A SHELF, A SHELVING SYSTEM, AND A METHOD THEREOF

Abstract

An embodiment of the present invention relates a shelf (200) and a shelving system (100) to generate one or more recommendations and a method (300) thereof. The system (100) is implemented to generate personalized product recommendations by analyzing parameters from both products and users in proximity. The system (100) comprises a shelf body (101) equipped with sensors (102) to capture product and user parameters, a camera (103) to record images of the shelf environment, and a scanner (104) to extract product data via codes like barcodes and RFID. A server (105) with a processor (105-1) that analyzes this data to map product information, process collected parameters, and generate recommendations for users based on AI or ML models. The recommendations, displayed on an interface (106), may include but not limited to complementary items, seasonal suggestions, or health-relevant choices, thus enhances user engagement and optimises inventory management.

Specification

Description:TECHNICAL FIELD
[0001] The present invention relates to the field of smart or intelligent shelving systems. Specifically, the present invention pertains to a smart interactive shelving system implemented to revolutionize the retail experience, more particularly relates to a shelf, a smart shelving system that generates product recommendations to users, and a method thereof.

BACKGROUND
[0002] The following description of the related art is intended to provide background information pertaining to the field of the present invention. This section may include certain aspects of the art that may be related to various features of the present invention. However, it should be appreciated that this section is used only to enhance the understanding of the reader with respect to the present invention, and not as admissions of the prior art.
[0003] In many shopping places or retail stores when people are shopping, they hope that all the items or products they will get as per their shopping list in one place. It is observed that, often the items are missing or misplaced and it's very difficult to get the assistance to trace the exact location of the product or items in the store. In many instances, shoppers are left with the choice of either going to a different retail store or returning the next day, hoping that the shelves will be restocked. There must be some solution to find out and trace the item or product that the shoppers want at that time instantly.
[0004] The computer-enabled or smart shelfs provide the ability to advertise, represent and provide information about the product in a small, accessible installation. The multi-functionality of such shelfs enhances the aesthetic appeal of its product offering for attracting customers, and can also foster a consistent set of visual and auditory features that customers may come to associate with a particular brand. Interactive shelfs are designed for extensive public use, the displayed objects can be moved from their assigned locations and manipulated in ways that change the overall appearance of the shelf over time, to the detriment of the consistent "look" for which the specifications of the shelf have been implemented.
[0005] In the existing shelving systems, digital screens and electronic labels are used to display product information, pricing, and promotions. It is easily updateable, enabling dynamic pricing and real-time information changes. Radio frequency identification (hereinafter "RFID") and near-field communication (hereinafter "NFC") are used for tracking inventory and providing product information through customer interactions with tags or smart devices. Also in some existing shelving systems, cameras and sensors are used for monitoring stock levels, tracking customer movements, and detecting product interactions. Further, augmented reality (hereinafter "AR") is used to enhance the shopping experience by overlaying digital information on the physical environment, often through mobile devices or smart glasses in some shelving systems. The touchscreens on shelves or kiosks provide detailed product information, reviews, and virtual try-ons. However, High initial setup and maintenance costs can be prohibitive for widespread adoption of such systems, especially for smaller retailers.
Traditional shelving units lack the capability to analyze in-store user behavior or product status in real-time, often resulting in missed opportunities for engaging customers with relevant product recommendations. The existing systems often fall short in providing adaptable, detailed, and dynamic recommendations based on an extensive range of product and user data.
[0006] A prior art reference US 20,170,228,686 A1, titled "Smart Shelves For Retail Industry" discloses the system and a method that includes a set of smart shelves. Each of the smart shelves has a mesh arrangement of sensors that include strain sensors, photodetectors, microphones, and spillage sensors placed on the bottom thereof to form a sensor mesh layer for generating a signal representative of a product count for a given product to be sold from a corresponding one of the smart shelves. The system further includes a data processing system for transforming the signal from each of the smart shelves into a product count value therefor. The system also includes a set of video displays for displaying characteristics of the given product to be sold from each of the smart shelves. The system additionally includes a set of wireless radios for transmitting the characteristics of the given product to be sold from each of the smart shelves to the set of video displays.
[0007] Another prior art reference "US 8,370,207 B2", titled "Virtual reality system including smart objects", discloses invention include a virtual reality system that includes an instrumented device used to present a virtual shopping environment to a simulation participant. The participant's interactions with the virtual shopping environment may be used to conduct market research into the consumer decision making process. The virtual shopping environment may include one or more smart objects configured to be responsive to participant interaction. The virtual shopping environment may recreate a real-world shopping environment.
[0008] Thus, there is a need in the art to provide an intelligent shelf, a shelving system to generate one or more recommendations to the users, and a method thereof.

OBJECTS OF THE PRESENT INVENTION
[0009] Some of the objects of the present invention, which at least one embodiment herein satisfies are as listed herein below.
