Edge computing storage nodes based on user's location and activity data separate from cloud computing environment

Abstract

Systems and methods are provided for edge computing storage nodes based on user's location and activity data separate from a cloud computing environment. Service providers, such as online transaction processors, can provide additional services to users through the edge computing system and edge computing storage nodes. The services can be for data that can be predictively loaded to an edge computing storage node at a particular location, where the edge computing storage node can more locally reside on the network at that location, such that the data can be provided faster and with less network resource consumption than from a remote cloud computing storage. The data can be predicted to be needed or useful to a user at the location using the user's user profile, monitored user activity, and / or one or more machine learning models that predict user behavior at the location.

Description

Technical Field

[0001] This application generally relates to edge computing networks and nodes, and more specifically to edge computing storage nodes that provide location-specific partitioned data at faster speeds and with lower latency. Background Technology

[0002] Users can utilize various mobile computing devices, such as tablets, smartphones, and wearable computing devices, to perform computational operations and communicate. For example, during daily activities, users may encounter various situations where they communicate with other users through their devices, such as via phone calls and text messages with friends, family members, etc. Users can also utilize location-specific computing devices to, for example, perform electronic transactions, view content (e.g., maps and / or directions), search for goods and services, etc. However, mobile computing devices interacting with cloud computing services and systems may not receive location-specific data, and data retrieval speeds may be limited by network traffic, cloud computing, and resource availability. Therefore, users may experience waiting times when attempting to retrieve data from a cloud computing environment. Furthermore, cloud computing environments are not location-specific and may not provide information related to the user's current location or activities the user may be engaging in at that location. When sharing data with a cloud computing environment, data may be unintentionally shared, contrary to the user's expected level of privacy. Attached Figure Description

[0003] Figure 1 This is a block diagram of a network system suitable for implementing the processes described herein, according to an embodiment. Figure 2A This is an exemplary environment according to an implementation method, having edge computing storage nodes that communicate with cloud computing environments and mobile devices; Figure 2B This is an exemplary environment with an edge computing storage node according to an implementation method, which provides location-specific data based on user profiles and data stored on the edge computing storage node; Figure 3 This is an exemplary interface of a mobile device when location-specific data is presented to a user from an edge computing storage node, according to an implementation method. Figure 4A This is a flowchart illustrating the exchange of data between a cloud computing system and an edge computing system, according to an implementation method. Figure 4B This is a flowchart illustrating, according to an implementation method, how to provide location-specific data using an edge computing system; Figure 4C This is a flowchart, according to an embodiment, for providing application data associated with sub-locations of interest to users within a location using an edge computing system; and Figure 5 It is suitable for implementation according to the method of implementation. Figure 1 A block diagram of a computer system consisting of one or more components.

[0004] The embodiments and advantages of this disclosure can be best understood by referring to the following detailed description. It should be understood that the same reference numerals are used to identify the same elements shown in one or more figures, which are shown in the figures for the purpose of illustrating embodiments of this disclosure and not for the purpose of limiting this disclosure. Detailed Implementation

[0005] A method is provided for edge computing storage nodes based on user location and activity data, decoupled from cloud computing environments. A system suitable for implementing the methods disclosed herein is also provided.

[0006] Online service providers, such as online platforms offering one or more services to users and user groups, can provide platforms and operations that allow users to access location- and activity-specific data using one or more edge computing systems and edge computing storage nodes. Edge computing systems can correspond to auxiliary cloud computing systems that provide one or more edge computing nodes that are location-specific and located on a network closer to that location, enabling faster and lower latency delivery of location-related data to associated computing devices. Edge computing can correspond to location-based applications and data, encompassing general-purpose or specialized computing, storage, and other operations utilizing these components, bringing them closer to end users and / or IoT endpoints on the network. This allows for better application performance and faster data delivery from edge storage nodes, enhancing and improving the experience and quality of network usage of applications and data. It can also improve the efficiency and speed of content delivery to users. In one implementation, edge computing nodes can be provided by cellular networks (e.g., 5G, however, other cellular networks may also be utilized). Edge computing systems and nodes can also be provided by cloud computing systems such as Amazon AWS®, Microsoft Azure®, etc.

[0007] Furthermore, the edge storage nodes discussed in this paper can be location-specific and can retain data not shared with cloud computing systems. This allows users to better protect their privacy and enables service providers and cellular providers to comply with regulatory laws and requirements regarding data privacy and security in certain locations. Users can be detected as being in or near a location and / or geofenced area, and user profiles of service providers can be identified. User activity can be detected or monitored, which can be activity at that location and / or activity when the user approaches that location (e.g., the intent to perform other activities at that location). Using one or more machine learning (ML) models, service providers can determine data storage actions between edge computing storage devices and cloud computing storage devices or other central storage devices used by users. Central storage devices can correspond to centralized data repositories that can be used by users, such as centralized data residing on remote servers and / or cloud computing environments. Data storage actions can move data between two different storages, such as by providing some data from cloud storage locally on edge storage for faster delivery to the user's mobile or computing device at that location. Subsequently, service providers can further determine data that may be relevant to the user at that location (e.g., application data of the user's device applications, such as interactive maps of the location), and can store that data on the edge computing storage device for later use by the user.

[0008] To enable users to utilize these services, online service providers (such as online transaction processors like PAYPAL®) can offer account services to their users and other entities requesting the services. Users wishing to create an account can first access the online service provider and request account creation. Account creation can be accomplished by providing account details such as a login name, password (or other authentication credentials such as biometric fingerprints, retinal scans, etc.) and other account creation details, along with / or authentication information corresponding to the service provider. Account creation details may include identifying information used to create the account, such as the user's personal information, the entity's business or merchant information, or other types of identifying information including name, address, and / or other information.

[0009] Users may also be required to provide financial information, including payment card (e.g., credit / debit card) information, bank account information, gift card information, offers / incentives, and / or financial investments. This information can be used to process transactions for goods and / or services, including purchases associated with locations visited by the user and linked to edge computing storage devices. Furthermore, incentives and past purchases can be provided to one or more edge computing storage devices and / or used by service providers when providing data to edge computing storage devices. In some implementations, account creation can establish account funds and / or value, such as by transferring money into the account and / or establishing available credit limits and corresponding credit values ​​for the account and / or card. Online payment providers can provide digital wallet services that offer financial services to send, store, and receive money, process financial instruments, and / or provide transaction history, including the tokenization of digital wallet data used for transaction processing. Service providers' applications or websites (e.g., PAYPAL® or other online payment providers) can provide payment and other transaction processing services. However, other service providers may also provide the computing services discussed herein, such as telecommunications and / or cellular service providers.

[0010] Once a user establishes an account with a service provider, the user can use the account through one or more computing devices (such as personal computers, tablets, mobile smartphones, etc.). The user can engage in one or more online or virtual interactions that can be associated with electronic transaction processing, images, music, media content and / or streaming, video games, documents, social networks, media data sharing, microblogging, etc. This can be performed in certain locations and / or while moving towards or near those locations. The service provider can first detect the user's geographic location and / or the user's movement via the user's computing device, such as whether the user is within a geofenced area, whether the user is approaching a geofence or other location, and / or whether the user is in a specific location. The service provider can utilize the geographic location detection component of the user's computing device (such as a mobile smartphone). The service provider can also use cellular network providers to detect users located or near a location, such as through cellular towers and / or using cellular tower triangulation. In some implementations, cellular network providers (e.g., 5G providers) can provide specific edge storage nodes via certain cellular towers and / or using cellular networks.

[0011] Therefore, detecting a user's location or proximity to a location can correspond to determining that the user is located in a specific location, a geofenced location, or area, and / or is approaching a location or geofenced area. This can be detected based on the user's movement over a period of time (such as the user's direction, speed, acceleration, vector, etc.). The service provider can then determine that the edge computing system and edge computing storage nodes are associated with that location. The service provider can leverage cloud computing architectures, cellular network providers, etc., to determine the edge computing storage nodes associated with that location. This can be performed through geolocation queries corresponding to the edge computing storage nodes, identification of nearby network or cellular nodes used by the edge computing system, and other geolocation matching techniques for nearby edge computing storage nodes corresponding to and / or within a predetermined proximity or distance (on the network) to that location or geofenced area.

