Abstract: A latency analysis system determines a latency period, such as a wait time, at a user destination. To determine the latency period, the latency analysis system receives location history from multiple user devices. With the location histories, the latency analysis system identifies points-of-interest that users have visited and determines the amount of time the user devices were at a point-of-interest. For example, the latency analysis system determines when a user device entered and exited a point-of-interest. Based on the elapsed time between entry and exit, the latency analysis system determines how long the user device was inside the point-of-interest. By averaging elapsed times for multiple user devices, the latency analysis system determines a latency period for the point-of-interest. The latency analysis system then uses the latency period to provide latency-based recommendations to a user. For example, the latency analysis system may determine a shopping route for a user.

Abstract: A roaming transport distribution management apparatus and method are provided. A controller selects transports within a defined service zone in response to customer transit requests from customer locations for customer pick-up and delivery inbound or outbound directions from the hub. A hub manager varies the position and/or the size of an exclusive coverage area of each transport within the overall service zone to insure a dense accumulation of transports over the entire service zone and alters the position of other transports in response to the movement of a transport inbound or outbound from the hub with a passenger. The hub manager can vary the size of the exclusive coverage area of each transport to account for population and request call densities and the number of available transports.

Abstract: A graphical item chooser sorts candidate products or services by initially classifying each of one or more objective icons as a primary objective icon or a secondary objective icon. Each objective icon represents one or more desired characteristics of a product or service that facilitates a particular objective. The graphical item chooser may further determine at least one most desired characteristic of the ideal product or service. The determination is made based on a frequency that each desired characteristic is represented by the one or more objective icons. Having made the determination, the graphical item chooser then sorts the candidate products or services based at least on similarities between one or more characteristics of each candidate product or service and the at least one most desired characteristic. Following the sort, the graphical item chooser generates a sorted list of suitable products or services.

Abstract: Embodiments for automated data exploration and validation by a processor. One or more optimal data flows are provided in response to a query for one or more heterogeneous data sources according to an inference model based on a knowledge graph of heterogeneous data source relationships, a plurality of data flows between one or more heterogeneous data sources relating to the query, and an ontology of concepts and representing a domain knowledge of the one or more heterogeneous data sources.

Abstract: A system and method for workflow orchestration for use with a cloud computing environment. Cloud environments, such as Oracle Public Cloud (OPC), provide a suite of applications, middleware, and database offerings that can be delivered to tenants in a self-service, elastically scalable, and secure manner. In accordance with an embodiment, the cloud environment can include a Platform as a Service (PaaS) environment, which provides a variety of services such as virtual assembly creation. A workflow orchestrator can be used to orchestrate operations between the cloud environment and the PaaS environment, e.g., by receiving a request from a tenant automation system, and coordinating the provisioning and deployment of virtual assemblies or applications. A customer can interact with the PaaS environment, e.g., to request a service, deploy to the service, or monitor the service.

Abstract: Embodiments of the present invention provide methods, systems, apparatuses, and computer program products for integrating user-specific context indicators into a searchable enterprise platform. In one embodiment, an apparatus is configured to apply a learned user profile, to a set of search results to obtain a user-specific, ranked arrangement of search results. The learned user profile may be developed through the application of a machine learning and/or trained model to a set of user behaviors that have been determined or otherwise detected within an enterprise platform, such that the user-specific context in which a user's search arises can be modeled and applied to retrieved digital content items associated with a search query within the enterprise platform.

Abstract: Provided is a device for determining a wheel fastening state that allows a wheel fastening state to be monitored during running. The device includes a sensor unit (3) that is attachable to and detachable from a wheel fastening part, an information terminal (4) that is an in-vehicle device (4A) or a portable terminal (4B), and a server (30). The terminal (4) includes a measurement instruction module (23) to read vehicle state data from a control and communication system (5) of a vehicle and send an instruction for to measurement to the sensor unit (3) at determined timing. The server (30) includes a first information processing module (32) configured to determine an abnormality of a fastening state of the wheel fastening part by comparing the measurement data with accumulated data that is measured under the same condition and stored in the past.

Abstract: A method and apparatus for vehicle monitoring of infrastructure lighting, an example of which includes a vehicle having a camera, an inter-vehicle communication module and a controller. The controller is to identify a stationary infrastructure object within an image captured by the camera and identify, in response to determining that the stationary infrastructure object includes a lamp, whether the lamp is inoperable. The controller also is to send, via vehicle-to-infrastructure communication utilizing the inter-vehicle communication module, an alert to an infrastructure communication node indicating that the lamp is inoperable.

