Abstract: Methods, systems, and computer programs are presented for generating a usage model for predicting user commands in an app. One method includes receiving model information from client devices. The model is obtained at each client device by training a machine-learning program with app usage data. The server generates synthetic data using the models from the client devices. A machine-learning program is trained using the synthetic data to obtain a global model, which receives as input information about recent commands entered on the app and generates an output with a prediction for the next command expected to be received by the app. The information of the global model is transmitted to a first client device, and the app provides at least one command option in the app user interface based on a prediction, generated by the global model, of the next command expected.

Abstract: Embodiments relate to an intelligent computer platform to build a federated learning framework including creating a hierarchy of machine learning models (MLMs). The hierarchy of MLMs has a primary MLM in a primary layer. Training the primary MLM includes capturing contributing model updates across at least one communication channel. A secondary MLM is created and logically positioned in a secondary layer of the hierarchy. The secondary MLM is operatively coupled to the primary MLM across the at least one communication channel. The created secondary MLM is initialized, including cloning weights and framework of the primary MLM into the secondary MLM, and populated with secondary data. The populated data has model updates local to the created secondary MLM. The secondary MLM is logically stored local to the secondary layer, and limits access to the secondary MLM to the secondary layer.

Abstract: Embodiments provide for detecting viruses and other malware in executing process threads based on thread patterns. According to one embodiment, detecting previously unknown malware associated with process threads can comprise capturing context information for each thread of a plurality of threads executing on a processor. The context information can define a thread pattern for the thread. The thread pattern for each thread can be compared to stored information defining one or more known patterns for thread execution based on previous execution of one or more threads. A thread pattern variation can be detected when the thread pattern for one or more threads does not match the stored information defining the known thread patterns. A determination can be made as to whether the detected thread pattern variation indicates presence of malware and actions can be performed based on determining the detected thread pattern variation indicates the presence of malware.

Abstract: Techniques for detecting malicious activity on an endpoint based on real-time system events are disclosed. In some embodiments, a system/process/computer program product for detecting malicious activity on an endpoint based on real-time system events includes monitoring an endpoint for malicious activity using an endpoint agent, in which the endpoint comprises a local device; detecting malicious activity associated with an application on the endpoint based on real-time system events using the endpoint agent based on a set of rules; and in response to detecting malicious activity on the endpoint based on real-time system events using the endpoint agent, performing a security response based on a security policy.

Abstract: A network authentication system can be configured for sampling a plurality of signal samples from a device on a network, providing the plurality of signal samples to a first machine-learned model that is configured to determine a device fingerprint based at least in part on the plurality of signal samples, and providing the device fingerprint to a second machine-learned model that is configured to classify the device based at least in part on the device fingerprint.

Abstract: The properties of a plurality of operational units are estimated by generating a central system state graph model representing the properties of the plurality of operational units as probabilities of transitions between states for the plurality of operational units, where the states represent operational data. Then a respective updated system state graph model is generated for each of the plurality of operational units, based on the central system state graph model and based on new operational data for the respective operational unit. A distance measure is determined between the respective updated system state graph models. If the distance measure fulfils a divergence criterion, a plurality of new central system state graph models are generated, each representing the properties of a respective subset of the plurality of operational units as the probabilities of transitions between states for the respective subset of the plurality of operational units.

Abstract: A machine learning (ML) system includes a student ML system, a learning coach ML system, and a reference system that generates training data for the student ML system. The learning coach ML system learns to make an enhancement to the student ML system or to its learning process, such as updated hyperparameter or a network structural change, based on training of the student ML system with the training data generated by the reference system. The system may also comprise a learning experimentation system that communicates with the reference system to conduct experiments on the learning of the student learning system. Also, the learning experimentation system can determine a cost function for the learning coach ML system.

Abstract: A distributed security system can include instances of a compute engine that can execute either locally in security agents on client devices or as cloud instances in a security network. Event data can be processed by elements of the distributed security system according to centrally-defined ontological definitions and/or configurations. Bounding managers of local security agents can control how much event data is sent to the security network. A storage engine in the security network can store event data received from client devices, can route event data to other elements of the security network, including cloud instances of the compute engine. An experimentation engine of the security network can also at least temporarily adjust other elements of the distributed security system during experiments or tests.