[0012] Once the location-associated edge computing storage node is identified, the service provider can access the user's user profile, which can be provided by the service provider and / or accessible from the cloud computing system associated with the service provider and / or the user. The user profile may correspond to or include interests, preferences, activities, and other attributes set by the user and / or learned over time based on past user behavior. For example, ML models can be used to predict user interests and activities a user might perform at a location, as well as which data from cloud or edge computing systems might be relevant to the user at that location. This can be based on the user's past behavior, including past purchases, past activities, etc. The user profile may also include preferences specifically established for that location.

[0013] Service providers can also monitor or detect one or more activities of a user at and / or as the user approaches that location. The types of activities can correspond to travel routes, purchases or product selections, use of the user's mobile device (e.g., opening and / or using an application, providing input including searching for products and / or locations, communicating with other users, social networking or microblogging, electronic transaction processing, etc.), and other activities. Activities can be monitored via the user's device or using one or more devices and / or sensors associated with the location. For example, activities on the user's device can be monitored; however, IoT sensors, point-of-sale (POS) devices, merchant terminals, etc., can also detect user activities or generate data associated with the monitored activities. Therefore, in some implementations, the location can correspond to a merchant location (e.g., a retail storefront, shopping mall, etc.).

[0014] Based on user profiles and monitored user activity at or near that location, service providers can determine data storage actions or operations between the cloud computing system or other central storage for the user and the corresponding edge computing system and edge storage nodes associated with that location. Data storage actions can move data between cloud storage in the cloud computing system and edge storage nodes in the edge computing system based on user profiles and monitored activity. By processing user profiles and monitored user activity, ML models associated with customer behavior, interests, and / or other activities at that location can be used to predict user interests at that location, such as products of interest, other activities the user might be interested in performing, and sub-locations of interest to the user.

[0015] For example, ML models can consider similar user behaviors of other users (e.g., based on training data) to predict what a user might be interested in. Past behaviors can include information associated with gait or stride length, one or more movements, age, demographics, customer characteristics, routes taken through the location, or past activities of other users at that location. Furthermore, past behaviors can be associated with other users' purchases, activities, and / or sub-locations based on information about their past behavior. In this respect, the ML model and predicted data can be used by the user at or near the location, and can correspond to data stored on edge computing storage nodes for faster retrieval and access when the user is at that location. In this respect, the data can correspond to at least a portion of the user's data transferred from a cloud computing system and / or transmitted to edge computing storage nodes for use by the user at that location. This allows data to be more localized to user devices on the network, providing faster data loading and reduced latency. Furthermore, this can alleviate potential data privacy concerns for users who maintain certain data on local nodes rather than in a central storage device. In other implementations, the forecast data may also be, or alternatively, data shared in the background cloud storage, such as for updating user profiles and / or making the data more widely available to users across different storage platforms.

[0016] In various implementations, the data exchanged for a data loading process or operation performed by a service provider may correspond to location-related data. For example, the data could be a user's past purchases, including receipts or transaction history that may be associated with the user (e.g., returns, additional purchases, etc.). This data could also correspond to past sub-locations visited by the user at that location, which could be an interactive map, and / or routes through and / or to those sub-locations (e.g., routes the user typically takes to purchase goods at that location or other similar locations). Other data that can be provided between cloud storage and edge storage may correspond to a user's accumulated and / or available loyalty or rewards, as well as other payment mechanisms and / or tools that the user can use. Data used to identify and / or authenticate users at that location may also be provided on edge storage nodes or may be provided back to cloud storage devices established and / or used by the user at that location. Other types of data may also be shared between storage, including data that can be used to build and / or update user profiles.

[0017] If data is moved to an edge computing storage node, it can be shared with the user's mobile device or other computing devices. This data can also be used by the service provider, and / or edge computing and / or applications on the edge computing node associated with that location, to provide the user with further application data and / or operations. For example, the service provider and / or ML model of the edge computing and / or application can leverage data already shared, loaded, and / or provided to the edge computing storage node to further predict the user's interests. For instance, one or more ML models that may reside on the edge computing storage node can be used to determine predicted goods that the user is interested in and / or may potentially purchase, based on data loaded to the edge computing storage node. Predicted goods can be based on past user purchases, such as if X months have passed since the last purchase and the user is expected to run out of the goods and need to purchase or replenish them. Other goods can be predicted, for example, based on the user's interests or other related purchases (e.g., demand for batteries, other building supplies, etc.). When goods are determined, the service provider and / or edge computing / application can further determine sub-locations of the goods within the merchant's location and can generate interactive maps or other visualizations for applications on the user's mobile device to locate the goods within that location. The application data can then be stored on edge computing storage nodes for rapid delivery to users' mobile devices.

[0018] In various implementations, service providers and / or edge computing can also predict other interests and / or activities of users at the location, as well as incentives that can be earned or provided to users at the location based on their participation in activities. For example, a treasure hunt or activity can be generated for users to find and / or access certain sublocations or objects at the location, where rewards (e.g., points, discounts, offers, etc.) can be earned by completing tasks, visiting sublocations, or finding objects, which can be exchanged and / or redeemed by the user at the location or at other locations, merchants, or service providers. Activities with these sublocations, objects, or tasks can be provided through interactive graphs, audiovisual outputs, etc., which can be provided through application data in a mobile application on the user's device. In some implementations, in-app mobile video games or other puzzles can be generated to earn rewards at the location, which can be user-specific. Therefore, application information can also include loyalty reward information for the location, image files associated with the location, audiovisual files associated with the location, media content for the location, or interactive game data for the location.

[0019] Such data can then be stored on an edge computing storage node and retrieved by the user's device when the device is located at that location or associated with a region of the edge computing node. Thus, data can be moved from the edge computing storage node to the user's mobile device. In various implementations, authentication may be required to access the data, such as credentials stored on the user's mobile device and / or authentication entered by the user into the mobile device when data is requested or pushed to it. In some implementations, authentication may correspond to a single user on the edge computing node. However, the edge computing storage node may also include user profiles and / or data for multiple users, which can be authenticated individually, or in group authentication if the user is associated with other users (e.g., family, friends, business or company employees, etc.).

[0020] In various implementations, the service provider of the edge computing storage node and / or the edge computing / application may also monitor additional user activity at that location, including activities based on data from computing or mobile devices provided to the user by the edge computing storage node. This data may be stored on the edge computing storage node for later use by the edge computing and / or application, as well as by the user. However, the data may not be shared back with the cloud computing system and / or central storage device used by the user. This may be based on the user's privacy settings and / or the user's opt-in / opt-out choices regarding data sharing rules and parameters. Furthermore, data sharing may be prevented based on privacy regulations associated with the edge computing system and / or cloud computing system, privacy laws affecting the region associated with the edge computing storage node and / or the user, etc.

[0021] Figure 1 This is a block diagram of a networking system 100 suitable for implementing the processes described herein, according to embodiments. As shown, system 100 may include or implement multiple devices, servers, and / or software components that operate to perform various methods according to the described embodiments. Exemplary devices and servers may include devices, standalone and enterprise-class servers that operate on operating systems such as MICROSOFTT®, UNIX®, LINUX®, or other suitable device-based and / or server-based operating systems. It is understood that... Figure 1 The devices and / or servers shown may be deployed in other ways, and for a given implementation, the operations performed and / or services provided by such devices and / or servers may be combined or separated, and may be performed by a greater or lesser number of devices and / or servers. One or more devices and / or servers may be operated and / or maintained by the same or different entities.

[0022] System 100 includes a client device 110 communicating via a network 160, an edge computing system 120, a service provider server 140, and a central cloud storage device 150. The client device 110 can be used to establish an account with the service provider server 140 and / or other service providers, and may include information about the user associated with the client device 110. The client device 110 may acquire the user when the user is near a location. The service provider server 140 can determine and exchange a subset of data associated with the edge computing system 120 and / or the central cloud storage device 150 based on the user at that location, the user's user profile, and / or user activity monitored at that location.

[0023] Client device 110, edge computing system 120, service provider server 140, and central cloud storage device 150 may each include one or more processors, memory, and other suitable components for executing instructions such as program code and / or data stored on one or more computer-readable media to implement the various applications, data, and steps described herein. For example, such instructions may be stored on one or more computer-readable media, such as internal and / or external memory or data storage devices of various components of system 100, and / or accessible via network 160.

