US-12619856-B2 - Mismatch detection model

US12619856B2US 12619856 B2US12619856 B2US 12619856B2US-12619856-B2

Abstract

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: obtaining a set of items that have been grouped together as matching items in a group; generating, using an ensemble learning model, a predictive indication of a mismatched item grouped together in error as part of the set of items, wherein the ensemble learning model comprises at least two detection models that are performed simultaneously with each other to output predictive indications comprising the predictive indication; and determining a final mismatch decision for an item of the set of items, wherein the final mismatch decision is based on the predictive indication, and wherein the item comprises the mismatched item. Other embodiments are disclosed.

Inventors

Yanxin Pan
Swagata Chakraborty
Abhinandan Krishnan
Abon Chaudhuri
Aakash Mayur Mehta
Edison Mingtao Zhang
Kyu Bin Kim

Assignees

WALMART APOLLO, LLC

Dates

Publication Date: 20260505
Application Date: 20231106

Claims (17)

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: obtaining a set of items from an online catalog, wherein the set of items have been grouped together as matching items in a group; training an ensemble learning model using training input data for a set of training items, wherein the ensemble learning model comprises at least two detection models arranged as a twin neural network with contrastive loss, and wherein respective training outputs obtained for the at least two detection models are combined to generate a predictive indication of a mismatch; generating, using the ensemble learning model, a predictive indication of a mismatched item in the group, wherein the at least two detection models are performed simultaneously with each other to simultaneously output predictive indications comprising the predictive indication, and wherein identical weight decay functions are applied to the twin neural network to regularize weights while processing respective input vectors to detect mismatches, and wherein the at least two detection models that are performed simultaneously with each other reduce errors in mismatch detection compared to a different ensemble learning model that does not use the at least two detection models simultaneously by calculating a similarity between the respective input vectors using the contrastive loss; determining a resultant mismatch decision for an item of the set of items, wherein the resultant mismatch decision is based on the predictive indication, and wherein the item comprises the mismatched item; separating, based on the resultant mismatch decision, the item of the set of items from the group; and in response to a request from a user interface of an electronic device to view products or services associated with the group, transmitting the group for display on the user interface of the electronic device.
2 . The system of claim 1 , wherein: the identical weight decay functions are applied to the twin neural network to regularize the weights while processing the respective input vectors to detect the mismatches based at least in part on at least one of: a respective title for each of the set of items; a respective description for each of the set of items; or one or more respective attributes for each of the set of items.
3 . The system of claim 1 , wherein the at least two detection models comprise: a convolutional neural network based on a respective title word matrix for each item of the set of items.
4 . The system of claim 1 , wherein the at least two detection models comprise: a fuzzy matching based on titles of the set of items.
5 . The system of claim 1 , wherein the at least two detection models are performed in parallel with each other on the set of items to simultaneously output predictive indications.
6 . The system of claim 1 , wherein a quantity of the at least two detection models is at least three.
7 . The system of claim 1 , wherein determining the resultant mismatch decision for the item of the set of items further comprises: separating at least one item of the set of items from the group when a quantity of detected mismatches is at least a predetermined threshold.
8 . The system of claim 7 , wherein the operations further comprise: maintaining each item of the set of items in the group when the quantity of detected mismatches is not at least the predetermined threshold.
9 . The system of claim 8 , wherein the predetermined threshold is one.
10 . A method being implemented via execution of computing instructions configured to run at one or more processors and stored at one or more non-transitory computer-readable media, the method comprising: obtaining a set of items from an online catalog, wherein the set of items have been grouped together as matching items in a group; training an ensemble learning model using training input data for a set of training items, wherein the ensemble learning model comprises at least two detection models arranged as a twin neural network with contrastive loss, and wherein respective training outputs obtained for the at least two detection models are combined to generate a predictive indication of a mismatch; generating, using the ensemble learning model, a predictive indication of a mismatched item in the group, wherein the at least two detection models are performed simultaneously with each other to simultaneously output predictive indications comprising the predictive indication, and wherein identical weight decay functions are applied to the twin neural network to regularize weights while processing respective input vectors to detect mismatches, and wherein the at least two detection models that are performed simultaneously with each other reduce errors in mismatch detection compared to a different ensemble learning model that does not use the at least two detection models simultaneously by calculating a similarity between the respective input vectors using the contrastive loss; determining a resultant mismatch decision for an item of the set of items, wherein the resultant mismatch decision is based on the predictive indication, and wherein the item comprises the mismatched item; separating, based on the resultant mismatch decision, the item of the set of items from the group; and in response to a request from a user interface of an electronic device to view products or services associated with the group, transmitting the group for display on the user interface of the electronic device.
11 . The method of claim 10 , wherein: the identical weight decay functions are applied to the twin neural network to regularize the weights while processing the respective input vectors to detect the mismatches based at least in part on at least one of: a respective title for each of the set of items; a respective description for each of the set of items; or one or more respective attributes for each of the set of items.
12 . The method of claim 10 , wherein the at least two detection models comprise: a convolutional neural network based on a respective title word matrix for each item of the set of items.
13 . The method of claim 10 , wherein the at least two detection models comprise: a fuzzy matching based on respective titles of the set of items.
14 . The method of claim 10 , wherein the at least two detection models are performed in parallel with each other on the set of items.
15 . The method of claim 10 , wherein a quantity of the at least two detection models is at least three.
16 . The method of claim 10 , wherein: determining the resultant mismatch decision for the item of the set of items further comprises: separating at least one item of the set of items from the group when a quantity of detected mismatches is at least a predetermined threshold; and the method further comprises: maintaining each item of the set of items in the group when the quantity of detected mismatches is not at least the predetermined threshold.
17 . A non-transitory computer-readable medium storing instructions, wherein the instructions, upon execution by a processor, cause the processor to perform operations comprising: obtaining a set of items from an online catalog, wherein the set of items have been grouped together as matching items in a group; training an ensemble learning model using training input data for a set of training items, wherein the ensemble learning model comprises at least two detection models arranged as a twin neural network with contrastive loss, and wherein respective training outputs obtained for the at least two detection models are combined to generate a predictive indication of a mismatch; generating, using the ensemble learning model, a predictive indication of a mismatched item in the group, wherein the at least two detection models are performed simultaneously with each other to simultaneously output predictive indications comprising the predictive indication, and wherein identical weight decay functions are applied to the twin neural network to regularize weights while processing respective input vectors to detect mismatches, and wherein the at least two detection models that are performed simultaneously with each other reduce errors in mismatch detection compared to a different ensemble learning model that does not use the at least two detection models simultaneously by calculating a similarity between the respective input vectors using the contrastive loss; determining a resultant mismatch decision for an item of the set of items, wherein the resultant mismatch decision is based on the predictive indication, and wherein the item comprises the mismatched item; separating, based on the resultant mismatch decision, the item of the set of items from the group; and in response to a request from a user interface of an electronic device to view products or services associated with the group, transmitting the group for display on the user interface of the electronic device.

