System and method for generating analytics associated with an object using an artificial intelligence (AI) model

Abstract

A method may receive, from a user device or an imaging device, an image of an object located in a display area of an end-user channel location; generate, using an artificial intelligence (AI) model, analytics associated with the object based on the image of the object located in the display area of the end-user channel location; display the generated analytics on a display device or transmit the generated analytics for display on the display device. The analytics may include object placement compliance information, value allocation compliance, promotion compliance information, inventory analytics related to inventory of the object at the end-user channel location, and object placement variance that identifies variances in object placements associated with the object or object placement performance that identifies performance metrics associated with the object placement model.

Description

SYSTEM AND METHOD FOR GENERATING ANALYTICS ASSOCIATED WITH AN OBJECT USING AN ARTIFICIAL INTELLIGENCE (Al) MODELCROSS-REFERENCE TO RELATED APPLICATION(S)

[0001] This patent application claims the benefit of priority to U.S. Provisional Patent Application No. 63 / 637,680, filed on April 23, 2024, the entirety of which is incorporated herein by reference.TECHNICAL FIELD

[0002] The present disclosure relates to systems and methods for generating analytics associated with a product using an Al model.BACKGROUND

[0003] A product manufacturer may manufacture a product and distribute the product to be sold at a retail location. The retail location may include a display area where the product is displayed so that consumers may view and purchase the product. The product manufacturer might desire to ensure that the display area is located in a particular area of the retail location, that the product is located in a particular area of the display area, that a particular amount of the product is maintained in the display area, that the product is being sold at a particular price, that a particular promotion is being displayed in association with the product, that particular other products are located adjacent to the product, etc. Given that the product is sold at a large number of retail locations, the product manufacturer might not be capable of monitoring compliance with the foregoing or ascertaining the efficacy of alternative arrangements.SUMMARY

[0004] In some aspects, the techniques described herein relate to a method including: receiving, from a user device or an imaging device, an image of an object located in a display area of an end-user channel location; generating, using an artificial intelligence (Al) model, analytics associated with the object based on the image of the object located in the display area of the end-user channel location; and displaying the generated analytics on a display device or transmitting the generated analytics for display on the display device, wherein the analytics include: object placement compliance information that identifies an object placement compliance of the object with an object placement model; value allocation compliance information that identifies a value allocation compliance of a value allocation of the object withvalue allocation information of the object, promotion compliance information that identifies a promotion compliance of the object with promotion information of the object, inventory analytics related to inventory of the object at the end-user channel location, and object placement variance that identifies variances in object placements associated with the object or object placement performance that identifies performance metrics associated with the object placement model.

[0005] In some aspects, the techniques described herein relate to a method, further including: generating a recommendation regarding the object using the Al model; and displaying the recommendation based on generating the recommendation using the Al model.

[0006] In some aspects, the techniques described herein relate to a method, wherein the analytics include supplier relationship management (SRM) insights that identify insights for entities associated with the object.

[0007] In some aspects, the techniques described herein relate to a method, wherein the analytics include analytics associated with a different object associated with a different entity, wherein the different object is related to the object.

[0008] In some aspects, the techniques described herein relate to a method, wherein the analytics include on-shelf availability (OSA) insights that identify insights for providing availability of the object.

[0009] In some aspects, the techniques described herein relate to a method, wherein the displaying includes displaying the analytics in substantially real-time via the user device.

[0010] In some aspects, the techniques described herein relate to a method, wherein the object is a confectionary object.

[0011] In some aspects, the techniques described herein relate to a device including: a memory configured to store instructions; and one or more processors configured to execute the instructions to perform operations including: receiving, from a user device or an imaging device, an image of an object located in a display area of an end-user channel location; generating, using an artificial intelligence (Al) model, analytics associated with the object based on the image of the object located in the display area of the end-user channel location; and displaying the generated analytics on a display device or transmitting the generated analytics for display on the display device, wherein the analytics include: object placement compliance information that identifies an object placement compliance of the object with anobject placement model; value allocation compliance information that identifies a value allocation compliance of a value allocation of the object with value allocation information of the object, promotion compliance information that identifies a promotion compliance of the object with promotion information of the object, inventory analytics related to inventory of the object at the end-user channel location, and object placement variance that identifies variances in object placements associated with the object or object placement performance that identifies performance metrics associated with the object placement model.

[0012] In some aspects, the techniques described herein relate to a device, wherein the operations further include: generating a recommendation regarding the object using the Al model; and displaying the recommendation based on generating the recommendation using the Al model.

[0013] In some aspects, the techniques described herein relate to a device, wherein the analytics include supplier relationship management (SRM) insights that identify insights for entities associated with the object.

[0014] In some aspects, the techniques described herein relate to a device, wherein the analytics include analytics associated with a different object associated with a different entity, wherein the different object is related to the object.

[0015] In some aspects, the techniques described herein relate to a device, wherein the analytics include on-shelf availability (OSA) insights that identify insights for providing the availability of the object.

[0016] In some aspects, the techniques described herein relate to a device, wherein the displaying includes displaying the analytics in substantially real-time via the user device.

[0017] In some aspects, the techniques described herein relate to a device, wherein the object is a confectionary object.

