Abstract: Aspects of the subject disclosure may include, systems and methods, for example, including receiving a user question data in a speech format or a text format, analyzing the user question data, selecting a plurality of documents from a plurality of domains corresponding to the user question data, searching for a plurality of passages including candidates for an answer value determined as being suitable for the user question data, in the plurality of documents, obtaining candidates by inputting the user question data and the plurality of passages into a plurality of MRC question and answer units, determining the answer value based on whether a reliability value of each of the candidates exceeds a threshold value, and providing the determined answer value to a user. Other embodiments are disclosed.

Abstract: The present disclosure relates generally to a risk-based fraud identification and risk analysis system. For example, the system may receive application data from a first borrower user, determine a segment associated with the application data, apply application data to one or more machine learning (ML) models, and receive a score based at least in part upon output of the ML model.

Abstract: Machine-learning-based, adaptive updating of quantitative data in a database system is provided, which includes training one or more machine learning models to facilitate adaptively updating quantitative data in the database system, and ascertaining an update urgency index for updating the quantitative data for one or more data structures of the database system. The update urgency index is representative of an urgency for updating the quantitative data for the data structure(s) and is based, at least in part, on real-time query metrics. The machine learning model(s) is used to adaptively update the quantitative data, where the adaptively updating is based, at least in part, on the ascertained update urgency index. Processing of a database query is optimized in the database system using the adaptively updated quantitative data.

Abstract: Described herein are technologies related to generating a predicted routine of a user of a mobile computing device. Location entries generated by the mobile computing device are processed to generate visit entries, wherein the visit entries are representative of visits made by the user to places over several days. An input sequence of states is constructed based upon the visit entries, wherein each state has a place identifier assigned thereto, and further wherein each state corresponds to a time interval of predefined length. A predicted routine of the user is generated based upon the input sequence of states.

Abstract: A work center in a manufacturing setup includes a machine learning model that uses a decision tree to facilitate the work of a supervisor on the production line to choose a machine to perform a particular operation on a particular part. The decision tree outputs a ranking of machines indicating the suitability of the ranked machines for performing the particular operation on the particular part.

Abstract: A method of extracting a table information, an electronic device, and a storage medium are provided, which relate to fields of artificial intelligence and big data, in particular to fields of machine learning, knowledge graph, intelligent search and intelligent recommendation, and may be used for an intelligent extraction of an information in a table and other scenarios. The method includes: performing a clustering based on features of a plurality of rows of cells and/or features of a plurality of columns of cells in a table, so as to determine candidate header cells in the table; and performing an information extraction on the table based on the candidate header cells, so as to extract attribute-attribute value pairs in the table.

Abstract: Examples of methods for part packing are described herein. In some examples, a first subset and a second subset of a set of parts are determined. In some examples a first packing of the first subset is determined. In some examples, a second packing of the second subset is determined based on the first packing.

Abstract: Systems, apparatuses, and methods for cost evaluation and motion planning for robotic devices are disclosed herein. According to at least one non-limiting exemplary embodiment, a method for producing and evaluating a continuous and differentiable total cost as a function of all available motion commands is disclosed and may be utilized in conjunction with a gradient descent to determine a minimum cost motion command corresponding to an optimal motion for a robotic device to execute in accordance with a target trajectory and obstacle avoidance.

Abstract: According to one embodiment, a data processing apparatus includes a processor provided with hardware. The processor extracts a first event data item, a second event data item, and a third event data item from input first document data. When a first relational data item indicating a presence of transitivity between the first event data item and the second event data item is extracted and a second relational data item indicating a presence of transitivity between the second event data item and the third event data item is extracted, the processor generates a third relational data item indicating a presence of a relation between the first event data item and the third event data item.