[0024] Client device 110 can be implemented using any suitable hardware and software configured to communicate with edge computing system 120, service provider server 140, and / or central cloud storage device 150 via wired and / or wireless communication for data communication. This data communication may include retrieving data from edge computing system 120 when a user uses client device 110 at a location associated with an edge data storage node of edge computing system 120. Client device 110 may correspond to an individual user, consumer, or merchant using a platform provided by edge computing system 120, service provider server 140, and / or central cloud storage device 150 for data storage, processing, and retrieval. In various embodiments, client device 110 may be implemented as a personal computer (PC), smartphone, laptop / tablet, watch with appropriate computer hardware resources, other types of wearable computing devices, and / or other types of computing devices capable of transmitting and / or receiving data. Although only one computing device is shown, multiple computing devices may operate similarly.

[0025] Figure 1 The client device 110 includes an application 112, a database 116, and a network interface component 118. The application 112 may correspond to an executable process, program, and / or application with associated hardware. In other embodiments, the client device 110 may include additional or different software as needed.

[0026] Application 112 may correspond to one or more processes executing software modules and associated components of client device 110 to provide features, services, and other operations to a user via network 160. It may receive data from edge computing system 120, service provider server 140, and / or central cloud storage device 150 for output via application 112 at a location. In this respect, application 112 may correspond to dedicated software used by a user of client device 110, which may be used to access websites or UIs to perform actions or operations. In various embodiments, application 112 may correspond to a general-purpose browser application configured to retrieve, present, and deliver information via the Internet (e.g., utilizing resources on the World Wide Web) or a dedicated network. For example, application 112 may provide a web browser that can send and receive information via network 160, including retrieving website information (e.g., a merchant's website), presenting website information to a user, and / or delivering information to a website.

[0027] However, in other embodiments, application 112 may include a dedicated application for service provider server 140 or other entities (e.g., merchants). Application 112 may be associated with account information, user financial information, and / or transaction history. However, in other embodiments, different services may be provided via application 112, including messaging, social networking, media publishing or sharing, microblogging, data browsing and searching, online shopping, and other services available through service provider server 120. Therefore, application 112 may also correspond to different service applications associated with location, merchants, service providers, edge computing system 120, service provider server 140, and / or central cloud storage device 150.

[0028] In this regard, application 112 can be used to detect that client device 110 and the corresponding user are at or near a location, such as through location detection components (e.g., GPS sensors and / or components, mapping applications or processes, compass processes, etc.). Application 112 can also be used to monitor user activity at that location and / or as the user approaches that location, including interactions and activities on client device 110 that can be detected using client device 110 or connected devices (e.g., biometrics, including heart rate, gait, or walking speed, etc.), electronic transaction processing, etc. Application 112 can provide activity to edge computing system 120, service provider server 140, and / or other service providers, which can determine data from central cloud storage device 150 to provide to edge computing system 120, or vice versa. Application 112 can receive edge application data 114 when located at a location, such as interactive data, displays, and / or outputs, which can provide relevant data of interest to the user at that location. When the client device 110 is located at or associated with the location of the edge computing system 120, edge application data 114 can be retrieved by the edge computing system 120 and / or pushed to the application 112.

[0029] Client device 110 may also include database 116, which may include identifiers such as operating system registry entries, cookies associated with application 112 and / or other applications, identifiers associated with the hardware of client device 110, or other suitable identifiers. Payment / service providers may use the identifiers in database 116 to associate client device 110 with specific accounts maintained by the payment / service provider (e.g., service provider server 140). Database 116 may also store input and / or detected user activity, which may be monitored on client device 110 and shared with one or more of edge computing system 120, service provider server 140, and / or central cloud storage device 150. Furthermore, edge application data 114 may be stored in database 116 before, during, and / or after use.

[0030] Client device 110 includes at least one network interface component 118 adapted to communicate with edge computing system 120, service provider server 140, and / or central cloud storage device 150 via network 160. In various embodiments, network interface component 118 may include a DSL (e.g., digital subscriber line) modem, PSTN (Public Switched Telephone Network) modem, Ethernet device, broadband device, satellite device, and / or various other types of wired and / or wireless network communication devices, including microwave, radio frequency, infrared, Bluetooth, and near-field communication devices.

[0031] Edge computing system 120 can be implemented using any suitable hardware and software configured to wirelessly communicate with edge computing system 120, service provider server 140, and / or central cloud storage device 150 to provide one or more edge computing cloud nodes that can be used by users associated with client device 110 with fast, low data loading time, low latency, low network communication and / or resource utilization, and / or low bandwidth utilization. In this regard, edge computing system 120 can be provided as a cloud computing environment utilizing edge nodes on a network such as a 5G cellular network or other cellular network types for cellular providers. In other embodiments, edge computing system 120 can correspond to one or more devices and / or servers comprising edge computing cloud nodes, including IoT devices and sensors, as well as standalone or enterprise-grade servers operating on an operating system such as MICROSOFT®, UNIX®, LINUX®, or other suitable server-based operating systems. Although only one edge computing system is shown, multiple edge computing systems can operate similarly, and each edge computing system can include multiple edge computing nodes with edge computing storage devices and computers associated with different locations. In this regard, the edge computing system 120 can reside more locally or be located near a location on the network to provide faster data transfer, loading, and delivery, where more localization can be compared to a central cloud storage device 150.

[0032] Figure 1 The edge computing system 120 includes an edge computing unit 130, an edge storage device 122, and a network interface component 126. The edge computing unit 130 may correspond to an executable process, program, and / or application with associated hardware. In other embodiments, the edge computing system 120 may include additional or different software as needed.

[0033] Edge computing 130 may correspond to one or more modules and associated components of edge computing system 120 to execute edge applications and processes that provide data to client device 110, and to determine the data to be provided to client device 110, and / or exchange data with central cloud storage device 150 based on data storage requests and processing from service provider server 140. In this respect, edge computing 130 may correspond to dedicated hardware and / or software used by edge computing system 120 to perform edge computing tasks and operations that can provide data to client device 110, such as edge application data 114 used via application 112. Edge computing 130 may also receive, access, and / or store data detected by edge computing system 120 and / or data from central cloud storage device 150, which may include edge user data 124. In this respect, edge user data 124 may correspond to a subset of data from central cloud storage device 150 that is specific to edge computing system 120, the user of client device 110, and / or the corresponding location. However, edge user data 124 may also include user-specific data of the edge computing system 120 that is not shared with the central cloud storage device 150.

[0034] Edge computing 130 can also be used to provide data to client device 110 and / or determine user-related or interest-related data associated with client device 110. In this regard, edge computing 130 can receive data that can be provided and / or pushed to client device 110 based on conditions such as being in or near edge computing system 120, performing certain activities, requesting data, etc. Edge computing 130 can also include ML model 132, user detection 134, and / or location data 136 to provide context-sensitive data. ML model 132 can take user detection 134, location data 136, and / or edge user data 124 as input and can make predictions about the interests or context-sensitive data of users associated with client device 110 at corresponding locations. For example, user detection 134 can be the detected location and / or movement of a user at or near a location, while location data 136 can include location-specific information such as maps, sublocations and / or layouts, product or object locations, rewards and other available offers, activities that can be participated in, etc. User detection 134 may also include monitored activities of one or more users at or associated with that location. Edge user data 124 may correspond to all or part of user data 152 stored by central cloud storage device 150, and may also include information about user profiles 146 (e.g., preferences, interests, past purchases, etc.) stored by service provider server 140. Access to user data and transmission of edge application data 114 to edge computing system 120 may require authentication, which may be done automatically (e.g., by automatically providing authentication tokens or credentials via client device 110) and / or by user input (such as authentication mechanisms including passwords, access codes, PINs, biometric fingerprints, voice responses, facial recognition, security questions, requests for known phrases or names, etc.).

[0035] ML model 132 can make predictions about user interests, providing predictive outputs based on features from input data. When constructing ML model 132, training data can be used to generate one or more classifiers and provide recommendations, predictions, or other outputs based on those classifications and the ML model. The training data can be used to determine the input features used to train the predicted scores of context-sensitive data 114 provided from edge computing system 120 to client device 110. For example, ML model 132 may include one or more layers, including an input layer, hidden layers, and an output layer with one or more nodes; however, different layers may also be utilized. For example, as many hidden layers as necessary or appropriate may be utilized. Each node within a layer is connected to nodes in adjacent layers, where a set of input values ​​can be used to generate one or more output scores or classifications. Within the input layer, each node may correspond to a different attribute or input data type used to train ML model 132.