[0010] It is an object of the present invention to provide a shelf, a shelving system to generate one or more recommendations to a user, and a method thereof.
[0011] It is another object of the present invention to ensure seamless integration of various sensors, cameras, and scanners to capture detailed product and environmental data.
[0012] It is another object of the present invention to enable a versatile recommendation system that adapts to different retail environments and product categories.

SUMMARY:
[0013] Within the scope of this application, it is expressly envisaged that the various aspects, embodiments, examples, and alternatives set out in the preceding paragraphs, in the claims and/or in the following description and drawings, and in particular the individual features thereof, may be taken independently or in any combination. Features described in connection with one embodiment are applicable to all embodiments, unless such features are incompatible.
[0014] In an aspect, a shelving system is disclosed which provides product recommendations to the users based on real-time parameters sensed from both the product and user environment. The shelving system includes a shelf body equipped with sensors to detect product and user parameters, a camera to capture images of the shelf surroundings, and a scanner for product data extraction. A processor embedded in a server is communicatively coupled to the sensors, camera, and scanner, enabling the retrieval and analysis of product and user data. Based on this analysis, the system generates recommendations, including but not limited to, complementary product suggestions or seasonal offers, displayed on a user interface.
[0015] In another aspect, a shelf to generate one or more recommendations to the user is disclosed. The shelf is integrated with digital displays, sensors, RFID/NFC technology, and data analytics to create a dynamic and engaging shopping environment. The digital displays provide real-time information on product pricing, promotions, and specifications, while sensors and cameras monitor inventory levels and customer interactions. The RFID/NFC integration facilitates seamless product tracking and offers customers instant access to detailed product information by tapping their smartphones. Additionally, the processor embedded in the shelf collects and analyzes customer behavior data, allowing retailers to optimize inventory management, product placement, and marketing strategies.
[0016] In yet another aspect, the present invention discloses a method of generating one or more recommendations to the user. The method includes a step-wise illustration of how the method is implemented using the shelving system to generate customised product recommendations based on real-time data.
[0017] Various objects, features, aspects, and advantages of the inventive subject matter will become more apparent from the following detailed description of preferred embodiments, along with the accompanying drawing figures in which like numerals represent like components.

BRIEF DESCRIPTION OF THE DRAWINGS
[0018] The accompanying drawings, which are incorporated herein, and constitute a part of this invention, illustrate exemplary embodiments of the disclosed methods and systems which like reference numerals refer to the same parts throughout the different drawings. Components in the drawings are not necessarily to scale, emphasis instead being placed upon clearly illustrating the principles of the present invention. Some drawings may indicate the components using block diagrams and may not represent the internal circuitry of each component. It will be appreciated by those skilled in the art that the invention of such drawings includes the invention of electrical components, electronic components or circuitry commonly used to implement such components.
[0019] FIG. 1 illustrates an exemplary block diagram of a shelving system to generate the recommendations to the user, in accordance with an embodiment of the present invention.
[0020] FIG. 2 illustrates a flow diagram of a method of generating one or more recommendations to the user using a shelving system, in accordance with an embodiment of the present invention.
[0021] FIG. 3 illustrates an overall architecture of a shelving system to generate the recommendations to the user, in accordance with an embodiment of the present invention.

DETAILED DESCRIPTION
[0022] In the following description, for the purposes of explanation, various specific details are set forth in order to provide a thorough understanding of embodiments of the present invention. It will be apparent, however, that embodiments of the present invention may be practiced without these specific details. Several features described hereafter can each be used independently of one another or with any combination of other features. An individual feature may not address all of the problems discussed above or might address only some of the problems discussed above. Some of the problems discussed above might not be fully addressed by any of the features described herein.
[0023] Various embodiments of the present invention will be explained in detail with respect to FIGs. 1-3.
[0024] FIG. 1 illustrates an exemplary block diagram (150) of a shelving system (100) to generate recommendations to the user, in accordance with an embodiment of the present invention.
[0025] In a first embodiment of the present invention, a shelving system (100) (the terms "system", "intelligent shelving system", or "smart shelving system" are used interchangeably) to generate one or more recommendations (hereinafter the terms "recommendations" or "product recommendations" are used interchangeably) is disclosed. The shelving system (100) includes a configuration that generates recommendations tailored to users. The shelving system (100) includes several components, such as a shelf body (101), one or more sensors (102) (hereinafter "sensors"), a camera (103), a scanner (104), a server (105) with an embedded processor (105-1), and a user interface (106). Each of these components functions collaboratively to obtain and process data related to products and users within the system's environment, thereby facilitating the generation of personalized product recommendations.
