DESC:CROSS REFERENCE TO RELATED APPLICATION
This application is based on and derives the benefit of Indian Provisional Application 202141013779 filed on 27/03/2021, the contents of which are incorporated herein by reference.

TECHNICAL FIELD
[001] The present disclosure relates to the field of computer vision and more particularly to curating a related list of items based on context and location using learning and computer vision.

BACKGROUND
[002] E-commerce websites and marketplaces enable users to perform various searches (such as, but not limited to, text-based searches, voice-based searches, image-based searches, and so on). In an example, the user can perform a text-based search using a search engine or a search box provided on the e-commerce platform. The user on querying a search term can receive a result set which is generally a huge catalog of items that are generic and runs into several pages and/or page scrolls. The user can filter the received generic result set by category, relevance, price, brand, features, etc., to decide. Thereby, consuming a lot of time and effort, which confuses the user while making a choice.
[003] The voice-based search is an interactive search that allows a user to be specific in using the search term to get a quick and deterministic result. Otherwise, it may provide a lengthier conversation with a machine rendering an unproductive result set. This kind of search is only suitable for short and specific queries.
[004] The image-based search can be performed either by looking up a pre-existing image on a computing device or through a camera pointing to an object. It uses image recognition to look up information for a specific object by performing visual analysis on a neural network. For instance, in a Google lens, the camera device can be pointed towards an apple, the result set can contain generic lists such as an “apple from a nursery”, “apples” from a website in New Zealand, or an apple from a brand as seen on its sticker. The result set can be broad, location is not relevant (can fetch products found in the US, while searching from India), limited to sequential search (one product at a time) and result set comprises products/items specific to the pointed search object. For example, pointing a camera device to a refrigerator can provide a result set consisting of refrigerators of the scanned brand from different vendors. Thus, the user performing a search can receive a result set that is not personalized to a specific user due to limited “context and location awareness”.
[005] Therefore, the conventional search method fetches a result set with a huge catalog of items that may be generic and irrelevant that runs into several pages which can be time and effort consuming, often can confuse the user in making a decision/choice.

OBJECTS
[006] The principal object of the embodiments herein is to disclose methods and systems for curating a related list of items based on the context and location of a user using machine learning and computer vision.
[007] Another object of the embodiments herein is to disclose methods and systems for providing a customized and personalized list of items by performing a visual search of at least one object based on context, location, and user preferences.
[008] Another object of the embodiments herein is to disclose methods and systems for customizing and improving the predictions of the result list of items based on computer vision and inference using one or more trained models.

BRIEF DESCRIPTION OF FIGURES
[009] Embodiments herein are illustrated in the accompanying drawings, throughout which reference letters indicate corresponding parts in the various figures. The embodiments herein will be better understood from the following description with reference to the drawings, in which:
[0010] FIG. 1 illustrates an environment for curating a related list of items based on context and location using machine learning and computer vision, according to embodiments as disclosed herein;
[0011] FIG. 2 depicts a block diagram illustrating various units of the electronic device, which is used to access the IoT environment, according to embodiments as disclosed herein;
[0012] FIG. 3 depicts a block diagram illustrating various units of a curating system to curate a related list of items based on context and location using machine learning and computer vision, according to embodiments as disclosed herein.
[0013] FIG. 4 is an example diagram depicting the identification of at least one object from the refrigerator by the computer vision based on at least one received media content, according to embodiments as disclosed herein;
[0014] FIG. 5 is an example diagram depicting the identification of at least one object from a grocery store by the computer vision based on at least one received media content, according to embodiments as disclosed herein;
[0015] FIGs. 6a and 6b are example diagrams depicting the curated list of items based on the inference of the machine learning and computer vision of the electronic device, according to embodiments as disclosed herein;
[0016] FIG. 7 is an example diagram illustrating a method of identifying at least one object from at least one container to curate the list of related items based on the inference of the learning module and computer vision, according to embodiments as disclosed herein; and
[0017] FIG 8 is a flow diagram illustrating a method identifying at least one object from at least one container to curate the list of related items based on the inference of the machine learning and computer vision, according to embodiments as disclosed herein.

DETAILED DESCRIPTION
[0018] The example embodiments herein and the various features and advantageous details thereof are explained more fully with reference to the non-limiting embodiments that are illustrated in the accompanying drawings and detailed in the following description. Descriptions of well-known components and processing techniques are omitted so as to not unnecessarily obscure the embodiments herein. The description herein is intended merely to facilitate an understanding of ways in which the example embodiments herein can be practiced and to further enable those of skill in the art to practice the example embodiments herein. Accordingly, this disclosure should not be construed as limiting the scope of the example embodiments herein.