Abstract: Various examples are directed to systems and methods for generating a contract form using a contract library data structure. A computing device may receive, from a user, a contract form request comprising a set of contract classifiers. The computing device may access a contract library data structure and executes a filter routine to traverse the contract library data structure to identify at least one contract term associated with one or more filter tags corresponding to the set of contract classifiers. The filter routine may return an indication of the first contract term associated with the first node. The computing device may generate a contract form comprising the first contract term.

Abstract: The disclosure herein describes intelligently managing distribution of tests to user devices. Device data is obtained from a user device via a network connection and a usage prediction model associated with the user device is generated based on the device data. Predicted usage context data of the user device is determined based on the usage prediction model. A test scheduled to be performed using distributed testing is identified based on the test including test requirements that are satisfied by the device data and the predicted usage context data of the user device. Test instructions of the identified test are sent to the user device. Based on the test instructions causing the user device to automatically execute the identified test, test results are received from the user device. As a result, the testing platform enables performance of distributed testing across user devices with minimal interaction with users of the user devices.

Abstract: Systems and methods for data collection in an industrial environment are disclosed. A system can include a plurality of analog sensors, wherein each of the plurality of analog sensors is operationally coupled to a respective data collection point of a machine component, and generates a respective stream of detection values. A data acquisition and analysis circuit can receive the respective stream of detection values and analyze the respective stream of detection values using an expert system analysis circuit, wherein the expert system analysis circuit determines an occurrence of an anomalous condition based on an analysis of the respective stream of detection values, wherein the expert system analysis circuit utilizes a neural network including one of a probabilistic, a time delay, and a convolutional neural network.

Abstract: Techniques for detecting malicious activity on an endpoint based on real-time system events are disclosed. In some embodiments, a system/process/computer program product for detecting malicious activity on an endpoint based on real-time system events includes monitoring an endpoint for malicious activity using an endpoint agent, in which the endpoint comprises a local device; detecting malicious activity associated with an application on the endpoint based on real-time system events using the endpoint agent based on a set of rules; and in response to detecting malicious activity on the endpoint based on real-time system events using the endpoint agent, performing a security response based on a security policy.

Abstract: Collaborative filtering systems based on variational autoencoders (VAEs) are provided. VAEs may be trained on row-wise data without necessarily training a paired VAE on column-wise data (or vice-versa), and may optionally be trained via minibatches. The row-wise VAE models the output of the corresponding column-based VAE as a set of parameters and uses these parameters in decoding. In some implementations, a paired VAE is provided which receives column-wise data and models row-wise parameters; each of the paired VAEs may bind their learned column- or row-wise parameters to the output of the corresponding VAE. The paired VAEs may optionally be trained via minibatches. Unobserved data may be explicitly modelled. Methods for performing inference with such VAE-based collaborative filtering systems are also disclosed, as are example applications to search and anomaly detection.

Abstract: A method checks a plug connection, in which a first plug part is connected to a second plug part. The method determines a force-time curve of a force applied by an assembler during an assembly process of a plug connection. In addition, the method determines characteristic values of a plurality of characteristics of the force-time curve. The method also classifies the plug connection by use of a machine-learned classifier on the basis of the characteristic values of the plurality of characteristics.

Abstract: Embodiments are disclosed for a method for machine learning model training outliers. The method includes determining multiple metric values for corresponding transactions generated by a machine learning model. The method also includes deleting multiple preliminary outliers from the transactions based on a derived cut-off value. Further, the method includes identifying an absolute goal for improving a metric of the machine learning model. Additionally, the method includes identifying multiple training outliers from the remaining transactions. The remaining transactions include the transactions remaining after deleting the preliminary outliers. Also, a metric value of the remaining transactions meets the absolute goal.

Abstract: Various examples of systems and methods are provided for Lyapunov control for uncertain systems. In one example, a system includes a process plant and a robust Lyapunov controller configured to control an input of the process plant. The robust Lyapunov controller includes an inner closed loop Lyapunov controller and an outer closed loop error stabilizer. In another example, a method includes monitoring a system output of a process plant; generating an estimated system control input based upon a defined output reference; generating a system control input using the estimated system control input and a compensation term; and adjusting the process plant based upon the system control input to force the system output to track the defined output reference. An inner closed loop Lyapunov controller can generate the estimated system control input and an outer closed loop error stabilizer can generate the system control input.

