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 .
Claim Rejections - 35 USC § 112
The following is a quotation of the first paragraph of 35 U.S.C. 112(a):
(a) IN GENERAL.—The specification shall contain a written description of the invention, and of the manner and process of making and using it, in such full, clear, concise, and exact terms as to enable any person skilled in the art to which it pertains, or with which it is most nearly connected, to make and use the same, and shall set forth the best mode contemplated by the inventor or joint inventor of carrying out the invention.
The following is a quotation of the first paragraph of pre-AIA 35 U.S.C. 112:
The specification shall contain a written description of the invention, and of the manner and process of making and using it, in such full, clear, concise, and exact terms as to enable any person skilled in the art to which it pertains, or with which it is most nearly connected, to make and use the same, and shall set forth the best mode contemplated by the inventor of carrying out his invention.
Claims 1-2, 6-9, 12-16, 18 and 21 are rejected under 35 U.S.C. 112(a) or 35 U.S.C. 112 (pre-AIA ), first paragraph, as failing to comply with the written description requirement. The claim(s) contains subject matter which was not described in the specification in such a way as to reasonably convey to one skilled in the relevant art that the inventor or a joint inventor, or for applications subject to pre-AIA 35 U.S.C. 112, the inventor(s), at the time the application was filed, had possession of the claimed invention.
Independent claims 1 and 15, as well as dependent claim 21 have been amended to include the limitation “feature vector”, which is not disclosed in the written description (specification, claims or drawings) as originally filed. Therefore, these limitations are considered to be new matter.
Dependent claims 2, 6-9, 12-14, 16, 18 and 21 are rejected for their dependency on their respective independent base claims 1 and 15.
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 19 is rejected under 35 U.S.C. 101 because the claimed invention is directed to an abstract idea without significantly more.
Step 1: Whether a Claim is to a Statutory Category
In the instant case, independent claim 19 recites a system/machine that is performing a series of functions. Therefore, these claims fall within the four statutory categories of invention of a process and a machine.
Step2A – Prong 1: Does the Claim Recite a Judicial Exception
Exemplary claim 19 recites the following abstract concepts that are found to include an enumerated “abstract idea”:
A system comprising:
a processor; and
a memory comprising a non-transitory computer readable storage medium having instructions encoded thereon that, when executed by a processor, cause the processor to:
receive, from a first client device, an order for items offered by a warehouse, wherein the order includes at least a first item associated with a first product category and a second item associated with a second product category and not associated with the first product category;
for each item in the order, identify one or more product categories associated with at least one sequence in a plurality of sequences of product categories, wherein each sequence in the plurality of sequences is associated with a level of a taxonomy, the plurality of sequences including a first sequence associated with a sub-aisle level of the taxonomy and a second sequence associated with an aisle level of the taxonomy, the plurality of sequences generated by:
selecting, for each level of a taxonomy, a product category in the level most associated with an initial pick in historical pick data; and
traversing, at a level of the selected product category in the taxonomy, pairwise relations between product categories in order of strongest pairwise relation to a currently selected product category in the taxonomy;
rank each item based on the order of the identified one or more product categories of the item in the first sequence, wherein, in response to determining that none of the identified product categories of a respective item are contained in the first sequence, estimating the rank for the respective item based on the second sequence;
generate a pick sequence for the order based on the ranking; and
send the pick sequence to a second client device, wherein the second client device performs one or more actions based on the pick sequence.
[Emphasis added to show the bolded abstract idea being executed by unbolded additional elements that do not meaningfully limit the abstract idea]
This system claim is grouped within the "certain methods of organizing human activity” grouping of abstract ideas in prong one of step 2A of the Alice/Mayo test because the claims involve a series of steps for following rules or instructions to generate a pick sequence for the order which is a process that is encompassed by the abstract idea of managing personal behavior. See e.g., MPEP 2106.04(a)(2)(II)(C); 2106.05(h); and July 2024 Subject Matter Eligibility Example 47 claim 2. Accordingly, the claims recite an abstract idea.
Step2A – Prong 2: Does the Claim Recite Additional Elements that Integrate the Judicial Exception into a Practical Application
This judicial exception is not integrated into a practical application because, when analyzed under prong two of step 2A of the Alice/Mayo test, the additional elements of the claims such as a processor, memory, non-transitory computer readable storage medium, first client device and second client device merely use a computer as a tool to perform an abstract idea and/or generally link the use of a judicial exception to a particular technological environment. Specifically, the processor, memory, non-transitory computer readable storage medium, first client device and second client device perform the steps or functions of following rules or instructions to generate a pick sequence for the order. The use of a processor/computer as a tool to implement the abstract idea and/or generally linking the use of the abstract idea to a particular technological environment does not integrate the abstract idea into a practical application because it requires no more than a computer (or technical elements disclosed at a high level of generality such as processor, memory, non-transitory computer readable storage medium, first client device and second client device) performing functions of receiving, identifying, generating, selecting, traversing, ranking, determining, estimating, sending and performing that correspond to acts required to carry out the abstract idea (MPEP 2106.05(f) and (h)). Accordingly, the additional elements do not impose any meaningful limits on practicing the abstract idea, and the claims are directed to an abstract idea.
Step2B: Does the Claim Amount to Significantly More
The claims do not include additional elements that are sufficient to amount to significantly more than the judicial exception. The additional element analysis of Step 2A Prong 2 is equally applied to Step 2B. “Another consideration when determining whether a claim recites significantly more than a judicial exception is whether the additional element(s) are well-understood, routine, conventional activities previously known to the industry. This consideration is only evaluated in Step 2B of the eligibility analysis.” MPEP 2106.05(d). The courts have recognized the following computer functions as well‐understood, routine, and conventional (“WURC”) functions when they are claimed in a merely generic manner (e.g., at a high level of generality) or as insignificant extra-solution activity. Exemplary claim 19 recites the following limitations that the courts have found to be WURC:
Claim 19 includes several limitations relating to receiving or transmitting data over a network (receive, from a first client device, an order for items …; and send the pick sequence to a second client device … as claimed) data. See MPEP 2106.05(d)(II) where courts found to be WURC - i. Receiving or transmitting data over a network, e.g., using the Internet to gather data, Symantec, 838 F.3d at 1321, 120 USPQ2d at 1362 (utilizing an intermediary computer to forward information); TLI Communications LLC v. AV Auto. LLC, 823 F.3d 607, 610, 118 USPQ2d 1744, 1745 (Fed. Cir. 2016) (using a telephone for image transmission); OIP Techs., Inc., v. Amazon.com, Inc., 788 F.3d 1359, 1363, 115 USPQ2d 1090, 1093 (Fed. Cir. 2015) (sending messages over a network); buySAFE, Inc. v. Google, Inc., 765 F.3d 1350, 1355, 112 USPQ2d 1093, 1096 (Fed. Cir. 2014) (computer receives and sends information over a network); but see DDR Holdings, LLC v. Hotels.com, L.P., 773 F.3d 1245, 1258, 113 USPQ2d 1097, 1106 (Fed. Cir. 2014) ("Unlike the claims in Ultramercial, the claims at issue here specify how interactions with the Internet are manipulated to yield a desired result‐‐a result that overrides the routine and conventional sequence of events ordinarily triggered by the click of a hyperlink." (emphasis added));
Claim 19 includes several limitations relating to performing repetitive calculations (identify one or more product categories associated with at least one sequence in a plurality of sequences of product categories … the plurality of sequences generated by: selecting, for each level of a taxonomy, …; traversing, at a level of the selected product category in the taxonomy, pairwise relations between product categories in order of strongest pairwise relation to a currently selected product category in the taxonomy; rank each item based on the order of the identified one or more product categories of the item in the first sequence …; and generate a pick sequence for the order based on the ranking as claimed) data. See MPEP 2106.05(d)(II) where courts found to be WURC - ii. Performing repetitive calculations, Flook, 437 U.S. at 594, 198 USPQ2d at 199 (recomputing or readjusting alarm limit values); Bancorp Services v. Sun Life, 687 F.3d 1266, 1278, 103 USPQ2d 1425, 1433 (Fed. Cir. 2012) ("The computer required by some of Bancorp’s claims is employed only for its most basic function, the performance of repetitive calculations, and as such does not impose meaningful limits on the scope of those claims.");
Accordingly, when viewed alone and in ordered combination, these additional elements are not found to recite significantly more than the underlying abstract idea.