[0018] In some aspects, the techniques described herein relate to a non- transitory computer-readable medium storing instructions that, when executed by one or more processors, cause the one or more processors to perform operations including: receiving, from a user device or an imaging device, an image of an object located in a display area of an end-user channel location; generating, using an artificial intelligence (Al) model, analytics associated with the object based on the image of the object located in the display area of the end-user channel location; and displaying the generated analytics on a display device or transmitting the generatedanalytics for display on the display device, wherein the analytics include: object placement compliance information that identifies an object placement compliance of the object with an object placement model; value allocation compliance information that identifies a value allocation compliance of a value allocation of the object with value allocation information of the object, promotion compliance information that identifies a promotion compliance of the object with promotion information of the object, inventory analytics related to inventory of the object at the end-user channel location, and object placement variance that identifies variances in object placements associated with the object or object placement performance that identifies performance metrics associated with the object placement model.

[0019] In some aspects, the techniques described herein relate to a non- transitory computer-readable medium, wherein the operations further include: generating a recommendation regarding the object using the Al model; and displaying the recommendation based on generating the recommendation using the Al model.

[0020] In some aspects, the techniques described herein relate to a non- transitory computer-readable medium, wherein the analytics include supplier relationship management (SRM) insights that identify insights for entities associated with the object.

[0021] In some aspects, the techniques described herein relate to a non- transitory computer-readable medium, wherein the analytics include different object insights associated with a different object associated with a different entity, wherein the different object is related to the object.

[0022] In some aspects, the techniques described herein relate to a non- transitory computer-readable medium, wherein the analytics include on-shelf availability (OSA) insights that identify insights for providing the availability of the object.

[0023] In some aspects, the techniques described herein relate to a non- transitory computer-readable medium, wherein the analytics include competitive insights associated with a different product associated with a different entity, wherein the different product is related to the product.

[0024] In some aspects, the techniques described herein relate to a non- transitory computer-readable medium, wherein the analytics include categoryinsights associated with overall confectionary and / or snacking category that is related to the object.

[0025] In some aspects, the techniques described herein relate to a non- transitory computer-readable medium, wherein the recommendation includes action recommendations associated with retail store operation and execution that helps to beneficially optimize sales with the SRM insights, the different product insights, the OSA insights, the competitive insights, and the category insights, and wherein a modality of the recommendation includes audio action guidance, video action guidance, and / or image action guidance.

[0026] In some aspects, the techniques described herein relate to a non- transitory computer-readable medium, wherein the object is a confectionary object, a snacking object, any consumer packaged object, a retail shelf, or a checkout counter.

[0027] It may be understood that both the foregoing general description and the following detailed description are exemplary and explanatory only and are not restrictive of the invention, as claimed.BRIEF DESCRIPTION OF THE DRAWINGS

[0028] FIG. 1 is a diagram of an example system for generating analytics associated with a product using an Al model.

[0029] FIG. 2 is a diagram of example components of one or more devices of FIG. 1.

[0030] FIG. 3 is a flowchart of an example process for generating analytics associated with a product using an Al model.

[0031] FIG. 4 is a diagram of acquiring an image of a product located in a display area of a retail location.

[0032] FIG. 5 is a diagram of generating, using an Al model, analytics associated with a product.

[0033] FIG. 6 is a diagram of displaying analytics associated with a product and a recommendation regarding the product.

[0034] FIG. 7 is a diagram of displaying analytics associated with a product and a recommendation regarding the product.

[0035] FIG. 8 is a diagram of a process for training, deploying, and monitoring an Al model for generating analytics associated with a product.DETAILED DESCRIPTION

[0036] As addressed above, a product manufacturer might desire to ensure that a display area for a product is located in a particular area of the retail location, that a product is located in a particular area of the display area, that a particular amount of the product is maintained in the display area, that the product is being sold at a particular price, that a particular promotion is being displayed in association with the product, that particular other products are located adjacent to the product, etc. Given that the product is sold at a large number of retail locations, the product manufacturer might not be capable of monitoring compliance with the foregoing, or ascertaining the efficacy of alternative arrangements.

[0037] Some embodiments of the present disclosure provide a platform for generating, using an Al model, analytics associated with a product. For example, the platform may receive an image of a product located in a display area of a retail location, and generate analytics associated with the product using an Al model and the image. Further, the platform may display the analytics and / or display a recommendation regarding the product.

[0038] Some embodiments of the present disclosure provide a technical improvement in the technical field of planogram compliance and inventory management by utilizing big data and Al techniques to provide the generation of real-time analytics and recommendations based on images of products. Accordingly, in this way, some embodiments of the present disclosure improve the functioning of the user devices associated with planogram compliance and inventory management by providing real-time analytics and recommendations for display.

[0039] The tool may prioritize recommendations to optimize sales and performance for retailers. A goal is to support retail optimization and generate better profitability for stores and better consumer experience for shoppers.

[0040] FIG. 1 is a diagram of an example system 100 for generating analytics associated with a product using an Al model. As shown in FIG. 1 , the system 100 may include a user device 110, a platform 120, an Al model 130, an imaging device 140, a database 150, and a network 160.

[0041] The user device 110 may be configured to acquire an image of a product (also referred to herein as an “object”) located in a display area of a retail location (also referred to herein as an “end-user channel location”), and / or display analytics generated by the Al model 130. For example, the user device 110 may bea smartphone, a tablet computer, a laptop computer, a desktop computer, a wearable device, or the like.

[0042] The platform 120 may be configured to receive an image of a product located in a display area of a retail location, and generate, using the Al model 130, analytics associated with the product based on the image of the product. For example, the platform 120 may be a server, a cloud server, a virtual machine, or the like.

