Abstract: Techniques are disclosed relating to training a neural network using private training data. In some embodiments, a central computing system is configured to maintain an at least partially trained neural network and information that specifies data formats for inputs to the model and outputs from the model. In some embodiments, partner computing systems maintain subsections of the neural network model and may train them using data that is not shared with other partner computing systems or the central computing system. Parameters resulting from the training may be transmitted to the central computing system. In some embodiments, the central computing system processes the parameters to generate the updated complete version of the neural network model and transmits parameters from the updated complete version of the model to the partner computing systems. The partner computing systems may use the updated complete model to detect anomalies in input data.

Abstract: A server computer system stores a plurality of display generation objects executable to cause display of display images. The server computer system receives a camera image from a user device. The server computer system determines that a particular display image included in the camera image corresponds to a particular display generation object. The server computer system then subscribes the user device to one or more data feeds selected based on the particular display generation object, and sends one or more notifications corresponding to the one or more selected data feeds to the user device.

Abstract: Systems and methods may include receiving performance data of components in a system. The performance data may include data for parameters for each of the components. The systems and methods may include determining aggregate data for each group of similar components of the components. The aggregate data for each group of similar components may include a group characteristic for each of the parameters. The systems and methods may include, for each group of similar components, determining whether the data for each of the parameters for each component is consistent with the group characteristic for the respective parameter. The systems and methods may include, for each component of the respective group determining that the component is anomalous in response to determining that the data for a parameter for the component is not consistent with the group characteristic for the parameter.

Abstract: A digital currency driven channel assignment technique is disclosed. Each AP in a distributed network uses a channel selection manager and a distributed ledger to select channels according to a channel assignment and a digital currency associated with the distributed ledger. The digital currency incentivizes APs to make sacrifices in their channel selection for the benefit of the overall network while punishing APs that select channels selfishly and cause bandwidth interference.

Abstract: Provided is a computer system that includes a processor and a memory coupled to the processor, the memory including computer readable program code embodied therein that, when executed by the processor, causes the processor to generate a catalog that identifies a plurality of tasks that a plurality of network resources are available to perform, the network resources including Internet-of-things devices and human network resources and to generate, in response to receiving a request to perform a complex project, a solution path that includes an ordered list corresponding to selected ones of the plurality of tasks that are capable of aggregately performing the complex project, wherein the selected ones of the plurality of tasks define the solution path in an edge graph that include the plurality of tasks represented as edges therein.

Abstract: Systems and methods may include receiving, by an expert system, performance data for a monitored system. The systems and methods may include generating a prediction for the monitored system in response to determining that the performance data satisfies a condition. The prediction may identify an anomaly that is predicted to occur. The systems and methods may include receiving, by a filter system, the prediction, information identifying the condition, and user information. The user information may include user preference information and user feedback information. The systems and methods may include determining a filter criteria based on the user information. The filter criteria may be based on the preferences for predictions to be provided to the user and on the historical user feedback regarding the historical predictions. The systems and methods may include providing the prediction to the user in response to determining that the particular prediction satisfies the filter criteria.

Abstract: Techniques are disclosed relating to serving an electronic search warrant. In some embodiments, a computer system accesses a blockchain including an electronic warrant that authorizes access to a controlled device having confidential data. The computer system sends a request for the confidential data to the controlled device, the request identifying the electronic warrant. The computer system receives the confidential data from the controlled device and appends a first record to a second record in blockchain. The first record includes the confidential data, a first digital signature generated from the contents of the first record, and a second digital signature obtained from the second record. In some embodiments, the computer system sends a request for the electronic warrant to a second computer system associated with a court. The request identifies a public key for inclusion in the electronic warrant and having a private key to generate the first digital signature.

Abstract: Methods, systems, and program products are disclosed for generating performance classifications for program elements. Program elements of a program are associated with reference elements of a reference document that describes the program. A first set of user interface inputs to the reference document are recorded including recording each of the first set of interaction based events in association with a respective one or more of the reference elements. A performance classifier is executed to generate a performance classification for one or more of the program elements based on one or more patterns formed, at least in part, by the first set of interaction based events.

Abstract: Embodiments are disclosed for distributing email delivery processing. In some embodiments, an inactivity indicator associated with a user agent is detected. Based on the inactivity indicator, a delivery completion request is generated and sent to a first sending user agent from which a first email is received prior to detecting the inactivity indicator. The delivery completion request includes an identifier for the first email and one or more selectable delivery options including at least a delivery termination option. In response to a reply from the first sender user agent to the delivery completion request that includes selection of the delivery termination option, delivery of the first email to the first user agent is terminated.

Abstract: Techniques are disclosed relating to a computer system receiving recordings of meetings between individuals, encrypting the recording, storing the encrypted recording, and determining whether to decrypt the encrypted recording based on decryption information indicative of ones of the individuals have assented to the decryption of the encrypted recording and a cryptographic policy. The computer system may also perform semantic analysis of the audio of the meeting to identify decision statements made at the meeting and factor statements made at the meeting upon which the decision statement is based. The computer system may also store meeting metadata associated with the meeting that is indicative of the decision statement and factor statements.