[0026] In an exemplary implementation of the first embodiment, the shelf body (101) serves as the structural base upon which various components are mounted. The sensors (102) are installed on the shelf body (101) and are configured to detect parameters pertaining to the products (600) positioned on the shelf and users in close proximity to the shelving system (100). The sensors (102) include but not limited to, weight sensors, proximity sensors, environmental sensors, or motion sensors. Each sensor performs distinct functions.
[0027] In the exemplary implementation of the first embodiment, the weight sensor may detect the weight of a product (600) positioned on the shelf body (101), while a proximity sensor may sense the presence and movement of users within the vicinity of the shelf. Further, environmental sensors may monitor conditions like temperature and humidity around the products (600), while motion sensors may detect dynamic interactions with the shelving system (100).
[0028] In the exemplary implementation of the first embodiment, the camera (103), also mounted on the shelf body (101), captures images of the products (600) and the surrounding environment. The imaging capability allows the shelving system (100) to record visual data of the products (600), including information about their shape, size, color, and position on the shelf body (101). The camera (103) also captures the spatial arrangement of products (600) and any interactions that occur around them, such as users picking up or replacing items on the shelf body (101).
[0029] In the exemplary implementation of the first embodiment, the scanner (104) is configured to retrieve product data by scanning a code attached to the products (600). The codes may include but not limited to, barcodes, QR codes, RFID tags, or NFC tags, which are commonly attached to products (600) for identification. The scanner (104) reads these codes to obtain specific product data, including unique identification details such as SKU numbers, product ID, and batch numbers. The codes are attached to the products (600) through means including printing, embossing, adhesives, labeling, sticking, embedding, heat transfer labeling, direct printing, or filming that depending on product type and application requirements.
[0030] In the exemplary implementation of the first embodiment, the server (105) includes the processor (105-1) and is communicably connected to the sensors (102), camera (103), and scanner (104).
[0031] The processor (105-1) retrieves data from the sensors (102), including product parameters and user parameters. The camera (103) supplies the processor (105-1) with captured images, while the scanner (104) provides scanned product data. The processor (105-1) uses this comprehensive set of data to conduct various processing operations, including mapping the product data to identifiers within an inventory database stored on the server (105).
[0032] In the exemplary implementation of the first embodiment, the product parameters include but not limited to weight, size, shape, and temperature sensitivity. The user parameters include but not limited to, dwell time, product interaction frequency, movement path, or proximity to specific product categories.
[0033] Upon successful mapping, the processor (105-1) retrieves the corresponding product data from one or more inventories. In such embodiment, one or more inventories include but not limited to, various categories, such as product category inventory, seasonal inventory, perishable inventory, high-demand inventory, promotional inventory, discounted inventory, bulk inventory, backup inventory, online inventory, or omnichannel inventory. Once the processor (105-1) retrieves and verifies the mapped product data, it processes the product parameters, user parameters, and image data to generate processed versions of each. The processor (105-1) then analyzes these processed product and user parameters, along with processed image data, to generate a recommendation.
[0034] The recommendations are generated by the processor (105-1) using an artificial intelligence (AI) model, a machine learning (ML) model, or an augmented reality (AR) model. It is based on the insights derived from the scanned product data or the sensed product and user parameters. The recommendations may include but not limited to, one or a combination of complementary product suggestions, substitute product options, cross-category recommendations, upsell offers, promotion-based suggestions, personalized recommendations based on purchase history, contextual or seasonal offers, recipe-based suggestions, health-relevant suggestions, or lifestyle-based options. For example- the processor (105-1) might generate a recommendation for a complementary item based on a user's recent purchase history, or a seasonal offer tailored to the time of year.
[0035] In the exemplary implementation of the first embodiment, the user interface (106) may be positioned on a shelf body (101) or the user interface (106) may be remotely located to display one or more recommendations about the products placed on the shelf body (101).
[0036] Further, the user interface (106) displays the generated recommendations to users. The user interface (106) is communicably linked to the processor (105-1), ensures that recommendations generated by the shelving system (100) are promptly presented to users. The user interface (106) is interactive and allows users to view relevant product suggestions in real-time as they engage with the products (600) on the shelf body (101), further enhancing user engagement and supporting informed purchase decisions.
[0037] In the exemplary implementation of the first embodiment, the users who interact with the shelving system (100) may include but not limited to, one or more individuals from diverse categories, such as customers, store staff, store managers, maintenance personnel, or information technology (IT) personnel, depending on the shelving system's context and operational environment.
[0038] In the exemplary implementation of the first embodiment, one or more products (600) may include but not limited to, physical goods including but not limited to, groceries, electronics, apparel, household items, or perishable items that include food, drinks, or medications.
[0039] In the exemplary implementation of the first embodiment, one or more recommendations are generated upon on successful scanning of the code or sensing one or more parameters associated with one or more products or one or more users. The recommendations include but are not limited to, complementary product recommendations, substitute product recommendations, cross-category recommendations, upsell recommendations, promotion-based recommendations, personalized recommendations based on purchase history, contextual or seasonal recommendations, recipe-based recommendations, health-relevant recommendations, or lifestyle recommendations.