[0036] Subsequently, ML algorithms, computations, and / or techniques can be used to train the hidden layer using these attributes and corresponding weights. For example, each node in the hidden layer can generate a representation of a mathematical ML computation (or algorithm) that produces a value based on the input value of the input node. The ML algorithm can assign different weights to each data value received from the input node. The hidden layer nodes can include different algorithms and / or different weights assigned to the input data, and thus can produce different values ​​based on the input values. The output layer nodes can use the values ​​generated by the hidden layer nodes to produce one or more output values ​​for the ML model 132, which attempts to classify or predict edge application data 114 that can be provided to the client device 110 at a certain location. Therefore, when the ML model 132 is used to perform predictive analytics and outputs, the input can provide corresponding outputs based on the classifications, scores, and predictions trained for the ML model 132.

[0037] The ML model 132 can be trained using training data associated with past user behavior and activity at locations associated with the edge computing system 120, and the aforementioned features for user and / or other user detection 134, location data 136, and / or edge user data 124. By providing training data to train the ML model 132, the nodes in the hidden layers can be trained (tuned) to produce optimal output (e.g., classification) in the output layer based on the training data. By continuously providing different training datasets and penalizing the ML model 132 when its output is incorrect, the ML model 132 (and specifically, the representations of the nodes in the hidden layers) can be trained (tuned) to improve its performance in data classification. Tuning the ML model 132 may include adjusting the weights associated with each node in the hidden layers. Thus, the training data can be used as an input / output dataset that allows the ML model 132 to classify based on input attributes. The output classification of the ML model 132, trained to predict interests, context-dependent data, and / or activity, can be a classification of the likelihood that the user needs the data. Such classifications can also be based on additional data, such as gait, age, demographics, customer characteristics, routes taken through the location, or past activities at the location.

[0038] Furthermore, it should be understood that the determination and provision of data (e.g., edge application data 114) can also be performed by the service provider server 140 when providing data to the client device 110, wherein the data can then be stored on and provided by the edge computing system 120. Therefore, one or more ML models 132 can be utilized and / or provided on the service provider server 140 for predictive analytics.

[0039] Edge computing system 120 may also include edge storage device 122, which may include identifiers associated with edge computing 130 and / or other applications, identifiers associated with the hardware of edge computing system 120, or other suitable identifiers. Edge storage device 122 may receive and store data from central cloud storage device 150, such as in response to data exchange, transmission, and / or storage requests from service provider server 140. Therefore, edge storage device 122 may also include edge user data 124 that can be provided to client device 110. Thus, edge storage device 122 may correspond to edge cloud storage devices residing on a network, such as edge cloud storage devices provided by cellular networks, and may reside closer to a location on the network to provide data to client device 110 in a fast and efficient manner.

[0040] Edge computing system 120 includes at least one network interface component 126 adapted to communicate with edge computing system 120, service provider server 140, and / or central cloud storage device 150 via network 160. In various embodiments, network interface component 126 may include a DSL (e.g., digital subscriber line) modem, PSTN (public switched telephone network) modem, Ethernet device, broadband device, satellite device, and / or various other types of wired and / or wireless network communication devices, including microwave, radio frequency, infrared, Bluetooth, and near field communication devices.

[0041] Service provider server 140 may be maintained, for example, by an online service provider, and may provide operations for transferring data between edge computing system 120 and central cloud storage device 150. Various implementations of the data storage process described herein may be provided by service provider server 140 and may be accessed by client device 110 and edge computing system 120, or may be provided by central cloud storage device 150 when data is provided to edge computing system 120. In such implementations, service provider server 140 may interface with client device 110 to detect user location and / or monitor user activity at a location, and determine data provided from central cloud storage device 150 to edge computing system 120. Service provider server 140 includes one or more processing applications that may be configured to interact with edge computing system 120, service provider server 140, and / or central cloud storage device 150. In one example, service provider server 140 may be provided by PAYPAL® Corporation, San Jose, California, USA. However, in other implementations, service provider server 140 may be maintained by or comprise another type of service provider.

[0042] Figure 1 The service provider server 140 includes an edge data application 142, a database 144, and a network interface component 148. The edge data application 142 may correspond to an executable process, program, and / or application with associated hardware. In other embodiments, the service provider server 140 may include additional or different modules with dedicated hardware and / or software as needed.

[0043] Edge data application 142 may correspond to one or more processes executing the module of service provider server 140 and associated dedicated hardware to provide data, operations, and processes for providing data between edge computing system 120 and / or central cloud storage device 150. In this regard, edge data application 142 may correspond to dedicated hardware and / or software used by a user associated with client device 110 to establish an account for edge data application 142 and / or access service provider server 140 or another service provider's account. For example, an account provided by PayPal® can be used to provide services to users. However, when utilizing edge data application 142, more general accounts (e.g., telephone, email, mobile service provider, etc.) may also provide the aforementioned account services. In other embodiments, edge data application 142 may also, or alternatively, use user profile 146 stored in database 144 for services of transferring or exchanging data between edge computing system 120 and / or central cloud storage device 150.

[0044] Edge detection application 142 can also execute one or more ML models, such as ML model 132, which can or alternatively be provided by edge detection application 142 on service provider server 142. When client device 110 is located in a location associated with edge computing system 120, the ML model can be used to predict user-related data that may be useful or associated with client device 110. Edge detection application 142 can detect or receive location information indicating that a user is at or near that location. Edge detection application 142 can also access one of the user's user profiles 146 and can monitor user activity at or near that location. Using data as input to the ML model, output predictions or classifications can be made to predict data that may be relevant to or useful to the user, such as all or part of user data 152, which may include stored user data from the user's past activities and information. This data may also include items or sublocations of interest available at that location, activities of interest, user rewards, etc. The ML model can be trained based on user and / or customer behavior at that location, and therefore can operate in the same or similar manner as the ML model 132 of the edge computing system 120 to determine data that may be useful or relevant to the user at that location. Thus, the ML model can provide output decisions for the user based on data provided to the client device 110 via the edge computing system 120. Once data that may be relevant to the user has been predicted, the edge data application 142 can be used to perform data storage actions, processes, or requests between the edge computing system 120 and the central cloud storage device 150. For example, a data storage action could cause all or part of the user data 152 to be transferred to the edge computing system 120 for storage and further transfer to the client device 110. This can allow for faster data loading times and lower latency for the client device 110.

[0045] Additionally, the service provider server 140 includes a database 144. Database 144 may store various identifiers associated with client devices 110. Database 144 may also store account data, including payment instruments and authentication credentials, as well as transaction processing history and data on processed transactions. Database 144 may also store user profiles 146, which edge data applications 142 may use when determining data to be transferred and / or exchanged between central cloud storage devices 150. Thus, user profiles 146 in database 144 may include information about one or more users' interests, preferences, past activities and behaviors, account data, available funds and / or rewards, etc. Computer or machine-executable instructions may also be stored in database 144 or in a separate storage device or database, wherein the instructions, when executed, enable a system or processor to perform the operations described herein.

[0046] In various embodiments, the service provider server 140 includes at least one network interface component 148 adapted to communicate via network 160 with the edge computing system 120, the service provider server 140, the central cloud storage device 150, and / or other devices / servers for the merchant. In various embodiments, the network interface component 148 may include a DSL (e.g., digital subscriber line) modem, a PSTN (Public Switched Telephone Network) modem, Ethernet equipment, broadband equipment, satellite equipment, and / or various other types of wired and / or wireless network communication equipment, including microwave, radio frequency (RF), and infrared (IR) communication equipment.

[0047] The central cloud storage device 150 can be implemented using any suitable hardware and software configured to wirelessly communicate with client device 110, edge computing system 120, service provider server 140, and / or other devices and servers to provide users with a cloud computing environment and / or other centralized storage, which can be used by users associated with client device 110 to utilize cloud storage, cloud applications, etc., for different user data. In this respect, the central cloud storage device 150 can be provided as a cloud computing environment for providing cloud-based services to users over a network. In other embodiments, the central cloud storage device 150 may correspond to one or more devices and / or servers for centralized storage, including standalone or enterprise-class servers, operating operating systems such as MICROSOFT®, UNIX®, LINUX®, or other suitable server-based operating systems.