Abstract: In an embodiment, a password risk evaluator may receive a request including a user identifier (ID) and a password. The password risk evaluator may retrieve a password preference model associated with the user ID, and may determine a risk score indicating a likelihood that the password is associated with the user ID. For example, the password preference model may be based on previous passwords used by the user, and may identify one or more characteristics, formulas, rules, or other indicia typically employed by the user in creating passwords. If the password supplied in the request matches or is similar to one or more elements of the password preference model, it may be more likely that the password in the request is a password supplied by the user. That is, the risk score may be an authentication of the user, or part of the authentication of the user, in some embodiments.

Abstract: A thing-sourcing project request including requirements for a thing-sourcing task that requires data input by a thing-sourcing device is received from a requestor device. A determination is made if real-time data is needed in order to complete the thing-sourcing task. In response to determining that real-time data is not needed, a determination is made if a similar thing-sourcing task has been previously completed. If not, the method determines if the thing-sourcing task can be completed using pre-existing data. If so, a data archive is searched for relevant pre-existing data that can be used to complete the thing-sourcing task. The thing-sourcing task is completed using the relevant pre-existing data, and a response to the thing-sourcing project request is transmitted to the requestor device.

Abstract: A computing device has a camera and tracks the movement of a user's eye as the user looks at a display monitor. Upon detecting that a user is unable to locate the position of a cursor on the display monitor, the computing device displays the cursor at a conspicuous location on the display monitor so that the user is likely to find the cursor. The location at which the cursor is conspicuously displayed is selected by the computing device based on an analysis of the user's eye movements.

Abstract: A method is described for receiving a plurality of node data streams through a data network from a plurality of source nodes, respectively, each of the plurality of node data streams comprising a plurality of node data. The method further comprises determining a respective risk assessment for each of the plurality of node data streams based on a plurality of elements, wherein the respective risk assessment indicates a level of trustworthiness of each of the plurality of node data streams. Moreover, the method comprises determining a plurality of respective actions for each of the plurality of source nodes, based on the respective risk assessment of the plurality of node data streams. The method further comprises instructing each of the plurality of source nodes to perform the respective action.

Abstract: In some embodiments, a method includes receiving an identification of an intended recipient of a physical package and a personalized message having content based on the identity of the intended recipient. The method further includes identifying a uniform resource locator (URL) comprising a reference to a webpage that displays the personalized message and one or more advertisements regarding products or services related to the physical package. A Quick Response (QR) code encoding the URL comprising the reference to the webpage that displays the personalized message and the one or more advertisements may be generated. The method further includes transmitting the personalized message and the one or more advertisements to the intended recipient via the webpage in response to the intended recipient accessing the URL encoded by the QR code.

Abstract: Systems and methods may include receiving real-time data about a real component operating in a real-world environment. The systems and methods may further include generating a virtual representation of the real component based on the real-time data about the real component and historical data associated with the real component. In addition, the systems and methods may include receiving injected data from a lab. The injected data may provide data about a lab component operating in the lab. The systems and methods may also include simulating, in a virtual environment, a real-time interaction in the real-world environment between the real component and the lab component using the virtual representation of the real component and the injected data. Moreover, the systems and methods may include determining a real-time performance characteristic of at least one of the lab component and the real component based on the simulated real-time interaction in the real-world environment.

Abstract: A user selects an appliance or other device to control using a wearable computing device, such as an augmented eyewear device, for example. Based on the selection, data regarding a current operating state and one or more subsequent operating states are provided for display to the user. Using the wearable computing device, the user selects one of the subsequent states and controls the appliance to transition from its current state to the selected subsequent state. The commands for controlling the transition may be proxied for the wearable computing device by a mobile device or a network server, for example, via one or more established communication links.

Abstract: Techniques for managing distributed state for stateless transactions are disclosed herein. In some embodiments a distributed state manager detects a state-changing event that corresponds to a stateless transaction between a node and an application server. The stateless transaction is generated from a first instance of an application that is executing on the node and hosted by the application server. The distributed state manager records the event in a blockchain comprising blocks that each record a batch of one or more events associated with execution of the application. The distributed state manager detects an update to the blockchain associated with the recorded event and modifies a state of a second instance of the application executing on at least one other node based, at least in part, on the update to the blockchain.

Abstract: In an embodiment, a password risk evaluator may receive a request including a user identifier (ID) and a password. The password risk evaluator may retrieve a password preference model associated with the user ID, and may determine a risk score indicating a likelihood that the password is associated with the user ID. For example, the password preference model may be based on previous passwords used by the user, and may identify one or more characteristics, formulas, rules, or other indicia typically employed by the user in creating passwords. If the password supplied in the request matches or is similar to one or more elements of the password preference model, it may be more likely that the password in the request is a password supplied by the user. That is, the risk score may be an authentication of the user, or part of the authentication of the user, in some embodiments.

Abstract: Techniques are disclosed relating to training a neural network using private training data. In some embodiments, a central computing system is configured to maintain an at least partially trained neural network and information that specifies data formats for inputs to the model and outputs from the model. In some embodiments, partner computing systems maintain subsections of the neural network model and may train them using data that is not shared with other partner computing systems or the central computing system. Parameters resulting from the training may be transmitted to the central computing system. In some embodiments, the central computing system processes the parameters to generate the updated complete version of the neural network model and transmits parameters from the updated complete version of the model to the partner computing systems. The partner computing systems may use the updated complete model to detect anomalies in input data.