DETAILED ACTION
Notice of Pre-AIA or AIA Status
The present application, filed on or after March 16, 2013, is being examined under the first inventor to file provisions of the AIA .
Claims 1, 3-11, 12-19, and 21-23 have been examined.
Claim Objections
Claim 10 is objected to because of the following informalities: In the seventh line of claim 10, “the item of the list of items” should be simply “the item”, as there is no antecedent basis for a list of items. In the sixth line of claim 10, “a list of substitutes” can, if desired, be changed back to “the list of substitutes”, since there is antecedent basis in claim 1 for a list of substitutes. Appropriate correction is required.
Claim 22 is objected to because of the following informalities: In the third line of claim 22, “determining the list” should be “determine the list”. Appropriate correction is required.
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.
Claims 1, 3-11, 13-19, and 21-23 are rejected under 35 U.S.C. 101 because the claimed invention is directed to a judicial exception (abstract idea) without significantly more. The claims recite a system, a parallel method, and a parallel non-transitory computer-readable medium comprising instructions for technologically performing certain operations, which could in their essentials be performed as mental processes by a human being. This judicial exception is not integrated into a practical application because the claims do not match one of the specific grounds which would indicate integration into a practical application, and do not otherwise apply or use the judicial exception in a meaningful way beyond generally linking the use of the judicial exception to a particular technological environment. Claims 9 and 10 are directed to commercial operations in the category of certain methods of organizing human activity, as well as to mental processes. The claims do not include additional elements that are sufficient to amount to significantly more than the judicial exception, as set forth in detail below.
The following 35 U.S.C. 101 analysis is performed in accordance with section 2106 of the Manual of Patent Examination Procedure (concerning Patent Subject Matter Eligibility Guidance). Independent claim 1 recites a system comprising one or more processors and one or more non-transitory computer-readable media storing computing instructions, and therefore falls within the statutory category of machine, as do its dependents; independent claim 11 recites a method, and therefore falls within the statutory category of process, as do its dependents (Mayo test, Step 1). Claims 1-20 are rejected under 35 U.S.C. 101 because the claimed invention is directed to an abstract idea, and specifically to mental processes, and, in the cases of claims 9 and 10, to commercial interactions under the field of organizing human activity without significantly more (Mayo test, Step 2A, Prong 1). The claims recite a method, system, and computer-readable medium for performing operations, including determining scores for a list of substitutes. This judicial exception is not integrated into a practical application because mere instructions to implement an abstract idea on a computer, or use a computer as a tool to perform an abstract idea, are not indicative of integration into a practical application, nor is linking the use of the judicial exception to a particular technological environment or field of use (Mayo test, Step 2A, Prong 2). Adding insignificant extra-solution activity to the judicial exception is also not indicative of integration into a practical application. The claims do not recite improvements to the functioning of a computer or to any other technology or technical field. The claims do not recite applying or using a judicial exception to effect a particular treatment or prophylaxis for a disease or medical condition. The claims do not recite applying the judicial exception with, or by the use of, a particular machine. The claims do not recite effecting a transformation or reduction of a particular article to different state or thing. The claims do not recite applying or using a judicial exception in some other meaningful way beyond generally linking the use of the judicial exception to a particular technological environment, such that the claim as a whole is more than a drafting effort designed to monopolize the exception (Mayo test, Step 2A, Prong 2).
There are no additional elements recited in the claims to raise them to significantly more than the judicial exception. In particular, the claims do not add a specific limitation other than what is well-understood, routine, and conventional activity in the field (Mayo test, Step 2B). The detailed method and system recited in dependent claims 1, 3-11, 13-19, and 21-23 are non-obvious over the prior art, but non-obviousness under 35 U.S.C. 103 is a different issue from eligibility under 35 U.S.C. 101. The specific steps of the claims, such as training, using labeled training data, a machine learning algorithm; using the machine learning algorithm, as trained, to determine scores for a list of substitutes for an item; and re-training the machine learning algorithm based on at least the labeled training data and a highest ranked substitute from a ranking of a list of substitutes based on the scores, etc., do not qualify, alone or in combination, to raise the claimed method, system, and computer-readable medium to significantly more than an abstract idea.