[0043] The Al model 130 may be configured to generate analytics associated with a product based on an image of the product located in a display area of a retail location. For example, the Al model 130 may be a generative Al model, large language model (LLM) for various modality tasks and content generation, LLM- based application, LLM-based agent, an artificial neural network (ANN), a convolutional neural network (CNN), a recurrent neural network (RNN), a generative adversarial network (GAN), a support vector machine (SVM), a Bayesian network, a graphical probabilistic model, a K-nearest neighbor classifier, a decision forests, a maximum margin method, or the like.

[0044] The imaging device 140 may be configured to acquire an image of a product located in a display area of a retail location. For example, the imaging device 140 may be a user device, a camera, an Internet of Things (loT) sensor, or the like. According to an embodiment, the imaging device 140 may be fixed in a particular location in the retail location. Alternatively, the imaging device 140 may be attached to a vehicle that is configured to move throughout the retail location. Alternatively, the imaging device 140 may be carried by a user.

[0045] The database 150 may be configured to store information associated with a product. For example, the database 150 may be a hierarchical database, a network database, a relational database, or the like.

[0046] The network 160 may be configured to permit communication between the user device 110, the platform 120, the imaging device 140, and / or the database 150. For example, the network 160 may be a cellular network (e.g., a fifth generation (5G) network, a long-term evolution (LTE) network, a third generation (3G) network, a code division multiple access (CDMA) network, etc.), a public land mobile network (PLMN), a local area network (LAN), a wide area network (WAN), a metropolitan area network (MAN), a telephone network (e.g., the Public Switched Telephone Network (PSTN)), a private network, an ad hoc network, an intranet, the Internet, afiber optic-based network, or the like, and / or a combination of these or other types of networks.

[0047] The number and arrangement of the devices of the system 100 shown in FIG. 1 are provided as an example. In practice, the system 100 may include additional devices, fewer devices, different devices, or differently arranged devices than those shown in FIG. 1 . Additionally, or alternatively, a set of devices (e.g., one or more devices) of the system 100 may perform one or more functions described as being performed by another set of devices of the system 100.

[0048] FIG. 2 is a diagram of example components of one or more devices of FIG. 1 . The device 200 may correspond to the user device 110, the platform 120, the imaging device 140, and / or the database 150. As shown in FIG. 2, the device 200 may include a bus 210, a processor 220, a memory 230, a storage component 240, an input component 250, an output component 260, and a communication interface 270.

[0049] The bus 210 includes a component that permits communication among the components of the device 200. The processor 220 may be implemented in hardware, firmware, or a combination of hardware and software. The processor 220 may be a central processing unit (CPU), a graphics processing unit (GPU), an accelerated processing unit (APU), a microprocessor, a microcontroller, a digital signal processor (DSP), a field-programmable gate array (FPGA), an applicationspecific integrated circuit (ASIC), or another type of processing component.

[0050] The processor 220 may include one or more processors capable of being programmed to perform a function. The memory 230 may include a random access memory (RAM), a read only memory (ROM), and / or another type of dynamic or static storage device (e.g., a flash memory, a magnetic memory, and / or an optical memory) that stores information and / or instructions for use by the processor 220.

[0051] The storage component 240 may store information and / or software related to the operation and use of the device 200. For example, the storage component 240 may include a hard disk (e.g., a magnetic disk, an optical disk, a magneto-optic disk, and / or a solid state disk), a compact disc (CD), a digital versatile disc (DVD), a floppy disk, a cartridge, a magnetic tape, and / or another type of non- transitory computer-readable medium, along with a corresponding drive.

[0052] The input component 250 may include a component that permits the device 200 to receive information, such as via user input (e.g., a touch screendisplay, a keyboard, a keypad, a mouse, a button, a switch, and / or a microphone for receiving the reference sound input). Additionally, or alternatively, the input component 250 may include a sensor for sensing information (e.g., a global positioning system (GPS) component, an accelerometer, a gyroscope, and / or an actuator). The output component 260 may include a component that provides output information from the device 200 (e.g., a display, a speaker for outputting sound at the output sound level, and / or one or more light-emitting diodes (LEDs)).

[0053] The communication interface 270 may include a transceiver-like component (e.g., a transceiver and / or a separate receiver and transmitter) that enables the device 200 to communicate with other devices, such as via a wired connection, a wireless connection, or a combination of wired and wireless connections. The communication interface 270 may permit the device 200 to receive information from another device and / or provide information to another device. For example, the communication interface 270 may include an Ethernet interface, an optical interface, a coaxial interface, an infrared interface, a radio frequency (RF) interface, a universal serial bus (USB) interface, a Wi-Fi interface, a cellular network interface, or the like.

[0054] The device 200 may perform one or more processes described herein. The device 200 may perform these processes based on the processor 220 executing software instructions stored by a non-transitory computer-readable medium, such as the memory 230 and / or the storage component 240. A computer-readable medium may be defined herein as a non-transitory memory device. A memory device may include memory space within a single physical storage device or memory space spread across multiple physical storage devices.

[0055] The software instructions may be read into the memory 230 and / or the storage component 240 from another computer-readable medium or from another device via the communication interface 270. When executed, the software instructions stored in the memory 230 and / or the storage component 240 may cause the processor 220 to perform one or more processes described herein. Additionally, or alternatively, hardwired circuitry may be used in place of or in combination with software instructions to perform one or more processes described herein. Thus, implementations described herein are not limited to any specific combination of hardware circuitry and software.