Abstract: A required time prediction apparatus (2000) acquires utilization facility information and assumed date and time information. The utilization facility information is information enabling to determine a departure facility and a destination facility. The assumed date and time information is information enabling to determine an assumed departure date and time assuming departure from the departure facility or an assumed arrival date and time assuming arrival at the destination facility. The apparatus (2000) estimates a waiting time at each facility being present between the departure facility and the destination facility, regarding a case of assuming departure from the departure facility at the assumed departure date and time, or a case of assuming arrival at the destination facility at the assumed arrival date and time. Then, the apparatus (2000) computes, based on the estimated waiting time, a predicted required time from departure from the departure facility to arrival at the destination facility.

Abstract: A computer-implemented method comprising: storing, using a server computer executing within a protected environment, a plurality of media items, each of the media items corresponding to one of a plurality of different status values; receiving, from a requesting computing device that is outside the protected environment, a request to send certain media items outside the protected environment to a client computing device; computing, using a plurality of machine learning systems executed by the server computer, each of the machine learning systems having been trained with one of the plurality of status values as an output, a plurality of likelihood values associated with a particular status value for the client computing device, each of the machine learning systems having been trained at least in part using attribute values associated with health data records as inputs, and an existence or a non-existence of a one of the plurality of different status values as outputs, the server computer storing first data comp

Abstract: A product configuration device outputs a configuration of a product in accordance with a set of configuration rules. The product configuration device includes a rule learning system configured to acquire a first set of data representing a plurality of configurations of the product; to generate a neural network model representing the first set of data; to extract relationships between configuration attributes from the neural network model; and to modify the set of configuration rules based on the extracted relationships to generate a modified set of configuration rules for the product configuration device. The product configuration device may also include a rule execution engine that outputs the configuration of the product based on the modified set of configuration rules.

Abstract: Techniques for performing an emissions demand response event are described. In an example, a cloud-based HVAC control server system receives an emissions rate forecast for a predefined future time period. Using the emissions rate forecast, a plurality of emissions differential values are created for a plurality of points in time during the predefined future time period. The emissions differential values represent a change in predicted emissions over time. Based on the plurality of emissions differential values and a predefined maximum number of emissions demand response events, an emissions demand response event is generated during the predefined future time period. The cloud-based HVAC control server system then causes a thermostat to control an HVAC system in accordance with the generated emissions demand response event.

Abstract: Machine-learning-based, adaptive updating of quantitative data in a database system is provided, which includes training one or more machine learning models to facilitate adaptively updating quantitative data in the database system, and ascertaining an update urgency index for updating the quantitative data for one or more data structures of the database system. The update urgency index is representative of an urgency for updating the quantitative data for the data structure(s) and is based, at least in part, on real-time query metrics. The machine learning model(s) is used to adaptively update the quantitative data, where the adaptively updating is based, at least in part, on the ascertained update urgency index. Processing of a database query is optimized in the database system using the adaptively updated quantitative data.

Abstract: This application relates to apparatus and methods for automatically detecting attacks to advertisement systems. In some examples, a computing device trains a machine learning process based on a training dataset. The training dataset may be an identified portion of a website session dataset that includes a lower percentage of malicious data caused by attacks than other portions, or may include no malicious data. Once trained, the computing device generates features from a website session dataset for a customer, and applies the trained machine learning process to the generated features to detect malicious data within the website session dataset for the customer. Further, the computing device may filter the website session data to remove the detected malicious data, and may store the filtered website session data within a data repository. The computing device may provide the filtered website session data to a recommendation system to generate item recommendations for the customer.

Abstract: The present invention is an apparatus for creating an index for conducting a search on a database based on a resource including a text sentence.

Abstract: A data analysis system to analyze data. The data analysis system includes a data buffer configured to receive data to be analyzed. The data analysis system also includes a state machine lattice. The state machine lattice includes multiple data analysis elements and each data analysis element includes multiple memory cells configured to analyze at least a portion of the data and to output a result of the analysis. The data analysis system includes a buffer interface configured to receive the data from the data buffer and to provide the data to the state machine lattice.