[0048] Figure 1 The central cloud storage device 150 contains user data 152. Edge computing 130 may correspond to executable processes, programs, and / or applications with associated hardware. In other embodiments, the central cloud storage device 150 may include additional or different software as needed. For example, the central cloud storage device 150 may also include, or be associated with, one or more cloud computing instances corresponding to one or more (e.g., shared) available machines and resources, which may execute applications, etc., to provide cloud-based environments and services to users, merchants, companies, and other entities via devices and servers corresponding to users, merchants, companies, and other entities.

[0049] User data 152 may correspond to information associated with one or more users, stored in a cloud computing environment or other centralized storage associated with central cloud storage device 150. In this respect, user data 152 may correspond to past user activity, purchases, behaviors, application usage, data processing requests, search and / or browser history, and other data that may be accumulated for the user and stored in the cloud. In this respect, user data 152 may correspond to “big data” that can be collected for users over time. User data 152 may also include user input and / or settings, such as user choices of interests, preferences, goods, locations, etc., that can be set in a user profile. User data 152 for a specific user can be large and non-specific, but may also include data that may be associated with the user at a specific location, such as data associated with edge computing system 120. Therefore, at least a portion of user data 152 may be allocated to edge computing system 120 for use at the corresponding location, enabling faster and lower latency delivery of data to client device 110.

[0050] Network 160 can be implemented as a single network or a combination of multiple networks. For example, in various implementations, network 160 may include the Internet or one or more intranets, terrestrial networks, wireless networks, and / or other suitable types of networks. Thus, network 160 may correspond to a small-scale communication network, such as a private network or local area network, accessible by various components of system 100, or a larger-scale network, such as a wide area network or the Internet.

[0051] Figure 2A This is an exemplary environment 200a according to an embodiment, having edge computing storage nodes that communicate with a cloud computing environment and mobile devices. Environment 200a includes client device 204a, client device 204b, and client device 204c, each client device corresponding to a reference... Figure 1 The system 100 discussed herein includes client device 110. Furthermore, environment 200a includes an edge computing cloud 216 and a main cloud environment 208, typically corresponding to the edge computing system 120 and central cloud storage device 150 discussed herein, respectively. Environment 200a may correspond to a related system for providing user and / or application data to the edge computing cloud 216, which can then provide that data to client devices 204a to 204c.

[0052] In system environment 200a, a mobile environment is illustrated, in which mobile smartphones and other computing devices can interact with different components during use while located or near a location (e.g., when approaching a location, within a geofenced area, etc.). The mobile environment includes client devices 204a to 204c operated by the user when the user is located or near a location. Client devices 204a to 204c can utilize cloud storage device 206 with a main cloud environment 208, such as for storage of user data and / or use of cloud computing services. In this regard, cloud computing 210 can be used to provide those services, such as storing data in cloud storage device 206 by executing cloud applications and operations, and / or using that data during interactions and requests with client devices 204a to 204c. Therefore, client devices 204a to 204c may sometimes communicate with the main cloud environment 208 to access data from cloud storage device 206, request data processing and services from cloud computing 210, etc. In some implementations, the main cloud environment 208 may be provided by a cloud computing system, such as Amazon AWS®, Microsoft Azure®, etc. However, other cloud computing systems may similarly operate and provide cloud storage devices 206 to client devices 204a to 204c.

[0053] However, it is expected that client devices 204a to 204c will receive and / or segment information from the main cloud environment 208 more quickly, for reasons such as quality of experience (QoE), privacy, and / or other concerns of users and / or service providers. In this regard, cellular network 212 can be used to provide edge storage device 214, which can store data with edge computing cloud 216 more locally (e.g., closer to the location of client devices 204a to 204c on the network). Cellular network 212 may correspond to a 5G cellular network provided by a cellular network associated with the location of client devices 204a to 204c, main cloud environment 208, and / or edge computing cloud 216. In other embodiments, main cloud environment 208 may alternatively provide edge computing cloud 216, which may be provided using cellular network 212 and / or other networks used by main cloud environment 208.

[0054] The service provider and / or the main cloud environment 208 can determine that one or more client devices 204a to 204c may require data from cloud storage device 206 and / or data that may be provided based on data within cloud storage device 206 when client devices 204a to 204c are located at a location associated with edge computing cloud 216 (e.g., user data associated with the behavior and activities of users at a location associated with edge computing cloud 216). In this regard, data storage actions, such as transfer, delivery, or other exchange actions, can be determined to provide data from cloud storage device 206 to edge storage device 214. This can be performed proactively to predict potentially useful data or data associated with client devices 204a to 204c when they are located at that location.

[0055] Edge computing cloud 216 can receive the data and can store it using edge storage device 214. Subsequently, when client devices 204a to 204c require the data or anticipate needing or using it, the data can be provided from edge storage device 214 to client devices 204a to 204c. This may include pushing data or transmitting it in response to a request for data. Edge computing 218 can also use the data while executing one or more edge applications or processes, such as applications or processes associated with an ML model of customer behavior at the location. In such an implementation, the data can be used to provide interactive graphs showing items of interest, sub-locations of interest and / or objects of interest, routes through the location and / or routes to the sub-locations, activities of interest or activities desired by the user at the location, rewards and games, or treasure hunts to obtain rewards, etc. Additionally, the data and other data, such as additional monitoring data of users and / or client devices 204a to 204c at the location, can be stored by edge storage device 214 and may not be shared with cloud storage device 206. This can be enforced based on privacy laws or regulations, user requests, or opt-in / opt-out options.

[0056] Figure 2B An exemplary environment 200b according to an embodiment has an edge computing storage node that provides location-specific data based on user profiles and data stored on the edge computing storage node. Environment 200b includes features that can be provided, for example, by referring to... Figure 1 The system 100 discusses client devices 110 and edge computing systems 120, and / or Figure 2A and Figure 2BClient devices 204a to 204c in environment 200 interact with users 224a and 224b of system 100 and / or environment 200b. Environment 200b may correspond to a system for providing data to users 224a and 224b via their computing devices (such as mobile devices) through edge computing system 120.

[0057] In environment 200b, user 224a may be approaching a location designated by geofenced region 222, such as a merchant location (e.g., a physical store where goods can be sold). User 224a may have a specific purpose for accessing geofenced region 222, such as purchasing goods. The goods could be refillable items, such as soft water pellets that need to be purchased at set or fairly regular intervals. User 224a may know about the goods based on search history, past purchases, user interests or preferences, etc. This user data can be built using a cloud computing system, but is associated with an edge computing system used for edge computing cloud region 220 that includes geofenced region 222. For example, the edge computing system could use this user information to provide user 224a with an interactive map of geofenced region 222, showing paths or routes to goods 226 on the map. Therefore, when user 224a is detected within edge computing cloud region 220 and / or when user 224a is detected approaching geofence region 222, user 224a's activities and other parameters can be detected, and the ML model can predict user 224a's need for such goods based on those activities and user profile. The edge storage nodes of the edge computing system used for edge computing cloud region 220 and / or geofence region 222 can be loaded with this information from the cloud computing system. User 224a can then quickly receive interactive graphs and other applications or user data via their computing devices.

[0058] User 224b may alternatively browse geofenced region 22 or otherwise not specifically target items or activities of interest. User 224b's activities can be detected, such as browsing items or slowly walking along different paths or aisles that do not indicate a specific interest. Using these activities and user profiles, the ML model can predict that user 224b may be interested in receiving rewards, playing games within geofenced region 222, and / or engaging in a treasure hunt, where the latter two can provide rewards to user 224b. For example, visiting hotspot 228 and / or performing some activity within hotspot 228 can earn user 224b a reward. Specific rewards can be based on user 224b's user profile, such as past purchases, where the reward can incentivize user 224b to make additional purchases within geofenced region 222. Therefore, the edge computing system for edge computing cloud region 220 can be loaded with specific user data, as well as user 224b's activities and other relevant data, enabling application data (e.g., interactive graphs, and other data of interest such as loyalty reward information, image files, audiovisual files, media content, or interactive game data) to be quickly shared with user 224b. In this regard, application data can provide information to user 224b to access hotspot 228, objects or activities at hotspot 228, etc.