[0019] The embodiments herein disclose methods and systems for curating a related list of items by performing a visual search of at least one object based on the context, location, and user preferences. Referring to the drawings, and more particularly to FIGS. 1 through 8, where similar reference characters denote corresponding features consistently throughout the figures, there are shown example embodiments.
[0020] FIG. 1 illustrates an environment for curating a related list of items based on context and location using machine learning and computer vision, according to embodiments as disclosed herein. As illustrated in FIG. 1, environment 100 includes the electronic device 102, configured to a plurality of IoT devices 104a-104n through a local network. The electronic device 102, the plurality of IoT devices 104a-104n can be connected to an IoT-based server 110 through a communication network 106. The electronic device 102 may be connected to the communication network 106 connected to an IoT-based server 110. The electronic device 102 may be connected to the IoT-based server 110 through the communication network 106 and/or at least one other communication network (not shown).
[0021] The communication network 106 may include at least one of, but is not limited to, a wired network, a value-added network, a wireless network, a satellite network, or a combination thereof. Examples of the wired network may be but are not limited to, a Local Area Network (LAN), a Wide Area Network (WAN), an Ethernet, and so on. Examples of the wireless network may be, but are not limited to, a cellular network, a wireless LAN (Wi-Fi), Bluetooth, Bluetooth low energy, Zigbee, Wi-Fi Direct (WFD), Ultra-wideband (UWB), infrared data association (IrDA), near field communication (NFC), and so on. In another example, IoT devices 104a-104n, the electronic device 102, and the databases may be connected with each other directly and/or indirectly (for example, via direct communication, via an access point, and so on). In another example, the IoT devices 104a-104n, the electronic device 102, and the databases may be connected with each other via a relay, a hub, and a gateway. It is understood that IoT devices 104a-104n, the electronic device 102, and the databases may be connected to each other in any of various manners (including those described above) and may be connected to each other in two or more of various manners (including those described above) at the same time.
[0022] The electronic device 102 referred to herein may be a device that enables the user(s) to identify at least one object from at least one container related to the environment 100. In an embodiment, at least one container referred to herein may be a storage unit containing one or more objects. For example, at least one container may include but not limited to a refrigerator, wardrobe, shoe rack, bookshelf, drawer, grocery shelves, and the like. The objects do not have any capabilities to communicate with any other devices (for example, the electronic device 102, a plurality of IoT devices, or the like). The objects referred to herein may be the things placed in the container, which may be, but are not limited to, fruits, vegetables, staples, frozen food, meat, and the like to be placed in the refrigerator; books, magazines, books placed in the bookshelves; clothes, bags, wallets/purses, fashion accessories, dresses placed in the wardrobe, shoes placed in the shoe rack, and so on. The container can comprise objects located in the user’s premises which can be tracked using one or more sensors.
[0023] The IoT devices 104a-104n may be devices capable of communicating with the other devices (for example herein, the electronic device 102). The plurality of IoT devices 104a-104n may be deployed in various locations or areas or rooms in the IoT environment with which users may interact and control the operations of each IoT device 104a-104n. Examples of the plurality of IoT devices 104a-104n may be, but are not limited to, a smartphone, a mobile phone, a video phone, a computer, a tablet personal computer (PC), a netbook computer, a laptop, a wearable device, a vehicle infotainment system, a workstation, a server, a personal digital assistant (PDA), a smart plug, a portable multimedia player (PMP), an MP3 layer, a mobile medical device, a light, a voice assistant device, a camera, a home appliance, one or more sensors, and so on. Examples of the sensors may be, but are not limited to, a temperature sensor, a humidity sensor, an infrared sensor, a gyroscope sensor, an atmospheric sensor, a proximity sensor, an RGB sensor (a luminance sensor), a photosensor, a thermostat, an Ultraviolet (UV) light sensor, a dust sensor, a fire detection sensor, a carbon dioxide (CO2) sensor, a smoke sensor, a window contact sensor, a water sensor, or any other equivalent sensor. A function of each sensor may be intuitively inferred by one of ordinary skill in the art based on its name, and thus, its detailed description is omitted.