Abstract: Example systems and methods for resource allocation for infrastructure engineering are described. In one implementation, a method identifies resources for infrastructure engineering with respect to an organization. The method also sorts the resources based on skills and roles associated with the infrastructure engineering, and then determines multiple teams based on the sorted resources.

Abstract: Systems, methods, and computer program products to perform an operation comprising receiving input specifying a first portion of a graphical user interface (GUI) of a first application executing on a first computing device, wherein the GUI is outputted on a display device, rendering the GUI of the first application on a first virtual display of the first computing device, and not on the first display device, and generating a first widget which displays the first portion of the GUI of the first application on the display device, wherein a unique identifier of the first widget is associated with a unique identifier of the first virtual display.

Abstract: A method and system for the ordered modification of a recurring event in a calendaring application. A method for applying ordered modifications to recurring event instances, can include identifying an event exception which corresponds to a separately defined recurring event instance. Subsequently, at least one property of the recurring event instance can be modified based upon the event exception. Additional event exceptions corresponding to the recurring event instance can be further identified in accordance with a preferred aspect of the present invention. For each further identified additional event exception, at least one property of the recurring event instance can be further modified based upon the further identified additional event exception. Notably, each of the identifying and modifying steps can be repeated for additional recurring event instances.

Abstract: A method and system adaptively improves potential customer conversion rates, revenue metrics, and/or other target metrics by providing effective user experience options, from a variety of different user experience options, to some users while concurrently testing user responses to other user experience options, according to one embodiment. The method and system selects the user experience options by applying user characteristics data to an analytics model, according to one embodiment. The method and system analyzes user responses to the user experience options to update the analytics model, and to dynamically adapt the personalization of the user experience options, at least partially based on feedback from users, according to one embodiment.

Abstract: Embodiments of the present disclosure are directed to an interactive development environment (IDE) interface that provides historical visualization of queries and query result information iteratively and intuitively. According to an embodiment of the present disclosure, a process is provided to generate visualizations of queries and processed query result information in a single, persistent, integrated display. Each query and resultant search data information is presented iteratively in chronological order and maintain a persistent, viewable history of asearch data exploration session.

Abstract: A method, system, and computer program product for creating or augmenting a business process model using a question and answer (Q and A) system are provided in the illustrative embodiments. A request to create the business process model of a business process is received. A knowledgebase is created using a business process modeling (BPM) data and user domain data. The user domain data comprises a combination of unstructured documents and structured documents related to an operation in a user domain. A natural language (NL) question is formed corresponding to the request. The NL question and the knowledgebase are submitted to the Q and A system. A set of answers is received from the Q and A system responsive to the NL question. An answer is presented as a part of the business process model.

Abstract: Example embodiments provide a system and method for providing user interfaces comprising calendar-based suggestions of single user, single event travel options. The system accesses calendar data of the user, which indicates an event that the user is scheduled to attend, and extracts data for the event from the calendar data. The system constructs an application program interface (API) request by incorporating the extracted data for the event as one or more search criteria in the API request. The system transmits the API request to a provider server of at least one service provider. In response, the system receives results from the provider server(s), which comprise options determined to be compatible with the event based on the one or more search criteria in the API request. The system causes presentation of at least some of the options from the results determined to be compatible with the event.

Abstract: Techniques are disclosed herein for reactively identifying software products, available from an electronic marketplace, that are exhibiting anomalous behavior. Data associated with software products is accessed and analyzed to determine anomalous behavior. The data analyzed may include, but is not limited to, crash data, ratings data, marketplace data, usage data, and the like. A machine learning mechanism may be used to classify the application into a category relating to whether a potential anomaly is identified for the software product. A score may also be calculated for the software applications that indicates a severity of the anomalous behavior. The classification and/or the score may be used to determine whether to perform further analysis or testing with regard to a software product. For instance, the score may be used to determine that the software product is to be tested by a testing service.

Abstract: A method of controlling machines for performing operations at a worksite is disclosed. The method includes receiving pre-construction terrain data, design terrain data, and resource data and then defining a plurality of constraints based on the data. Operations of the machines are simulated based on the data. The method includes estimating process variables associated with the operations and defining and scheduling tasks to be performed by the machines. The method includes collecting real time data from the worksite and updating the estimated process variables and the scheduled tasks of the machines based on the collected real time data. Instructions are then provided to the machines for executing the tasks.