Abstract: A disease-specific ontology crafted by a consensus of expert clinicians may be used to semantically characterize/provide semantic meaning to dynamically changing patient electronic medical record (EMR) data in critical care settings. Hierarchical, directed node-edge-node graphs (concept maps or Vmaps) developed with an end-user friendly graphical user interface and ontology editor, can be used to represent structured clinical reasoning and serve as the first step in disease-specific ontology building. Disease domain Vmaps reflecting expert clinical reasoning associated with management of acute illnesses encountered in critical care settings (e.g. ICUs) that extend core clinical ontologies, developed and reviewed by experts, are in turn extended with existing medical ontologies and automatically translated to a domain ontology processing engine.

Abstract: An environmental assessment system for correlating environmental data with traffic data having, a traffic/environment system including a) a traffic count system for obtaining the traffic data of moving objects on a road, and classifying the moving objects into several vehicle types, b) an environmental sensor system including a particulate matter (PM) sensor for measuring PM concentration and/or a carbon dioxide (CO2) concentration sensor, c) a microphone for obtaining sound signals originated from the moving objects on the road, d) a communication device and e) a microcomputer/memory for running computer programs, the computer programs including a function for adding a time stamp showing a time onto the traffic data, and a sever having functions for correlating the traffic data with the environmental data, wherein the traffic count system is arranged to classify the traffic data by referring to the sound signals obtained by the microphone.

Abstract: A determination result output device and a determination result output system output a determination result indicating various states of a subject, and a determination result provision device provides a determination result. A determination result output system includes a determination result output device that outputs a determination result indicating the state of a subject, and a determination result provision device that provides the determination result. When acquiring facial-surface change information related to a target purpose from the determination result output device, the determination result provision device generates determination information from facial-surface change information, determines a determination result including a state level of the subject, and sends the determination result to the determination result output device.

Abstract: Constraining adaptive optimizations of a state of an operation module of a medical device includes determining if a new state has at least one operational parameter that is outside a constraint that has been provided to the medical device in a non-repudiable manner, accepting the new state if no operational parameters are outside any of the constraints, and reverting the medical device to a previous valid state if at least one operational parameter is outside at least one of the constraints. The adaptive optimizations may be provided using artificial intelligence along with relevant inputs thereto. The medical device may be a dialysis system. Constraint data may be provided to the medical device along with a one-way hash value of the constraint data using, for example, a SHA 256 hash. The one-way hash value may be digitally signed using a private key that is part of a public/private key pair.

Abstract: The present disclosure relates to the electronic document review field and, more particularly, to various apparatuses and methods of implementing batch-mode active learning for technology-assisted review (TAR) of documents (e.g., legal documents).

Abstract: Cyber-attacks can be mitigated by automatically coordinating responses from cyber-security tools. For example, a cyber-security engine can include software modules created by multiple sources, each of the software modules being for integrating a respective cyber-security tool with the cyber-security engine. The cyber-security engine can use the software modules to communicate with the cyber-security tools in order to detect one or more events indicative of a cyber-attack against a computing environment. The cyber-security engine can then determine a coordinated-response strategy involving cooperation among the cyber-security tools to mitigate the cyber-attack. The cyber-security engine can transmit commands to the cyber-security tools to cause the cyber-security tools to implement the coordinated-response strategy.

Abstract: Provided herein are methods and systems for improved accessibility scoring for content items. A predicted accessibility score may be based on a plurality of multimodal features present within a content item. The plurality of multimodal features may include video features (e.g., based on video/image analysis), audio features (e.g., based on audio analysis), text-based features (e.g., based on closed-captioning analysis), features indicated by metadata (e.g., duration, genre, etc.), a combination thereof, and/or the like. A predicted accessibility score for a content item may indicate how accessible the content item may be for persons who are visually impaired, hearing impaired, cognitively impaired, etc., as well as for persons who desire to view content that requires less visual attention and/or audio attention as the case may be.

Abstract: There is provided a method for evaluating a network comprising: providing graphs each indicative of a respective sequential snapshot of a dynamic graph obtained over a historical time interval, the dynamic graph denoting the network, computing sets of meta-parameters, each set of meta-parameters computed according to a respective graph of the graphs, wherein each one of the meta-parameters denotes a network level parameter computed according to a plurality of at least one of edges and nodes of the respective graphs, analyzing sets of meta-parameters according to values computed based on a physics-based analytical model of an evolving physical system, and predicting a likelihood of stabilization of the network during a future time interval according to an indication of convergence of the values according to a convergence requirement, computed based on the physics-based analytical model during the future time interval.