Abstract: A computer-implemented method for generating content recommendations for content items, each content item associated with one of a plurality of customers, the method comprising: receiving, by a network-connected server, a content request from a requesting user, the content request comprising a user identifier and a customer identifier; retrieving request parameters from a computer-implemented parameter service, the request parameters comprising indicia of a plurality of models and parameters for the models; retrieving user data comprising a set of indicia of recommendable resources associated with the customer identifier; routing the content request, request parameters and user data to a plurality of ranking and optimization component, each component generating a recommendation score for each recommendable resource; generating content recommendations based on the recommendation score which content recommendations are returned to the requesting user and stored by the server as a recommendation event within a r

Abstract: The present disclosure relates to shaping the architecture of a neural network. For example, the disclosed systems can provide a neural network shaping mechanism for at least one sampling layer of a neural network. The neural network shaping mechanism can include a learnable scaling factor between a sampling rate of the at least one sampling layer and an additional sampling function. The disclosed systems can learn the scaling factor based on a dataset while jointly learning the network weights of the neural network. Based on the learned scaling factor, the disclosed systems can shape the architecture of the neural network by modifying the sampling rate of the at least one sampling layer.

Abstract: A device that includes an enterprise data indexing engine (EDIE) configured to receive a set of sentences and to compare the words in the sentences to a set of predefined keywords. The EDIE is further configured to identify one or more sentences that do not contain any of the keywords and to associate the identified sentences with a first classification type. The EDIE is further configured to identify a sentence that contains one or more keywords and to associate the sentence with a second classification type. The EDIE is further configured to link together the sentence that is associated with the second classification type and the sentences that are associated with the first classification type.

Abstract: A system and a method for monitoring and detecting drifts and configuration changes in an infrastructure that facilitates the availability of software applications to a large organization are provided. The method includes: obtaining metric information that indicates values of various parameters that relate to the infrastructure; comparing the obtained metric information with expected values thereof; determining whether a drift has occurred based on a result of the comparison; and providing a notification of a detected drift. When a drift is detected, a potential remedy may be diagnosed and automatically applied.

Abstract: A method, computer system, and computer program product are provided for managing time record events. Time record events are collected for a number of users. Each time record event includes a geolocation of one of a number of users. The time record events and geolocations for each of the number of users are models via machine learning. A current geolocation for a given user is identified. A suggested event is predicted based on the current geolocation and a current time. The suggested event is pushed to the user.

Abstract: Embodiments of the disclosure are directed to methods and systems for selecting targets for an advertisement campaign. A method may comprise adjusting one or more slider axes that control selection methods, wherein the selection methods may comprise using target demographic data, target behavioral data, filtering criteria, and/or ranking criteria. Then, an analysis application may complete analysis using the input adjustments to determine a selection of potential targets. The analysis application may be operable to complete multiple methods of analysis (or selection), wherein the user may have input and/or control over the use of the methods.

Abstract: Apparatuses and methods for adaptive control of memory are disclosed. One example apparatus includes a memory translation unit configured to receive a memory access request including a requested address and to determine a mapping state of a region of a memory associated with the requested address. The memory translation unit further configured to provide a mapped address to the memory. The mapped address is selected from one of the requested address or a translated requested address based on the state of the region of the memory associated with the requested address.

Abstract: Methods, apparatus, systems, and computer-readable media are set forth for providing a graphing database for exploration and/or production data, e.g., as used in the oil & gas industry. The graphing database can include multiple different entities that are defined by nodes, node edges, and properties that are generated from information collected by an exploration and/or production system. Entities can be designated as complete when the attribute data associated with those entities satisfy mapping rules for standardizing different types of entities. In this way, end users that access data from the graphing database can receive complete data that is consistently available through a variety of sources.