[0024] The plurality of IoT devices 104a-104n may perform one or more operations/actions based on their capabilities. Examples of the operations may be, but are not limited to, playing media (audio, video, or the like), capturing the media, purifying air, performing cooling, or heating of a defined area, controlling lights, capturing the current location/proximity of the user, sensing various environmental factors (for example, temperature, smoke, humidity, or the like), and so on. The plurality of IoT devices 104a-104n may perform the respective one or more actions simultaneously.
[0025] The plurality of IoT devices 104a-104n may register with the electronic device 102 by communicating device information, the capabilities, location/proximity information, or the like to the electronic device 102, once being deployed in the IoT environment. In an example herein, the identification value/device ID information may include information such as but are not limited to, a Media Access Control (MAC) identifier (MAC ID), a serial number, a unique device ID, and so on. The capabilities include information about one or more capabilities of each of the plurality of IoT devices (104a-104n). Examples of the capabilities of the IoT device (104a-104n) may be, but are not limited to, audio, a video, a display, location/proximity information, sensing environmental factors such as temperature, humidity, climate, data sensing capability, and so on. The location/proximity information includes information about the location of each of the plurality of IoT devices (104a-104n). The location of the IoT device (104a-104n) may indicate an area or a room (for example a living room, a kitchen, a bedroom, a study room, a child room, a factory unit, a grocery store, a supermarket, a clothing store, a stationery store, and so on) in the IoT environment, where the IoT device (104a-104n) is present.
[0026] The electronic device 102 referred to herein may be configured to capture and identify the objects present in the container. The electronic device 102 may also be a user device that is being used by the user to connect, and/or interact, and/or control the operations of the plurality of IoT devices (104a-104n). Examples of the electronic device 102 maybe, but are not limited to, a smartphone, a mobile phone, a video phone, a computer, a tablet personal computer (PC), a laptop, a wearable device, a personal digital assistant (PDA), an IoT device, or any other device that may be portable.
[0027] The electronic device 102 can be configured to capture the media content of the objects present in the container. The media content of the objects referred to herein maybe, but not limited to audio, video, image, or any media content of the things present in the container. Embodiments herein use the terms such as “media content”, “image”, and so on, interchangeably to refer to objects/things captured by the electronic device 102 present in the container.
[0028] The capturing unit/input unit of the electronic device 102 can be configured to capture the media contents of objects present in the container. The capturing unit/input unit of the electronic device 102 referred herein can be any kind of device used to capture media. The capturing unit/input unit can be, but not limited to, digital camera, web camera, single-lens reflex (SLR), Digital SLR (DSLR), mirrorless camera, compact cameras, video recorders, digital video recorders, and the like. The media content referred to herein can be, but not limited to video, image, audio, and the like. Embodiments herein use the terms such as “capturing unit”, “input unit”, and so on, interchangeably to refer to the device/unit used to capture the objects/things present in the container.
[0029] In an embodiment, the electronic device 102 can process the captured media content of the objects present in the container with respect to the computer vision element. The computer vision element is an Artificial Intelligence (AI) based element, that can train the electronic device 102 to interpret and understand the visual world. The media received from the capturing unit (camera device) can accurately identify and classify the objects. Computer vision element, AI can allow the electronic device to understand and label objects from the images. In an instance, the computer vision element, AI can be used in convenience stores, driverless car testing, medical diagnostics, monitoring the health of crops, livestock, and the like. The electronic device 102 can be configured with the computer vision element, which enables the capturing unit (camera device) to intelligently look at and learn from objects in its field of view using Artificial Intelligence (AI). The computer vision element can synthesize the captured information and classify/interpret the information within its field of view by applying trained models. Thus, the capturing unit (camera device) can independently or through a combination of a plurality of IoT devices (104a – 104n) provide meta information such as context, location, physical distance to objects, color, light intensity, ambient environment factors such as temperature, humidity, and other attributes of the user.
[0030] The computer vision element can be configured to enable the capturing unit (camera device) to capture and identify the objects. Thus, the computer vision element with the trained model can interpret the context of the search criteria performed by the user to generate a list of related items/objects to be procured/used by the user. The search criteria performed by the user may be an image-based search, using which the electronic device can capture and display the list of related items. The context of the search criteria can be obtained from the plurality of IoT devices, sensors of the electronic device, which may include, but are not limited to context parameters such as a display, location/proximity information, sensing environmental factors such as temperature, humidity, climate, data sensing capability, and so on. The container can comprise a list of related items/objects that can be the objects that are frequently used by the user.