Independent claim 1 recites: A system comprising: one or more processors; and one or more non-transitory computer-readable media storing computing instructions that, when executed on the one or more processors, cause the one or more processors to perform operations comprising: training, using labeled training data, a machine learning algorithm, wherein the labeled training data comprises positive and negative historical acceptance data that includes at least one of: a probability of a similarity between a historical title for a historical item and a historical description of a historical substitute, a taxonomy difference for the historical item and the historical substitute, a difference between the historical item and the historical substitute, or a normalized rank comparison for the historical item and the historical substitute; using the machine learning algorithm, as trained, to determine scores for a list of substitutes for an item; and re-training the machine learning algorithm based on at least the labeled training data and a highest ranked substitute from a ranking of the list of substitutes. Avidan et al. (U.S. Patent Application Publication 2017/0193592) discloses (paragraph 25, emphasis added), “Although not illustrated, it should be appreciated that the ecommerce server 110, the merchant computer 120, and the customer computer 130 each include conventional components, such as a processor and a memory medium storing computer-readable instructions that are executable by the processor to perform various operations including those described herein. The computer-readable instructions can be stored on non-transitory computer-readable storage media of a conventional type, whether devices and/or materials.” Hence, the one or more processors and the one or more non-transitory computer-readable media storing computing instructions that, when executed on the one or more processors, cause the one or more processors to perform operations require only the use of well-understood, routine, and conventional technology. He et al. (U.S. Patent Application Publication 2009/0049002) discloses (paragraph 3, emphasis added), “A conventional machine learning algorithm undergoes a training process by inputting known data and comparing actual output to the expected output.” Hence, the training and re-training steps require only the use of well-understood, routine, and conventional technology. The determining step is not inherently technological, and could readily be performed by a human being. The limitations of claim 1, whether considered separately or in combination with each other, do not raise the claimed invention to significantly more than an abstract idea.
Claim 3, which depends from claim 1, recites that the computing instructions, when executed on the one or more processors, further cause the one or more processors to perform an operation comprising: determining the list of substitutes for the item comprising: accessing an item taxonomy database comprising a respective item taxonomy for each item in a catalog of items; identifying a specific item taxonomy for the item; filtering out non-matching items of the catalog of items, wherein the non-matching items comprise a different item taxonomy than the specific item taxonomy of the item; and adding matching items of the catalog of items to the list of substitutes, wherein the matching items of the catalog of items comprise the specific item taxonomy. The steps of determining, identifying, filtering, and adding are not in themselves technological. The courts have recognized storing and retrieving information in memory as well-understood, routine, and conventional functions, in Versata Dev. Group, Inc. v. SAP Am., Inc., 793 F.3d at 1306, 1334, 115 USPQ2d 1681, 1701 (Fed. Cir. 2015); OIP Techs., Inc., v. Amazon.com, Inc., 788 F.3d 1363, 115 USPQ2d at 1092-93 (Fed. Cir. 2015). Therefore, the step of accessing an item taxonomy database requires only the use of well-understood, routine, and conventional functions and technology, e.g., to access data in a memory; this can also apply to adding matching items of the catalog of items to the list of substitutes, if the matching items are being added a list stored in memory. The limitations of claim 3, whether considered separately or in combination with each other and with the limitations of claim 1, do not raise the claimed invention to significantly more than an abstract idea.
Claim 4, which depends from claim 1, recites that the scores are based on comparisons of: a respective brand for each substitute of the list of substitutes; a respective attribute for each substitute of the list of substitutes and an attribute of the item; and a respective product for each substitute of the list of substitutes and a product of the item. The requisite comparing need not be technological, and the particulars of what is compared do not make the comparing steps technological. The limitations of claim 4, whether considered separately or in combination with each other and with the limitations of claim 1, do not raise the claimed invention to significantly more than an abstract idea.
Claim 5, which depends from claim 1, recites that the operations further comprise: storing information, based on a selection of the highest ranked substitute as additional training data for the labeled training data. The courts have recognized storing and retrieving information in memory as well-understood, routine, and conventional functions, in Versata Dev. Group, Inc. v. SAP Am., Inc., 793 F.3d at 1306, 1334, 115 USPQ2d 1681, 1701 (Fed. Cir. 2015); OIP Techs., Inc., v. Amazon.com, Inc., 788 F.3d 1363, 115 USPQ2d at 1092-93 (Fed. Cir. 2015). Therefore, the recited information as additional training data for the labeled training data requires only the use of well-understood, routine, and conventional functions and technology. The limitation of claim 5, whether considered separately or in combination with the limitations of claim 1, does not raise the claimed invention to significantly more than an abstract idea.
Claim 6, which depends from claim 1, recites that the operations further comprise: determining the ranking of the list of substitutes by: when two or more substitutes of the list of substitutes have approximately similar final scores, determining a quantity ratio comprising a ratio of a quantity for the item to a respective quantity for each substitute of the list of substitutes, wherein: the quantity for the item comprises: either (i) a weight of the item or (ii) a volume of the item, divided by a count of the item; and the respective quantity for each substitute of the list of substitutes comprises: either (i) a respective weight of each substitute of the list of substitutes or (ii) a respective volume of each substitute of the list of substitutes, divided by a respective count of each substitute of the list of substitutes; and ranking a first one of the two or more substitutes of the list of substitutes with a first quantity ratio above a second one of the two or more substitutes of the list of substitutes with a second quantity ratio that is higher than the first quantity ratio. The determining operation is not in itself technological, and could be performed by a human being. The limitations of claim 6, whether considered separately or in combination with each other and with the limitations of claim 1, do not raise the claimed invention to significantly more than an abstract idea.