Abstract: In one embodiment, a computer implemented method comprises receiving and storing in relational database tables in a secure data processing environment comprising one or more first virtual machine instances coupled to one or more first data stores, master data comprising records having first de-identified token values associated with health data and second data comprising records having second de-identified token values associated with historical media delivery data; in the secure data processing environment, executing one or more database table join operations to merge the master data and the second data to produce a joined table having records comprising third de-identified token values associated with the health data and the second data; receiving, using one or more virtual computing instances of a service provider environment, one or more filter specifications that define a target audience and a forecast request, and in real time in response to the forecast request: based on the one or more filter specific

Abstract: The disclosed embodiments include a method for performing financial fraud assessment that includes creating a machine learning model based on features used to identify financial fraud risk; receiving financial information associated with customer accounts; establishing communities for the customer accounts; creating a baseline set of the features for each of the communities; receiving new financial information associated with customer accounts; updating the communities for the customer accounts based on the new financial information; extracting an updated set of the features for each of the communities; and determining a difference between the baseline set of the features and the updated set of the features for each of the communities; and using the machine learning model to determine financial fraud risk for each of the communities based on the difference between the baseline set of the features and the updated set of the features for each of the communities.

Abstract: In non-limiting examples of the present disclosure, systems, methods and devices for surfacing collected web content are presented. A collection of web content may be maintained, wherein the collection of web content is divided into a plurality of sections, each of the plurality of sections comprising a subset of web content from a different webpage. An indication to export the collection of web content to a productivity application may be received. A plurality of attributes that each of the plurality of sections have a value for may be identified. A productivity application document may be populated with the plurality of attributes and the corresponding values from each of the sections.

Abstract: A computer-implemented method is presented for automatically generating alerting rules. The method includes identifying, via offline analytics, abnormal patterns and normal patterns from history logs based on machine learning, statistical analysis and deep learning, the history logs stored in a history log database, automatically generating the alerting rules based on the identified abnormal and normal patterns, and transmitting the alerting rules to an alerting engine for evaluation. The method further includes receiving a plurality of online log messages from a plurality of computing devices connected to a network, augmenting the plurality of online log messages, and extracting information from the plurality of augmented online log messages to be provided to the alerting engine, the alerting engine configured to approve and enforce the alerting rules automatically generated by the offline analytics processing.

Abstract: A method, apparatus and computer program product are provided for electronic transactions based on a reply message. In the context of a computer executed method, the method includes receiving a message, from a sender device, including a reply to buy (RTB) identifier associated with a promotion and a RTB validation code. The method also includes authenticating, using a promotion and marketing service host, the RTB validation code, associating the message from the sender with a recipient identifier, and causing the transmission of a purchase order message to the recipient device based on the RTB identifier.

Abstract: The present disclosure describes methods, systems, and computer program products for enabling advanced analytics with large datasets.

Abstract: A non-transitory computer-readable recording medium stores therein an extraction program that causes a computer to execute a process including: generating a plurality of combinations of conditions relating to a plurality of item values included in data; calculating an index value that indicates a degree of cooccurrence between a specified response variable and each of the plurality of combinations, by using a machine learning model that estimates a response variable from the plurality of item values, the machine learning model having been trained by using the data; and extracting a specific combination from among the plurality of combinations based on any one of the condition and the index value.

Abstract: Disclosed are an electronic apparatus for dynamic note matching (DNM) and an operating method thereof, the method including acquiring a first section sequence by reducing a first sequence extracted from an input signal based on at least one first section in which the respective values are successively arranged; acquiring a second section sequence reduced from a pre-stored second sequence based on at least one second section in which the respective values are successively arranged; and calculating a similarity between the first section sequence and the second section sequence.

Abstract: A method of receiving one or more signals emanated from a monitored device, signal processing, based on a software model and a hardware-software (HW/SW) interaction model of the monitored device, one or more signals to determine if an anomaly exists in one or more signals, and responsive to determining that an anomaly exists based on the signal processing, transmitting an indication of the anomaly.

Abstract: A regular expression that is able to be used to identify an item as belonging to a specific group among a plurality of different groups is determined. The regular expression is tested against a sampling of items known to belong to the specific group to determine a true positive metric. The regular expression is tested against a sampling of items known to belong to other groups among the plurality of different groups outside the specific group to determine a false positive metric. An accuracy metric of the determined regular expression is calculated based at least in part on the true positive metric and the false positive metric. The accuracy metric is provided for use in evaluating the regular expression.