[0031] The computer vision element and the trained model can capture the objects present in the container and interpret the absence or presence of objects in the container. For instance, if the field of view is on the “vegetable compartment” of the “refrigerator” and the computer vision element does not identify carrots, the computer vision element lists the carrot at the top of the list because carrots are one of the probable items that the user may want to buy. Similarly, if the computer vision element identifies quite a few tomatoes in the compartment, then tomatoes are listed at the bottom of the list, so the user may either ignore or buy lesser quantities of tomatoes.
[0032] The electronic device 102 processes the pre-learned objects present in the container and the context collected from the sensors using electronic devices and IoT devices. Based on the pre-learned objects and the context of the user, the electronic device may curate a list of personalized items. The electronic device 102 can be configured with an inbuilt dataset that is trained to perform detection of objects and to classify the objects to the categories of various levels based on the degree of confidence within the field of view. For instance, the electronic device 102 is configured to detect and identify accessories present in kitchens such as a refrigerator, a microwave, a mixer, a toaster, a grinder, and the like (which are containers).
[0033] The electronic device 102 on identifying a container (a refrigerator or a mixer), can process the partition/ divisions present in the container. An example is the electronic device 102 on identifying a “refrigerator” with both freezers and fresh food sections appearing in a closed-door position, the electronic device 102 can provide a result set containing both fresh foods and frozen foods. If on the other hand, the freezer appears closed, then the result set contains items from only the fresh foods section.
[0034] In an embodiment, the opening, and closing of the refrigerator doors is an event or a state that can be recorded by the electronic device 102, which provides the context and location information, for instance, a refrigerator with a freezer door opened. Before training, the inbuilt dataset of the electronic device is unable to identify "a refrigerator with an open door” context and requires training. In an embodiment, the user can train the model manually to enhance the capability of the dataset for future predictions. Hence, the manual training of the dataset can enhance the model to build improved predictions.
[0035] The user may continue to train the model and computer vision elements to display customized and curated lists of items. The training of the model and the computer vision elements can be manually performed by the user to enhance the predictions. Manual training of the model and computer vision element provides a customized and curated list of items. Thus, providing a personalized list of items make it convenient for the users to look up items than perform a search for items one at a time. Therefore, the computer vision element, the trained model can curate a personalized list of items based on user preferences.
[0036] FIG. 2 depicts a block diagram illustrating various units of the electronic device, which is used to access the IoT environment, according to embodiments as disclosed herein. The electronic device 102 includes a memory 202, a communication interface 204, an input unit 206, an output unit 208, a sensor unit 214, a controller/processor 210, and a database 212.
[0037] The memory 202 referred herein include at least one type of storage medium, from among a flash memory type storage medium, a hard disk type storage medium, a multi-media card micro type storage medium, a card type memory (for example, an SD or an XD memory), random-access memory (RAM), static RAM (SRAM), read-only memory (ROM), electrically erasable programmable ROM (EEPROM), programmable ROM (PROM), a magnetic memory, a magnetic disk, or an optical disk.
[0038] The memory 202 may store at least one of, but is not limited to, the objects/user actions performed on the objects present in the container placed in the vicinity of the electronic device 102 and a plurality of IoT devices, location/proximity information, environmental sensing information such as temperature, humidity, climate, data sensing capability, and so on.
[0039] The memory 202 may also comprise a management module to manage the objects in the IoT environment. Embodiments herein may refer to a controller 210 and the management module interchangeably, wherein both the terms indicate the controller 210.
[0040] The memory 202 may also store the learning module, neural network, computer vision element and customizing module 306. The computer vision element can be configured to enable the capturing unit to capture the media comprising the image, video, audio of the objects present in the container. The computer vision element can be processed by the controller to capture and identify the objects present in the container. The learning module of the neural network can be processed by controller 210 to obtain the input from the capturing unit of the electronic device 102. The learning module can be provided with the user’s choice of consuming/ using objects present in the container. The learning module can be continuously provided with the user’s choice/ decision on consuming objects.
[0041] The learning module of the neural network can be processed by controller 210 to obtain the context and location information of the object using a plurality of IoT devices 104a-104n. The learning module can be processed to obtain the user preferences by receiving a set of inputs from the capturing unit of the electronic device 102 from time to time. Based on continuous learning of the user’s choice and decision to consume objects, the learning module can interpret a curated list of items.
[0042] The customizing module 306 can be configured to receive inputs from the learning module to interpret or provide inference on the user preferences. The customizing module 306 can be processed by the electronic device 102 to generate a curated list of items based on user preferences. The customizing module 306 can be configured to receive input from the learning module based on the user preferences by receiving a set of inputs from the electronic device 102.