Claim 7, which depends from claim 1, recites that the computing instructions, when executed on the one or more processors, further cause the one or more processors to perform an operation comprising: determining a respective historical substitution score, comprising: determining a respective number of successful substitutions for each substitute of the list of substitutes; determining a respective number of unsuccessful substitutions for each substitute of the list of substitutes; calculating a respective historical acceptance rate for each substitute of the list of substitutes using the respective number of successful substitutions for each substitute of the list of substitutes and the respective number of unsuccessful substitutions for each substitute of the list of substitutes; and assigning the respective historical substitution score based on the respective historical acceptance rate for each [substitute] of the list of substitutes and the respective number of successful substitutions for each substitute of the list of substitutes. The two determining steps, the calculating step, and the assigning step are not in themselves technological, and could be performed by a human being. The limitations of claim 7, whether considered separately or in combination with each other and with the limitations of claim 1, do not raise the claimed invention to significantly more than an abstract idea..
Claim 8, which depends from claim 1, recites that the computing instructions, when executed on the one or more processors, further cause the one or more processors to perform an operation comprising: inputting a respective similarity score for each substitute of the list of substitutes and a respective historical substitution score for each substitute of the list of substitutes into a feed-forward neural network comprising one or more rectifiers having ReLU non-linearity, wherein the feed-forward neural network is trained without unsupervised pre-training. Medasani et al. (U.S. Patent Application Publication 2009/0055330) discloses (paragraph 33, emphasis added), “The specific methodology of a multi-layered feed-forward neural network is well known and will not be discussed in detail herein.” Kim et al. (U.S. Patent Application Publication 2018/0144209) discloses (paragraph 125, emphasis added), “The activation function may be, for example, a rectified linear unit (ReLU) function. For reference, to solve a vanishing gradient problem in which learning through back-propagation is not performed properly as the number of layers increases, the ReLU function instead of a sigmoid function may be used as an activation function. The ReLU function is an activation function well known in the art to which the inventive concept pertains, and thus a description of the ReLU function is omitted.” Involvement of a feed-forward neural network comprising one or more rectifiers having ReLU non-linearity, wherein the feed-forward neural network is trained without unsupervised pre-training, requires only the use of well-understood, routine, and conventional technology. The limitations of claim 8, whether considered separately or in combination with each other and with the limitations of claim 1, do not raise the claimed invention to significantly more than an abstract idea.
Claim 9, which depends from claim 1, recites that the computing instructions, when executed on the one or more processors, further cause the one or more processors to perform operations comprising: determining respective qualities for each substitute of the list of substitutes; facilitating a display, on a user interface of a user device, of the highest ranked substitute of the list of substitutes; receiving, from the user interface of the user device, a selection of the highest ranked substitute; after receiving the selection of the highest ranked substitute, substituting the highest ranked substitute for the item; receiving a respective title for each substitute of the list of substitutes; and identifying a respective brand for each substitute of the list of substitutes using the respective title for each substitute of the list of substitutes. The determining step and the identifying step need not be technological, nor need the steps of receiving a respective title for each substitute of the list of substitutes, or the step of substituting the highest ranked substitute of the list of substitutes for the item. Sivadas (U.S. Patent Application Publication 2012/0011477) discloses (paragraph 2, emphasis added), “It is well known to provide portable communication devices, such as mobile telephones, with a user interface that causes graphics and text to be displayed on a display and that allows a user to provide inputs to the device, for the purpose of controlling the device and interacting with software applications.” Hence, the step of facilitating a display, on a user interface of a user device, of the highest ranked substitute of the list of substitutes, and the step of receiving, from the user interface of the user device, a selection of the highest ranked substitute of the list of substitutes require only the use of well-understood, routine, and conventional technology. The limitations of claim 9, whether considered separately or in combination with each other and with the limitations of claim 1, do not raise the claimed invention to significantly more than an abstract idea.
Claim 10, which depends from claim 1, recites that the computing instructions, when executed on the one or more processors, further cause the one or more processors to perform operations comprising: when the item is out of stock, comparing a respective dietary restriction for each substitute of the list of substitutes with a dietary restriction of the item; and when a dietary restriction of a substitute of a list of substitutes does not match the dietary restriction of [the item], removing the substitute of the list of substitutes from the list of substitutes. The comparing and removing steps are not in themselves technological, and could be performed by a human being. The limitations of claim 10, whether considered separately or in combination with each other and with the limitations of claim 1, do not raise the claimed invention to significantly more than an abstract idea.