[0040] To summarise, the shelving system (100) enables a responsive and data-driven approach to user engagement and inventory management. The components of the shelving system (100) work cohesively to ensure real-time data collection, accurate product identification, comprehensive parameter processing, and delivery of targeted recommendations. The system's structure supports an enhanced retail experience by providing users with relevant information, aligning product offerings with customer preferences, and allowing retailers to manage inventory dynamically based on user interactions with the shelf body (101).
[0041] Working example 1: If a user is browsing in the snack aisle near the disclosed shelving system (100), He may receive recommendations for beverages like sparkling water, juice, or coffee, which are commonly purchased with snacks, to inspire a broader shopping selection. (Cross-category recommendations).
[0042] In a second embodiment of the present invention, a shelf (200) (the terms "intelligent shelf", "smart shelf", or "interactive shelf" are used interchangeably) to generate one or more commendations to the users is disclosed.
[0043] In an exemplary implementation of the second embodiment, a shelf (200) provides product recommendations to users based on real-time parameters sensed from both the product and the user environment. The intelligent shelf (200) includes a shelf body (101) equipped with sensors (102) (such as weight, proximity, environmental, and motion sensors) to detect product and user parameters, a camera (103) to capture images of the shelf surroundings, and a scanner (104) for product data extraction. A processor (105-1) on a server (105) is communicatively coupled to the sensors (102), camera (103), and scanner (104), enabling the retrieval and analysis of product and user data. Based on the analysis, the intelligent shelf (200) generates recommendations, such as complementary product suggestions or seasonal offers, displayed on an interface mounted either on the shelf body (101) or remotely located at the server (105) or end-user devices.
[0044] In an exemplary implementation of the second embodiment, the shelf (200) includes a configuration with a shelf body (101) and an embedded processor (105-1) that facilitates data-driven operations for analyzing and recommending products based on collected parameters. The shelf body (101) functions as the structural component housing the processor (105-1), which is programmed to handle and process multiple types of data. The processor (105-1) is configured to obtain one or more product parameters and one or more user parameters, images, and product data related to one or more products (600) positioned on the shelf body (101). The processor (105-1) retrieves and analyzes data from both product interactions and user presence around the shelf (200).
[0045] Further, the processor (105-1) also maps the obtained product data to identifiers associated with inventories stored on a server (105). In such embodiment, one or more identifiers may include but not limited to, item numbers, SKUs, or batch numbers that enable accurate linking of physical items to digital records. Upon successful mapping, the processor (105-1) retrieves the associated mapped product data from the server (105) for further analysis. The processor (105-1) subsequently processes the product parameters, user parameters, image data, and retrieved product data, generating processed data sets for each. The processed data elements provide insights into specific aspects, such as product attributes or user behavior, which form the basis of subsequent recommendations.
[0046] In an exemplary implementation of the second embodiment, once processing is complete, the processor (105-1) performs an analysis of the processed product parameters, processed user parameters, processed images, and the mapped product data. The analysis enables the processor (105-1) to generate one or more recommendations to users. Recommendations provided by the processor (105-1) may include but not limited to, suggestions based on complementary products, alternatives, promotional offers, or other criteria relevant to enhancing the user's selection and purchasing experience.
[0047] In an exemplary implementation of the second embodiment, the shelf (200) further includes one or more sensors (102) mounted on the shelf body (101), designed to sense various parameters associated with the products (600) and users in proximity to the shelf (200). The sensors (102) include a combination of devices, such as weight sensors, proximity sensors, environmental sensors, and motion sensors, each serving a distinct purpose. For instance, the weight sensor provides data on the physical load of products (600) on the shelf body (101), the proximity sensor detects users nearby, and the environmental sensor monitors factors like temperature and humidity that could affect product quality.
[0048] In an exemplary implementation of the second embodiment, the shelf (200) also includes a camera (103) mounted on the shelf body (101), capable of capturing images of the products (600) and the surrounding environment. The camera (103) records visual characteristics, such as the shape, size, and color of products (600), as well as the interactions users have with the items on the shelf body (101). The imaging capability supports the processor (105-1) in processing and analyzing the spatial layout and positioning of products (600) for more refined recommendations.
[0049] In an exemplary implementation of the second embodiment, the shelf (200) includes a scanner (104) configured to scan codes attached to products (600) on the shelf body (101) to retrieve product data. The scanner (104) is adaptable to scan various types of codes. The scanner (104) captures product-specific information, which is then passed to the processor (105-1) to facilitate accurate product identification and data mapping.