[0043] Examples of the neural network, the customizing module 306 may be, but are not limited to, an Artificial Intelligence (AI) model, a multi-class Support Vector Machine (SVM) model, a Convolutional Neural Network (CNN) model, a deep neural network (DNN), a recurrent neural network (RNN), a restricted Boltzmann Machine (RBM), a deep belief network (DBN), a bidirectional recurrent deep neural network (BRDNN), generative adversarial networks (GAN), a regression-based neural network, a deep reinforcement model (with ReLU activation), a deep Q-network, and so on. The neural network may include a plurality of nodes, which may be arranged in layers. Examples of the layers may be but are not limited to, a convolutional layer, an activation layer, an average pool layer, a max pool layer, a concatenated layer, a dropout layer, a fully connected layer, a SoftMax layer, and so on. Each layer has a plurality of weight values and performs a layer operation through calculation of a previous layer and an operation of a plurality of weights/coefficients. A topology of the layers of the neural network may vary based on the type of the respective network. In an example, the neural network may include an input layer, an output layer, and a hidden layer. The input layer receives a layer input and forwards the received layer input to the hidden layer. The hidden layer transforms the layer input received from the input layer into a representation, which may be used for generating the output in the output layer. The hidden layers extract useful/low-level features from the input, introduce non-linearity in the network and reduce a feature dimension to make the features equivalent to scale and translation. The nodes of the layers may be fully connected via edges to the nodes in adjacent layers. The input received at the nodes of the input layer may be propagated to the nodes of the output layer via an activation function that calculates the states of the nodes of each successive layer in the network based on coefficients/weights respectively associated with each of the edges connecting the layers.
[0044] The customizing module 306 may be trained using at least one learning method. Examples of the learning method may be, but are not limited to, supervised learning, unsupervised learning, semi-supervised learning, reinforcement learning, regression-based learning, and so on. The customizing module 306 may be neural network models in which several layers, a sequence for processing the layers, and parameters related to each layer may be known and fixed for performing the intended functions. Examples of the parameters related to each layer may be, but are not limited to, activation functions, biases, input weights, output weights, and so on, related to the layers. A function associated with the learning method may be performed through the non-volatile memory, the volatile memory, and/or the controller 210. The controller 210 may include one or a plurality of processors. At the time, one or a plurality of processors may be a general-purpose processor, such as a central processing unit (CPU), an application processor (AP), or the like, a graphics-only processing unit such as a graphics processing unit (GPU), a visual processing unit (VPU), and/or an Artificial Intelligence (AI)-dedicated processor such as a neural processing unit (NPU).
[0045] Here, being provided through learning means that, by applying the learning method to a plurality of learning data, a predefined operating rule, or the neural network, the customizing module 306 of the desired characteristic is made. Functions of the neural network, customizing module 306 may be performed in the electronic device 102 itself in which the learning according to an embodiment is performed, and/or maybe implemented through a separate server/system.
[0046] The communication interface 204 may include one or more components, which enable the electronic device 102 to communicate with another device (for example, the IoT devices 104a-104n, the IoT server (not shown)) using the communication methods that have been supported by the communication network 106. The communication interface 204 may include the components such as a wired communicator, a short-range communicator, a mobile/wireless communicator, and a broadcasting receiver.
[0047] The wired communicator may enable the electronic device 102 to communicate with the other devices using the communication methods such as, but are not limited to, wired LAN, Ethernet, and so on. The short-range communicator may enable the electronic device 102 to communicate with the other devices using the communication methods such as, but are not limited to, Bluetooth low energy (BLE), near field communicator (NFC), WLAN (or Wi-fi), Zigbee, infrared data association (IrDA), Wi-Fi Direct (WFD), UWB communication, Ant+ (interoperable wireless transfer capability) communication, shared wireless access protocol (SWAP), wireless broadband internet (Wibro), wireless gigabit alliance (WiGiG), and so on. The mobile communicator may transmit/receive wireless signals with at least one of a base station, an external terminal, or a server on a mobile communication network/cellular network. For example, the wireless signal may include a speech call signal, a video telephone call signal, or various types of data, according to transmitting/receiving of text/multimedia messages. The broadcasting receiver may receive a broadcasting signal and/or broadcasting-related information from the outside through broadcasting channels. The broadcasting channels may include satellite channels and ground wave channels. In an embodiment, the electronic device 106 may or may not include the broadcasting receiver.