Claim Rejections - 35 USC § 103
The following is a quotation of 35 U.S.C. 103 which forms the basis for all obviousness rejections set forth in this Office action:
A patent for a claimed invention may not be obtained, notwithstanding that the claimed invention is not identically disclosed as set forth in section 102, if the differences between the claimed invention and the prior art are such that the claimed invention as a whole would have been obvious before the effective filing date of the claimed invention to a person having ordinary skill in the art to which the claimed invention pertains. Patentability shall not be negated by the manner in which the invention was made.
Claims 1-2, 6-9, 12-16, 18-19 and 21 are rejected under 35 U.S.C. 103 as being unpatentable over Francis (US 2024/0303594 A1) in view of Fu et al. (US 2021/0139256 A1).
Regarding Claim 1, modified Francis teaches:
A method comprising:
at a computer system comprising at least one processor and non-transitory memory (See Francis ¶ [0073-0074] – an order filling system (OFS) comprising a central computing system (CCS) and one or more mobile scanning devices (MSDs), [0217-0219] – processing module of the MSDs sending data and [0267] – CCS and MSDs using data stored in memory):
obtaining historical pick data for a plurality of items located in a warehouse (See Francis ¶ [0073-0074] – an order filling system (OFS) for items located in a retail store, warehouse, etc. and [0356] – using historical scanning/ picking data for items to determine an efficient picking route), the historical pick data comprising product data for each of the items picked and pick times between each of the items picked (See Francis ¶ [0356] – using historical scanning/ picking data for items comprising a time each item was scanned/ picked, [0390] – scan data comprises item IDs [product data] and [0724] – historical scan data is used to guide user movement for picking items);
determining a taxonomy of the plurality of items offered by the warehouse, the taxonomy identifying a plurality of product categories structured in a hierarchy, each level of the hierarchy corresponding to a particular level of granularity of product data (The specification of the instant application gives no special definition of the limitation taxonomy, for the purpose of examination, said taxonomy is interpreted to mean a hierarchy relating to product categories. Therefore, see Francis ¶ [0360] – grouping items based on item types/ categories showing item location data associated with aisle numbers [a particular level of granularity of product data], [0491] – location data comprising department names [another particular level of granularity of product data and [0677] – using a hierarchy of operations to calculate picking routes), wherein the hierarchy includes an aisle level and a sub-aisle level (See Francis ¶ [0112] – similar types of items may be grouped together along an aisle in a typical store. For example, the items located along aisle 122-1 [aisle level] (i.e., the items accessible in aisle 122-1 from rack 116-1 and rack 116-2 [sub-aisle level]) may be items of a similar type), wherein each product category in the sub-aisle level corresponds to a different subsection of an aisle associated with a respective product category in the aisle level (See Francis ¶ [0112] – the items along aisle 122-1 may be cereal items (e.g., bags or boxes of cereal), [0433] - The captured image depicts a plurality of items 5804 (e.g., boxes) that are included on a rack 5802. For example, the image depicts, inter alia, a box of Froot Loops 5806, a location indicator 5808 (e.g., a barcode) attached to a shelf 5810, and an aisle sign 5812 including text (e.g., an aisle name and/or number), [0543] - location descriptors may include aisle names and/or numbers. Additional example location descriptors may also include aisle descriptors, such as first/second aisle ends, aisle middle, and/or shelf location (e.g., bottom shelf, top shelf) [subsection of an aisle by example]), and wherein the sub-aisle level has a higher level of granularity of product data than the aisle level (See Francis ¶ [0365] – the MSDs and/or CCS may add granularity to, or enhance resolution of, relative locations of the items included in the zone and [0401] - if a location indicator covers an entire aisle of items, the item adjacency map may define more granular arrangements of items on the display);
applying the historical pick data to a trained machine learning model (See Francis ¶ [0441] – MSD using a machine learning model for image classification while in “picking” mode, thereby training said MSD from pick data) to generate pairwise relations between product categories in the plurality of product categories, wherein the machine learning model generates a pairwise relation for each pair of product categories at each level of the taxonomy (See Francis ¶ [0392-0393] – scanning multiple items and recognizing paired relationships between items signifying adjacency based on time between each scan of each item and [0441-0442] – MSD using a machine learning image classification models based on product categories at each level of the taxonomy by example by segmenting said model based on the particular areas/ sections [departments or aisles as noted above regarding ¶ [0360] & [0491]] of the store), the machine learning model trained by:
applying, to the machine learning model configured with a first set of weights, training data including historical pick data and target pairwise relations (See Francis ¶[0392-0393] - the CCS may determine that the three items in two pairs of adjacent items are adjacent if the sum of the scan times between the first pair of items and the second pair of items is less than a threshold value… The CCS may make the determination in block 5212 using various scan times associated with the pairs, such as the most recent scan times, average scan times, etc. In block 5214, the CCS updates the item adjacency map to indicate the items in the pairs of items are adjacent if the criteria in block 5212 are satisfied and [0629] – the CCS/MSDs may implement a scoring model in which different possible routes for an MSD are scored, and the highest scoring route is assigned (e.g., highest scoring indicates a best route)… a scoring module at the CCS/MSDs may apply different weights and scores to different aspects of a route (e.g., route length, item number, distance from MSD, etc.) … the CCS/MSDs may implement a machine learned model for generating routes/scores, where the machine learned model receives different routing factors as inputs. The machine learned model may be trained on historic picking/movement data);
determining, by the machine learning model configured with the first set of weights (See Francis ¶[0392-0393] and [0629] as noted above), a first predicted pairwise relation for each pair of product categories at each level of the taxonomy based on a feature vector representing the historical pick data for items in the respective pair of product categories (The limitation “feature vector” is not supported by the written description of the instant application and is new matter. Nonetheless, see Francis ¶[0377] - the MSD determines that the first and second items are adjacent to one another… reinforcing a determination of adjacency may include updating data associated with the adjacent items that indicates the scan times between items have satisfied item adjacency criterion multiple times… the MSD and/or CCS may update the item adjacency map to include, for each pair of adjacent items, a reinforcement indicator value that indicates the number of times the two items have been considered adjacent); and