[0050] In an exemplary implementation of the second embodiment, the shelf (200) configuration supports an interactive and intelligent retail experience. The system's ability to obtain, process, and analyze product and user data in real-time allows for the generation of personalized recommendations that enhance the user experience.
[0051] FIG. 2 illustrates a flow diagram (300) of a method (300) of generating one or more recommendations to the users using a shelving system (100), in accordance with an embodiment of the present invention.
[0052] In a third embodiment of the present invention, the method (300) is implemented to generate product recommendations using the shelving system (100) is disclosed.
[0053] At block 301, the method (300) begins with one or more sensors (102) configured to sense one or more product parameters associated with one or more products (600) positioned on the shelf body (101) as well as one or more user parameters associated with the users present near the sensors (102).
[0054] At block 302, the camera (103) is mounted on the shelf body (101), configured to capture one or more images of the products (600) and the surrounding environment of the shelf body (101). The camera (103) records visual information on the products (600), including their physical characteristics and their position on the shelf body (101). Additionally, the camera (103) captures user interactions with products (600) and movement patterns, providing a visual record that complements the sensor-based data.
[0055] At block 303, the scanner (104) decodes information embedded in the code, allowing accurate retrieval of product data such as identification numbers, batch numbers, or SKUs.
[0056] At block 304, a processor (105-1) of the server (105) obtained the sensed product and user parameters, captured images, and scanned product data through the processor (105-1) embedded therein. The server (105) is communicably connected to the sensors (102), camera (103), and scanner (104), receives these inputs for processing.
[0057] At block 305, the processor (105-1) within the processor (105-1) maps the obtained product data with one or more identifiers linked to inventory records stored on the server (105). The mapping process associates physical products (600) with digital inventory information, enables the server (105) to retrieve mapped product data based on accurate identification of products (600) on the shelf body (101).
[0058] At block 306, the processor (105-1) subsequently processes the obtained data, which includes product parameters, user parameters, images, and mapped product data. The processing step allows the processor (105-1) to refine raw inputs, converting them into processed data sets.
[0059] At block 307, the processed data sets by the processor (105-1) is analysed to generate recommendations for the users. During analysis, the processor (105-1) evaluates patterns, preferences, and relevant product characteristics to create personalized suggestions.
[0060] The method (300) facilitates an intelligent recommendation process using the shelving system (100), leads to effective, user-oriented product recommendations to the users.
[0061] FIG. 3 illustrates an overall architecture (500) of a shelving system (100) to generate the recommendations to the user, in accordance with an embodiment of the present invention.
[0062] In a fourth embodiment of the present invention, the system (100) includes advanced sensors and cameras to monitor customer presence and behavior, while RFID/NFC technology allows seamless product tracking and instant access to detailed information via smartphone interactions. The present invention also includes an integrated data analytics engine that collects and analyzes customer behavior data, optimizing inventory management, product placement, and marketing strategies. The augmented reality (AR) module provides personalized recommendations and immersive experiences. Additionally, the system's seamless integration with retailer backend systems facilitates efficient inventory and marketing optimizations. Overall, the smart and interactive shelving system (100) combines convenience, personalization, and enhanced customer engagement, distinguish from existing retail technologies. The system (100) offers personalized recommendations and interactive experiences using artificial intelligence (AI) model, machine learning (ML) model, or augmented reality (AR).
[0063] In an exemplary implementation of the fifth embodiment, the system (100) includes the data analytics engine represents the processing unit of the system, where a processor (105-1) analyzes the data collected from sensors (102), camera (103), and RFID/NFC reader (104). The processor (105-1) processes and interprets product parameters, user parameters, and captured images to generate actionable insights. Through ML model or AI model, the engine provides personalized recommendations and predictions based on user behavior, product characteristics, and inventory data.
[0064] In the exemplary implementation of the fifth embodiment, the system (100) further includes a touchscreen interface, part of the smart shelving system, that allows users to interact directly with the recommendations and product information. The users can view detailed descriptions, explore complementary products, or receive personalized recommendations. The touchscreen enhances engagement, enabling users to navigate options and interact intuitively with the system.
[0065] In the exemplary implementation of the fifth embodiment, the system (100) may include an augmented reality module that further enriches the customer experience by overlaying virtual information onto the physical products (600). Through AR technology, users can view product demonstrations, visualize usage scenarios, or receive step-by-step guidance on using certain items. The AR module supports enhanced product visualization, which can be instrumental in categories like apparel, electronics, or home decor.
[0066] In the exemplary implementation of the fifth embodiment, the system (100) may further include a backend system. The backend system includes but is not limited to inventory management system, marketing system, customer relationship management (CRM) system, product database, consumer database, and store staff interface.
[0067] In the exemplary implementation of the fifth embodiment, the inventory management system manages stock levels, product categories, and availability across the shelf body (101). It tracks real-time inventory levels, assisting in generating stock-related recommendations and ensuring products (600) on display are sufficiently stocked.