[0048] The input unit 206 may be configured to enable the user to interact with the electronic device 102. The input unit 206 can be a capturing unit configured to capture the media contents of objects present in the container. The capturing unit/input unit referred to herein can be any kind of device used to capture inputs (the video input, the image input, or any media input) from the environment which comprises objects present in the container. The input unit 206 may also capture the media inputs from the environment comprising objects, which may be, but not limited to fruits, vegetables, staples, frozen food, meat, and the like to be placed in the refrigerator; books, magazines, notebooks placed in the bookshelves; clothes, bags, wallets/purses, fashion accessories, dresses placed in the wardrobe, shoes placed in the shoe rack.
[0049] The input unit 206 referred to herein can be any kind of device used to capture media. The input unit 110 can be, but not limited to, digital camera, media capturing device, web camera, Single-lens reflex (SLR), Digital SLR (DSLR), mirrorless cameras, compact cameras, video recorders, digital video recorders, and the like. The media referred to herein can be, but not limited to video, image, and the like.
[0050] The output unit 208 may be configured to display a curated list of items based on user preferences. The output unit 208 may include at least one of, for example, but is not limited to, a display, a User Interface (UI) module, a light-emitting device, and so on, to display a personalized list of items based on user preferences. The UI module may provide a specialized UI or graphical user interface (GUI), or the like, synchronized to the electronic device 102, according to the applications.
[0051] For input and output purposes, other devices and separate devices can be used. For example, the input can be in the form of performing image search by scanning the electronic device 102 to capture the objects and the output can be provided to a display screen containing the objects present in the container, or the container itself or the container and the objects by the electronic device 102.
[0052] The sensor unit 214 may include one or more sensors for monitoring the movements of the electronic device 106, context and location of the objects present in the container. It may also monitor the one or more objects with respect to the electronic device 102, and so on.
[0053] The controller 210 may include one or a plurality of processors. The one or a plurality of processors may be a general-purpose processor, such as a central processing unit (CPU), an application processor (AP), or the like, a graphics-only processing unit such as a graphics processing unit (GPU), a visual processing unit (VPU), and/or an Artificial Intelligence (AI)-dedicated processor such as a neural processing unit (NPU).
[0054] The controller/processor 210 may be configured to identify and personalize a list of related objects based on user preferences. The controller can process a plurality of IoT devices (104a – 104n) to obtain the context and location information of the devices in the IoT environment. Controller 210 identifies the objects which are frequently consumed by the users present in the container. The controller on identifying the context and location of the objects can generate a list of related objects based on user preferences. The controller can provide inference based on the interpretation by the learning modules (based on the user’s choice of consuming/using objects). The inference provided by controller 210 can be a curated/customized list of objects present in the container based on the context and location of the user.
[0055] In another example, IoT devices 104a-104n, the electronic device 102, and the database 212 may be connected with each other directly (for example: via direct communication, via an access point, and so on). In another example, the IoT devices 104a-104n, the electronic device 102, and the database 212 may be connected with each other via a relay, a hub, and a gateway. It is understood that IoT devices 104a-104n, the electronic device 212, and the database 212 may be connected to each other in any of various manners (including those described above) and may be connected to each other in two or more of various manners (including those described above) at the same time.
[0056] FIG. 3 depicts a block diagram illustrating various units of a curating system to curate a related list of items based on context and location using machine learning and computer vision, according to embodiments as disclosed herein. As depicted in FIG. 3, the curating system 300 includes a media capturing module 310, a context and location-identifying module 302, a learning module 304, a customizing module 306, and an inference module 308.
[0057] The media capturing module 310 can be configured to capture the media of objects present in the container. The media capturing module 310 referred to herein can be any kind of device that can capture media. The media content referred to herein can be, but not limited to video, image, audio, and the like. Embodiments herein use the terms such as “media capturing module”, “capturing unit”, “input unit”, and so on, interchangeably to refer to module/device/unit used to capture the objects/things present in the container.
[0058] In an embodiment, the electronic device 102 can process the captured media content of the objects present in the container with respect to the computer vision element. The electronic device 102 can be configured with the computer vision element, which enables the media capturing module 310 of the capturing unit (camera device) to intelligently look at and learn from objects in its field of view.
