer 26 in step 160, to ensure that all the SKUs associated with the pallet id of the pallet 22 on the pick sheet 64 are present on the correct pallet 22”). The motivation to combine is to ensure that all the SKUs associated with the pallet id of the pallet 22 on the pick sheet 64 are present on the correct pallet 22”. One of ordinary skill in the art could have easily modified Vogele to compare the detected SKU to an expected listed as described in Martin Jr. Therefore, it would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to combine Vogele and Martin Jr to reach the aforementioned advantage.
Claim(s) 16 and 32 is/are rejected under 35 U.S.C. 103 as being unpatentable over Voegele US 2022/0332504 in view of Martin Jr US 2020/0273131 Jindal US 20220261579 A1 and Hogg US 2022/0318773.
Re claim 16 Voegele further discloses inferring a classification using a machine learning model (see paragraph 178 and 209 note that details such as labels on the cases may be determined using machine learning);
Voegele and Martin Jr does not disclose wherein the operations further include: g) comparing results of operation c) with the inferred at least one classification; and h) comparing the results of operation c) with the expected SKU.
Jindal discloses comparing results of operation c) with the at least one classification (see paragraph 93 “the extracted text from the identified objects in the captured scene is compared to the inputted name of the target object to determine if any of the identified objects are a match. In some embodiments, the extracted text is used from each and every identified object within the captured scene. In some other embodiments, the extracted text is used from only those identified objects having sufficiently matching label vectors where one or more classification labels match to one or more classification labels associated with the target object”) One of ordinary skill in the art could have easily modified the combination of Voegele and Martin Jr with teaching of Jindal and the results text of a classified object is compared with OCR text and the results(i.e. text associated with a classification is compared with the text of the OCR), would have been predictable. These elements perform the same function in combination as they do separately as the combination merely requires an additional comparison of data. Therefore, it would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to combine Jindal Voegele and Martin Jr.
Jindal Voegele and Martin Jr further do not disclose comparing the results of operation c) with the expected SKU.
Hogg discloses and h) comparing the results of operation c) with the expected SKU (see paragraph 48 note that OCR is compared to known structures of SKU). One of ordinary skill in the art could have easily compared OCR data to a expected SKU and the results (i.e. the two pieces of information are compared) would have been predictable. The combined features function the same in combination as the do separately as comparison operation is to simply an extra step to compare information against known information and the features of Hogg Vogel and Jindal are not meaningly changed. Therefore, it would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to combine Hogg with Voegele, Martin Jr and Jindal.
Re claim 32 Voegele further discloses inferring a classification using a machine learning model (see paragraph 178 and 209 note that details such as labels on the cases may be determined using machine learning);
Voegele and Martin Jr does not disclose g) comparing results of step c) with the inferred at least one classification; and h) comparing the results of step c) with the expected classification.
Jindal discloses comparing results of step c) with the inferred at least one classification (see paragraph 93 ”the extracted text from the identified objects in the captured scene is compared to the inputted name of the target object to determine if any of the identified objects are a match. In some embodiments, the extracted text is used from each and every identified object within the captured scene. In some other embodiments, the extracted text is used from only those identified objects having sufficiently matching label vectors where one or more classification labels match to one or more classification labels associated with the target object”) One of ordinary skill in the art could have easily modified the combination of Voegele and Martin Jr with teaching of Jindal and the results text of a classified object is compared with OCR text and the results(i.e. text associated with a classification is compared with the text of the OCR), would have been predictable. These elements perform the same function in combination as they do separately as the combination on requires an additional comparison of data. Therefore, it would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to combine Jindal Voegele and Martin Jr.
Jindal Voegele and Martin Jr further do not disclose comparing the results of step c) with the expected classification.
Hogg US 2022/0318773 discloses and h) comparing the results of step c) with the expected classification (see paragraph 48 note that OCR is compared to known structures of SKU). One of ordinary skill in the art could have easily compared OCR data to a expected SKU and the results (i.e. the two pieces of information are compared) would have been predictable. The combined features function the same in combination as the do separately as comparison operation is to simply an extra step to compare information against known information and the features of Hogg Vogel and Jindal are not meaningly changed. Therefore, it would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to combine Hogg with Voegele, Martin Jr and Jindal.
Claim(s) 35 is/are rejected under 35 U.S.C. 103 as being unpatentable over Adato US 2019/0149725 in further view of Nechiporenko WO 2011/115570 A1.
Re claim 35 Adato discloses all the elements of claim 34. Adato does not expressly disclose wherein the at least one image of the package includes a plurality of images, each of the plurality of images being of a different one of a plurality of package faces of the package. Nechiporenko discloses wherein the at least one image of the package includes a plurality of images, each of the plurality of images being of a different one of a plurality of package faces of the package (“For instance, if one side of a goods package is detected in a first view of the goods package (or of a stack of goods packages) and two possible sides are detected in a second view of the package from a second side, this might represent a conflict which must be resolved. Techniques are disclosed which allow for such conflicts to be resolved with reference to data relating to know types of goods packages, such as information relating to the expected contents” see page 4 lines 10-15, note that multiple sides of a package may be ). The motivation to combine is “provide higher confidence in the analysis of the goods package(s)” (see page 14 lines 5 AND 6). One of ordinary skill in the art could have easily modified techniques of Adato with the techniques of Nechiporenko to capture images of multiple sides of a package provide high confidence. Therefore, it would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to combine Adato and Nechiporenko to reach the aforementioned advantage.
