Abstract: Systems and methods are provided for managing organizational or corporate structures, including the employee roles or activities administered by human resources. A portion of the role datasets received within human resource records may be used to generate role tokens comprising unique datasets that have been truncated and deduped. Such tokens may be extracted based on assigned prioritization scores, and further assigned training labels representing categorical levels. Predictive labels may be assigned to a remaining portion of the extracted tokens via a logistic regression classifier, and a model organizational dataset may be generated based on the assigned training labels and the assigned predictive labels. The prediction certainty of the role tokens in the model organizational dataset may be used to map the identified role tokens to the roles represented in the human resource records.

Abstract: Systems and methods are provided for managing organizational or corporate structures, including the employee roles or activities administered by human resources. A portion of the role datasets received within human resource records may be used to generate role tokens comprising unique datasets that have been truncated and deduped. Such tokens may be extracted based on assigned prioritization scores, and further assigned training labels representing categorical levels. Predictive labels may be assigned to a remaining portion of the extracted tokens via a logistic regression classifier, and a model organizational dataset may be generated based on the assigned training labels and the assigned predictive labels. The prediction certainty of the role tokens in the model organizational dataset may be used to map the identified role tokens to the roles represented in the human resource records.

Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for test cycle optimization using contextual association mapping. In one aspect, a method includes obtaining an artefact that includes a collection of reference items, where each reference item includes a sequence of words, generating candidate tags from each of the reference items based on the sequences of words in the reference items, selecting a subset of the candidate tags as context tags based on an amount that the candidate tags appear in the reference items, obtaining a sample item that includes a sequence of words, identifying a subset of the context tags in the sequence of words in the sample item, and classifying a subset of the reference items as contextually similar to the sample item based the context tags that were identified.

Abstract: A customer assistance guidance system includes an interface for communicating information to a customer relationship management (CRM) system. The system receives state information from the CRM system that defines a current interaction state between an agent of the CRM system and a customer. The system may predict, based on the state information, a next interaction state between an agent of the CRM system and the customer. The system may communicate the predicted next interaction state to the CRM system to facilitate the suggestion of a next course of action for the agent to perform.

Abstract: An image retrieval system may receive an image query that includes image data. The image retrieval system may determine an image descriptor based on the image data. The image retrieval system may obtain a text descriptor associated with the image descriptor in the descriptor repository. The image retrieval system may generate a document query comprising a search parameter, the search parameter including the text descriptor. The image retrieval system may identify, in a document database, text documents based on the document query. The text documents may be associated with document identifiers. The image retrieval system may obtain, from the file mapping repository, image identifiers associated with the document identifiers. The image query result from the image retrieval system may reference images associated with the image identifiers.

Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for helping service providers. The methods, systems, and apparatus include actions of obtaining a mobile computing device identifier, identifying a customer corresponding to the mobile computing device identifier, obtaining information regarding the customer that is identified, determining a likely intent of the customer from the information regarding the customer, and providing, using the likely intent of the customer, information that helps a provider.

Abstract: Implementations include determining a set of routes for delivery of assets within a delivery network based on realized and forecasted demand for a period, during at least partial execution of the set of routes, receiving real-time data representative of delivery of assets, and updated demand forecasts, determining, by an optimization controller, a time-to-trigger, and a cut-off time, and an updated demand forecast, the time-to-trigger defining an interval, at which the set of routes for delivery of assets is to be reoptimized, in response to the time-to-trigger being achieved, re-optimizing, by a route optimization module of the continuous delivery platform, the set of routes to provide a revised set of routes, and conveying at least one route of the revised set of routes to a delivery personnel, the at least one route being different from any route in the set of routes, and being executed during the period.

Abstract: A distributed computing design system facilitates the creation and deployment of complex data and mathematical models. In one implementation, the system generates a graphical user interface of a visual distributed computing design workspace. The visual distributed computing design workspace includes a node palette comprising individually selectable nodes, each with a graphical representation and corresponding to a distributed computing function available on a pre-determined target distributed computing cluster, a linking tool for establishing connection links between the individually selectable nodes, and a digital canvas.

Abstract: Systems and methods are provided for managing organizational or corporate structures, including the employee roles or activities administered by human resources. A portion of the role datasets received within human resource records may be used to generate role tokens comprising unique datasets that have been truncated and deduped. Such tokens may be extracted based on assigned prioritization scores, and further assigned training labels representing categorical levels. Predictive labels may be assigned to a remaining portion of the extracted tokens via a logistic regression classifier, and a model organizational dataset may be generated based on the assigned training labels and the assigned predictive labels. The prediction certainty of the role tokens in the model organizational dataset may be used to map the identified role tokens to the roles represented in the human resource records.

Abstract: A system may parse a group of manuscripts to extract manuscript properties and textual data included in each respective manuscript. The system may perform computer based identification of a predetermined category in which each respective manuscript resides and generate a categorized inventory of log entries, which include the manuscript properties and the textual data as respective field values. Each of the log entries may be representative of one of the manuscripts and may be categorized in the categorized inventory of log entries according to the predetermined category. The system may generate derived field values in at least some of the log entries. The derived field values may be indicative of at least some of the respective field values. The system may generate an architectural computer based dimensional mapping of a categorized inventory of log entries based on the relational association among the respective field values and the derived field values.

Abstract: Examples of a process optimization system are provided. The system may obtain a query from a user and process data associated with the query from a plurality of data sources. The system may identify a plurality of factors and a target variable from the process data. The system may identify a factor range for the plurality of factors. The system may deconstruct the factor range to identify a plurality of data partitions. The system may identify a data pruning activator based on the plurality of data partitions and a preponderant data partition therefrom. The system may identify a plurality of clusters associated with the preponderant data partition. The system may identify a preponderant cluster from the plurality of clusters. The system may identify a confidence score associated with the preponderant cluster. The system may generate a process optimization result based on the preponderant cluster and the confidence score.