Abstract: Methods, apparatus, systems and articles of manufacture are disclosed to improve cluster efficiency. An example apparatus includes a cluster manager to identify cluster resource details to execute a workload, a workload manager to parse the workload to identify services to be executed by cluster resources, and an optimization formula manager to identify service optimization formulas associated with respective ones of the identified services, and improve cluster resource efficiency by generating a cluster formula configuration to calculate cluster parameter values for the cluster resources.

Abstract: A system for identifying secondary effects of medications. The system may include one or more processors and a storage medium. The storage medium may stores instructions that configure the processors to perform operations. As configured, the processors may retrieve records associated with medications from servers. The processors may also extract machine readable content from records and identify portions that are associated with secondary effects of medications. Further, the processors may aggregate identified portions in a database, determine a level of evidence for records based on sources, associate records with metadata indicating the level of evidence; and generate index files mapping the markup language files, the metadata tags, and the medications. Moreover, the processor may receive search queries from a client, identify a subset of the records associated with medications in the query using index files, and transmit the identified subset ranked according to the level of evidence.

Abstract: A hybrid processor includes a classical (digital) processor and a quantum processor and implements a calibration procedure to calibrate devices in the quantum processor. Parameter measurements are defined as vertices in a directed acyclic graph. Dependencies between measurements are defined as directed edges between vertices. The calibration procedure orders the vertices, respecting the order of the dependencies while at least attempting to reduce the time needed to perform all the measurements. The calibration procedure provides a level of abstraction to allow non-expert users to use the calibration procedure. Each vertex has a set of attributes defining the status of the measurement, time of the measurement and value of the measurement.

Abstract: One or more application forms can be hosted, which application forms are received from a service provider, the service provider having been authenticated by at least one data custodian of a set of data custodians. One or more application forms include at least form fields to be populated with information. A user selection of an application form to be automatically populated can be received, the user having been authenticated by at least one data custodian of the set of data custodians. Data request is sent to at least one data custodian of the set of data custodians for automatically populating at least some of the form fields. Received data from said at least one data custodian can be collated and used to populate one or more form fields. The populated form fields can be returned to the service provider, for instance, provided a minimum requirement is met.

Abstract: The present disclosure relates to the electronic document review field and, more particularly, to various apparatuses and methods of implementing batch-mode active learning for technology-assisted review (TAR) of documents (e.g., legal documents).

Abstract: Systems and methods for data collection in an industrial environment are disclosed. A system can include a plurality of analog sensors, wherein each of the plurality of analog sensors is operationally coupled to a respective data collection point of a machine component, and generates a respective stream of detection values. A data acquisition and analysis circuit can receive the respective stream of detection values and analyze the respective stream of detection values using an expert system analysis circuit, wherein the expert system analysis circuit determines an occurrence of an anomalous condition based on an analysis of the respective stream of detection values, wherein the expert system analysis circuit utilizes a neural network including one of a probabilistic, a time delay, and a convolutional neural network.

Abstract: In an information processing device according to the present invention, an acquisition unit is configured to acquire a plurality of values related to a state quantity of a target device. An extraction unit is configured to extract a state value group constituted by a plurality of values related to an identical state quantity from the acquired plurality of values. A specification unit is configured to specify a value to be used to manage the target device from the state value group based on reliabilities of the values included in the state value group.

Abstract: Systems and methods for selective use of examples are provided. For example, information associated with external devices may be obtained, weights may be assigned to examples using the obtained information, and inference models may be generated using the assignment of weights. In some examples, update information associated with the external devices may be obtained, the assignment of weights may be updated using the update information, and updated inference models may be generated using the updated assignment of weights.

Abstract: Interactions between a classical computing system and a quantum computing system can be structured to increase the effective memory available to hold instructions for a quantum processor. The system stores a schedule of compiled quantum processing instructions in a memory storage location on a classical computing system. A small program memory is included in close proximity to a control system for the quantum processor on the quantum computing system. The classical computing system sends a subset of instructions from the schedule of quantum instructions to the program memory. The control system manages execution of the instructions by accessing them at the program memory and configuring the quantum processor accordingly. While the quantum processor executes the instructions, additional instructions are transferred from the classical computing system to the program memory to await execution.