[0056] The number and arrangement of the components shown in FIG. 2 are provided as an example. In practice, the device 200 may include additional components, fewer components, different components, or differently arranged components than those shown in FIG. 2. Additionally, or alternatively, a set of components (e.g., one or more components) of the device 200 may perform one or more functions described as being performed by another set of components of the device 200.

[0057] FIG. 3 is a flowchart of an example process 300 for generating analytics associated with a product using an Al model. According to an embodiment, the platform 120 may be configured to perform the operations of the process 300. Additionally, or alternatively, the user device 110, the imaging device 140, and / or the database 150 may be configured to perform one or more operations of the process 300.

[0058] As shown in FIG. 3, the process 300 may include receiving an image of a product located in a display area of a retail location (operation 310).

[0059] The retail location may be any location where the product is displayed, sold, advertised, provided, or the like. For example, the retail location may be a store, a venue, a restaurant, a hotel, an airport, a transportation station, a mall, or the like. According to an embodiment, the retail location may be associated with products provided by different manufacturers. Alternatively, the retail location may be associated with products provided by a single manufacturer.

[0060] The display area may be any area in which the product is displayed, sold, advertised, provided, or the like. For example, the display area may be an aisle, a shelf, a refrigerator, a kiosk, a counter, a display, or the like.

[0061] The product may be any product that can be displayed, sold, advertised, provided, or the like. For example, the product may be a confectionary, such as a cake, a cookie, a pie, a candy, a mint, a chewing gum, a gelatin, ice cream, sorbet, jam, jelly, chocolate, fudge, fondant, liquorice, taffy, or the like. Alternatively, the product may be food, such as bread, cereal, pizza, meat, chicken, or the like. Alternatively, the product may be a beverage, such as water, juice, alcohol, coffee, or the like. Alternatively, the product may be a non-food item, such as a book, a video game, an electronic device, or the like. It should be understood that the product may be any product that can be displayed. In some embodiments, the product, of which an image may be captured, may include a confectionaryproduct, a snacking product, any consumer packaged product, a retail shelf or checkout counter.

[0062] The image may include an image of the product. For example, the image may depict one or more sides of the product. The image may include a name of the product. For example, the image may include a label, a title, a designator, or the like, of the product. The image may include a design of the product. For example, the image may include a cover of the product, an illustration on the product, or the like. The image may include a price associated with the product. The image may include a promotion associated with the product. The image may include a product identifier (e.g., a stock keeping unit (SKU), a universal product code (UPC), a price look up (PLU) code, or the like) of the product. The image may include a machine- readable code associated with the product. The image may include a set of products adjacent to the product. For example, the set of products may all be a same underlying type of product. Alternatively, the set of products may be different types of products. The image may include a display condition of the display area. For example, the display condition may identify if the display area is clean, dirty, worn- out, broken, damaged, adequately lit, or the like.

[0063] According to an embodiment, the image may depict a shelf, a store display area, a transaction zone, a checkout counter, or the like.

[0064] According to an embodiment, the platform 120 may receive an image of a product located in a display area of a retail location from the user device 110. For example, the user device 110 may acquire an image of the product based on a user input, and the user device 110 may transmit the image to the platform 120 based on acquiring the image. Alternatively, the platform 120 may receive an image of a product located in a display area of a retail location from the imaging device 140. For example, the imaging device 140 may acquire an image of the product, and the imaging device 140 may transmit the image to the platform 120. The imaging device 140 may acquire the image of the product based on a predetermined time frame (e.g., every hour, every day, every week, or the like), based on a request from another device, based on an occurrence of a particular event, based on a number of sales of the product as determined based on information received from a point-of- sale (POS) device, or the like.

[0065] FIG. 4 is a diagram 400 of acquiring an image of a product located in a display area of a retail location. As shown in FIG. 4, a display area 410 may includevarious products on display, such as the product 420. Further, the display area 410 may include a label 430 that identifies a product identifier of the product 420 and a price of the product 420. A user may use the user device 110 to capture an image 440 of the display area 410.

[0066] As further shown in FIG. 3, the process 300 may include generating, using an artificial intelligence (Al) model, analytics associated with the product based on the image of the product located in the display area of the retail location (operation 320), displaying the analytics (operation 330), and displaying a recommendation regarding the product, display, pricing, promotion, and / or overall strategic planning around retail execution based on analysis and compliance outcome to improve operation efficiency and / or sales performance (operation 340).

[0067] The analytics may be any type of analytics associated with the product. For example, the analytics may include planogram compliance that identifies a compliance of the product with a planogram (also referred to herein as an “object placement” or “object placement model / diagram”). Additionally, or alternatively, the analytics may include pricing (also referred to herein as “value allocation”) compliance that identifies a compliance of a price of the product with pricing information of the product. Additionally, or alternatively, the analytics may include promotion compliance that identifies a compliance of the product with promotion information of the product. Additionally, or alternatively, the analytics may include inventory analytics related to inventory of the product. Additionally, or alternatively, the analytics may include planogram variance that identifies variances in planograms associated with the product. Additionally, or alternatively, the analytics may include supplier relationship management (SRM) insights that identify insights for entities (e.g., manufacturers, vendors, suppliers, or the like) associated with the product. Additionally, or alternatively, the analytics may include planogram performance that identifies performance metrics associated with different planograms associated with the product. Additionally, or alternatively, the analytics may include analytics associated with other products that are associated with other entities. Additionally, or alternatively, the analytics may include on-shelf availability (OSA) insights that identify insights for providing the availability of the product.