[0068] In the exemplary implementation of the fifth embodiment, the product database stores essential product information, such as SKU, dimensions, category, and description. It links to the RFID/NFC reader data, allowing for quick retrieval of product-specific details when a code is scanned. The database acts as a central repository for all product data. The consumer database contains user-related information, capturing parameters such as demographic data, shopping frequency, or interaction history. The database aids in tailoring recommendations and promotional offers to match customer preferences and past engagement. Further,
The store staff interface provides access for personnel to monitor, update, or manage the smart shelving system. Through the interface, staff can manage inventory, review analytics, or address any system alerts. It serves as a control point for the backend system, ensuring smooth operations and facilitating in-store management. Overall, the system (100) allows seamless coordination between customer interaction and data processing to improve the shopping experience and optimize inventory management.
[0069] In the sixth embodiment of the present invention, the broad workable ranges for various parameters of the shelving system (100) are disclosed.
[0070] In an exemplary implementation of the sixth embodiment, the digital display i.e. user interface (106) is used in the system (100) may vary in size ranges between 10 to 50 inches diagonally, depending on the shelf size and visibility requirements. The resolution ranges from 720p to 4K (1920x1080 to 3840x2160 pixels), provides clear product information and high-quality images. Brightness is adjustable and ranges between 250 to 1000 nits, depending on the ambient lighting conditions within the store.
[0071] In the exemplary implementation of the sixth embodiment, the sensors (102) may have a detection range of up to 5 meters, allowing them to sense customer presence and interactions effectively. Camera resolution can range from 720p to 4K (1280x720 to 3840x2160 pixels) to ensure clear image capture for interaction analysis. Additionally, the field of view (FOV) spans 60° to 120°, enabling broad coverage in front of the shelf (200for optimal tracking and monitoring.
[0072] In the exemplary implementation of the sixth embodiment, the RFID technology includes a range from 1 to 3 meters for standard RFID tags and up to 10 meters for high-frequency (HF) RFID systems. NFC technology, used for close-range interactions, ranges between 1 to 10 centimetres, suitable for interactions with smartphones. The tag storage capacity varies from 64 bytes to 4 KB, depending on the amount of data required for each product.
[0073] In the exemplary implementation of the sixth embodiment, the touchscreen may vary in size ranges between 7 to 20 inches diagonally, adaptable to the shelf's size and available space. The user interface (106) may provide a resolution range of 800x600 to 1920x1080 pixels, ensures clarity and ease of interaction. The user interface (106) may support multi-touch gestures with a response time of under 50 milliseconds, facilitates quick and responsive interactions.
[0074] The AR module is typically integrated with smartphones or tablets that are AR-compatible, generally requiring hardware with at least a 720p display for proper functionality. The AR module operates with a latency of under 100 milliseconds to ensure smooth and responsive AR experiences for users.
[0075] Power requirements vary across components. Digital displays consume between 30 to 150 watts, depending on their size and brightness settings. Sensors and cameras collectively require watts ranges between 5 to 20 watts, while RFID/NFC readers need 5 to 15 watts. Touchscreens consume between 15 to 50 watts, depending on their size and specifications.
[0076] The system (100) supports network connectivity through Wi-Fi (802.11 b/g/n/ac) or Ethernet (100 Mbps to 1 Gbps) for data transmission. API support allows integration with retailers' backend systems and third-party services, facilitates seamless data exchange and operational alignment with other retail management systems.
[0077] The system (100) may operate reliably within a temperature range of 0°C to 40°C (32°F to 104°F), suitable for most retail environments. It also accommodates humidity levels from 10% to 90% in non-condensing conditions, allowing for use in various store climates and settings.
[0078] In a seventh embodiment of the present invention, the working example is illustrated.
[0079] Working example: In retail grocery store, consider a smart interactive shelving system (100) placed within a grocery store to enhance customer experience through real-time, personalized product recommendations. Each component of the shelving system works together to gather product and user data, analyse it, and generate suggestions that may be relevant to individual customers. The shelving system is installed within the grocery store and is strategically positioned to display a range of products (600) such as beverages, snacks, or personal care items. The shelf body (101) holds the products and provides a structural base for the mounting of various sensors (102), a camera (103), and a scanner (104). The shelf body (101) is communicably connected to a server (105) that processes data. The system (100) includes multiple sensors (102) mounted on the shelf body (101) that are configured to detect specific parameters related to both the products and users. For instance, the sensors (102) might detect product weight, stock level, or freshness based on shelf time. Simultaneously, the sensors (102) can monitor user parameters such as proximity, number of users near the shelf, and duration of their interaction with the shelf. As a customer approaches the shelf and reaches for a product, the sensors (102) register the movement and begin collecting relevant data. The camera (103) mounted on the shelf body (101) that captures real-time images of the products (600) on the shelf as well as the surrounding environment. For example, the camera might capture images of the product arrangement, as well as images of the customer browsing the items. The camera (103) may also identify if a product has been removed from the shelf, potentially indicating user interest in that item. The scanner (104) is used to read barcodes, QR codes, or RFID tags attached to each product (600). The server (105) with the embedded processor (105-1) is connected to the sensors (102), camera (103), and scanner (104).