[0059] Figure 3 This is an exemplary interface 300 of a mobile device when presenting location-specific data to a user from an edge computing storage node, according to an implementation. Figure 3 Interface 300 can be referenced Figure 1 The client device 110 discussed in system 100 is displayed. In this regard, edge computing system 120 can provide data for displaying interface 300 in the application based on user profile and user activity of user 304 at the location associated with edge computing system 120.

[0060] The user interface 300 on client device 110 can display an interactive graph 302, which includes information about the user's relevant data, activities, or interests at a particular location. Generally, a storefront may have different areas and "real estate" for different products. More prominent areas may be those with higher visibility, such as when entering the store (e.g., entrance aisle 306). However, not all products can be placed in these high-visibility areas, and users may not be interested in products placed in high-visibility areas. Instead, user 304 may want to find products that are perhaps more hidden, such as those located in back aisles or hard-to-find places. Additionally, user 304 may be interested in earning rewards or performing other browsing activities that may lead to rewards or other offers that interest the user.

[0061] In this regard, interactive graph 302 can be loaded from an edge computing storage node associated with the location of interactive graph 302 to client device 110. The interactive graph can be dedicated to user 304 and can be generated, loaded, and output based on predictions of user 304's activities from user profiles and / or monitored activities (such as those at that location). User 304 may be interested in item 308, which is not located in entrance aisle 306 but is hidden in a rear aisle. Therefore, interactive graph 302 can show the location of item 308 based on the user's profile and activities. This allows user 304 to quickly find item 308.

[0062] Additionally, since user 304's interest in rewards is also predicted based on user profiles and / or activities, the interactive graph provided by the edge computing storage node can include information for earning those rewards by completing certain activities. For example, route 310 shows a path to hotspot 312. If user 304 follows route 310, user 304 can earn rewards by reaching hotspot 312 and / or performing some activities at hotspot 312. Activity 314 is also shown in the area of ​​that location in the interactive graph. Activity 314 could be some activities that user 304 is interested in, such as those predicted based on user profiles and user 304's activities (e.g., presentations, courses, executable activities to receive rewards, audiovisual content of interest, etc.). Therefore, interactive graph 302 also shows activity 314 within that location. When using interactive graph 302 and / or in locations that can be provided and / or stored by edge computing storage nodes, further activity of user 304 can be monitored. This can include preventing sharing with cloud computing systems and storage so that data resides on edge computing storage nodes rather than in the cloud or central storage.

[0063] Figure 4A This is a flowchart 400a according to an embodiment for exchanging data between a cloud computing system and an edge computing system. Note that one or more steps, processes, and methods of the flowchart 400a described herein may be omitted, performed in a different order, or combined as needed or appropriate.

[0064] In step 402 of flowchart 400a, a user is detected as being located at or associated with a location. In one or more embodiments, based on this detection, an edge computing storage node corresponding to that location can be determined. The edge computing storage device may reside more locally and / or closer to the network (e.g., using more local devices, servers, IoT components, and devices for that location). Users can be detected using location detection components of their computing devices, cellular networks and one or more cell towers, check-ins or other social network posts, and / or location-specific devices using short-range wireless communication at that location. In step 404, a user profile is determined. This user profile may correspond to the user's settings (e.g., user interests, preferences, etc.) and past data detected or accumulated for the user (e.g., past purchases, search history, messages, and / or communication exchanges, etc.).

[0065] In step 406, one or more user activities associated with the location are monitored. This may include user biometrics and / or other user movement and physical activity at the location (e.g., gait, visited sublocations, etc.). However, other activities may include activities and interactions with computing devices and / or with other users at the location. These are monitored to determine predicted reasons for visiting the location, etc. In step 408, data to be migrated between the user's edge computing storage device and central cloud storage device is determined, for example, by using one or more predictive models. The predictive models may correspond to ML models that can predict customer behavior and / or other user behaviors or activities of interest at a location. In this respect, the ML model may attempt to predict what activities the user might perform at a location and / or what the user might be interested in at that location.

[0066] The data to be migrated may correspond to all or a subset of data from a central cloud storage device, which may be more relevant to the user at that location and / or used by the edge computing system to provide data from the edge computing storage device to the user's device. For example, the data may correspond to interests and / or rewards that a user can redeem at that location. Interests may be used to provide users with an interactive graph of goods at that location, which may reside on the edge computing storage device. Thus, the data may be particularly relevant to the user at that location, and thereby improve QoE and data loading / latency times by storing it on the edge computing storage device. In other embodiments, the data may correspond to data that needs to be loaded from the edge computing storage device to a cloud computing storage device. Thus, data migration from cloud computing storage to edge computing storage, or vice versa, may occur in a single direction. However, in other embodiments, data migration may also correspond to data exchange and / or data synchronization between storage devices. Thus, data may be stored in a single edge computing storage device (or multiple similar or related edge computing storage devices) or a cloud computing storage device; however, other data migrations and exchanges may also occur.

[0067] In various implementations, data to be migrated between central cloud storage devices can be selected, constrained, and / or restricted based on data privacy laws, regulations, and / or preferences. Data privacy laws and / or regulations can be location-specific, thus applicable to a user's location (e.g., state, country, or other region associated with the user), the location associated with the central cloud storage device (which can span multiple locations, regions, countries, etc.), and / or the location corresponding to the edge computing storage device. However, users can opt-in to or assign their own data privacy settings to the central cloud storage device, service provider, and / or edge computing storage device, which can restrict the data shared between the central cloud storage device and / or edge computing storage device. Merchants may also have data privacy rules or preferences for data sharing. Therefore, certain data may be blocked or restricted from sharing, or certain data may need to be purged or extracted from PII or other sensitive data. Thus, data privacy restrictions limiting data sharing can depend on user profiles, data types, merchant and / or user locations, etc.

[0068] Therefore, user profiles, location-related laws and regulations, merchant profiles, etc., can be analyzed to identify and / or determine user privacy profiles or privacy settings. Privacy profiles can correspond to privacy requirements that restrict or adjust the types of data and data shared or migrated between edge computing storage devices and central cloud storage devices. In some implementations, privacy profiles can restrict data in a specific direction. For example, data may be effectively stored by one of the edge computing storage devices or the central cloud storage device, but not by the other. In this regard, certain PII or financial data may be restricted from migrating from the central cloud storage device to the edge computing storage device, but can be effectively stored in the central cloud storage device. Conversely, edge computing storage devices may store certain location-specific data, user activity monitored at that location, and / or electronic transaction processing information at that location, but can restrict background sharing with the central cloud storage device.

[0069] Therefore, data privacy restrictions and preferences can be used as another feature input to an ML model trained to predict the migration of data from one edge computing storage device or central cloud storage device to the other. Thus, the ML model may restrict or remove data expected to migrate from one platform to another based on a privacy profile. In step 410, data is migrated between the edge computing storage device and the central cloud storage device. This may correspond to transferring and / or transmitting data so that the data can reside on the edge computing storage device and be made available to the user's device more quickly. However, when the data is provided back to the central cloud storage device, it can be made more widely available.

[0070] Figure 4B This is a flowchart 400b according to an embodiment for providing location-specific data using an edge computing system. Note that one or more steps, processes, and methods of the flowchart 400b described herein may be omitted, performed in a different order, or combined as needed or suitably.

[0071] In step 420 of flowchart 400b, a user approaching a location associated with the edge computing storage device is identified. A user approaching the location can be identified based on geographic location and / or current movement (such as the user's speed and / or direction, the vehicle the user is using, the user's schedule, and / or other parameters specific to the user). In some implementations, a user approaching a location can be detected by detecting the user entering a geofenced area of ​​the location, such as a parking lot or building, an area wider than a specific location (e.g., a campus), etc. However, a user can also be detected at or within a location by detecting the user's geographic location and matching or associating that geographic location with the location.

[0072] In step 422, user data is accessed from the edge computing storage device. Data may be migrated from central storage (e.g., cloud storage used by the user) or moved to the edge computing storage device. In one or more implementations, data may be determined or predicted to be useful or relevant to the user at that location, and therefore the data is stored or migrated to the edge computing storage device for faster access (e.g., with lower loading times and / or latency). For example, based on the detection of a user at the location referenced in step 420, location-specific or user-specific data may be migrated from the central storage device to the edge computing storage device / node associated with that location. In some implementations, the data may be location-specific data for the user, such as past purchases, available rewards, the user's interests at that location, scheduled activities, or past activities performed by the user at that location, as well as other data that may be associated with the location. However, in other implementations, the data may not be location-specific and may correspond to a broader range of user data, such as all or part of a user profile that can be used to make predictions corresponding to the user.