updating the machine learning model with a second set of weights, wherein the updated machine learning model is configured to produce a second predicted pairwise relation for each pair of product categories (See Francis ¶ [0435] - The image processing module may feed the set of features to one or more machine-learned image classification models, which respectively output a classification of the blob based on the set of features, [0441] - an MSD may include an image processing module that classifies images … the MSD may implement a set of machine-learned image classification models stored thereon that the MSD uses to perform image classification… the image classification model(s) of an MSD may be updated when new items or objects are identified… the image classification models used by the MSD when the MSD is in a “picking” mode may be trained to identify a reduced subset of the items in the store… and [0629] - the CCS/MSDs may implement a scoring model in which different possible routes for an MSD are scored… a scoring module at the CCS/MSDs may apply different weights and scores to different aspects of a route … the CCS/MSDs may implement a machine learned model for generating routes/scores, where the machine learned model receives different routing factors as inputs… the machine learned model may be trained on historic picking/movement data), wherein a value between the second predicted pairwise relation and a respective target pairwise relation is smaller than the value between the first predicted pairwise relation and the respective target pairwise relation (See Francis ¶ [0373] - an indication of whether two of the items are adjacent to one another may be determined and/or reinforced based on relatively temporally close scan times associated with the items, indicating that the items are adjacent to one another. Alternatively, the indication of whether the two of the items are adjacent to one another may be removed based on relatively temporally distant scan times associated with the items, indicating that the items are not adjacent to one another and [0492] - the MSD and/or the CCS may generate/update an item association table that associates object-based IDs with items. Although the scanned items may be associated with previously determined object-based IDs, in some cases, the MSD and/or the CCS may be configured to associate a scanned item with a later determined object-based ID, such as when the later determined object-based ID [second predicted pairwise relation] is determined closer in time [smaller than the value between the first predicted pairwise relation] to the scanned item than a previously determined object-based ID [target pairwise relation]. The association between object-based IDs and items may be updated over time.);
generating a plurality of sequences of product categories based on the generated pairwise relations, wherein each sequence in the plurality of sequences is associated with a level of the taxonomy, the plurality of sequences including a first sequence associated with the sub-aisle level of the taxonomy and a second sequence associated with the aisle level of the taxonomy, (See Francis ¶ [0360] – grouping items based on item types/ categories showing item location data associated with aisle numbers [aisle level of the taxonomy], [0371] – generating adjacency maps [sequence of products] shown as a list of adjacent items [products], [0392-0393] – scanning multiple items and recognizing paired relationships between items signifying adjacency based on time between each scan of each item and [0440] - the map generation module may generate the image-based map to indicate locations of items and/or store objects with respect to one another… if a first brand of cereal and a second brand of cereal are classified in the same image (e.g., they are both on the same rack [sub-aisle level of taxonomy]), the map generation module may indicate an adjacency between the first and second brand of cereal in the image-based map), by:
selecting, for each level of the taxonomy, a product category in the level most associated with an initial pick in the historical pick data (See Francis ¶ [0357] – one or more other items in a customer order are included for a particular user based on adjacency of said items to said seed item, wherein said adjacent items are determined to be closest to said user and designated as the next item to be picked, [0654] – the initially selected item acting as a seeding item and [0718-0720] – ranking items by individual item or item type [category] and using said item ranking and user movement data to generate a pick sequence); and
traversing, at a level of the selected product category in the taxonomy, the generated pairwise relations in order of strongest pairwise relation to a currently selected product category in the taxonomy (As the specification of the instant application describes the strongest pairwise relation as the shortest distance from an initial “seed” item to the next item in a sequence of items, see Francis ¶ [0385-0387] – displaying items [product category] to a user MSD device in order of closest item to said device at the top of a list with other items following based on relative proximity to said user device when an initial item is scanned [pairwise relations in order of strongest pairwise relation to a currently selected product category in the taxonomy by example] and Fig. 48 – showing a sequence of items to pick relative to a location of a user MSD [at a level of the selected product category in the taxonomy by example]);
receiving an order for items offered by the warehouse (See Francis ¶ [0073-0075] – receiving customer orders to be fulfilled by a warehouse), wherein the order includes at least a first item associated with a first product category and a second item associated with a second product category and not associated with the first product category (See Francis ¶ [0360-0361] – one or more of the MSDs and/or the CCS may be configured to use metadata indicating a type/category (e.g., produce, dairy, meat products) [at least first and second product category by example] associated with an item included in a customer order to group (e.g., cluster) the item with one or more other items that are also included in the customer order… one or more of the MSDs and/or the CCS may be configured to identify a first item included in a first group and identify a second, different item, that is adjacent to the first item but not included in the first group [second product category and not associated with the first product category by example]); and
comparing the order to two or more sequences to generate a pick sequence for the order (See Francis ¶ [0365-0367] – the MSDs and/or CCS may be configured to identify a first item (e.g., an anchor item) included in a particular zone associated with a location indicator, and then determine relative locations of one or more different items also included in the zone [sequence by example] with respect to the first item using an adjacency map… one or more of the MSDs and/or CCS may be configured to make use of items (e.g., an anchor item) included in zones and MSDs transitioning from one zone to another zone [two or more sequences in the plurality of sequences by example]. For example, the MSDs and/or the CCS may determine that an item included in a first zone is proximate to an item included in a second zone upon an MSD scanning the two items within a predetermined threshold amount of time when the MSD transitions between the two zones, thereby defining edges of the zones… if an aisle has one or more zones in a line, the arrangement of items for picking may be organized in a linear fashion down the aisle from zone to zone based on the edge items and sequential items between the edge items… an MSD may be configured to display a subset of the items included in a customer order (e.g., items that are located proximate to the MSD at that time) [comparing the order by example]) by:
identifying, from each item in the order, one or more product categories associated with the respective item and the compared sequence (See Francis ¶ [0360-0361] – one or more of the MSDs and/or the CCS may be configured to use metadata indicating a type/category (e.g., produce, dairy, meat products) [at least first and second product category by example] associated with an item included in a customer order to group (e.g., cluster) the item with one or more other items that are also included in the customer order… one or more of the MSDs and/or the CCS may be configured to identify a first item included in a first group and identify a second, different item, that is adjacent to the first item but not included in the first group);
…each item in the order based on position of its identified one or more product categories in the first sequence, wherein, in response to determining that none of the identified product categories of a respective item are contained in the first sequence, estimating … for the respective item based on the second sequence… (See Francis ¶ [0360-0361] and [0365-0367] as noted above, as well as [0383] - the MSD may display the initial item at the top of a list and display the other items lower on the list based on the relative distances and/or times associated with the items and the initial item, [0387] - with respect to FIG. 48 , an MSD near item 4804-5 may display items 4804-3, 4804-4, 4804-5, and 4804-6 higher on the display to prompt the user to pick those items due to their adjacency. Due to the item adjacency map, this may even be the case if items 4804-3 and/or 4804-4 are in different zones (e.g., associated with different location values) than item 4804-5, wherein said different zones are different aisles [second sequence] as shown in Fig. 48); and
outputting the pick sequence, … (See Francis ¶ [0366-0367] – identifying a sequence of items in a customer order and generating a displayed list of said sequence, wherein said sequence may not be based on adjacency of said items in said order).