[0080] Further, the processor (105-1) maps the obtained product data with unique identifiers associated with inventory information stored on the server (105). For example, if the scanned product is a specific type of beverage, the processor (105-1) maps this data to the corresponding entry in the inventory database, retrieving further details about the product, such as promotional offers, alternative options, or nutritional information. Once the data is mapped, the processor (105-1) then processes the collected product and user parameters, images, and retrieved product data. For example, based on sensor readings, the processor might assess that the product stock is low or that the customer interaction time is prolonged, possibly indicating interest in that product. The processor (105-1) analyzes the processed parameters and generates personalized recommendations for the customer. For instance, if the customer has shown interest in a specific type of beverage, the system may recommend complementary products, such as a discount on a similar drink or a bundled snack option. The generated recommendations are displayed on a digital screen integrated into the shelf body (101). The digital display could show the customer options such as, "Customers who liked this product also liked..." or "Special discount on this product." Furthermore, the system (100) might allow the customer to view nutritional details, product reviews, or loyalty points related to the product. As customers continue to interact with the shelf and new products are stocked, the system remains in constant operation. In this way, the shelving system (100) dynamically engages customers, provides valuable product recommendations based on real-time data analysis, and creates a more personalized and efficient shopping experience.
[0081] While considerable emphasis has been placed herein on the preferred embodiments, it will be appreciated that many embodiments can be made and that many changes can be made in the preferred embodiments without departing from the principles of the invention. These and other changes in the preferred embodiments of the invention will be apparent to those skilled in the art from the invention herein, whereby it is to be distinctly understood that the foregoing descriptive matter is to be implemented merely as illustrative of the invention and not as a limitation.

ADVANTAGES OF THE PRESENT INVENTION
[0082] The present invention provides a shelf, a shelving system to generate the recommendations, and a method thereof.
[0083] The present invention provides a shelving system that effectively captures user attention, increases engagement, and improves the shopping experience by offering tailored recommendations.
[0084] The present invention provides a shelving system that provides adaptable recommendations that cater to various user profiles and preferences, leveraging AI and ML models for optimized recommendations.
[0085] The present invention provides real-time sensing and analysis of user behavior and product attributes allowing for immediate adjustments to recommendations based on current user activity and stock levels.
, Claims:1. A shelving system (100) to generate one or more recommendations to one or more users, the shelving system (100) comprising:
a shelf body (101);
one or more sensors (102) mounted on the shelf body (101), the one or more sensors (102) are configured to sense one or more product parameters associated with one or more products (600) being positioned on the shelf body (101) and one or more user parameters associated with the one or more users being present in a proximity of the one or more sensors (102);
a camera (103) mounted on the shelf body (101), the camera (103) is configured to capture one or more images of the one or more products (600) and a surrounding environment of the shelf body (101);
a scanner (104) configured to scan a code being coupled to the one or more products (600) to obtain product data; and
a sever (105) having a processor (105-1), the server (105) is communicably coupled to the one or more sensors (102), the camera (103), and the scanner (104), the processor (105-1) is configured to:
obtain the one or more sensed product parameters and the one or more sensed user parameters, the one or more captured images, and the scanned product data;
map the obtained product data with one or more identifiers associated with one or more inventories stored at the server (105) to retrieve, upon successful mapping, the mapped product data;
process the one or more obtained product parameters and the one or more obtained user parameters, the one or more obtained images and the retrieved product data to obtain the one or more processed product parameters, the one or more processed user parameters, the one or more processed images, and the processed product data; and
analyse the one or more processed product parameters, the one or more processed user parameters, the one or more processed images, and the processed product data so as to generate one or more recommendations to the one or more users.
2. The shelving system (100) as claimed in the claim 1, wherein the shelving system (100) further comprises a user interface (106) configured to display the one or more generated recommendations, wherein the user interface (106) is communicably coupled to the processor (105-1).
3. The shelving system (100) as claimed in the claim 1, wherein:
the one or more recommendations are generated by the processor (105-1) using an artificial intelligence (AI) model, a machine learning (ML) model or an augmented reality (AR) model; and
the one or more recommendations are generated upon on successful scanning of the code or sensing one or more parameters associated with one or more products (600) or one or more users, and wherein the one or more recommendations are selected from any or a combination of complementary product recommendations, substitute product recommendations, cross-category recommendations, upsell recommendations, promotion-based recommendations, personalized recommendations based on purchase history, contextual or seasonal recommendations, recipe-based recommendations, health relevant recommendations or lifestyle recommendations.