Abstract: A security auditing computer system efficiently evaluates and reports security exposures in a target Web site hosted on a remote Web server system. The auditing system includes a crawler subsystem that constructs a first list of Web page identifiers representing the target Web site. An auditing subsystem selectively retrieves and audits Web pages based on a second list, based on the first. Retrieval is sub-selected dependent on a determined uniqueness of Web page identifiers relative to the second list. Auditing is further sub-selected dependent on a determined uniqueness of structural identifiers computed for each retrieved Web page, including structural identifiers of Web page components contained within a Web page. The computed structural identifiers are stored in correspondence with Web page identifiers and Web page component identifiers in the second list. A reporting system produces reports of security exposures identified through the auditing of Web pages and Web page components.

Abstract: Introduced here are computer programs and associated computer-implemented techniques for streaming pre-recorded social media sessions involving a host (also referred to as a “communicator”) and one or more participants. In some embodiments the pre-recorded social media sessions are based on recordings of live interactions between the host and the participant(s), while in other embodiments the pre-recorded social media sessions are based on separate recordings that are combined in such a way to mimic a live face-to-face interaction. Accordingly, these pre-recorded social media sessions may be presented in such a manner that they appear to be live broadcasts that are streamed in real time. Various embodiments also concern technologies that enable an interaction management platform to intelligently create social media sessions from pre-recorded media content generated by the host and/or the participant(s).

Abstract: A mobile application portfolio management system that estimates performance of a mobile application portfolio on various metrics and provides suggestions for improvements is disclosed. The mobile application portfolio manager calculates different KPIs for estimating performance of the mobile applications within the mobile application portfolio. The KPIs that underperform their respective thresholds are analyzed to isolate the elements of the KPIs that result in subpar performances by the KPIs. Various corrective actions to improve the performance of the elements of the KPIs can be derived based on the rules configured within the mobile application portfolio management system.

Abstract: Examples of the disclosure are directed toward methods of providing a user interface for a job applicant self-assessment and computing an overall fit score between the applicant and a target job. An ideal job candidate may be specified by an employer on the basis of four categories: competencies, personality traits, motives, and experience levels. Then, an actual job applicant may interact with a user interface to perform a self-assessment on each of the four categories. A fit score may be determined between the applicant and the job for each of the four categories, and the four fit scores may be used to compute an overall fit score between the applicant and the job.

Abstract: One embodiment described herein is a method comprising obtaining at least one sharing rule, each sharing rule associated with at least one subset of information and defined by at least one criterion to be verified in order to authorize making available to a consulter the associated subset of information, at least one criterion specifying at least one place of publication where the publisher—must be situated and/or at least one place of consultation where a consulter must be situated. It may include obtaining a location of the publisher user and/or a location of the consulter, identification on the basis of the location or locations obtained of at least one information subset for which all the criteria of at least one associated sharing rule are satisfied, making available—via a terminal of at least one consulter of at least one identified subset of information.

Abstract: The technology disclosed relates to processing events generated by Internet of Things (IoT) devices. In particular, it relates to storing a machine-readable declarative specification of stateful event processing of an automated multi-step progression of monitoring of Internet of Things (IoT) devices that generate events. It includes compiling into tangible memory, in response to the declarative specification, a state processing network that implements a multi-step progression of monitoring events generated by the IoT devices. The state processing network implements both the time based transition triggers and the event based transition triggers after being initiated by the IoT devices. Further, data structures, which record monitoring status of particular IoT devices, are compiled. Finally, the state processing network further selects an alternative action to trigger, and triggers the selected action using at least some data from a particular event being processed.

Abstract: Machine logic (for example, software) for determining a placement mode of at least one kind of objects in a multiplicity of storage areas are disclosed. A placement method includes the following operations: determining attraction factors of the multiplicity of storage areas, an attraction factor of each storage area indicating a capability that the storage area attracts attention of a customer; determining a spatial elasticity factor of the at least one kind of objects, a spatial elasticity factor of each kind of objects indicating an impact of a change of the storage areas where the kind of objects are placed on an attention degree of the kind of objects; and determining the placement mode of the objects in the multiplicity of storage areas, at least according to the attraction factors of the multiplicity of storage areas and the spatial elasticity factor of the at least one kind of objects.