While Francis teaches arranging items in an order into a picking sequence based on item groupings associated with item categories (Francis ¶ [0360-0361] and [0365-0367]), Francis does not explicitly teach ranking or estimating the rank of said items in compared picking sequences or that the pick sequence is based on the ranking. This is taught by Fu (See Fu ¶ [0051-0052] – As each available case [item] is identified in progression (ranked and resolved into a sequence solution as further described) the matrix 999A, 999B is updated and reduced… where the flexible sequencer sequences case for picking … each available sequence solution of available cases of the generated sequence solution set (e.g., solution A, solution B, . . . , solution N) is ranked). It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to include in the item pick sequence generation system of Francis the use of ranked item pick sequences from multiple pick sequence solution options as taught by Fu to formulate an optimal, yet flexible sequence solution (Fu ¶ [0027]), thereby increasing the accuracy and efficiency of the item pick sequence generation system of Francis.
Regarding Claim 2, modified Francis teaches:
The method of claim 1, further comprising:
While Francis teaches arranging items in an order into a picking sequence based on item groupings associated with item categories (Francis ¶ [0360-0361] and [0365-0367]), Francis does not explicitly teach that the pick sequence is generated based on the ranking. This is taught by Fu (See Fu ¶ [0051-0052] – As each available case [item] is identified in progression (ranked and resolved into a sequence solution as further described) the matrix 999A, 999B is updated and reduced… where the flexible sequencer sequences case for picking … each available sequence solution of available cases of the generated sequence solution set (e.g., solution A, solution B, . . . , solution N) is ranked). It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to include in the item pick sequence generation system of Francis the use of ranked item pick sequences from multiple pick sequence solution options as taught by Fu to formulate an optimal, yet flexible sequence solution (Fu ¶ [0027]), thereby increasing the accuracy and efficiency of the item pick sequence generation system of Francis.
Regarding Claim 6, modified Francis teaches:
The method of claim 1, wherein the plurality of sequences includes a third sequence associated with a department level of the taxonomy (See Francis ¶ [0360] – grouping items based on item types/ categories showing item location data associated with aisle numbers and [0491] – location data comprising department names).
Regarding Claim 7, modified Francis teaches:
The method of claim 1, wherein each of the pairwise relations comprises a distance value (See Francis ¶ [0387] – displaying items based on relative distances between said items and [0391] – items are paired together based on satisfying adjacency criterion).
Regarding Claim 8, modified Francis teaches:
The method of claim 7, wherein the distance value is calculated based on or more of: a median pick time or a weighted average pick time (See Francis ¶ [0356] – describing scanning and picking to be the same activity and [0371] – estimating relative distance between adjacent items based on average/ median scan times).
Regarding Claim 9, modified Francis teaches:
The method of claim 7, wherein selecting, for each level of the taxonomy, a product category in the level most associated with an initial pick in the historical pick data (See claim 1 above) comprises:
a) selecting a particular level in the hierarchy (See Francis ¶ [0357] – user selecting one of a plurality of items from a display to start picking a customer order); and
b) selecting a seed from the particular level as a currently selected product category, the seed establishing a first product category in a generated sequence (See Francis ¶ [0357] – said item is a “seed” or “re-seed” item that is a next item to be picked by the user, thereby starting a picking sequence).
Regarding Claim 12, modified Francis teaches:
The method of claim 1, wherein the pairwise relations are stored in a symmetrical matrix (See Francis ¶ [0377] – adjacent items are paired together in an adjacency map, [0382] – adjacency map includes a table and Fig. 49 – said table comprises item IDs and adjacent item IDs for each respective item ID, thereby showing a symmetrical matrix by example).
Regarding Claim 13, modified Francis teaches:
The method of claim 1, wherein the pick sequence is rendered as a shopping list at a client device (See Francis ¶ [0501] – maps and tables used for picking routes may include a customer’s shopping list, wherein said list is sent to a customer in a GUI [rendered]).
Regarding Claim 14, modified Francis teaches:
The method of claim 13, wherein the order for the items offered at the warehouse is generated by a first client device operated by a first user, and wherein the shopping list is rendered at a second client device operated by a second user (See Francis ¶ [0095-0097] – customers placing orders on mobile devices and third party pickers picking items for said orders based websites or application running on devices used by said third parties and [0501] – maps and tables used for picking routes may include a customer’s shopping list, wherein said list is sent to a customer in a GUI [rendered]).