Independent claim 11 is directly parallel to claim 1, and therefore fails to raise the claimed invention to significantly more than an abstract idea on the same grounds set forth above with respect to claim 1 above, and based on the Avidan and He references.
Claim 13, which depends from claim 11, is directly parallel to claim 3, and therefore fails to raise the claimed invention to significantly more than an abstract idea on the same grounds set forth above with respect to claim 3 above, and further based on the cited judicial precedents.
Claim 14, which depends from claim 11, is directly parallel to claim 4, and therefore fails to raise the claimed invention to significantly more than an abstract idea on the same grounds set forth above with respect to claim 4 above.
Claim 15, which depends from claim 11, is directly parallel to claim 5, and therefore fails to raise the claimed invention to significantly more than an abstract idea on the same grounds set forth above with respect to claim 5 above, and further based on the cited judicial precedents.
Claim 16, which depends from claim 11, is directly parallel to claim 6, and therefore fails to raise the claimed invention to significantly more than an abstract idea on the same grounds set forth above with respect to claim 6 above.
Claim 17, which depends from claim 11, is directly parallel to claim 7, and therefore fails to raise the claimed invention to significantly more than an abstract idea on the same grounds set forth above with respect to claim 7 above.
Claim 18, which depends from claim 11, is directly parallel to claim 8, and therefore fails to raise the claimed invention to significantly more than an abstract idea on the same grounds set forth above with respect to claim 8 above, and further based on the Medasani and Kim references.
Claim 19, which depends from claim 11, is now not directly parallel to claim 9, and is therefore further analyzed Claim 19 recites that the method of claim 11 further comprises: facilitating a display, on a user interface of a user device, of information identifying the highest ranked substitute of the list of substitutes; receiving, from the user interface of a user device, a selection of the highest ranked substitute of the list of substitutes; and after receiving the selection of the highest ranked substitute, substituting the highest ranked substitute for the item. The step of receiving a selection of the highest ranked substitute need not be technological, nor need the step of substituting the highest ranked substitute of the list of substitutes for the item. Sivadas (U.S. Patent Application Publication 2012/0011477) discloses (paragraph 2, emphasis added), “It is well known to provide portable communication devices, such as mobile telephones, with a user interface that causes graphics and text to be displayed on a display and that allows a user to provide inputs to the device, for the purpose of controlling the device and interacting with software applications.” Hence, the step of facilitating a display, on a user interface of a user device, of the highest ranked substitute of the list of substitutes, and the step of receiving, from the user interface of the user device, a selection of the highest ranked substitute of the list of substitutes require only the use of well-understood, routine, and conventional technology. The limitations of claim 19, whether considered separately or in combination with each other and with the limitations of claim 11, do not raise the claimed invention to significantly more than an abstract idea.
Independent claim 21 is directly parallel to claim 1, and therefore fails to raise the claimed invention to significantly more than an abstract idea on the same grounds set forth above with respect to claim 1 above, and based on the Avidan and He references.
Claim 22, which depends from claim 21, recites that the instructions are further to cause the processing resource to determine the list of substitutes for the item by accessing an item taxonomy database comprising a respective item taxonomy for each item in a catalog of items. The courts have recognized storing and retrieving information in memory as well-understood, routine, and conventional functions, in Versata Dev. Group, Inc. v. SAP Am., Inc., 793 F.3d at 1306, 1334, 115 USPQ2d 1681, 1701 (Fed. Cir. 2015); OIP Techs., Inc., v. Amazon.com, Inc., 788 F.3d 1363, 115 USPQ2d at 1092-93 (Fed. Cir. 2015). Therefore, the step of accessing an item taxonomy database requires only the use of well-understood, routine, and conventional functions and technology, e.g., to access data in a memory. The limitation of claim 22, whether considered separately or in combination with the limitations of claim 21, does not raise the claimed invention to significantly more than an abstract idea.
Claim 23, which depends from claim 21, recites that the positive and negative historical acceptance data includes the probability of the similarity between the historical title and the historical description of the historical substitute. Having data include a particular probability is not in itself technological. The limitation of claim 23, whether considered separately or in combination with the limitations of claim 21, does not raise the claimed invention to significantly more than an abstract idea.