Abstract: An automated method for processing security events begins upon receipt of information representing an offense. Based in part on context data extracted from the offense, an offense context graph is built. The offense context graph comprises nodes and edges, with an edge therein representing a relationship between a pair of nodes, at least one of the nodes being a root node representing an entity associated with the offense. The method then continues by mining information about other events that are determined to share a local contextual relationship with the offense represented by the offense context graph. This operation generates an enriched offense context graph. The enriched offense context graph is then pruned to identify an offense context for further examination. Pruning may involve applying a metric to events associated with the offense and removing nodes that, based on evaluation of the metric, do not contribute to the offense.

Abstract: Systems, methods, and other embodiments associated with allocation of retail goods in a warehouse to warehouse transfer based on warehouse inventory data are described. In one embodiment, a method includes receiving a request for allocation of a quantity of an item sold in multiple types, where the quantity of items is to be transferred from a source warehouse to a destination warehouse. An allocation method is selected from a plurality of allocation methods. Each allocation method specifies a subset of warehouse inventory data to be used to generate allocation ratios. The method includes reading the subset warehouse inventory data specified by the selected allocation method; generating allocation ratios by determining a contribution of each of the multiple types to the subset of warehouse inventory data; and generating allocation quantities for each respective type in the multiple types by applying the respective allocation ratios to the quantity.

Abstract: A list presentation device generates list information that is sent to a first user and includes a plurality of items each indicating a trade object, obtains an item that is selected by the first user among the plurality of items included in the list information, lowers, in a case where a first item is selected by the first user among the items included in the list information, display priority stored in a storage in association with a trade object indicated by a second item, which has been selected before by the first user among the plurality of items included in the list information, and generates new list information, which is sent to a second user, based on a transmission request from the second user and the display priority stored in the storage.

Abstract: Techniques for gamifying risk management services include associating a financial status of a user with a defensible position display element in a gameplay scenario, receiving risk management data regarding at least one risk management service secured by the user, associating the risk management service with at least one defensive display element in the gameplay scenario, and providing the defensible position display element and each defensive display element to a display to cause the display to visualize the defensible position display element protected by each defensive display element in the gameplay scenario.

Abstract: There is provided a method of website optimization for a website hosted on a server system, the website for use by a plurality of users, the method including steps executed by the server system of: (i) collecting data for constructing a plurality of user profiles corresponding to the plurality of users; (ii) constructing the plurality of user profiles using the collected data; (iii) quantifying affinities between the plurality of user profiles; (iv) constructing a user network map, in which users are represented as nodes, and in which the affinities are represented as links between the nodes; (v) segmenting the user network map into a plurality of communities of users, and (vi) providing website content to each user according to the segmented community of each user.

Abstract: An approach is provided for point-based map matchers using machine learning. The approach involves retrieving points collected within proximity to a map feature represented by a link of a geographic database. The probe points are collected from sensors of devices traveling near the map feature. The approach also involves determining a probe feature set for each probe point comprising probe attribute values, and determining a link feature set for the link comprising link attribute values. The apparatus further involves classifying, using a machine learning classifier, each probe point to determine a matching probability based on the probe feature set and the link feature to indicate a probability that each probe point is classified as map-matched to the link. The machine learning classifier is trained using ground truth data comprising reference probe points with known map-matches to respective reference links, and comprising known probe attribute values and known link attribute values.

Abstract: Computer program products, methods, systems, apparatus, and computing entities are provided for transacting e-commerce. In one embodiment, item information is stored for a plurality of items available for purchase from respective sellers. The item information that is displayed for each item can depend on the delivery zone of the customer.

Abstract: A manufacturing resource planning system for a manufacturer to avoid margin stacking is provided that receives order information identifying a product and provides sales information including a sales price of the product. The manufacturing resource planning system identifies the electronic components required to manufacture the product, identifies whether each electronic component is an owned electronic component owned by the manufacturer or a consigned electronic component consigned to the manufacturer, determines an acquisition cost of each owned electronic component and a consignment fee associated with each consigned electronic component, and determines the sales price of the product based on the acquisition cost of each respective owned electronic component, the consignment fee associated with each respective consigned electronic component, and a markup associated with the product.