Abstract: The invention provides a method, system, and a software program product for assisting a user and/or managing tasks of the user, by a mobile secretary cloud application configured to operate in a mobile client device and cloud server network. The mobile secretary cloud application reads data from another software application and operates at least one of another application and a third application based on the read data. Further, Artificial intelligence is utilized by the mobile secretary cloud application for operating another application and the third application.

Abstract: Methods and systems are disclosed herein for establishing communication with users based on biometric data. For example, in response to determining that a user has a particular biometric state, the media guidance application may present an option to contact another user that is associated with that biometric state.

Abstract: A method includes improved techniques for preparing the initial state of a quantum computer by reducing the number of redundant or unnecessary gates in a quantum circuit. Starting from an initial state preparation circuit ansatz, the method recursively removes gates and re-optimizes the circuit parameters to generate a reduced-depth state preparation.

Abstract: A system and method for predicting medical outcomes of patients having a variety of diseases, and communicating these predicted outcomes to the patients. The system and method incorporates a plurality of variables and available medical treatments and/or therapies that are available to a patient. All of the variables and treatments are analyzed to predict medical outcomes without treatment, and with each of the plurality of available treatments. The system includes a graphical user interface for inputting the variables and the treatment options. This graphical user interface can comprise a plurality of toggle switches for manipulating each variable as desired. The graphical user interface can display a risk of complication of a disease, both with and without treatment, to a patient, thereby improving communication to the patient and providing healthcare providers and professionals with a procedure and system by which medical outcomes may be predicted and readily communicated to patient.

Abstract: A method may include a processor training a machine learning model with a training data set, computing a data distribution of the training data set, processing a stream of new data to determine a likelihood of the new data from the data distribution that is computed, incrementing a counter when the likelihood of the new data is less than a first threshold, and retraining the machine learning model when the counter exceeds a second threshold.

Abstract: Processes and systems are disclosed for selecting a producer system from a number of producer systems to lease to a consumer system. A leasing agent, in response to a request from the consumer system for access to a service at a producer system, can identify a producer system to lease to the lease requestor based, at least in part, on a selection weight associated with each producer system that the leasing agent is assigned. The selection weights can be modified based on status information associated with each of the producer systems. This status information may be obtain from the producer systems and/or from a consumer system that has previously accessed the producer system. The consumer system may provide the status information to the leasing agent as part of the consumer system's lease request.

Abstract: A system for determining regulatory compliance of smart contracts is disclosed. The system may receive positive smart contracts that comply with regulations, convert positive section(s) of the positive smart contracts into a first set of intermediate representation of code, and train a neural network to classify smart contract sections. The system may then receive a first smart contract including first sections, convert the first sections into a second set of intermediate representation of code, classify the second set of intermediate representation of code as a first classification corresponding to the first set of intermediate representation of code or as a second classification not corresponding to the first set of intermediate representation of code, and generate for display a negative or positive indication based on the classification.

Abstract: Method and environment controller using a neural network for bypassing a legacy environment control software module. The environment controller receives at least one environmental characteristic value and determines a plurality of input variables. At least one of the plurality of input variables is based on one among the at least one environmental characteristic value. The environment controller transmits the plurality of input variables to an inference server executing a neural network inference engine. The environment controller receives at least one inferred output variable from the inference server. The environment controller uses the at least one inferred output variable received from the inference server in place of at least one output variable calculated by the legacy environment control software module based on the plurality of input variables.

Abstract: A system may detect multiple accesses of an engagement interface from a user. The multiple accesses may include a first group of accesses performed by a first device and a second group of accesses performed by a second device. Both the first device and the second device may correspond to the user. A message may be selected from a set of messages. Moreover, the message may correspond to the engagement interface. The system may identify the first group of accesses as having a greater amount of user interaction with the engagement interface than the second group of accesses. The system may then determine that the selected message has the greatest likelihood of being read on the first device. The selected message may be communicated to the first device based on the determination.