Double Patenting
The nonstatutory double patenting rejection is based on a judicially created doctrine grounded in public policy (a policy reflected in the statute) so as to prevent the unjustified or improper timewise extension of the “right to exclude” granted by a patent and to prevent possible harassment by multiple assignees. A nonstatutory double patenting rejection is appropriate where the conflicting claims are not identical, but at least one examined application claim is not patentably distinct from the reference claim(s) because the examined application claim is either anticipated by, or would have been obvious over, the reference claim(s). See, e.g., In re Berg, 140 F.3d 1428, 46 USPQ2d 1226 (Fed. Cir. 1998); In re Goodman, 11 F.3d 1046, 29 USPQ2d 2010 (Fed. Cir. 1993); In re Longi, 759 F.2d 887, 225 USPQ 645 (Fed. Cir. 1985); In re Van Ornum, 686 F.2d 937, 214 USPQ 761 (CCPA 1982); In re Vogel, 422 F.2d 438, 164 USPQ 619 (CCPA 1970); In re Thorington, 418 F.2d 528, 163 USPQ 644 (CCPA 1969).
A timely filed terminal disclaimer in compliance with 37 CFR 1.321(c) or 1.321(d) may be used to overcome an actual or provisional rejection based on nonstatutory double patenting provided the reference application or patent either is shown to be commonly owned with the examined application, or claims an invention made as a result of activities undertaken within the scope of a joint research agreement. See MPEP § 717.02 for applications subject to examination under the first inventor to file provisions of the AIA as explained in MPEP § 2159. See MPEP § 2146 et seq. for applications not subject to examination under the first inventor to file provisions of the AIA . A terminal disclaimer must be signed in compliance with 37 CFR 1.321(b).
The filing of a terminal disclaimer by itself is not a complete reply to a nonstatutory double patenting (NSDP) rejection. A complete reply requires that the terminal disclaimer be accompanied by a reply requesting reconsideration of the prior Office action. Even where the NSDP rejection is provisional the reply must be complete. See MPEP § 804, subsection I.B.1. For a reply to a non-final Office action, see 37 CFR 1.111(a). For a reply to final Office action, see 37 CFR 1.113(c). A request for reconsideration while not provided for in 37 CFR 1.113(c) may be filed after final for consideration. See MPEP §§ 706.07(e) and 714.13.
The USPTO Internet website contains terminal disclaimer forms which may be used. Please visit www.uspto.gov/patent/patents-forms. The actual filing date of the application in which the form is filed determines what form (e.g., PTO/SB/25, PTO/SB/26, PTO/AIA /25, or PTO/AIA /26) should be used. A web-based eTerminal Disclaimer may be filled out completely online using web-screens. An eTerminal Disclaimer that meets all requirements is auto-processed and approved immediately upon submission. For more information about eTerminal Disclaimers, refer to www.uspto.gov/patents/apply/applying-online/eterminal-disclaimer.
Claims 1, 3, 4, 5, 6, 7, 8, 9, 10, 21, 22, and 23 are rejected on the ground of nonstatutory double patenting as being unpatentable over claims 1, 2, 3, 4, 5, 6, 7, 8, and 10 of U.S. Patent No. 11,847,685. Although the claims at issue are not identical, they are not patentably distinct from each other because claim 1 of the instant application is essentially a broader version of claim 1 of the ‘685 patent, with various limitations of claim 1 of the ‘685 patent omitted, and now with language corresponding to claim 3 of the ‘685 patent incorporated, but with nothing to significantly narrow the claims. As may be seen in Table 1 below (where language present in one claim, but not in a parallel claim to which that claim is being compared, is bolded), claim 1 of the instant application has re-training based on at least the labeled training data and a highest ranked substitute of the list of substitutes; claim 1 of the ’685 patent stores a selection of a highest ranked possible substitute as additional training data, and then recites re-training the machine learning algorithm based on the additional training data and the labeled training data. Claim 3 of the instant application directly corresponds to claim 2 of the ‘685 patent. Claim 4 of the instant application corresponds, with minor differences in wording, to parts of claim 4 of the ‘685 patent. Claim 5 of the instant application corresponds to a limitation in claim 1 of the ‘685 patent. Claim 6 of the instant application corresponds, with minor differences in wording, to parts of claim 7 of the ‘685 patent. Claim 7 of the instant application corresponds, with minor differences in wording, to claim 5 of the ‘685 patent. Claim 8 of the instant application corresponds, with minor differences in wording, to claim 6 of the ‘685 patent. Claim 9 of the instant application corresponds, with minor differences in wording, to parts of claim 8 of the ‘685 patent. Claim 10 of the instant application corresponds, with minor differences in wording, to claim 10 of the ‘685 patent.