Abstract: Disclosed herein are systems, devices, and methods related to assets and predictive models and corresponding workflows that are related to the operation of assets. In particular, examples involve defining and deploying aggregate, predictive models and corresponding workflows, defining and deploying individualized, predictive models and/or corresponding workflows, and dynamically adjusting the execution of model-workflow pairs.

Abstract: An inspection work support device that supports inspection work performed in a plant, includes: a storage that stores an apparatus ledger in which apparatus information of an apparatus installed in the plant is registered, and an inspection list which indicates a list of inspection targets; an indicator that indicates the inspection target to be inspected based on the inspection list; an acquisition part that acquires apparatus specification information which is required for specifying the apparatus; a search part that searches the apparatus ledger based on the apparatus specification information acquired by the acquisition part to obtain the apparatus information; and a display that displays the inspection target indicated by the indicator and the apparatus information obtained by the search part.

Abstract: A computer system is operable to receive a plurality of database tables from a plurality of clients, and store the database tables. The system permits a user to create a plurality of views for the database tables. Each of the plurality of views includes a plurality of fields. The system associates the plurality of views with a generic application, and presents to a user one or more configuration options. The configuration options include the plurality of fields. The system permits a user to define a generic field role for one or more of the plurality of fields. Finally, the system executes the generic application using the configuration options selected by the user and the defined generic field roles to create a user interface for a particular client.

Abstract: A distributed topology system may include a distributed topology engine configured to run on a server device and define a topology consisting of one or more building blocks. Each building block may represent one or more tasks pertaining to an application. The system may also include a distributed topology application configured to run on a client device and automatically execute one or more of the building blocks. A distributed topology database may be used to store the topology. A continuous integration module may be configured to validate at least one product change and, responsive to a successful validation, promote the at least one product change.

Abstract: A method carried out on a computer system for receiving information corresponding to a plurality of variables that can be applied to the manufacture of a designed product. When a user selects from a menu of first attributes, related ones of a second set of attributes are presented for selection. In an embodiment, the set of possible manufacturing attributes is initially compared to attributes of the designed product to eliminate from consideration those manufacturing attributes that are not compatible with the attributes of the product.

Abstract: An information processing method includes, when receiving a workflow including a conditional branch and procedures, obtaining branch probability information corresponding to a classification of the conditional branch, the branch probability information being calculated for each piece of classification information defined for the conditional branch and indicating a probability that a condition has been satisfied in an executed conditional branch; obtaining cost information and availability information that correspond to the procedure, the cost information indicating a cost needed for a service provided by the procedure, and the availability information indicating availability of the service; calculating an execution probability of the procedure on the basis of the obtained branch probability information; and calculating a probability that the received workflow properly or improperly terminates, and a cost needed to execute the received workflow by using the calculated execution probability of the procedure, th

Abstract: Methods, systems, and media for personalizing computerized services based on mood and/or behavior information from multiple data sources are provided.

Abstract: A system and method for performing large-scale data processing using a statistical programming language are disclosed. One or more high-level statistical operations may be received. The received high-level statistical operations may be dynamically translated into a graph of low-level data operations. The unnecessary operations may be removed and operations may be fused or chained together. Operations may then be grouped into distributed data processing operation. The low-level operations may then be run.

Abstract: System and method for assessing liability/accountability of a driver or a driver assistance technology in a vehicle is disclosed. One or more components used to assist a driver and to collect information of the driver and the vehicle is identified. The one or more components comprise driver assistance technologies and on-board diagnostic systems. After identifying, the information is analyzed to create a plurality of scenarios based on one or more factors. Subsequently, a first score and a second score is calculated corresponding to activation of each of the driver assistance technologies and the driving behavior in the plurality of driving scenarios. Subsequently, the plurality of driving scenarios is classified into one of a technology priority mode and a driver priority mode based on the analysis, the first score and the second score. Based on the classification, a liability of the driver/driver assistance technology is assessed and recommendations are processed.

Abstract: A computer system constructs a robust recipient profile. The system receives data associated with recipient digital interactions from, e.g., streaming and/or batch sources. The recipient data may include digital transactional data, social media data, or other recipient-specific information. The system may employ heuristic data ingestion processing to derive further data based on the data inputs and attributization, and thereby may develop a robust recipient profile by aggregating the processed and derived data. The system may implement production rules to determine recipient-specific custom metadata based on the robust recipient profile to transmit to the recipient.