Abstract: A domain-specific question answering system receives an end-user's question, identifies relevant information from domain-specific documents, composes a natural-language based response including the relevant information to be provided to the end-user. A knowledge base includes a domain-specific ontology and is built from data structures configured to preserve the hierarchy of the informational elements within the domain-specific documents. The question received from the end-user is analyzed to extract the features and the key phrases which are used to identify the relevant data structures. A pre-trained model that is further trained on domain-specific data is used to identify the sentences that include information responsive to the question. A response to the end-user's question is composed from the sentences. The question answering system also enables validation of the answers provided to the users' questions.

Abstract: A system may receive a request to perform a token exchange between a first account and a second account. A selected token for the token exchange may be associated with the first account. A hash of the selected token may be stored on a furnisher blockchain of a first distributed ledger. The system may generate a new token and a hash of the new token. The system may generate a shielded exchange instruction, the shielded exchange instruction comprising the hash of the new token and a zero-knowledge proof, wherein the zero-knowledge proof is indicative of the selected token being associated with the first account. The system may submit the shielded exchange instruction to a distributed ledger technology platform to cause execution of a furnisher smart contract and a receiver smart contract. Each of the smart contracts are configured to separately verify the zero-knowledge proof and update corresponding blockchains to consummate and record the token exchange.

Abstract: In some implementations, a system may generate information that identifies a passphrase to be used as a biometric input. The system may receive a voice input of a user speaking the passphrase. The system may generate one or more cryptographic keys based on the voice input. The system may generate a digital identifier based on the one or more cryptographic keys. The system may generate one or more biometric templates for the user. The system may encrypt the one or more biometric templates using the one or more cryptographic keys and to generate one or more encrypted biometric templates. The system may store in a secure storage associated with the user, at least one of the digital identifier, a public key of the one or more cryptographic keys, a phone number associated with the user, or the one or more encrypted biometric templates. Numerous other aspects are provided.

Abstract: A system may facilitate distributed ledger technology (DLT) record based (for example, blockchain-based) voting. A voter may distribute vote-value to answers using committed tokens that bind the voter to a particular vote-value without divulging the particular vote value while in a cryptographic form. The voter may distribute committed tokens to multiple answers. In some cases, the distribution of the committed tokens to multiple answers may frustrate attempts to determine the one or more targets to which the voter delivers a non-null vote-value.

Abstract: A robotic operations control system enables seamless distribution of tasks among a blended workforce that includes human employees and robot assistants. The robot assistants include an intelligent billing assistant (IBA), an intelligent collections assistant (iNCA), a dispute resolution assistant (DRA) and a cash processor. Each of the assistants includes a workflow manager that receives work items to be processed by the robot assistant based on the priority levels assigned to the work items. The IBA includes a dispute prediction model that predicts the likelihood of dispute for a work item and automatically generates a customized checklist. The iNCA includes an AI prioritizing assistant that identifies priorities for work items to be processed. The DRA includes an AI assisted investigator that expedites investigations of disputes by proactively gathering information for a human employee to review and mark the dispute as valid, invalid or for query.

Abstract: A system includes a security controller located within a central-zone in communication with a provisioned agent operating on an edge-zone device. The security controller may implement controller-blind security control on the edge-zone device by making security authorization determinations using a secure-operation confidence analysis performed by the provisioned agent. The provisioned agent, operating within the edge-zone, may have access to un-sanitized data, which may be unavailable to the security controller in the central-zone. The security controller may provide condition-descriptors via a secure-operation confidence assignment matrix. Using the condition-descriptors, the provisioned agent determine feedback, which may include a secure-operation confidence coefficient, based on the un-sanitized data to which the security controller is blind.

Abstract: In some examples, recruitment process graph based unsupervised anomaly detection may include obtaining log data associated with a recruitment process for a plurality of candidates, and generating knowledge graphs and graph embeddings. The graph embeddings may be trained to include a plurality of properties such that graph embeddings of genuine candidate hires and fraudulent candidate hires are appropriately spaced in a vector space. The trained graph embeddings may be clustered to generate a plurality of embedding clusters that include a genuine candidate cluster, and a fraudulent candidate cluster. For a new candidate graph embedding for a new candidate, a determination may be made as to whether the new candidate graph embedding belongs to the genuine candidate cluster, to the fraudulent candidate cluster, or to an anomalous cluster, and instructions may be generated to respectively retain or suspend the new candidate.

Abstract: In some examples, data classification and modelling based application compliance analysis may include generating, for application data for an application, and based on data laws, a knowledge graph schema that is used to generate an instantiated knowledge graph. Based on a plurality of data sources, domain knowledge and patterns, and the instantiated knowledge graph, classified data may be generated to generate an annotated knowledge graph. Based on the annotated knowledge graph, an indication of applicable sovereign laws and compliance related to the application data for the application may be generated. Based on the annotated knowledge graph and the applicable sovereign laws and compliance related to the application data for the application, a sovereign cloud strategy related to the application data for the application may be generated. Further, the sovereign cloud strategy may be applied to the application data for the application.

Abstract: A device may receive data associated with customers, a customer-related process, or customer-related operations of an organization. The device may process the data using a technique. The device may map the data to an organization operating model. The organization operating model may be used to perform an analysis to identify a deficiency related to the customers, the customer-related process, or the customer-related operations, or a first manner in which to improve a customer-channel combination, the customer-related process, or the customer-related operations. The device may perform the analysis of the data. The device may identify the customer-channel combination of the organization. The customer-channel combination may identify a channel via which the organization acquires, engages, or retains the customers.