Claim 21 of the instant application is parallel to claim 1 of the instant application and to claim 1 of the ‘685 patent, reciting “A non-transitory computer-readable medium comprising instructions”, which is also present, worded slightly differently, in the system claim 1 of the ‘685 patent. Therefore claim 21 is likewise rejected for double patenting over claims 1 and 3 of the ‘685 patent. Claim 22 of the instant application is essentially parallel to the preamble and first subsequent clause of claim 2 of the ‘685 patent. Claim 23 of the instant application is essentially parallel to language of claim 3 of the ‘685 patent (the preamble and first subsequent clause).
Table 1
Instant Application
U.S. Patent 11,847,685
1. A system comprising:
one or more processors; and
one or more non-transitory computer-readable media storing computing instructions that, when executed on the one or more processors, cause the one or more processors to perform operations comprising:
training, using labeled training data, a machine learning algorithm, wherein the labeled training data comprises positive and negative historical acceptance data that includes at least one of:
a probability of a similarity between a historical title for a historical item and a historical description of a historical substitute,
a taxonomy difference for the historical item and the historical substitute,
a difference between the historical item and the historical substitute, or
a normalized rank comparison for the historical item and the historical substitute;
using the machine learning algorithm, as trained, to determine scores for a list of substitutes for an item; and
re-training the machine learning algorithm based on at least the labeled training data and a highest ranked substitute from a ranking of the list of substitutes based on the scores.
3. The system of claim 1, wherein the computing instructions, when executed on the one or more processors, further cause the one or more processors to perform an operation comprising: determining the list of substitutes for the item comprising:
accessing an item taxonomy database comprising a respective item taxonomy for each item in a catalog of items; identifying a specific item taxonomy for the item; filtering out non-matching items of the catalog of items, wherein the non-matching items comprise a different item taxonomy than the specific item taxonomy of the item; and adding matching items of the catalog of items to the list of substitutes, wherein the matching items of the catalog of items comprise the specific item taxonomy.
4. The system of claim 1, wherein determining the scores are based on comparisons of:
a respective brand for each substitute of the list of substitutes;
a respective attribute for each substitute of the list of substitutes and an attribute of the item; and
a respective product for each substitute of the list of substitutes and a product of item.
5. The system of claim 1, wherein the operations further comprise:
storing information, based on a selection of the highest ranked substitute as additional training data for the labeled training data.
6. The system of claim 1, wherein the operations further comprise:
determining the ranking of the list of substitutes by:
when two or more substitutes of the list of substitutes have approximately similar final scores, determining a quantity ratio comprising a ratio of a quantity for the item to a respective quantity for each substitute of the list of substitutes, wherein:
the quantity for the item comprises:
either (i) a weight of the item or (ii) a volume of the item, divided by a count of the item; and
the respective quantity for each substitute of the list of substitutes comprises:
either (i) a respective weight of each substitute of the list of substitutes or (ii) a respective volume of each substitute of the list of substitutes, divided by a respective count of each substitute of the list of substitutes.
.
7. The system of claim 1, wherein the computing instructions, when executed on the one or more processors, further cause the one or more processors to perform an operation comprising: determining a respective historical substitution score, comprising: determining a respective number of successful substitutions for each substitute of the list of substitutes; determining a respective number of unsuccessful substitutions for each substitute of the list of substitutes; calculating a respective historical acceptance rate for each substitute of the list of substitutes using the respective number of successful substitutions for each substitute of the list of substitutes and the respective number of unsuccessful substitutions for each substitute of the list of substitutes; and
assigning the respective historical substitution score based on the respective historical acceptance rate for each substitute of the list of substitutes and the respective number of successful substitutions for each substitute of the list of substitutes.
8. The system of claim 1, wherein the computing instructions, when executed on the one or more processors, further cause the one or more processors to perform an operation comprising:
inputting the respective similarity score for each substitute of the list of substitutes and a respective historical substitution score for each substitute of the list of substitutes into a feed-forward neural network comprising one or more rectifiers having ReLU non-linearity, wherein the feed-forward neural network is trained without unsupervised pre-training.
9. The system of claim 1, wherein the computing instructions, when executed on the one or more processors, further cause the one or more processors to perform operations comprising: determining respective qualities for each substitute of the list of substitutes;
facilitating a display, on a user interface of a user device, of the highest ranked substitute of the list of substitutes;
receiving, from the user interface of the user device, a selection of the highest ranked substitute;
after receiving the selection of the highest ranked substitute, substituting the highest ranked substitute for the item;
receiving a respective title for each substitute of the list of substitutes; and
identifying a respective brand for each substitute of the list of substitutes using the respective title for each substitute of the list of substitutes.
10. The system of claim 1, wherein the computing instructions, when executed on the one or more processors, further cause the one or more processors to perform operations comprising:
when the item is out of stock, comparing a respective dietary restriction for each substitute of the list of substitutes with a dietary restriction of [the item];
when a dietary restriction of a substitute of a list of substitutes does not match the dietary restriction of [the item], removing the substitute of the list of substitutes from the list of substitutes.