Claim(s) 41 is/are rejected under 35 U.S.C. 103 as being unpatentable over Adato US 2019/0149725 in further view of Voegele US 20220332504 A1.
Re claim 41 Adato discloses all the elements of claim 34, Adato does not expressly disclose wherein the operations further include associating one of a plurality of SKUs with the package based upon the classification selected i. Voegele discloses wherein the operations further include associating one of a plurality of SKUs with the package based upon the classification selected. (See paragraph 209 “The second image processing operations can aim to identify, specifically, what is included in the pallet, such as the specific SKUs” note that a plurality of SKUs are determined in part based on object detection). The motivation to combine is to “identify, specifically, what is included in the pallet, such as the specific skus that are contained”. The motivation to combine is “The items can also have unique identification information that can be used throughout a supply chain” (see paragraph 2) see paragraph 209 “aim to identify, specifically, what is included in the pallet, such as the specific skus” That is one of ordinary skill in the art would have been motivated to modify Adato to identify specific SKUS for the products on Adato. Therefore it would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to combine Adato and Voegele to reach the aforementioned advantage.
Allowable Subject Matter
Claim 42-47 would be allowable if rewritten or amended to overcome the rejection(s) under 35 U.S.C. 101, set forth in this Office action.
Re claim 42
A computing system for identifying a classification associated with a package, the classification being one of a plurality of classifications, the computing system comprising: at least one processor; (see paragraph 215 note that the device is implemented by a memory and a processor); and at least one non-transitory computer-readable media storing (see paragraph 215 note that the device is implemented by a memory and a processor): at least one non-transitory computer-readable media storing at least one machine learning model that has been trained with a plurality of images of packages; (see paragraph 215 note that memory stores the computer instructions see paragraph 209 note that different types of label are detected from a machine learning model) that has been trained with a plurality of images of packages (see paragraph 145 note that machine learning is trained using images of pallets see paragraph 74 note that the pallets contain cases corresponding to the packages); and instructions that, when executed by the at least one processor, cause the computing system to perform the following operations: (see paragraph 215 note that memory stores the computer instructions):
a) receiving plurality of images of the package, each of a different one of a plurality of package faces of the package. (see claim 26 “Images can also be captured of every side of the pallet, thereby providing a more complete view of the pallet for profiling via image analysis techniques.” See paragraph 26 note that a complete view of the pallet will include images of multiple sides of some packages see for example figure 1 b note that in this scenario a picture of each side of the pallet will include multiple faces of the packages depicted)
using the at least one machine learning model, inferring at least one classification based upon the at least one image (see paragraph178 and 209 note that details such as labels on the cases may be determined using machine learning);
performing optical character recognition on the at least one image (see paragraph 209 text comprising OCR may by used to identify information on the packaging);
determining a classification based on the classification identified for the image in operation c) and the optical character recognition of the image in operation d (see paragraph 209 “The second image processing operation can include, for example, identifying details on the contents and cases included on the pallet, such as text, markings, codes, and/or other labeling on the cases. The second image processing operations can aim to identify, specifically, what is included in the pallet, such as the specific sku’s that are contained in the pallet” note that the second processing operations including label detection and text detection are used to determine an SKU of the package).
The prior art of record does not disclose the combination of A computing system for identifying a classification associated with a package, the classification being one of a plurality of classifications, the computing system comprising: at least one processor; and at least one non-transitory computer-readable media storing: at least one machine learning model that has been trained with a plurality of images of packages; and instructions that, when executed by the at least one processor, cause the computing system to perform the following operations: a) receiving a plurality of images of the package, each of the plurality of images being of a different one of a plurality of package faces of the package; b) applying each of the plurality of images to the at least one machine learning model; c) identifying, for each of the plurality of images, a plurality of classifications based upon a result of operation b), each of the plurality of classifications having an associated confidence level; d) performing optical character recognition on each of the plurality of images; e) determining a best classification independently for each of the plurality of images based upon the plurality of classifications identified for the image in operation c) and the optical character recognition of the image in operation d); and f) determining the classification associated with the package based upon the best classifications determined for the plurality of images.
Claim 4-6 9,10, 22-24, 27, 28, 30 36-38 would be allowable if rewritten to overcome the rejection(s) under 35 U.S.C. 101, , set forth in this Office action and to include all of the limitations of the base claim and any intervening claims.
Conclusion
Applicant's amendment necessitated the new ground(s) of rejection presented in this Office action. Accordingly, THIS ACTION IS MADE FINAL. See MPEP § 706.07(a). Applicant is reminded of the extension of time policy as set forth in 37 CFR 1.136(a).
A shortened statutory period for reply to this final action is set to expire THREE MONTHS from the mailing date of this action. In the event a first reply is filed within TWO MONTHS of the mailing date of this final action and the advisory action is not mailed until after the end of the THREE-MONTH shortened statutory period, then the shortened statutory period will expire on the date the advisory action is mailed, and any nonprovisional extension fee (37 CFR 1.17(a)) pursuant to 37 CFR 1.136(a) will be calculated from the mailing date of the advisory action. In no event, however, will the statutory period for reply expire later than SIX MONTHS from the mailing date of this final action.
Any inquiry concerning this communication or earlier communications from the examiner should be directed to SEAN T MOTSINGER whose telephone number is (571)270-1237. The examiner can normally be reached 9AM-5PM.
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, Chineyere Wills-Burns can be reached at (571) 272-9752. 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.
/SEAN T MOTSINGER/Primary Examiner, Art Unit 2673