[0059] The context and location identifying module 302 can be configured to identify the context and location of the objects present in the container. The context and location information of the objects can be obtained from electronic devices and the plurality of IoT devices 104a-104n. The context information may include environmental factors such as temperature, humidity, climate, data sensing capabilities which may include, but not limited to object information such as type, category, quantity, quality, price, expiry life of the object and, the like. The location information may include the proximity/location of the objects present in the container. Based on the identified location information of the objects, the electronic device can generate a curated list of items to reach the user’s location.
[0060] The learning module 304 can be configured with the computer vision element, the trained model to train and interpret the objects consumed by the user. The learning module 304 can be processed to obtain the user preferences by receiving a set of inputs from the media capturing module 310 of the electronic device 102. The learning module 304 can be configured to learn user behavior based on the usage of objects on daily basis, the user can add new objects to the container/remove objects from the container. The learning module 304 can be configured to learn user behavior based on which the curated list of objects can be generated.
[0061] The customizing module 306 may be processed by the electronic device 102 to interpret/generate a curated list of items based on user preferences. The customizing module 306 can be configured to receive input from the learning module 304 based on the user preferences and interpret a personalized list of items to be consumed by the users. The customizing module 306 provides a list of curated items based on the context and location information of the user. Therefore, generating a personalized list of items specific to the user.
[0062] FIG. 4 is an example diagram depicting the identification of at least one object from the refrigerator by the computer vision based on at least one received media content, according to embodiments as disclosed herein. As depicted in the example, an IoT device 150 can be fixated to a wall in the kitchen unit behind a refrigerator. The IoT device 150 can serve as a sensor for obtaining positional or proximity information of the electronic device 102 with the physical parameters such as temperature, humidity, and other sensing parameters.
[0063] In another embodiment, the capturing unit (camera device) of the electronic device 102 can be configured to focus the refrigerator to obtain the curated list of items based on the inference of the computer vision element on device 102.
[0064] As depicted in FIG. 4, a fixed computer vision element installed on a camera 20 can be mounted against a wall/door of a kitchen using a clamp or a stand 21. The camera 20 can be positioned, so as to focus the refrigerator 110 with its door open with the field of view 450 (indicated by dotted lines) which can be outward from the camera towards the refrigerator indicating a region of coverage that is visible for object detection and inference. The compartments of the refrigerator comprising egg tray 410, empty compartment 420, compartment holding juice bottles 430 and vegetable compartment 440 are covered in the field of view. The vision element narrows the scope of search to the bottom portion of refrigerator compartment. The result set is generated by the vision element to the electronic device 102 for completing the purchase of the objects to be placed in the refrigerator.
[0065] FIG. 5 is an example diagram depicting the identification of at least one object from a grocery store by the computer vision based on at least one received media content, according to embodiments as disclosed herein. As depicted in FIG. 5, a computer vision element installed on a camera 20 can be mounted against a wall on a grocery store to focus on items which are being purchased by the customers. The field of view can be towards the shelves on which the items are placed. The vision element performs the search on the shelves of the grocery store to interpret the customer behavior. The result set is generated to the grocery shop owner based on the interpretation of the vision element to replenish the food items based on customer requirements. Therefore, vision elements can be configured to assist the store manager to purchase a list of curated items based on customer needs.
[0066] FIGs. 6a and 6b are example diagrams depicting the curated list of items based on the inference of the machine learning and computer vision of the electronic device, according to embodiments as disclosed herein. As depicted in FIG. 6a, the electronic device can be configured to generate a list of curated items-based user preferences. The curated list of items can be of associated items obtained based on inference of the vision element looking at the container with the objects.
[0067] In an embodiment, as depicted in FIG. 6a, the user has an option to choose one or more sub-sections 220 by clicking on the selection box 230. The user action button 210 can broaden the scope of search and button 160 narrows down the scope of search.
[0068] In an embodiment, as depicted in FIG. 6b, an ordered list of curated items for a user based on the selection performed in FIG. 6a, is displayed. The grocery manager/representatives/house-owner/any users can purchase the customized list of products, thereby replenishing the personalized items to the containers.
[0069] FIG. 7 is an example diagram illustrating a method of identifying at least one object from at least one container to curate the list of related items based on the inference of the learning module and computer vision, according to embodiments as disclosed herein.
[0070] As illustrated in FIG. 7, the media capturing module, the vision element, the learning module may be configured to capture and identify the objects present in the container. On identifying the container, the electronic device 102 can be configured to fetch associated items present in the container to be provided as a return ordered list of curated items to the user. The user can purchase a personalized list of items interpreted by the electronic device using the learning module.