1. A system comprising:
one or more processors; and
one or more non-transitory computer-readable media storing computing instructions that, when executed on the one or more processors, cause the one or more processors to perform operations
comprising:
determining a list of possible substitutes for an item of a list of items when the item of the list of items is out of stock;
training a machine learning algorithm, using labeled training data as input and a list of possible substitutes for the item as output;
determining, using the machine learning algorithm, as trained, a respective similarity score for each possible substitute of the list of possible substitutes;
determining a respective historical substitution score for each possible substitute of the list of possible substitutes;
determining a respective final substitution score for each possible substitute of the list of possible substitutes comprises using at least one or more rectifiers having ReLU non-linearity that enables training of deep supervised neural networks without unsupervised pre-training;
ranking each possible substitute of the list of substitutes based upon the respective final score for each possible substitute;
storing a selection of a highest ranked possible substitute as additional training data with the labeled training data; and
re-training the machine learning algorithm based on the additional training data and the labeled training data.
3. The system of claim 1, wherein the labeled training data further comprises: all positive historical acceptance data and randomly sampled negative historical acceptance data, wherein each labeled training datum of the labeled training data is labeled with at least one of:
a respective probability of a respective similarity between a respective historical title for a respective historical item and a respective historical description of a respective historical substitute;
a respective taxonomy difference for the respective historical item and the respective historical substitute;
a respective price difference between the respective historical item and the respective historical substitute; or a respective normalized sales rank comparison for the respective historical item and the respective historical substitute.
2. The system of claim 1, wherein determining the list of possible substitutes comprises:
accessing an item taxonomy database comprising a respective item taxonomy for each item in a catalog of items;
identifying a specific item taxonomy for the item; filtering out non-matching items of the catalog of items, wherein the non-matching items comprise a different item taxonomy than the specific item taxonomy of the item; and adding matching items of the catalog of items to the list of substitutes, wherein the matching items of the catalog of items comprise the specific item taxonomy.
4. The system of claim 1, wherein determining the respective similarity score for each substitute of the list of substitutes further comprises:
determining a respective title similarity score for each substitute of the list of substitutes by comparing:
a respective brand for each possible substitute of the list of possible substitutes and a brand of the item of list of items;
a respective attribute for each possible substitute of the list of possible substitutes and an attribute of the item of the list of items; and
a respective product for each possible substitute of the list of possible substitutes and a product of the item of the list of items; and
determining the respective title similarity score for each possible substitute of the list of possible substitutes comprises using a logistic regressor trained on at least:
respective historical acceptance data for each possible substitute of the list of possible substitutes; or manually chosen substitute data.
7. The system of claim 1, wherein ranking each substitute of the list of substitutes further comprises:
when two or more possible substitutes of the list of possible substitutes have approximately similar final scores, determining a quantity ratio comprising a ratio of a quantity for the item to a respective quantity for each possible substitute of the list of possible substitutes, wherein
the quantity for the item comprises:
either (i) a weight of the item or (ii) a volume of the item, divided by a count of the item; and
the respective quantity for each possible substitute of the list of possible substitutes comprises:
either (i) a respective weight of each possible substitute of the list of possible substitutes or (ii) a respective volume of each possible substitute of the list of possible substitutes, divided by a respective count of each possible substitute of the list of possible substitutes; and
ranking a first possible substitute of the list of possible substitutes of the list of possible substitutes with a first quantity ratio above a second possible substitute of the list of possible substitutes with a second quantity ratio that is higher than the first quantity ratio.
5. The system of claim 1, wherein determining the historical substitution score comprises:
determining a respective number of successful substitutions for each possible substitute of the list of possible substitutes;
determining a respective number of unsuccessful substitutions for each possible substitute of the list of possible substitutes;
calculating a respective historical acceptance rate for each possible substitute of the list of possible substitutes using the respective number of successful substitutions for each possible substitute of the list of possible substitutes and the respective number of unsuccessful substitutions for each possible substitute of the list of possible substitutes; and
assigning the respective historical substitution score based on the respective historical acceptance rate for each substitution of the list of possible substitutes and the respective number of successful substitutions for each possible substitute of the list of possible substitutes.
6. The system of claim 1, wherein determining the respective final score for each possible substitute of the list of possible substitutes further comprises: inputting the respective similarity score for each possible substitute of the list of possible substitutes and a respective historical substitution score for each possible substitute of the list of possible substitutes into a feed-forward neural network comprising the one or more rectifiers having ReLU non-linearity, wherein the feed-forward neural network is trained without unsupervised pre-training.