4. The shelving system (100) as claimed in the claim 1, wherein:
the one or more sensors (102) are selected from any or a combination of a weight sensor, a proximity sensor, an environmental sensor, or a motion sensor; and
the one or more products (600) are selected from any or a combination of physical goods includes groceries, electronics, apparel, household items, or perishable items that includes food, drinks, or medications.
5. The shelving system (100) as claimed in the claim 1, wherein:
the code is selected from any or a combination of a barcode, a quick response (QR) code, a radio frequency identification (RFID) tag, or a near field communication (NFC) tag; and
the code is coupled to the one or more products (600) through one or more means selected from any or a combination of printing, embossing, adhesives, labelling, sticking, embedding, heat transfer labelling, direct printing, or filming.
6. The shelving system (100) as claimed in the claim 1, wherein:
the one or more product parameters are selected from any or a combination of weight, dimensions, size, shape, temperature sensitivity, product location and position, product identification code, expiry date, product interaction frequency, color or visual characteristics; and
the one or more user parameters are selected from any or a combination of dwell time, product interaction frequency, movement path or foot traffic, purchase history, engagement with digital displays, proximity to specific product categories, shelf interactions via the computing device, demographic information, shopping frequency and timing, or in-store engagement patterns.
7. The shelving system (100) as claimed in the claim 1, wherein:
the one or more identifiers comprises any or a combination of identification number (ID), item number, stock keeping unit (SKU), product code, product identification number (ID) or batch number;
the one or more inventories comprises any or a combination of product category inventory, seasonal inventory, perishable inventory, high-demand inventory, promotional inventory, discounted inventory, bulk inventory, backup inventory, online inventory or omnichannel inventory; and
the one or more users are selected from any or a combination of customer, shopper, store staff, store manager, maintenance person or information technology (IT) personnel.
8. A shelf (200) comprising:
a shelf body (101); and
a processor (105-1) embedded in the shelf body (101), the processor (105-1) is configured to:
obtain one or more product parameters and the one or more user parameters, the one or more images, and product data;
map the obtained product data with one or more identifiers associated with one or more inventories stored at a server (105) to retrieve, upon successful mapping, the mapped product data;
process the one or more obtained product parameters and the one or more obtained user parameters, the one or more obtained images and the retrieved product data to obtain the one or more processed product parameters, the one or more processed user parameters, the one or more processed images, and the processed product data; and
analyse the one or more processed product parameters, the one or more processed user parameters, the one or more processed images, and the processed product data so as to generate one or more recommendations to the one or more users.
9. The shelf (200) as claimed in claim 8, wherein the shelf (200) further comprising:
one or more sensors (102) mounted on the shelf body (101), the one or more sensors (102) are configured to sense the one or more product parameters associated with one or more products (600) on the shelf body (101) and the one or more user parameters associated with one or more users being present in a proximity of the one or more sensors (102);
a camera (103) mounted on the shelf body (101), the camera (103) is configured to capture the one or more images of the one or more products (600) and a surrounding environment of the shelf body (101);
a scanner (104) configured to scan a code being coupled to the one or more products (600) to obtain the product data; and
a user interface (106) configured to display the one or more generated recommendations, wherein the user interface (106) is communicably coupled to the processor (105-1).
10. A method (300) for generating recommendations to a user, the method (300) comprising:
sensing (301), by one or more sensors (102), one or more product parameters associated with one or more products (600) being positioned on the shelf body (101) and one or more user parameters associated with the one or more users being present in a proximity of the one or more sensors (102), wherein the one or more sensors (102) are mounted on a shelf body (101);
capturing (302), by a camera (103), one or more images of the one or more products (600) and a surrounding environment of the shelf body (101), wherein the camera (103) is mounted on the shelf body (101);
scanning (303), by a scanner (104), a code being coupled to the one or more products (600) to obtain product data; and
obtaining (304), by a processor of a server (105), the one or more sensed product parameters and the one or more sensed user parameters, the one or more captured images, and the scanned product data, wherein the server (105) is communicably coupled to the one or more sensors (102), the camera (103), and the scanner (104);
mapping (305), by the processor (105-1), the obtained product data with one or more identifiers associated with one or more inventories stored at the server (105) to retrieve, upon successful mapping, the mapped product data;
processing (306), by the processor (105-1), the one or more obtained product parameters and the one or more obtained user parameters, the one or more obtained images and the retrieved product data to obtain the one or more processed product parameters, the one or more processed user parameters, the one or more processed images, and the processed product data; and
analysing (307), by the processor (105-1), the one or more processed product parameters, the one or more processed user parameters, the one or more processed images, and the processed product data so as to generate one or more recommendations to the one or more users.

Documents