Regarding Claim 15, modified Francis teaches:
A computer program product comprising a non-transitory computer readable storage medium having instructions encoded thereon that, when executed by a processor, cause the processor to (See Francis ¶ [0073-0074] – an order filling system (OFS) comprising a central computing system (CCS) and one or more mobile scanning devices (MSDs), [0217-0219] – processing module of the MSDs sending data and [0267] – CCS and MSDs using data stored in memory):
obtain historical pick data for a plurality of items located in a warehouse (See Francis ¶ [0073-0074] – an order filling system (OFS) for items located in a retail store, warehouse, etc. and [0356] – using historical scanning/ picking data for items to determine an efficient picking route), the historical pick data comprising product data for each of the items picked and pick times between each of the items picked (See Francis ¶ [0356] – using historical scanning/ picking data for items comprising a time each item was scanned/ picked, [0390] – scan data comprises item IDs [product data] and [0724] – historical scan data is used to guide user movement for picking items);
determine a taxonomy of the plurality of items offered by the warehouse, the taxonomy identifying a plurality of product categories structured in a hierarchy, each level of the hierarchy corresponding to a particular level of granularity of product data (The specification of the instant application gives no special definition of the limitation taxonomy, for the purpose of examination, said taxonomy is interpreted to mean a hierarchy relating to product categories. Therefore, see Francis ¶ [0360] – grouping items based on item types/ categories showing item location data associated with aisle numbers [a particular level of granularity of product data], [0491] – location data comprising department names [another particular level of granularity of product data and [0677] – using a hierarchy of operations to calculate picking routes), wherein the hierarchy includes an aisle level and a sub-aisle level (See Francis ¶ [0112] – similar types of items may be grouped together along an aisle in a typical store. For example, the items located along aisle 122-1 [aisle level] (i.e., the items accessible in aisle 122-1 from rack 116-1 and rack 116-2 [sub-aisle level]) may be items of a similar type), wherein each product category in the sub-aisle level corresponds to a different subsection of an aisle associated with a respective product category in the aisle level (See Francis ¶ [0112] – the items along aisle 122-1 may be cereal items (e.g., bags or boxes of cereal), [0433] - The captured image depicts a plurality of items 5804 (e.g., boxes) that are included on a rack 5802. For example, the image depicts, inter alia, a box of Froot Loops 5806, a location indicator 5808 (e.g., a barcode) attached to a shelf 5810, and an aisle sign 5812 including text (e.g., an aisle name and/or number), [0543] - location descriptors may include aisle names and/or numbers. Additional example location descriptors may also include aisle descriptors, such as first/second aisle ends, aisle middle, and/or shelf location (e.g., bottom shelf, top shelf) [subsection of an aisle by example]), and wherein the sub-aisle level has a higher level of granularity of product data than the aisle level (See Francis ¶ [0365] – the MSDs and/or CCS may add granularity to, or enhance resolution of, relative locations of the items included in the zone and [0401] - if a location indicator covers an entire aisle of items, the item adjacency map may define more granular arrangements of items on the display);
apply the historical pick data to a trained machine learning model (See Francis ¶ [0441] – MSD using a machine learning model for image classification while in “picking” mode, thereby training said MSD from pick data) to generate pairwise relations between product categories in the plurality of product categories, wherein the machine learning model generates a pairwise relation for each pair of product categories at each level of the taxonomy (See Francis ¶ [0392-0393] – scanning multiple items an recognizing paired relationships between items signifying adjacency based on time between each scan of each item and [0441-0442] – MSD using a machine learning image classification models based on product categories at each level of the taxonomy by example by segmenting said model based on the particular areas/ sections [departments or aisles as noted above regarding ¶ [0360] & [0491]] of the store) , the machine learning model trained by:
applying, to the machine learning model configured with a first set of weights, training data including historical pick data and target pairwise relations (See Francis ¶[0392-0393] - the CCS may determine that the three items in two pairs of adjacent items are adjacent if the sum of the scan times between the first pair of items and the second pair of items is less than a threshold value… The CCS may make the determination in block 5212 using various scan times associated with the pairs, such as the most recent scan times, average scan times, etc. In block 5214, the CCS updates the item adjacency map to indicate the items in the pairs of items are adjacent if the criteria in block 5212 are satisfied and [0629] – the CCS/MSDs may implement a scoring model in which different possible routes for an MSD are scored, and the highest scoring route is assigned (e.g., highest scoring indicates a best route)… a scoring module at the CCS/MSDs may apply different weights and scores to different aspects of a route (e.g., route length, item number, distance from MSD, etc.) … the CCS/MSDs may implement a machine learned model for generating routes/scores, where the machine learned model receives different routing factors as inputs. The machine learned model may be trained on historic picking/movement data);
determining, by the machine learning model configured with the first set of weights (See Francis ¶[0392-0393] and [0629] as noted above), a first predicted pairwise relation for each pair of product categories at each level of the taxonomy based on a feature vector representing the historical pick data for items in the respective pair of product categories (The limitation “feature vector” is not supported by the written description of the instant application and is new matter. Nonetheless, see Francis ¶[0377] - the MSD determines that the first and second items are adjacent to one another… reinforcing a determination of adjacency may include updating data associated with the adjacent items that indicates the scan times between items have satisfied item adjacency criterion multiple times… the MSD and/or CCS may update the item adjacency map to include, for each pair of adjacent items, a reinforcement indicator value that indicates the number of times the two items have been considered adjacent); and
updating the machine learning model with a second set of weights, wherein the updated machine learning model is configured to produce a second predicted pairwise relation for each pair of product categories (See Francis ¶ [0435] - The image processing module may feed the set of features to one or more machine-learned image classification models, which respectively output a classification of the blob based on the set of features, [0441] - an MSD may include an image processing module that classifies images … the MSD may implement a set of machine-learned image classification models stored thereon that the MSD uses to perform image classification… the image classification model(s) of an MSD may be updated when new items or objects are identified… the image classification models used by the MSD when the MSD is in a “picking” mode may be trained to identify a reduced subset of the items in the store… and [0629] - the CCS/MSDs may implement a scoring model in which different possible routes for an MSD are scored… a scoring module at the CCS/MSDs may apply different weights and scores to different aspects of a route … the CCS/MSDs may implement a machine learned model for generating routes/scores, where the machine learned model receives different routing factors as inputs… the machine learned model may be trained on historic picking/movement data), wherein a value between the second predicted pairwise relation and a respective target pairwise relation is smaller than the value between the first predicted pairwise relation and the respective target pairwise relation (See Francis ¶ [0373] - an indication of whether two of the items are adjacent to one another may be determined and/or reinforced based on relatively temporally close scan times associated with the items, indicating that the items are adjacent to one another. Alternatively, the indication of whether the two of the items are adjacent to one another may be removed based on relatively temporally distant scan times associated with the items, indicating that the items are not adjacent to one another and [0492] - the MSD and/or the CCS may generate/update an item association table that associates object-based IDs with items. Although the scanned items may be associated with previously determined object-based IDs, in some cases, the MSD and/or the CCS may be configured to associate a scanned item with a later determined object-based ID, such as when the later determined object-based ID [second predicted pairwise relation] is determined closer in time [smaller than the value between the first predicted pairwise relation] to the scanned item than a previously determined object-based ID [target pairwise relation]. The association between object-based IDs and items may be updated over time.);