Description

CROSS-REFERENCE TO RELATED APPLICATIONS The present application is a Continuation Application of U.S. patent application Ser. No. 16/779,510, filed on Jan. 31, 2020. U.S. patent application Ser. No. 16/779,510, now issued as U.S. Pat. No. 11,809,979 on Nov. 7, 2023, is herewith incorporated by reference in its entirety. TECHNICAL FIELD This disclosure relates generally relates to a mismatch detection model. BACKGROUND Items grouped together based on their similarity can include items that are mismatched. Some of the items are mismatched based one or more different concepts, including size, color, condition, pattern, brand, model, etc., depending on the similarity factor(s) used to group the items together. Processes for correcting the mismatches can be time consuming due to the complexity of computer-processes searching an entire catalog to identify mismatched products. BRIEF DESCRIPTION OF THE DRAWINGS To facilitate further description of the embodiments, the following drawings are provided in which: FIG. 1 illustrates a front elevational view of a computer system that is suitable for implementing an embodiment of the system disclosed in FIG. 3; FIG. 2 illustrates a representative block diagram of an example of the elements included in the circuit boards inside a chassis of the computer system of FIG. 1; FIG. 3 illustrates a block diagram of a system that can be employed for mismatch detection model, according to an embodiment; FIG. 4 illustrates a flow chart for a method, according to another embodiment; FIG. 5 illustrates a representative block diagram of FIG. 3; FIG. 6 illustrates a flow chart for a method, according to another embodiment; and FIG. 7 illustrates a flow chart for a method, according to another embodiment. For simplicity and clarity of illustration, the drawing figures illustrate the general manner of construction, and descriptions and details of well-known features and techniques may be omitted to avoid unnecessarily obscuring the present disclosure. Additionally, elements in the drawing figures are not necessarily drawn to scale. For example, the dimensions of some of the elements in the figures may be exaggerated relative to other elements to help improve understanding of embodiments of the present disclosure. The same reference numerals in different figures denote the same elements. The terms “first,” “second,” “third,” “fourth,” and the like in the description and in the claims, if any, are used for distinguishing between similar elements and not necessarily for describing a particular sequential or chronological order. It is to be understood that the terms so used are interchangeable under appropriate circumstances such that the embodiments described herein are, for example, capable of operation in sequences other than those illustrated or otherwise described herein. Furthermore, the terms “include,” and “have,” and any variations thereof, are intended to cover a non-exclusive inclusion, such that a process, method, system, article, device, or apparatus that comprises a list of elements is not necessarily limited to those elements, but may include other elements not expressly listed or inherent to such process, method, system, article, device, or apparatus. The terms “left,” “right,” “front,” “back,” “top,” “bottom,” “over,” “under,” and the like in the description and in the claims, if any, are used for descriptive purposes and not necessarily for describing permanent relative positions. It is to be understood that the terms so used are interchangeable under appropriate circumstances such that the embodiments of the apparatus, methods, and/or articles of manufacture described herein are, for example, capable of operation in other orientations than those illustrated or otherwise described herein. The terms “couple,” “coupled,” “couples,” “coupling,” and the like should be broadly understood and refer to connecting two or more elements mechanically and/or otherwise. Two or more electrical elements may be electrically coupled together, but not be mechanically or otherwise coupled together. Coupling may be for any length of time, e.g., permanent or semi-permanent or only for an instant. “Electrical coupling” and the like should be broadly understood and include electrical coupling of all types. The absence of the word “removably,” “removable,” and the like near the word “coupled,” and the like does not mean that the coupling, etc. in question is or is not removable. As defined herein, two or more elements are “integral” if they are comprised of the same piece of material. As defined herein, two or more elements are “non-integral” if each is comprised of a different piece of material. As defined herein, “approximately” can, in some embodiments, mean within plus or minus ten percent of the stated value. In other embodiments, “approximately” can mean within plus or minus five percent of the stated value. In further embodiments, “approximately” can mean within plus or minus three percent o