[0073] In step 424, a prediction or determination corresponding to a user at that location is generated based on the data and one or more prediction models. The prediction model may correspond to an ML model based on past customer behavior, interests, purchases, activities, etc., at that location. In some implementations, the ML model may also be trained for a specific user group, demographic, age range, etc., to predict user data at that location. Therefore, the prediction or determination may include transmitting the predicted user's expected data to their device when the user is at that location and / or when using an edge computing storage device (e.g., based on faster loading times and / or lower latency required to receive the data). In one or more implementations, as part of the prediction or determination process, data may be migrated to an edge computing storage device associated with that location. In some implementations, the data may also correspond to location-specific data associated with that location, such as... Figure 4C The process is discussed in flowchart 400c.

[0074] In step 426, data corresponding to the prediction or determination can be identified based on the prediction / determination. The relevant data may be data stored in an edge computing storage device, or data with another storage, such as a cloud computing storage device, a location-associated database system, and / or a database system used by service providers to predict user-related data. Therefore, it may be necessary to retrieve and / or generate data based on internal and / or external data from the edge computing storage device. In step 428, the data is provided to the user via the edge computing storage device. The data may be retrievable upon request from the user's computing device, or the data may be automatically pushed to the user's computing device. In the case of pushing data to the user's computing device, the data may be pushed from the edge computing storage device to the computing device when the user is near or at the location, or it may be pushed when it is useful to the user, such as at the checkout location or other sub-locations within that location. Therefore, using an edge computing storage device can provide data with faster loading times and lower latency.

[0075] Figure 4C This is a flowchart 400c, according to an embodiment, for providing application data associated with sub-locations of interest to users within a location using an edge computing system. Note that one or more steps, processes, and methods in the flowchart 400c described herein may be omitted, performed in a different order, or combined as needed or suitably. Figure 4C Flowchart 400c includes Figure 4B The predicted sub-implementation methods or specific categories are provided in flowchart 400b.

[0076] In step 440 of flowchart 400c, a user performing an activity at a location associated with the edge computing storage device is detected. This activity can be some action or interaction the user engages in at that location. The activity can be about the user and objects, people, or other things at that location, about the user and their corresponding device, and / or can be an upcoming or predicted activity performed by the user at that location. In step 442, user-specific data is accessed from the edge computing storage device. For example, user-specific data can correspond to user data that can be specifically loaded from the cloud computing or central storage used by the user to the edge computing storage device. User-specific data can therefore correspond to data that is particularly relevant or useful to the user's current location.

[0077] In step 444, sub-locations within the user's area of ​​interest are determined based on user-specific data and one or more predictive models. Sub-locations may correspond to items the user wants to purchase, activities the user wants to participate in, and / or areas the user may be interested in. Sub-locations may also correspond to locations where the user can obtain access rewards, etc. Therefore, in step 446, application data for the sub-locations within that location is generated. Application data may correspond to data from a specific application on the user's device, which may be output by the application. For example, application data may include interactive maps, audiovisual content, video games, etc., that the user can utilize, and / or data that can be used within the application (e.g., rewards that can be used with electronic transaction processing within the application).

[0078] In step 448, application data is provided to the user via an edge computing storage device. The application data can be retrieved by the user's computing device, such as a mobile smartphone or other mobile device, which can request data from the edge computing storage device. However, in other implementations, such as when the user is detected to be at or near the location and / or likely to access the sub-location, the application data can be pushed from the edge computing storage device to the user's computing device. By using an edge computing storage device, application data can be provided faster and with lower loading times and / or latency.

[0079] Figure 5 It is suitable for implementation according to the method of implementation. Figure 1 A block diagram of a computer system 500 comprising one or more components. In various embodiments, the communication device may include a personal computing device capable of communicating with a network (e.g., a smartphone, tablet computer, personal computer, laptop computer, wearable computing device such as glasses or a watch, Bluetooth device, key FOB, badge, etc.). Service providers may utilize network computing devices capable of communicating with a network (e.g., a web server). It should be understood that each device used by the user and the service provider may be implemented as computer system 500 in such a way as follows.

[0080] Computer system 500 includes bus 502 or other communication mechanisms for transmitting information, data, signals, and information between various components of computer system 500. Components include input / output (I / O) components 504 that process user actions, such as selecting key input from a keypad / keyboard, selecting one or more buttons, images, or links, and / or moving one or more images, and sending corresponding signals to bus 502. I / O component 504 may also include output components such as display 511 and cursor controls 513 (such as keyboard, keypad, mouse, etc.). Optional audio / visual input / output (I / O) components 505 may also be included to allow users to input information using speech by converting audio signals and / or to input or record images / video by capturing visual data of a scene with objects. Audio / video I / O component 505 can allow users to hear audio and view images / video, including projections of such images / video. Transceiver or network interface 506 sends and receives signals between computer system 500 and other devices (e.g., other communication devices, service devices, or service provider servers) via network 160. In one embodiment, the transmission is wireless, but other transmission media and methods may also be suitable. One or more processors 512 may be microcontrollers, digital signal processors (DSPs), or other processing components that process these various signals, for example, for display on computer system 500 or for transmission to other devices via communication link 518. Processor 512 may also control the transmission of information such as cookies or IP addresses to other devices.

[0081] The computer system 500 also includes a system memory component 514 (e.g., RAM), a static storage device component 516 (e.g., ROM), and / or a disk drive 517. The computer system 500 performs specific operations by a processor 512 and other components by executing one or more sequences of instructions contained in the system memory component 514. The logic may be encoded in a computer-readable medium, which can refer to any medium that participates in providing instructions to the processor 512 for execution. Such media can take many forms, including but not limited to non-volatile media, volatile media, and transmission media. In various embodiments, non-volatile media include optical discs or magnetic disks, volatile media include dynamic memory, such as the system memory component 514, and transmission media include coaxial cables, copper wires, and optical fibers, including wires forming the bus 502. In one embodiment, the logic is encoded in a non-transitory computer-readable medium. In one example, the transmission medium may take the form of acoustic or optical waves, such as those generated during radio wave, optical, and infrared data communication.

[0082] Some common forms of computer-readable media include, for example, floppy disks, floppy hard disks, magnetic tapes, any other magnetic media, CD-ROMs, any other optical media, punch cards, paper tapes, holes in any other physical media with patterns, RAM, PROMs, EEPROMs, FLASH-EEPROMs, any other memory chips or cartridges, or any other media suitable for a computer to read.

[0083] In various embodiments of this disclosure, the execution of the instruction sequence for practicing this disclosure may be performed by computer system 500. In various other embodiments of this disclosure, multiple computer systems 500 coupled to a network via communication link 518 (e.g., LAN, WLAN, PTSN and / or various other wired or wireless networks, including telecommunications, mobile and cellular telephone networks) may execute instruction sequences to practice this disclosure in a coordinated manner with each other.

[0084] Where applicable, the various embodiments provided in this disclosure may be implemented using hardware, software, or a combination of hardware and software. Furthermore, where applicable, the various hardware and / or software components described herein may be combined into composite components comprising software, hardware, and / or both without departing from the spirit of this disclosure. Where applicable, the various hardware and / or software components described herein may be divided into sub-components comprising software, hardware, or both without departing from the spirit of this disclosure. Additionally, where applicable, it is contemplated that software components may be implemented as hardware components, and vice versa.

[0085] The software, such as program code and / or data, according to this disclosure can be stored on one or more computer-readable media. It is also contemplated that the software identified herein can be implemented using one or more networked and / or otherwise networked general-purpose or special-purpose computers and / or computer systems. Where applicable, the order of the various steps described herein can be changed, combined into compound steps, and / or divided into sub-steps to provide the features described herein.

[0086] The foregoing disclosure is not intended to limit this disclosure to the precise form disclosed or a particular field of use. Therefore, various alternative embodiments and / or modifications of this disclosure, whether expressly described or implied herein, are conceivable in light of its contents. Embodiments of this disclosure have been so described that those skilled in the art will recognize that changes in form and detail may be made without departing from the scope of this disclosure. For example, while the description focuses on gift cards, other types of funding sources that can be used to finance transactions and add value to their purchases are also within the scope of various embodiments of the invention. Therefore, this disclosure is limited only by the claims.