Abstract: Disclosed are various embodiments for event processing architecture for real-time user engagement. Events that describe user interactions with client applications are analyzed in real-time when received in a data stream. The events are compared to patterns specified, for example, by administrators. If a pattern is matched based on a comparison to events received in the data stream, a predetermined action may be performed. The processing of events may be performed by a compute engine, which may include a virtual machine or a thread implemented in a parallel computing arrangement.

Abstract: A method and system are provided. The method includes determining, by a processor-based capability determining element, different capabilities of each of different devices connected through one or more networks. The different capabilities include communication capabilities and manageability capabilities. The method further includes classifying, by the processor-based capability determining element, the different devices according to capability maturity rankings supported by the different capabilities to provide maturity-based capability classifications for the different devices. The capability maturity rankings are based on capability maturity criteria. The method also includes dynamically managing, by a controller, operations of the different devices in accordance with the maturity-based capability classifications.

Abstract: A method and associated systems for ensuring resilience of a business function manages resource availability for projects that perform mission-critical tasks for the business function. The method and systems create a model that reveals dependencies among types of resources needed by a project, such that the model describes how the unavailability of one instance of a resource propagates disruptions to other instances of the same type of resource. This model automatically identifies a resource type as being critical if a disruption of an instance of the resource type would render a project task infeasible, and if restoring that task would incur unacceptable cost. The model may also automatically identify a first resource type as being critical for a second resource type when disruption of the first resource type reduces the available capacity of the second resource type to an unacceptable level.

Abstract: Techniques are described for dynamically adjusting the layout of an organizational chart being presented inside a browser window. Adjusting the layout of the organization chart has certain advantages such as ensuring that the organizational chart can be displayed in the browser window with minimal scrolling. The direct reports of a manager can be presented as a matrix in the organizational chart when the manager is selected. In one example, the layout of the matrix can be a vertical vector or a two dimensional vector depending on the number of direct reports the manager has. In another example, the layout of the matrix can change depending on the space available within the browser window to display the matrix. In other examples, the organizational chart can also be scaled based on the screen resolution or screen size of the client device that is presenting the organizational chart.

Abstract: A system and method for generating a recommendation counter for a business entity based on social networking interactions is provided. In an embodiment, a social networking server provides an interface for users of social networking accounts to request recommendations for business entities and to reply to the requests with recommendations. When the social networking server computer receives a recommendation for a particular business entity, the social networking server computer determines whether the recommending social networking account has recommended the particular business entity in the past. In response to determining that the social networking account has not recommended the particular business entity in the past, the social networking server computer increments a recommendation counter for the particular business entity.

Abstract: Embodiments of the present invention provide an approach for differentiated service identification/exposure in a networked computing environment (e.g., a cloud computing environment). In a typical embodiment, input model criteria will be generated. Such criteria may (among other things): identify service categories based on contextual bindings and domain centric functions; identify inter-service dependencies for a given business model (BPM); and/or provide dynamic validation of services to be exposed/identified. Embodiments of the present invention may further analyze service exposure criteria to provide efficient and accurate service exposure decisions as well as validation of the service exposure. This approach allows for consistent service exposure determinations based on decision histories of similarly (2-dimensional) aligned services in the past.

Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, including a method that comprises: determining a target geographic feature that has insufficient targeting information associated therewith, the target geographic feature defining a location; determining one or more similar geographic features to the target geographic feature, each geographic feature including targeting information, the determining based on shared excess queries that are shared between geographic features that are determined to be similar to the target geographic feature, wherein each excess query is a query associated with and exceeds an expected query count for each of the similar geographic features and the target geographic feature; attributing targeting information associated with at least one of the one or more similar geographic features to the target geographic feature; and serving content responsive to queries that relate to the target geographic feature based at least in part on the at

Abstract: Systems and techniques are provided for tracking puts and takes of inventory items by subjects in an area of real space. A plurality of cameras with overlapping fields of view produce respective sequences of images of corresponding fields of view in the real space. A processing system is coupled to the system. In one embodiment, the processing system comprises image recognition engines receiving corresponding sequences of images from the plurality of cameras. The image recognition engines process the images in the corresponding sequences to identify subjects represented in the images and generate classifications of the identified subjects. The system processes the classifications of identified subjects for sets of images in the sequences of images to detect takes and puts of inventory items on shelves by identified subjects.