generate a plurality of sequences of product categories based on the generated pairwise relations, wherein each sequence in the plurality of sequences is associated with a level of the taxonomy, the plurality of sequences including a first sequence associated with the sub-aisle level of the taxonomy and a second sequence associated with the aisle level of the taxonomy, (See Francis ¶ [0360] – grouping items based on item types/ categories showing item location data associated with aisle numbers [aisle level of the taxonomy], [0371] – generating adjacency maps [sequence of products] shown as a list of adjacent items [products], [0392-0393] – scanning multiple items and recognizing paired relationships between items signifying adjacency based on time between each scan of each item and [0440] - the map generation module may generate the image-based map to indicate locations of items and/or store objects with respect to one another… if a first brand of cereal and a second brand of cereal are classified in the same image (e.g., they are both on the same rack [sub-aisle level of taxonomy]), the map generation module may indicate an adjacency between the first and second brand of cereal in the image-based map), by:
selecting, for each level of the taxonomy, a product category in the level most associated with an initial pick in the historical pick data (See Francis ¶ [0357] – one or more other items in a customer order are included for a particular user based on adjacency of said items to said seed item, wherein said adjacent items are determined to be closest to said user and designated as the next item to be picked, [0654] – the initially selected item acting as a seeding item and [0718-0720] – ranking items by individual item or item type [category] and using said item ranking and user movement data to generate a pick sequence); and
traversing, at a level of the selected product category in the taxonomy, the generated pairwise relations in order of strongest pairwise relation to a currently selected product category in the taxonomy (As the specification of the instant application describes the strongest pairwise relation as the shortest distance from an initial “seed” item to the next item in a sequence of items, see Francis ¶ [0385-0387] – displaying items [product category] to a user MSD device in order of closest item to said device at the top of a list with other items following based on relative proximity to said user device when an initial item is scanned [pairwise relations in order of strongest pairwise relation to a currently selected product category in the taxonomy by example] and Fig. 48 – showing a sequence of items to pick relative to a location of a user MSD [at a level of the selected product category in the taxonomy by example]);
receive an order for items offered by the warehouse (See Francis ¶ [0073-0075] – receiving customer orders to be fulfilled by a warehouse), wherein the order includes at least a first item associated with a first product category and a second item associated with a second product category and not associated with the first product category (See Francis ¶ [0360-0361] – one or more of the MSDs and/or the CCS may be configured to use metadata indicating a type/category (e.g., produce, dairy, meat products) [at least first and second product category by example] associated with an item included in a customer order to group (e.g., cluster) the item with one or more other items that are also included in the customer order… one or more of the MSDs and/or the CCS may be configured to identify a first item included in a first group and identify a second, different item, that is adjacent to the first item but not included in the first group [second product category and not associated with the first product category by example]); and
compare the order to two or more sequences to generate a pick sequence for the order (See Francis ¶ [0365-0367] – the MSDs and/or CCS may be configured to identify a first item (e.g., an anchor item) included in a particular zone associated with a location indicator, and then determine relative locations of one or more different items also included in the zone [sequence by example] with respect to the first item using an adjacency map… one or more of the MSDs and/or CCS may be configured to make use of items (e.g., an anchor item) included in zones and MSDs transitioning from one zone to another zone [two or more sequences in the plurality of sequences by example]. For example, the MSDs and/or the CCS may determine that an item included in a first zone is proximate to an item included in a second zone upon an MSD scanning the two items within a predetermined threshold amount of time when the MSD transitions between the two zones, thereby defining edges of the zones… if an aisle has one or more zones in a line, the arrangement of items for picking may be organized in a linear fashion down the aisle from zone to zone based on the edge items and sequential items between the edge items… an MSD may be configured to display a subset of the items included in a customer order (e.g., items that are located proximate to the MSD at that time) [comparing the order by example]) by:
identifying, from each item in the order, one or more product categories associated with the respective item and the compared sequence (See Francis ¶ [0360-0361] – one or more of the MSDs and/or the CCS may be configured to use metadata indicating a type/category (e.g., produce, dairy, meat products) [at least first and second product category by example] associated with an item included in a customer order to group (e.g., cluster) the item with one or more other items that are also included in the customer order… one or more of the MSDs and/or the CCS may be configured to identify a first item included in a first group and identify a second, different item, that is adjacent to the first item but not included in the first group);
…each item in the order based on position of its identified one or more product categories the first sequence, wherein, in response to determining that none of the identified product categories of a respective item are contained in the first sequence, estimating … for the respective item based on the second sequence (See Francis ¶ [0360-0361] and [0365-0367] as noted above, as well as [0383] - the MSD may display the initial item at the top of a list and display the other items lower on the list based on the relative distances and/or times associated with the items and the initial item, [0387] - with respect to FIG. 48 , an MSD near item 4804-5 may display items 4804-3, 4804-4, 4804-5, and 4804-6 higher on the display to prompt the user to pick those items due to their adjacency. Due to the item adjacency map, this may even be the case if items 4804-3 and/or 4804-4 are in different zones (e.g., associated with different location values) than item 4804-5, wherein said different zones are different aisles [second sequence] as shown in Fig. 48); and
outputting the pick sequence, … (See Francis ¶ [0366-0367] – identifying a sequence of items in a customer order and generating a displayed list of said sequence, wherein said sequence may not be based on adjacency of said items in said order).
While Francis teaches arranging items in an order into a picking sequence based on item groupings associated with item categories (Francis ¶ [0360-0361] and [0365-0367]), Francis does not explicitly teach ranking or estimating the rank of said items in compared picking sequences or that the pick sequence is based on the ranking. This is taught by Fu (See Fu ¶ [0051-0052] – As each available case [item] is identified in progression (ranked and resolved into a sequence solution as further described) the matrix 999A, 999B is updated and reduced… where the flexible sequencer sequences case for picking … each available sequence solution of available cases of the generated sequence solution set (e.g., solution A, solution B, . . . , solution N) is ranked). It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to include in the item pick sequence generation system of Francis the use of ranked item pick sequences from multiple pick sequence solution options as taught by Fu to formulate an optimal, yet flexible sequence solution (Fu ¶ [0027]), thereby increasing the accuracy and efficiency of the item pick sequence generation system of Francis.
Regarding Claim 16, modified Francis teaches:
The computer program product of claim 15, wherein the instructions further cause the processor to:
While Francis teaches arranging items in an order into a picking sequence based on item groupings associated with item categories (Francis ¶ [0360-0361] and [0365-0367]), Francis does not explicitly teach that the pick sequence is generated based on the ranking. This is taught by Fu (See Fu ¶ [0051-0052] – As each available case [item] is identified in progression (ranked and resolved into a sequence solution as further described) the matrix 999A, 999B is updated and reduced… where the flexible sequencer sequences case for picking … each available sequence solution of available cases of the generated sequence solution set (e.g., solution A, solution B, . . . , solution N) is ranked). It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to include in the item pick sequence generation system of Francis the use of ranked item pick sequences from multiple pick sequence solution options as taught by Fu to formulate an optimal, yet flexible sequence solution (Fu ¶ [0027]), thereby increasing the accuracy and efficiency of the item pick sequence generation system of Francis.
Regarding Claim 18, modified Francis teaches:
The computer program product of claim 15, wherein generating the plurality of sequences comprises:
a) selecting a particular level in the hierarchy (See Francis ¶ [0357] – user selecting one of a plurality of items from a display to start picking a customer order); and
b) selecting a seed from the particular level as a currently selected product category, the seed establishing a first product category in a generated sequence (See Francis ¶ [0357] – said item is a “seed” or “re-seed” item that is a next item to be picked by the user, thereby starting a picking sequence).