Claims

1. A service provider system, the service provider system comprising: Non-transitory memory; and One or more hardware processors, coupled to the non-transitory memory, are configured to read instructions from the non-transitory memory to cause the service provider system to perform operations including: The service provider system detects users within a geofence area associated with the merchant's location, wherein the service provider system is associated with an edge computing system having edge computing storage nodes associated with the merchant's location, wherein the edge computing storage nodes are separate from the central storage device used by the user, and the edge computing storage nodes are location-specific and retain data not shared with the central storage device; The user's user profile is determined through the service provider system; Identify one or more activities previously performed by users within the vicinity of the geofence; A machine learning (ML) model associated with the merchant's location is used to determine data storage actions between the edge computing storage node and the central storage device, wherein the data storage action moves at least a portion of data from the edge computing storage node to the central storage device; or the data storage action moves at least a portion of data from the central storage device to the edge computing storage node; and The data storage operation is performed between the edge computing storage node and the central storage device.

2. The service provider system according to claim 1, wherein, The data storage operation moves at least a portion of the data from the central storage device to the edge computing storage node, and the operation further includes: Based on the user profile, the one or more activities, and at least a portion of the data moved to the edge computing storage node, the activity of the user at the merchant's location is predicted; Generate application data associated with the merchant location and the activity, wherein the application data includes user-specific guidance for users at the merchant location; and The application data is stored on the edge computing storage node, and the application data is capable of being transmitted to the user's mobile device via the edge computing storage node.

3. The service provider system according to claim 2, wherein, Predicting the activity includes predicting whether the user intends to purchase goods from the merchant location, wherein the application data is specific to the merchant location, and the user-specific guide includes a visualization of the layout of the merchant location, the layout of which has sub-locations within the merchant location where the goods the user intends to purchase are located.

4. The service provider system according to claim 3, wherein, Predicting the products that the user intends to purchase includes: Identify past purchases associated with the product from one of the user profiles or from at least a portion of the data moved to the edge computing storage node; Determine the amount of time that has occurred since the aforementioned past purchase; and The merchant's location is used to model customer behavior using a machine learning (ML) model, and the amount of time since the last purchase is used to predict whether the user will buy the product.

5. The service provider system according to claim 3, wherein, Before generating the application data, the operation further includes: The merchant's location and the user's loyalty program information are determined, wherein the loyalty program information includes one or more hotspot sub-locations within the merchant's location, and the user is provided with one or more loyalty rewards at the one or more hotspot sub-locations when the user is detected at the hotspot sub-location. The application data also includes the loyalty program information, and the user-specific guide includes the hotspot sub-locations.

6. The service provider system according to claim 1, wherein, The operation also includes: Additional user data of users at the merchant's location or associated with the one or more activities is monitored; Update the user's user profile based on the additional user data; and The updated user profile is retained at the edge computing storage node.

7. The service provider system according to claim 6, wherein, The operation also includes: The data is determined based on the updated user profile, wherein the data includes one subset of all data in the user profile, or the data does not include data from the user profile; and Based on the determined data, data from the updated user profile is shared with the central storage device.

8. The service provider system according to claim 7, wherein, The data is determined based on at least one of the following: privacy regulations associated with the edge computing system, privacy laws affecting the region associated with the edge computing storage node, or user selection to join or opt out of data sharing between the edge computing storage node and the central storage device.

9. The service provider system according to claim 6, wherein, In the case of purchasing one or more items at the merchant location, the update is performed using one or more ML models trained based on user behavior patterns at the merchant location.

10. The service provider system according to claim 9, wherein, The user behavior pattern includes at least one of the following: gait, age, demographics, customer profile, route taken through the merchant location, or past activity at the merchant location.

11. The service provider system according to claim 1, wherein, The edge computing storage node also includes multiple user profiles associated with multiple users, the multiple user profiles including the user and the user profile corresponding to the user, wherein the edge computing storage node requires an authentication mechanism for single-user authentication or group authentication to access the multiple user profiles, and wherein the operation further includes: Receive authentication credentials for the authentication mechanism from the user; and Based on the authentication credentials and the authentication mechanism, the user is authenticated using either single-user authentication or group authentication.

12. A method for using an edge computing cloud storage device based on user location and activity data, separate from the cloud computing environment, the method comprising: The service provider detects users located at or near locations associated with edge computing cloud storage devices via the user's mobile device, wherein the edge computing cloud storage device is separate from the main cloud storage device that has user data for the user, and the edge computing cloud storage device is location-specific and retains data that is not shared with the main cloud storage device. Access to the user's user profile through the service provider; Monitor one or more activities corresponding to the user at the said location; Using at least one machine learning (ML) model and based on one or more monitored activities and the user profile, determine the data to be moved from the primary cloud storage device to the edge cloud storage device; and In response to the determination, the data is moved from the main cloud computing storage device to the edge computing cloud storage device.

13. The method according to claim 12, wherein, Before monitoring the one or more activities, the method further includes: Request permission from the mobile device to monitor the one or more activities at the location; Receive permission from the mobile device; and Prevent sharing of data associated with the one or more activities with the main cloud storage device until the user grants permission.

14. The method according to claim 13, wherein, Monitoring the one or more activities includes monitoring at least one of the following: purchases at the location, movement of the user through the location, locations of interest to the user, loyalty rewards earned or used at the location, or use of the mobile device at the location, wherein moving the data includes: Receive one or more preferences of the user and one or more past purchases of the user from the main cloud storage device.

15. The method according to claim 12, further comprising: Using the at least one ML model, based on the user profile, to predict one or more sub-locations of interest to the user at the location; An application notification is generated based on the one or more sub-locations of interest and the layout of the locations, wherein the application notification includes an interactive map of the locations displayed within a mobile application on the mobile device, wherein the interactive map includes products associated with the one or more sub-locations of interest and hotspots within the locations that offer rewards to the user, and wherein the application notification causes the mobile application to direct the user to the products and the hotspots; and The application notification is output via a mobile application on the mobile device.

16. The method according to claim 15, wherein, The application notification also includes mobile application data stored on the edge computing cloud storage device, wherein the mobile application data includes one of the following: loyalty reward information for the location, image files associated with the location, audiovisual files associated with the location, media content for the location, or interactive game data for the location.

17. The method according to claim 12, wherein, Before accessing the user profile, the method further includes: Request authentication from the mobile device for access to the user profile from the edge computing cloud storage device; and Authentication is received from the mobile device via either user input or automatically transmitted credentials stored on the mobile device.

18. The method according to claim 12, wherein, The at least one ML model is trained using features derived from past customer behavior at the location, and wherein the at least one ML model provides a predicted output of activities of interest to the user based on at least one current parameter in the case that the user is detected at or near the location.

19. A non-transitory machine-readable medium storing machine-readable instructions that are executable to cause a machine to perform operations including: The user's geographical location is detected via the user's mobile device, wherein... The mobile device is associated with a cellular network that can use the geographic location to provide edge computing services to the user. Access the user's edge computing cloud storage device, which is separate from the user's main cloud computing storage device, wherein the edge computing cloud storage device is location-specific and holds data that is not shared with the main cloud computing storage device; Access the user's user profile; Monitor the activity of one or more users at the said geographical location; Using at least one machine learning (ML) model and based on one or more monitored activities and the user profile, determine the data to be moved from the main cloud storage device to the edge cloud storage device; In response to the determination, the data is moved from the main cloud computing storage device to the edge computing cloud storage device; One or more user interests are predicted based on one or more monitored user activities and one or more ML models trained based on other user activities of the user at the geographic location. Update the user's user profile based on one or more user interests; and The updated user profile is stored in the edge computing cloud storage device, independent of the storage in the main cloud storage device.

20. The non-transitory machine-readable medium according to claim 19, wherein, The operation also includes: The user is located in the vicinity of the geographical location via the mobile device through the cellular network; Retrieve the updated user profile of the user from the edge computing cloud storage device; and Based on the updated user profile, one or more recommendations are provided from the edge computing cloud storage device to the mobile device via the cellular network.

Images