[0071] FIG 8 is a flow diagram illustrating a method identifying at least one object from at least one container to curate the list of related items based on the inference of the machine learning and computer vision, according to embodiments as disclosed herein.
[0072] At step 1002, the method includes, capturing, by the electronic device, at least one container based on at least one context and location of the electronic device, wherein the at least one context and location is received from a plurality of IoT devices using context parameters.
[0073] At step 1004, the method includes, identifying, by the electronic device, at least one object in the at least one container based on vision element configured to the electronic device, wherein the vision element captures at least one object in the at least one container.
[0074] At step 1006, the method includes, customizing, by the electronic device, at least one object in the at least one container based on user preferences, wherein the user preferences include at least one object interpreted by the vision element; and
[0075] At step 1008, the method includes, generating, by the electronic device, at least one curated list of items with at least one object interpreted by the vision element based on the user preferences.
[0076] The various actions, acts, blocks, steps, or the like in the method and the flow diagram 1000 may be performed in the order presented, in a different order or simultaneously. Further, in some embodiments, some of the actions, acts, blocks, steps, or the like may be omitted, added, modified, skipped, or the like without departing from the scope of the invention.
[0077] The foregoing description of the specific embodiments will so fully reveal the general nature of the embodiments herein that others can, by applying current knowledge, readily modify and/or adapt for various applications such specific embodiments without departing from the generic concept, and, therefore, such adaptations and modifications should and are intended to be comprehended within the meaning and range of equivalents of the disclosed embodiments. It is to be understood that the phraseology or terminology employed herein is for the purpose of description and not of limitation. Therefore, while the embodiments herein have been described in terms of embodiments, those skilled in the art will recognize that the embodiments herein can be practiced with modification within the spirit and scope of the embodiments as described herein.
,CLAIMS:I/We claim:
1. A method for curating a related list of items, the method comprising:
capturing, by an electronic device (102), at least one container based on at least one context and location of the electronic device, wherein the at least one context and location is received from a plurality of IoT devices (104a-104n) using at least one context parameter;
identifying, by the electronic device (102), at least one object in the at least one container based on a vision element, wherein the vision element captures at least one object in the at least one container;
customizing, by the electronic device (102), at least one object in the at least one container based on at least one user preference, wherein the at least one user preference includes at least one object interpreted by the vision element; and
generating, by the electronic device (102), at least one curated list with the at least one object interpreted by the vision element based on the user preferences, wherein the at least one curated list comprises of at least one item.

2. The method as claimed in claim 1, wherein the at least one context and location is received from the plurality of IoT devices (104a-104n) using at least one context parameter, wherein the at least one context parameter comprise location, proximity information of the electronic device, and environmental factors.

3. The method as claimed in claim 1, wherein the vision element is configured to identify at least one object present in the at least one container and to interpret the at least one curated list.

4. The method as claimed in claim 1, wherein the at least one user preference is obtained from a learning module (304), associated with the received at least one object present in the at least one container.

5. The method as claimed in claim 1, wherein the learning module (304) is configured to learn user behavior based on the usage of at least one object and to generate the at least one curated list.

6. A system (300) for curating a related list of items, the system comprising:
a cloud server (110);
a hardware processor (210), wherein the hardware processor is configured to:
capture at least one container based on at least one context and location of the electronic device, wherein the at least one context and location is received from a plurality of IoT devices (104a-104n) using at least one context parameter;
identify at least one object in the at least one container based on a vision element, wherein the vision element captures at least one object in the at least one container;
customize at least one object in the at least one container based on at least one user preference, wherein the at least one user preference includes at least one object interpreted by the vision element; and
generate at least one curated list with the at least one object interpreted by the vision element based on the user preference, wherein the at least one curated list comprises of at least one item.

7. The system (300) as claimed in claim 6, wherein the at least one context and location is received from the plurality of IoT devices (104a-104n) using at least one context parameter, wherein the at least one context parameter comprise location, proximity information of the electronic device, and environmental factors.
8. The system (300) as claimed in claim 6, wherein the vision element is configured to identify at least one object present in the at least one container and to interpret the at least one curated list.

9. The system (300) as claimed in claim 6, wherein the at least one user preference is obtained from a learning module (304), associated with the received at least one object present in the at least one container.

10. The system (300) as claimed in claim 6, wherein the learning module (304) is configured to learn user behavior based on the usage of at least one object and to generate at least one curated list.