Abstract: A method, computer program product, and computing system device for receiving, at a computing device, a plurality of candidate therapy options, a corpus of therapy data, and a set of therapy recipient cohorts. At least a portion of therapy data may be filtered from the corpus of therapy data based upon, at least in part, the plurality of candidate therapy options and the set of therapy recipient cohorts. A graph may be generated to include a plurality of nodes representative of the plurality of candidate therapy options and a plurality of connections between the plurality of nodes indicating a sentiment factor with respect to the plurality of candidate therapy options based upon, at least in part, the at least a portion of therapy data filtered from the corpus of therapy data. Using the graph, a ranked list of the plurality of candidate therapy options may be generated.

Abstract: A system may include a decentralized communication network and multiple processing devices on the network. Each processing device may have an artificial intelligence (AI) chip, the device may be configured to generate an AI model, determine the performance value of the AI model on the AI chip, receive a chain from the network where the chain contains a performance measure. If the performance value of the AI model is better than the performance measure, then the processing device may broadcast the AI model to the network for verification. If the AI model is verified by the network, the device may update the chain with the performance value so that the chain can be shared by the multiple processing devices on the network. Any processing device on the network may also verify an AI model broadcasted by any other device. Methods for generating the AI model are also provided.

Abstract: A system may include a decentralized communication network and multiple processing devices on the network. Each processing device may have an artificial intelligence (AI) chip, the device may be configured to generate an AI model, determine the performance value of the AI model on the AI chip, receive a chain from the network where the chain contains a performance measure. If the performance value of the AI model is better than the performance measure, then the processing device may broadcast the AI model to the network for verification. If the AI model is verified by the network, the device may update the chain with the performance value so that the chain can be shared by the multiple processing devices on the network. Any processing device on the network may also verify an AI model broadcasted by any other device. Methods for generating the AI model are also provided.

Abstract: Encrypted user data are received at a service device from at least one user equipment, and the user data is encrypted in a trusted zone of the at least one user equipment. The encrypted user data then be decrypted in a trust zone of the service device by a first central processing unit (CPU) to obtain decrypted user data. A model is trained by using the decrypted user data to determine a training intermediate value and a training effective representative value, and a determination is made whether the training effective representative value satisfies a specified condition is determined. If so, the trained model is generated based on a model parameter. Otherwise, a model parameter is literately adjusted and the model is iteratively trained based on an adjusted model parameter until the trained effective representative value satisfies the specified condition.

Abstract: A method and system for linking a multimedia data element (MMDE) and a webpage are provided. The method includes receiving a MMDE from a source; generating a signature representative of the MMDE using a plurality of computational cores; matching the generated signature with a plurality of signatures stored in a database to find at least one matching signature, wherein at least one of the stored signatures has at least one corresponding universal resource locator (URL) of a web page stored therein as metadata of the at least one of the stored signatures; and providing to the source at least a URL that is a metadata of a matched signature upon determination of a match between the generated signature and at least one of the plurality of signatures stored in the database.

Abstract: The present invention is a system and method for cognitive customer interaction. The system includes a humanoid robot having a processor operably connected to a camera and a speaker within the robot. The system has a social interactions database connected to the processor. The social interactions database stores interaction patterns representing speech, facial expressions, and body movement. An advanced analytics program, such as Watson Analytics, determines the identity of a customer in a store and performs social content analysis of the customer on social media platforms. The advanced analytics program generates a psycholinguistic profile of the user so gestures and speech of the customer is compared to the psycholinguistic profile and the humanoid robot may response appropriately.

Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for training a neural network. In one aspect, a method includes maintaining data specifying, for each of the network parameters, current values of a respective set of distribution parameters that define a posterior distribution over possible values for the network parameter. A respective current training value for each of the network parameters is determined from a respective temporary gradient value for the network parameter. The current values of the respective sets of distribution parameters for the network parameters are updated in accordance with the respective current training values for the network parameters. The trained values of the network parameters are determined based on the updated current values of the respective sets of distribution parameters.

Abstract: The present disclosure describes a device, computer-readable medium, and method for generating messages that are customized for an individual human recipient. In one example, the method includes identifying a target to whom a message is to be sent, a goal of the message, and a topic of the message, retrieving information relevant to the topic from a library of core content, wherein the core content comprises a plurality of fixed inputs, building the message using the information retrieved from the library of core content, wherein the building comprises presenting the information retrieved from the library of core content in a manner that is customized for the target, delivering the message to the target via a delivery medium, wherein a selection of the delivery medium is customized for the target, and soliciting feedback from the target to confirm that the goal of the message has been achieved.