[0068] According to an embodiment, the platform 120 may input the image of the product into the Al model 130. The Al model 130 may be configured to perform one or more image processing techniques in association with the image. Forexample, the Al model 130 may perform object detection, segmentation, classification, captioning, entity resolution, registration, edge detection, pattern recognition, optical character recognition, gauging, or the like. Additionally, or alternatively, the platform 120 may input external data into the Al model 130. For example, the platform 120 may receive external data from the database 150, and input the external data into the Al model 130. The external data may include data associated with the product (e.g., images of the product, a description of the product, a product identifier product, or the like), a planogram associated with the product, sales data associated with the product, pricing data of the product, promotion data of the product, a category of the product, third-party equivalents of the product, competitor data of the product, or the like.

[0069] The platform 120 may generate the analytics based on an output of the Al model 130. According to an embodiment, the platform 120 may generate the analytics in substantially real-time. As used herein, “substantially real-time” may refer to a threshold amount of time that is measured from a time point such as the acquiring of the image, the inputting of the image and / or the external data into the Al model 130, an instruction to generate the analytics, or the like. As examples, “substantially real-time” may be one second, thirty seconds, one minute, or the like.

[0070] According to an embodiment, the system may receive an image and / or additional inputs, such as Pricing / Promo / overall display and transaction zones, which are all relevant in Intelligent Retail Store settings for Al Image Analysis and can provide insights to optimize sales.

[0071] The system may output compliance analysis, product insights and recommendation, and / or additional outputs, such as competitive insights, operational insights, and action recommendations with the purpose of improving operational efficiency and / or sales performance. The output can also be multi-modal, with GenAI, anywhere from audio / video instruction, to image design, to text.

[0072] For example, a recommendation may include action recommendations associated with retail store operation and execution that helps to beneficially optimize sales. The recommendation may further be associated with the derived insights discussed herein (e.g., SRM insights, OSA insights, insights from related product, competitive insights, category insights, etc.) that is related to the product, category, and entity. The insights may include category insights associated with an overall confectionary and / or snacking category that is related to the product. Themodality of recommendation may be multi-modal as previously mentioned. That is, the recommendation may be provided via multiple formats and may support various purposes. This may include audio, video, and / or image action guidance including new planogram designs, displays and layouts, pricing promos labels, text instructions, etc.

[0073] FIG. 5 is a diagram 500 of generating, using an Al model, analytics associated with a product. As shown in FIG. 5, the Al model 130 may receive an image 510 of a product and external data 520 associated with the product. Further, the Al model 130 may generate analytics 530 based on the image 510 of the product and the external data 520 associated with the product. For example, the analytics 530 may include planogram compliance 530-1 , pricing compliance 530-2, promotion compliance 530-3, inventory 530-4, planogram variance 530-5, SRM insights 530-6, planogram performance 530-7, other product(s) analytics 530-8, . . ., and OSA insights 530-n.

[0074] According to an embodiment, the analytics may be associated with planogram compliance that identifies a compliance of the product with a planogram. The platform 120 may receive the image of the product, and information identifying a planogram associated with the product. The platform 120 may compare the image of the product with the information identifying the planogram, and determine a compliance of the product with the planogram. The platform 120 may display analytics that indicate a level of compliance with a planogram, such as “100%,” “90%, ” “complaint,” “non-compliant,” etc. Additionally, or alternatively, the platform 120 may display analytics indicating particular non-compliance, such as an incorrect location of the product, an incorrect quantity of the product, an incorrect arrangement of the product, an incorrect arrange of an adjacent product, an incorrect display area of the product, or the like. The platform 120 may display a recommendation for rectifying non-compliance of the product relative to the planogram.

[0075] According to an embodiment, the analytics may be associated with pricing compliance that identifies a compliance of a price of the product with pricing information of the product. The platform 120 may receive the image of the product, and information identifying pricing associated with the product. The platform 120 may compare the image of the product with the information identifying the pricing and determine a compliance of the product with the pricing. The platform 120 may display analytics indicating particular non-compliance with the pricing information,such as an incorrect price of the product. The platform 120 may display a recommendation for rectifying non-compliance of the product relative to the pricing information.

[0076] According to an embodiment, the analytics may be associated with promotion compliance that identifies a compliance of the product with promotion information of the product. The platform 120 may receive the image of the product, and information identifying a promotion associated with the product. The platform 120 may compare the image of the product with the information identifying the promotion and determine a compliance of the product with the promotion. The platform 120 may display analytics indicating particular non-compliance, such as an incorrect price of the product, an incorrect promotion, an absence of a promotion, incorrect promotion conditions, incorrect promotion benefits, or the like. The platform 120 may display a recommendation for rectifying non-compliance of the product relative to the promotion.

[0077] FIG. 6 is a diagram 600 of displaying analytics associated with a product and a recommendation regarding the product, pricing, promo, display or overall retail operation planning and execution. For example, as shown in FIG. 6, the user device 110 may display a user interface including information 610 identifying planogram compliance, information 620 identifying particular non-compliance with a promotion, an image 630 of the product, and information 640 identifying a recommendation for rectifying the non-compliance with the promotion.