Abstract: A method, system, and computer program product are provided for generating a predictive model. A processor(s) obtains a raw data set (peptide libraries) of patients designated as diagnosed/pre-diagnosed with a condition or not diagnosed with the condition. The processor(s) segments the raw data set into a pre-defined number of groups and separates out a holdout group. The processor(s) performs a principal component analysis on the remaining groups to identify, based on a frequency of features in the remaining groups, common features (principal components) in the remaining groups and weighs the common features based on frequency of occurrence. The processor(s) determines a smallest number of the principal components that yields a pre-defined level of validation accuracy. The processor(s) generates a predictive model, by utilizing the smallest number for a best fit in a logistic regression model. The predictive model provides binary outcomes.

Abstract: A method, system, and computer program product are provided for generating a predictive model. A processor(s) obtains a raw data set (peptide libraries) of patients designated as diagnosed/pre-diagnosed with a condition or not diagnosed with the condition. The processor(s) segments the raw data set into a pre-defined number of groups and separates out a holdout group. The processor(s) performs a principal component analysis on the remaining groups to identify, based on a frequency of features in the remaining groups, common features (principal components) in the remaining groups and weighs the common features based on frequency of occurrence. The processor(s) determines a smallest number of the principal components that yields a pre-defined level of validation accuracy. The processor(s) generates a predictive model, by utilizing the smallest number for a best fit in a logistic regression model. The predictive model provides binary outcomes.

Abstract: Systems and methods for protecting information used to train a machine learning system are described herein. In an embodiment, first data identifying one or more status values of a plurality of personal data records are been sent to a server computer from a processor server and stored in a de-identified manner through a generation of a unique identifier for each personal data record using a unique identifier generation scheme and encrypted using an encryption scheme. Second data comprising a plurality of attributes for each of the plurality of personal data records are also sent to the server computer from a database and stored in a de-identified manner through a generation of the unique identifier for each personal data record using the unique identifier generation scheme and encrypted using the encryption scheme. An external server transmits, to the server computer, instructions to generate a machine learning system and to train the machine learning system using the first data and the second data.

Abstract: Systems and methods are provided for implementing safety-aware artificial intelligence (AI) that can be used for autonomously controlling systems, such as an autonomous vehicle, in a manner that is proven to satisfy given safety constraints. Additionally, a safety-aware training technique can be applied to learned AI-based models, such as neural networks. The safety-aware training techniques can apply automated reasoning tools (ART) while the AI model is trained, in order to produce a model that is provable safe with respect to the safety constraints. The ART can integrate verification into the training process, and thereby dynamically re-train the model based on the safety verification in a feedback loop approach. The ART can be configured to either verify that the AI model is provably safety, or to provide updates to the training parameters used during to re-train the AI model in instances when the safety verification has failed.

Abstract: A method for determining isothermal phase behavior for reservoir simulation includes generating a training data set using negative flash calculations, training a first machine learning algorithm to identify a supercritical phase and a subcritical phase, training a second machine learning algorithm to identify a number of stable phases in the subcritical phase, and training a third machine learning algorithm to determine a phase split of the subcritical phase that has more than one identified stable phase.

Abstract: Media items associated with status values are stored using a server in a protected environment. A device outside the protected environment requests sending media items to a client device that is also outside. Using machine learning systems that can be trained using attribute values associated with personal data records to output the existence of a status value, the server computer trains a particular machine learning system in the protected environment only if specified data meets specified criteria, then sends the resulting trained ML system to the requesting device. That device evaluates the trained ML system to determine which media items to deliver to the client device in the manner set forth in the claims.

Abstract: In some embodiments, techniques are provided for improving the detection of repeated actions during the manipulation of tabular data in order to enable the creation of automated action sequences. Activity log records are created that represent actions taken with respect to a set of tabular data. One or more normalized versions of the activity log records may be created. The activity log records (and, in some embodiments, the normalized versions of the activity log records) may be grouped and hashed together, such that groups of activity log records may be compared to each other by comparing the resulting hashes. Grouping and hashing may allow large numbers of comparisons to be made efficiently enough to support detection of repeated actions on large scale, multi-user, and multi-tenant systems.