8. The system of claim 1, wherein the computing instructions, when executed on the one or more processors, further cause the one or more processors to perform operations comprising: determining respective qualities for each possible substitute of the list of possible substitutes;
facilitating a display, on a user interface of a user device, of a highest ranked possible substitute of the list of possible substitutes;
receiving, from the user interface of the user device, the selection of the highest ranked possible substitute of the list of possible substitutes;
after receiving the selection of the highest ranked possible substitute, substituting the highest ranked possible substitute of the list of possible substitutes for the item;
receiving a respective title for each possible substitute of the list of possible substitutes;
identifying a respective brand for each possible substitute of the list of possible substitutes using the respective title for each possible substitute of the list of possible substitutes, wherein identifying the respective brand, a respective attribute, and a respective dietary restriction comprises using a Hidden Markov Model;
identifying the respective attribute for each possible substitute of the list of possible substitutes using the respective title for each possible substitute of the list of possible substitutes;
identifying the respective product for each possible substitute of the list of possible substitutes using the respective title for each possible substitute of the list of possible substitutes;
and identifying the respective dietary restriction for each possible substitute of the list of possible substitutes using the respective title for each possible substitute of the list of possible substitutes.
10. The system of claim 1, wherein, the computing instructions, when executed on the one or more processors, further cause the one or more processors to perform operations comprising:
when the item is out of stock, comparing a respective dietary restriction for each possible substitute of the list of possible substitutes with a dietary restriction of the item of the list of items;
when a dietary restriction of a possible substitute of the list of possible substitutes does not match the dietary restriction of the item of the list of items, removing the possible substitute of the list of possible substitutes from the list of possible substitutes.
Claims 11, 13, 14, 15, 16, 17, 18, and 19 are rejected on the ground of nonstatutory double patenting as being unpatentable over claims 11, 12, 13, 14, 15, 16, 17, and 18 of U.S. Patent No. 11,847,685. Although the claims at issue are not identical, they are not patentably distinct from each other because claim 11 of the instant application is essentially a broader version of claim 11 of the ‘685 patent, with various limitations of claim 11 of the ‘685 patent omitted, and now with language corresponding to claim 13 of the ‘685 patent incorporated, but with nothing to significantly narrow the claims. As may be seen in Table 2 below (where language present in one claim, but not in a parallel claim to which that claim is being compared, is bolded), claim 11 of the instant application has re-training based on at least the labeled training data and a highest ranked substitute of the list of substitutes; claim 11 of the ’685 patent stores a selection of a highest ranked possible substitute as additional training data, and then recites re-training the machine learning algorithm based on the additional training data and the labeled training data. Claim 13 of the instant application directly corresponds to claim 12 of the ‘685 patent. Claim 14 of the instant application now corresponds, with minor differences in wording, to some elements of claim 14 of the ‘685 patent. Claim 15 of the instant application corresponds to a limitation in claim 11 of the ‘685 patent. Claim 16 of the instant application now corresponds, with minor differences in wording, to some of the limitations of claim 17 of the ‘685 patent (and to the recitation of “ranking each possible substitute” in claim 11 of the ‘685 application). Claim 17 of the instant application corresponds, with minor differences in wording, to claim 15 of the ‘685 patent. Claim 18 of the instant application now corresponds, with minor differences in wording, to most of claim 16 of the ‘685 patent. Claim 19 of the instant application now corresponds, with minor differences in wording, to parts of claim 18 of the ‘685 patent.
Table 2
Instant Application
U.S. Patent 11,847,685
11. A method being implemented via execution of computing instructions configured to run on one or more processors and stored at one or more non-transitory computer-readable media, the method comprising:
training, using labeled training data, a machine learning algorithm, wherein the labeled training data comprises positive and negative historical acceptance data that includes at least one of:
a probability of a similarity between a historical title for a historical item and a historical description of a historical substitute,
a taxonomy difference for the historical item and the historical substitute,
a difference between the historical item and the historical substitute, or
a normalized rank comparison for the historical item and the historical substitute;
using the machine learning algorithm, as trained, to determine a ranking of a list of substitutes for an item; and
re-training the machine learning algorithm based on at least the labeled training data and a highest ranked substitute from the ranking of the list of substitutes.
13. The method of claim, 11 further comprising:
determining the list of substitutes for the item comprising:
accessing an item taxonomy database comprising a respective item taxonomy for each item in a catalog of items; identifying a specific item taxonomy for the item;
filtering out non-matching items of the catalog of items, wherein the non-matching items comprise a different item taxonomy than the specific item taxonomy of the item; and
adding matching items of the catalog of items to the list of substitutes, wherein the matching items of the catalog of items comprise the specific item taxonomy.
14. The meth