Regarding Claim 19, modified Francis teaches:
A system comprising:
a processor; and
a memory comprising a non-transitory computer readable storage medium having instructions encoded thereon that, when executed by a processor, cause the processor to (See Francis ¶ [0073-0074] – an order filling system (OFS) comprising a central computing system (CCS) and one or more mobile scanning devices (MSDs), [0217-0219] – processing module of the MSDs sending data and [0267] – CCS and MSDs using data stored in memory):
receive, from a first client device, an order for items offered by a warehouse (See Francis ¶ [0073-0075] – receiving customer orders to be fulfilled by a warehouse), wherein the order includes at least a first item associated with a first product category and a second item associated with a second product category and not associated with the first product category (See Francis ¶ [0360-0361] – one or more of the MSDs and/or the CCS may be configured to use metadata indicating a type/category (e.g., produce, dairy, meat products) [at least first and second product category by example] associated with an item included in a customer order to group (e.g., cluster) the item with one or more other items that are also included in the customer order… one or more of the MSDs and/or the CCS may be configured to identify a first item included in a first group and identify a second, different item, that is adjacent to the first item but not included in the first group [second product category and not associated with the first product category by example]);
for each item in the order, identify one or more product categories associated with at least one sequence in a plurality of sequences of product categories (See Francis ¶ [0360] – the system using item type/ category information to associated items with customer orders, [0366-0367] – identifying a sequence of items in a customer order), wherein the hierarchy includes an aisle level and a sub-aisle level (See Francis ¶ [0112] – similar types of items may be grouped together along an aisle in a typical store. For example, the items located along aisle 122-1 [aisle level] (i.e., the items accessible in aisle 122-1 from rack 116-1 and rack 116-2 [sub-aisle level]) may be items of a similar type), wherein each product category in the sub-aisle level corresponds to a different subsection of an aisle associated with a respective product category in the aisle level (See Francis ¶ [0112] – the items along aisle 122-1 may be cereal items (e.g., bags or boxes of cereal), [0433] - The captured image depicts a plurality of items 5804 (e.g., boxes) that are included on a rack 5802. For example, the image depicts, inter alia, a box of Froot Loops 5806, a location indicator 5808 (e.g., a barcode) attached to a shelf 5810, and an aisle sign 5812 including text (e.g., an aisle name and/or number), [0543] - location descriptors may include aisle names and/or numbers. Additional example location descriptors may also include aisle descriptors, such as first/second aisle ends, aisle middle, and/or shelf location (e.g., bottom shelf, top shelf) [subsection of an aisle by example]), and wherein the sub-aisle level has a higher level of granularity of product data than the aisle level (See Francis ¶ [0365] – the MSDs and/or CCS may add granularity to, or enhance resolution of, relative locations of the items included in the zone and [0401] - if a location indicator covers an entire aisle of items, the item adjacency map may define more granular arrangements of items on the display), the plurality of sequences generated by:
selecting, for each level of the taxonomy, a product category in the level most associated with an initial pick in the historical pick data (See Francis ¶ [0357] – one or more other items in a customer order are included for a particular user based on adjacency of said items to said seed item, wherein said adjacent items are determined to be closest to said user and designated as the next item to be picked, [0654] – the initially selected item acting as a seeding item and [0718-0720] – ranking items by individual item or item type [category] and using said item ranking and user movement data to generate a pick sequence); and
traversing, at a level of the selected product category in the taxonomy, pairwise relations between product categories in order of strongest pairwise relation to a currently selected product category in the taxonomy (As the specification of the instant application describes the strongest pairwise relation as the shortest distance from an initial “seed” item to the next item in a sequence of items, see Francis ¶ [0385-0387] – displaying items [product category] to a user MSD device in order of closest item to said device at the top of a list with other items following based on relative proximity to said user device when an initial item is scanned [pairwise relations in order of strongest pairwise relation to a currently selected product category in the taxonomy by example] and Fig. 48 – showing a sequence of items to pick relative to a location of a user MSD [at a level of the selected product category in the taxonomy by example]);
… each item based on the order of the identified one or more product categories of the item in the first sequence, wherein, in response to determining that none of the identified product categories of a respective item are contained in the first sequence, estimating … for the respective item based on the second sequence (See Francis ¶ [0360-0361] and [0365-0367] as noted above, as well as [0383] - the MSD may display the initial item at the top of a list and display the other items lower on the list based on the relative distances and/or times associated with the items and the initial item, [0387] - with respect to FIG. 48 , an MSD near item 4804-5 may display items 4804-3, 4804-4, 4804-5, and 4804-6 higher on the display to prompt the user to pick those items due to their adjacency. Due to the item adjacency map, this may even be the case if items 4804-3 and/or 4804-4 are in different zones (e.g., associated with different location values) than item 4804-5, wherein said different zones are different aisles [second sequence] as shown in Fig. 48);
generate a pick sequence for the order based … (See Francis ¶ [0718-0720] – ranking items by individual item or item type [category] and using said item ranking and user movement data to generate a pick sequence); and
send the pick sequence to a second client device, wherein the second client device performs one or more actions based on the pick sequence (See Francis ¶ [0095-0097] – customers placing orders on mobile devices and third party pickers picking items for said orders based websites or application running on devices used by said third parties and [0501] – maps and tables used for picking routes may include a customer’s shopping list, wherein said list is sent to a customer in a GUI [rendered]).
While Francis teaches arranging items in an order into a picking sequence based on item groupings associated with item categories (Francis ¶ [0360-0361] and [0365-0367]), Francis does not explicitly teach ranking said items in the at least one sequence or that the pick sequence is based on the ranking. This is taught by Fu (See Fu ¶ [0051-0052] – As each available case [item] is identified in progression (ranked and resolved into a sequence solution as further described) the matrix 999A, 999B is updated and reduced… where the flexible sequencer sequences case for picking … each available sequence solution of available cases of the generated sequence solution set (e.g., solution A, solution B, . . . , solution N) is ranked). It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to include in the item pick sequence generation system of Francis the use of ranked item pick sequences from multiple pick sequence solution options as taught by Fu to formulate an optimal, yet flexible sequence solution (Fu ¶ [0027]), thereby increasing the accuracy and efficiency of the item pick sequence generation system of Francis.