[0078] According to an embodiment, the analytics may be associated with inventory analytics related to inventory of the product. The platform 120 may receive the image of the product, and determine, using external data, inventory of the product based on the image of the product. The platform 120 may display analytics related to the inventory of the product. The platform 120 may display a recommendation related to the inventory of the product, such as a recommendation to order additional product, refrain from ordering additional product, or the like.

[0079] According to an embodiment, the analytics may be associated with planogram variance that identifies variances in planograms associated with the product. The platform 120 may receive the image of the product, and determine, using external data, various planograms associated with the product. The platform 120 may display analytics indicting various planograms associated with the product. For example, the platform 120 may display different types of planograms includingthe product that are displayed at one or more respective retail locations. The platform 120 may display a recommendation for adjusting a planogram associated with the product. For example, the platform 120 may display a recommendation for adjusting a planogram associated with the product based on a different planogram associated with the product provided at a different retail location.

[0080] According to an embodiment, the analytics may be associated with SRM insights that identify insights for entities (e.g., manufacturers, vendors, suppliers, or the like) associated with the product. The platform 120 may receive the image of the product, and determine, using external data, performance metrics (e.g., a quantity of sales) associated with the product across planograms, retail locations, display area types, or the like. The platform 120 may display analytics including the SRM insights. The platform 120 may display a recommendation to adjust an assortment of the product, an arrangement of the product, a price of the product, a promotion of the product, or the like, based on the SRM insights.

[0081] According to an embodiment, the analytics may be associated with planogram performance that identifies performance metrics associated with different planograms associated with the product. The platform 120 may receive the image of the product, and determine, using external data, planograms associated with the product. Further, the platform 120 may determine performance metrics of the planograms. For example, the performance metrics may include a quantity of sales of one or more individual products included in the planogram, a total quantity of sales of the products included in the planogram, sentiment scores associated with one or more products included in the planogram, a sentiment score of the planogram, or the like. The platform 120 may display analytics identifying the performance metrics associated with the different planograms. The platform 120 may display a recommendation for adjusting the planogram based on the performance metrics of the different planograms.

[0082] FIG. 7 is a diagram 700 of displaying analytics associated with a product and a recommendation regarding the product. As shown in FIG. 7, the user device 110 may display a user interface including an image of a first planogram 710 and a second planogram. Further, the user interface may include an identifier 730 of the first planogram 710, a number of retail locations 740 including the first planogram 710, and a quantity of sales 750 associated with one or more products included in the first planogram 710. Further, the user interface may include an identifier 760 ofthe second planogram 720, a number of retail locations 770 including the second planogram 720, and a quantity of sales 780 associated with one or more products included in the second planogram 720.

[0083] According to an embodiment, the analytics may include analytics and / or insights associated with other products and / or associated with other entities. The platform 120 may receive the image of the product, and determine, using external data, one or more related products. For example, the one or more related products may include one or more products of another entity that are in a same category as the product, that are regarded as competitors of the product, that are regarded as alternatives to the product, or the like. The platform 120 may display analytics indicating planograms associated with the other products, retail location associated with the other products, sales data of the other products, inventory of the other products, sentiment scores of the other products, or the like. The platform 120 may display a recommendation related to the product based on the analytics associated with the other products.

[0084] According to an embodiment, the analytics may include OSA insights that identify insights for providing the availability of the product. The platform 120 may receive the image of the product, and determine, using external data, OSA insights related to the product. The platform 120 may display a recommendation related to the product based on the OSA insights. For example, the platform 120 may display a recommendation for a product located in a first retail location by suggesting inventory management techniques related to the product located in a second retail location.

[0085] In this way, the platform 120 may use the Al model 130 to generate analytics associated with a product, and recommendations associated with the product. Accordingly, some embodiments of the present disclosure provide a technical improvement in the technical field of planogram compliance and inventory management by utilizing big data and Al techniques to provide the generation of real-time analytics and recommendations based on images of products. Accordingly, in this way, some embodiments of the present disclosure improve the functioning of the user devices 110 associated with planogram compliance and inventory management by providing real-time analytics and recommendations for display.

[0086] Although FIG. 3 depicts particular operations and a particular order of operations, it should be understood that other embodiments may include different operations, a different order of operations, or the like.

[0087] FIG. 8 is a diagram of a process 800 fortraining, deploying, and monitoring an Al model for generating analytics associated with a product.

[0088] The platform 120 may generate, store, train, and / or use the Al model 130. According to an embodiment, the platform 120 may include the Al model 130 and / or instructions associated with the Al model 130. For example, the platform 120 may include instructions for generating the Al model 130, training the Al model 130, using the Al model 130, etc. According to another embodiment, a system or device other than the platform 120 may be used to generate and / or train the Al model 130. For example, a system or device may include instructions for generating the Al model 130, and / or instructions for training the Al model 130. The system or device may provide a resulting trained Al model 130 to the platform 120 or the user device 110 for use.

[0089] As shown in FIG. 8, according to an embodiment, the process 800 may include a training phase 802, a deployment phase 808, and a monitoring phase 814. In the training phase 802, at operation 806, the process 800 may include receiving and processing training data 804 to generate a trained Al model 130 for generating analytics associated with a product. The training data 804 may include images of the product, images of the other products, images of planograms, images of labels, images of pricing information, images of promotion information, external data, or the like.