Abstract: An image recognition method is provided. The method includes obtaining predicted locations of joints of a target person in a to-be-recognized image based on a joint prediction model, where the joint prediction model is pre-constructed by: obtaining a plurality of sample images; inputting training features of the sample images and a body model feature to a neural network and obtaining predicted locations of joints in the sample images outputted by the neural network; updating a body extraction parameter and an alignment parameter; and inputting the training features of the sample images and the body model feature to the neural network to obtain the joint prediction model.

Abstract: The invention refers to a natural language processing system configured for receiving an input sequence ci of input words (v1, v2, . . . vN) representing a first sequence of words in a natural language of a first text and generating an output sequence of output words (, , . . . ) representing a second sequence of words in a natural language of a second text and modeled by a multinominal topic model, wherein the multinominal topic model is extended by an incorporation of language structures using a deep contextualized Long-Short-Term Memory model.

Abstract: The present system and method may generally include organizing the task flow of a virtual agent in a way that is controlled by a set of rules and set of conditional probability distributions. The system and method may include receiving a user utterance including a first task, identifying the first task from the user utterance, and obtaining a set of rules related to the plurality of tasks. The set of rules may determine whether pre-tasks and/or pre-conditions are to be executed before executing the first task. The set of rules may also determine whether post-tasks and/or post-conditions are to be executed after executing the first task. The system and method may include executing the task; running a probabilistic graphical model on the plurality of tasks to determine a second task based on the first task; suggesting to the user the second task; and updating the probabilistic graphical model after a threshold number of runs.

Abstract: Blockchain based IoT data management can include receiving IoT data are with one or more processing units. At least one aggregation pattern of the IoT data can be determined by one or more processing units. The IoT data can be hashed, based upon the at least one aggregation pattern to obtain hash values of the IoT data by one or more processing units. The hash values can be sent to a blockchain system for storing by one or more processing units.

Abstract: There is provided a method of operating a certifying node to certify incremental trained machine learning (ML) models of one or more edge devices associated with a peer to peer network. The method includes (i) generating a predictive outcome value for a test data set by executing a candidate ML model against the test data set available to the certifying node; (ii) determine a measure of quality of the candidate ML model by matching the predictive outcome value of the candidate ML model with an actual outcome value of the test data set; and (iii) certify the candidate ML model by comparing the measure of quality of the candidate ML model against a threshold error value, for use in real time incremental training by the one or more edge devices of the peer to peer network.

Abstract: A method for optimizing network decision nodes is described. In one embodiment, the method includes generating an initial network of decision nodes constructed according to one or more rules, rearranging one or more decision nodes of the initial network based at least in part on a conversion of the one or more rules to a disjunctive normal form, analyzing the rearranged network of decision nodes in an upstream direction, and optimizing the rearranged network by merging two or more decision nodes of the rearranged network based at least in part on the analysis of the rearranged network. In some cases, the decision nodes include one or more levels of parent nodes and child nodes, each level of child nodes being connected to respective parent nodes. In some cases, the upstream direction is in a direction from the child nodes to the parent nodes.

Abstract: Embodiments of the present invention provide a computer-implemented method for performing unsupervised time-series feature learning. The method generates a set of reference time-series of random lengths, in which each length is uniformly sampled from a predetermined minimum length to a predetermined maximum length, and in which values of each reference time-series in the set are drawn from a distribution. The method generates a feature matrix for raw time-series data based on a set of computed distances between the generated set of reference time-series and the raw time-series data. The method provides the feature matrix as an input to one or more machine learning models.

Abstract: An advanced intelligence engine (AIE) for use in identifying what may be complex events or developments on one or more data platforms or networks from various types of structured or normalized data generated by one or more disparate data sources. The AIE may conduct one or more types of quantitative, correlative, behavioral and corroborative analyses to detect events from what may otherwise be considered unimportant or non-relevant information spanning one or more time periods. Events generated by the AIE may be passed to an event manager to determine whether further action is required such as reporting, remediation, and the like.