Regarding Claim 21, modified Francis teaches:
The system of claim 19, wherein the pairwise relations by a machine learning model applied to historical pick data, the machine learning model trained by:
applying, to the machine learning model configured with a first set of weights, training data including historical pick data and target pairwise relations (See Francis ¶[0392-0393] - the CCS may determine that the three items in two pairs of adjacent items are adjacent if the sum of the scan times between the first pair of items and the second pair of items is less than a threshold value… The CCS may make the determination in block 5212 using various scan times associated with the pairs, such as the most recent scan times, average scan times, etc. In block 5214, the CCS updates the item adjacency map to indicate the items in the pairs of items are adjacent if the criteria in block 5212 are satisfied and [0629] – the CCS/MSDs may implement a scoring model in which different possible routes for an MSD are scored, and the highest scoring route is assigned (e.g., highest scoring indicates a best route)… a scoring module at the CCS/MSDs may apply different weights and scores to different aspects of a route (e.g., route length, item number, distance from MSD, etc.) … the CCS/MSDs may implement a machine learned model for generating routes/scores, where the machine learned model receives different routing factors as inputs. The machine learned model may be trained on historic picking/movement data);
determining, by the machine learning model configured with the first set of weights (See Francis ¶[0392-0393] and [0629] as noted above), a first predicted pairwise relation for each pair of product categories at each level of the taxonomy based on a feature vector representing the historical pick data for items in the respective pair of product categories (The limitation “feature vector” is not supported by the written description of the instant application and is new matter. Nonetheless, see Francis ¶[0377] - the MSD determines that the first and second items are adjacent to one another… reinforcing a determination of adjacency may include updating data associated with the adjacent items that indicates the scan times between items have satisfied item adjacency criterion multiple times… the MSD and/or CCS may update the item adjacency map to include, for each pair of adjacent items, a reinforcement indicator value that indicates the number of times the two items have been considered adjacent); and
updating the machine learning model with a second set of weights, wherein the updated machine learning model is configured to produce a second predicted pairwise relation for each pair of product categories (See Francis ¶ [0435] - The image processing module may feed the set of features to one or more machine-learned image classification models, which respectively output a classification of the blob based on the set of features, [0441] - an MSD may include an image processing module that classifies images … the MSD may implement a set of machine-learned image classification models stored thereon that the MSD uses to perform image classification… the image classification model(s) of an MSD may be updated when new items or objects are identified… the image classification models used by the MSD when the MSD is in a “picking” mode may be trained to identify a reduced subset of the items in the store… and [0629] - the CCS/MSDs may implement a scoring model in which different possible routes for an MSD are scored… a scoring module at the CCS/MSDs may apply different weights and scores to different aspects of a route … the CCS/MSDs may implement a machine learned model for generating routes/scores, where the machine learned model receives different routing factors as inputs… the machine learned model may be trained on historic picking/movement data), wherein a value between the second predicted pairwise relation and a respective target pairwise relation is smaller than the value between the first predicted pairwise relation and the respective target pairwise relation (See Francis ¶ [0373] - an indication of whether two of the items are adjacent to one another may be determined and/or reinforced based on relatively temporally close scan times associated with the items, indicating that the items are adjacent to one another. Alternatively, the indication of whether the two of the items are adjacent to one another may be removed based on relatively temporally distant scan times associated with the items, indicating that the items are not adjacent to one another and [0492] - the MSD and/or the CCS may generate/update an item association table that associates object-based IDs with items. Although the scanned items may be associated with previously determined object-based IDs, in some cases, the MSD and/or the CCS may be configured to associate a scanned item with a later determined object-based ID, such as when the later determined object-based ID [second predicted pairwise relation] is determined closer in time [smaller than the value between the first predicted pairwise relation] to the scanned item than a previously determined object-based ID [target pairwise relation]. The association between object-based IDs and items may be updated over time).
Response to Arguments
Applicant's arguments filed 05/04/2026 have been fully considered but they are not persuasive.
Rejection under 35 U.S.C. § 101:
In light of the amended claims, the previous rejection of claims 1-2, 6-9, 12-16 and 18 under 35 U.S.C. § 101 is withdrawn. The previous rejection of claim 19 is maintained.
Independent claims 1 and 15 comprise the limitations “updating the machine learning model with a second set of weights, wherein the updated machine learning model is configured to produce a second predicted pairwise relation for each pair of product categories, wherein a value between the second predicted pairwise relation and a respective target pairwise relation is smaller than the value between the first predicted pairwise relation and the respective target pairwise relation”. These limitations, along the other limitations of claims 1 and 15, show the claims as a whole as reciting specific elements that reflect an improvement to how the machine learning model itself operates, such as by reducing storage requirements or system complexity. Therefore, claims 1-2, 6-9, 12-16 and 18 are patent eligible.
Independent claim 19 lacks these limitations as amended and remains ineligible for a patent for reasons described above in the current rejection under 35 U.S.C. § 101.
Rejection under 35 U.S.C. § 103:
Considering the applicant’s arguments and the amendments to independent claims 1, 15 and 19, the claims as they are currently limited do not overcome the prior art combination of Francis and Fu and the previous rejection under 35 U.S.C. § 103 is maintained.
The applicant’s arguments are based on previously cited sections of Francis for not teaching the requirements of the amended claims. For instance, the applicant argues that Francis does not teach the amended limitations of a sub-aisle level of granularity, nor does Francis describe that each product category in the “sub-aisle level corresponds to a different subsection of an aisle associated with a respective product category in the aisle level”, as previously cited in ¶ [0360] and [0491], however, these amended limitations remain to be taught by Francis in ¶ [0112], [0433] and [0543] as described above in the current rejection under 35 U.S.C. § 103.
Contrary to the applicant’s assertion that Francis does not teach conditionally estimating a rank based on a coarser sequence in response to determining that an item's categories are not contained in a more granular sequence, as is described in amended claim 1, these requirements are taught by the combination of Francis and Fu as described above in the current rejection under 35 U.S.C. § 103. Francis teaches by example the arrangement of pick items on a display based on item adjacency when the next adjacent items to pick are not on the same shelf of a current item, but in the next aisle from said current item as described in ¶ [0360-0361], [0365-0367], [0383], [0387] and Fig. 48. Fu, for their part, more explicitly teaches that item arrangement is a ranking type of arrangement as cited above in the current rejection under 35 U.S.C. § 103.
The applicant is generally reminded that prior art must be considered in its entirety (MPEP 2141.02 (VI)).
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 MATTHEW S WERONSKI whose telephone number is (571)272-5802. The examiner can normally be reached M-F 8 am - 5 pm EST.
Examiner interviews are available via telephone, in-person, and video conferencing using a USPTO supplied web-based collaboration tool. To schedule an interview, applicant is encouraged to use the USPTO Automated Interview Request (AIR) at http://www.uspto.gov/interviewpractice.
If attempts to reach the examiner by telephone are unsuccessful, the examiner’s supervisor, Fahd A. Obeid can be reached at 5712703324. 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.
/MATTHEW S WERONSKI/Examiner, Art Unit 3627
/MICHAEL JARED WALKER/Primary Examiner, Art Unit 3627
Prosecution Insights