[0090] Generally, the Al model 130 may include a set of variables (e.g., nodes, neurons, filters, or the like) that are tuned (e.g., weighted, biased, or the like) to different values via the application of the training data 804. According to an embodiment, the training process at operation 806 may employ supervised, unsupervised, semi-supervised, and / or reinforcement learning processes to train the Al model 130. According to an embodiment, a portion of the training data 804 may be withheld during training and / or used to validate the trained Al model 130.

[0091] For supervised learning processes, the training data 804 may include labels or scores that may facilitate the training process by providing a ground truth. Training may proceed by feeding a training dataset from the training data 804 into the Al model 130. The Al model 130 may have variables set at initialized values(e.g., at random, based on Gaussian noise, based on pre-trained values, or the like). The Al model 130 may output analytics associated with a product. The output may be compared with the corresponding label or score (e.g., the ground truth) indicating the data quality, which may then be back-propagated through the Al model 130 to adjust the values of the variables. This process may be repeated for a plurality of samples at least until a determined loss or error is below a predefined threshold. According to an embodiment, some of the training data 804 may be withheld and used to further validate or test the trained Al model 130.

[0092] For unsupervised learning processes, the training data 804 may not include pre-assigned labels or scores to aid the learning process. Instead, unsupervised learning processes may include clustering, classification, or the like, to identify naturally occurring patterns in the training data 804. As an example, the training data 804 may be clustered into groups based on identified similarities and / or patterns. K-means clustering or K-Nearest Neighbors may also be used, which may be supervised or unsupervised. Combinations of K-Nearest Neighbors and an unsupervised cluster technique may also be used. For semi-supervised learning, a combination of training data 804 with pre-assigned labels or scores and training data 804 without pre-assigned labels or scores may be used to train the Al model 130.

[0093] When reinforcement learning is employed, an agent (e.g., an algorithm) may be trained to make a decision regarding the data quality from the training data 804 through trial and error. For example, based on making a decision, the agent may then receive feedback (e.g., a positive reward if the prediction was above a predetermined threshold), adjust its next decision to maximize the reward, and repeat until a loss function is optimized.

[0094] After being trained, the trained Al model 130 may be stored and subsequently applied by the platform 120 during the deployment phase 808. For example, during the deployment phase 808, the trained Al model 130 executed by the platform 120 may receive input data 810. The input data 810 may include an image of a product and / or external data. The Al model 130 may provide, as output data 812, analytics associated with a product and / or a recommendation associated with the product.

[0095] The monitoring data 816 may include data that identifies analytics associated with a product and / or recommendations that are displayed. During process 818, the monitoring data 816 may be analyzed along with the predictedoutput data 812 and input data 810 to determine an accuracy of the trained Al model 130. According to an embodiment, based on the analysis, the process 800 may return to the training phase 802, where at operation 806 values of one or more variables of the model may be adjusted to improve the accuracy of the Al model 130.

[0096] The example process 800 described above is provided merely as an example, and may include additional, fewer, different, or differently arranged aspects than depicted in FIG. 8.

[0097] FIG. 8 describes the training, deployment, and monitoring associated with a trained Al model 130 for generating analytics associated with a product. According to an embodiment, one or more other trained Al models may be applied, such as trained Al model 130 for performing image processing, performing recommendation generation, or the like. Each of the trained Al models may include similar training, deployment, and / or monitoring phases as described above for the trained Al model 130 in FIG. 8, however the particular types of training data, input data, output data, and monitoring data may be different.

[0098] According to an embodiment, the system may simulate 3D virtual retail placement, shelf, store layout design and experience with Al recommendations that leverage GenAI for planogram position, layout design, drive collaboration and cocreation. The system may simulate 2D shelf placement and positioning to drive collaboration and productivity.

[0099] The system may conduct real-time compliance check on SKU, pricing, shelf, etc., to drive collaboration, quality, and efficiency. The system may obtain a planogram shelving picture and select an area of interest. The system may detect and classify products and pricing. The system may display planogram KPIs.

[0100] The system may provide an immersive virtual retail shelf and store experience design and simulation. The user navigates into the store. The user uses shelf menu to add shelves. The user selects one of the shelves with a mouse. The user selects SKU items from SKU menu. The user clicks the “generate planogram” button. The application sends a request to a GenAI API for positioning advice. The user may inform the GenAI of the shelf and SKUs optimization priorities through a chat Ul. The GenAI API responds with positioning information based on the user’s shelf and SKU optimization priority inputs. The application may use the GenAI API response and place the 3D models of the SKU items on the selected shelf. The user evaluates the positioning and decides if the suggestion is acceptable. If thepositioning is accepted, the planogram can be saved using the “save planogram” button. If the positioning is not accepted, the user can click the “generate planogram” button again.

[0101] The application may include a 3D retail store model, 3D shelves model, 3D SKU items, shelf placement, SKU placement, and a GenAI III.

[0102] Smart augmented reality technology enables visualization of in-store product placement and shelf design choices, facilitating real-time collaboration and shelf layout review between retail customer teams and associate teams. The same 3D assets can be used in VR environments to design and run store simulations share of facings simulations, and other predictive modeling scenarios. State of the art computer vision and augmented reality technology can automate planogram compliance audits, enhance associate experiences with regular inventory and pricing checks, and empower merchandizing teams with real-time collaboration and troubleshooting at their fingertips with a mobile phone.

[0103] While principles of the present disclosure are described herein with reference to illustrative embodiments for particular applications, it should be understood that the disclosure is not limited thereto. Those having ordinary skill in the art and access to the teachings provided herein will recognize additional modifications, applications, embodiments, and substitution of equivalents all fall within the scope of the embodiments described herein. Accordingly, the invention is not to be considered as limited by the foregoing description.

Claims

CLAIMSWhat is claimed is:1 . A method comprising: receiving, from a user device or an imaging device, an image of an object located in a display area of an end-user channel location; generating, using an artificial intelligence (Al) model, analytics associated with the object based on the image of the object located in the display area of the enduser channel location; and displaying the generated analytics on a display device or transmitting the generated analytics for display on the display device, wherein the analytics include: object placement compliance information that identifies an object placement compliance of the object with an object placement model; value allocation compliance information that identifies a value allocation compliance of a value allocation of the object with value allocation information of the object, promotion compliance information that identifies a promotion compliance of the object with promotion information of the object, inventory analytics related to inventory of the object at the end-user channel location, and object placement variance that identifies variances in object placements associated with the object or object placement performance that identifies performance metrics associated with the object placement model.

2. The method of claim 1 , further comprising: generating a recommendation regarding the object using the Al model; and displaying the recommendation based on generating the recommendation using the Al model.

3. The method of claim 1 , wherein the analytics include supplier relationship management (SRM) insights that identify insights for entities associated with the object.

4. The method of claim 1 , wherein the analytics include analytics associated with a different object associated with a different entity, wherein the different object is related to the object.

5. The method of claim 1 , wherein the analytics include on-shelf availability (OSA) insights that identify insights for providing availability of the object.

6. The method of claim 1 , wherein the displaying comprises displaying the analytics in substantially real-time via the user device.

7. The method of claim 1 , wherein the object is a confectionary object.

8. A device comprising: a memory configured to store instructions; and one or more processors configured to execute the instructions to perform operations comprising: receiving, from a user device or an imaging device, an image of an object located in a display area of an end-user channel location; generating, using an artificial intelligence (Al) model, analytics associated with the object based on the image of the object located in the display area of the end-user channel location; and displaying the generated analytics on a display device or transmitting the generated analytics for display on the display device, wherein the analytics include: object placement compliance information that identifies an object placement compliance of the object with an object placement model; value allocation compliance information that identifies a value allocation compliance of a value allocation of the object with value allocation information of the object, promotion compliance information that identifies a promotion compliance of the object with promotion information of the object, inventory analytics related to inventory of the object at the enduser channel location, andobject placement variance that identifies variances in object placements associated with the object or object placement performance that identifies performance metrics associated with the object placement model.

9. The device of claim 8, wherein the operations further comprise: generating a recommendation regarding the object using the Al model; and displaying the recommendation based on generating the recommendation using the Al model.

10. The device of claim 8, wherein the analytics include supplier relationship management (SRM) insights that identify insights for entities associated with the object.11 . The device of claim 8, wherein the analytics include analytics associated with a different object associated with a different entity, wherein the different object is related to the object.

12. The device of claim 8, wherein the analytics include on-shelf availability (OSA) insights that identify insights for providing the availability of the object.

13. The device of claim 8, wherein the displaying comprises displaying the analytics in substantially real-time via the user device.

14. The device of claim 8, wherein the object is a confectionary object.

15. A non-transitory computer-readable medium storing instructions that, when executed by one or more processors, cause the one or more processors to perform operations comprising: receiving, from a user device or an imaging device, an image of an object located in a display area of an end-user channel location; generating, using an artificial intelligence (Al) model, analytics associated with the object based on the image of the object located in the display area of the enduser channel location; anddisplaying the generated analytics on a display device or transmitting the generated analytics for display on the display device, wherein the analytics include: object placement compliance information that identifies an object placement compliance of the object with an object placement model; value allocation compliance information that identifies a value allocation compliance of a value allocation of the object with value allocation information of the object, promotion compliance information that identifies a promotion compliance of the object with promotion information of the object, inventory analytics related to inventory of the object at the end-user channel location, and object placement variance that identifies variances in object placements associated with the object or object placement performance that identifies performance metrics associated with the object placement model.

16. The non-transitory computer-readable medium of claim 15, wherein the operations further comprise: generating a recommendation regarding the object using the Al model; and displaying the recommendation based on generating the recommendation using the Al model.

17. The non-transitory computer-readable medium of claim 15, wherein the analytics include supplier relationship management (SRM) insights that identify insights for entities associated with the object.

18. The non-transitory computer-readable medium of claim 15, wherein the analytics include different object insights associated with a different object associated with a different entity, wherein the different object is related to the object.

19. The non-transitory computer-readable medium of claim 15, wherein the analytics include on-shelf availability (OSA) insights that identify insights for providing the availability of the object.

20. The non-transitory computer-readable medium of claim 15, wherein the analytics include competitive insights associated with a different product associated with a different entity, wherein the different product is related to the product.

21. The non-transitory computer-readable medium of claim 15, wherein the analytics include category insights associated with overall confectionary and / or snacking category that is related to the object.

22. The non-transitory computer-readable medium of claims 15-21 , wherein the recommendation includes action recommendations associated with retail store operation and execution that helps to beneficially optimize sales with the SRM insights, the different product insights, the OSA insights, the competitive insights, and the category insights, and wherein a modality of the recommendation includes audio action guidance, video action guidance, and / or image action guidance.

23. The non-transitory computer-readable medium of claim 15, wherein the object is a confectionary object, a snacking object, any consumer packaged object, a retail shelf, or a checkout counter.

Images