Abstract: Systems, methods, and computer-readable storage media for building knowledge graphs which map the aspects of entities, then transforming the graphs into vectors for a similarity comparison. The resulting vectors can be used to identify skills and competencies of individuals, which the system uses to compare those individuals to others. The system can then quantify who would make for a good replacement for a given individual and make an associated recommendation.

Abstract: A method receives an electronic image and uses the image as an input to a neural network. Based on a determination that the image represents a document, the method uses the image as an input to another neural network to identify a portion of the document containing an identifier. The method extracts the identifier by performing character recognition on the identified portion and determines whether the identifier is valid by using a validation API to determine whether the identifier is associated with a valid account at an institution. Based on a determination that the identifier is associated with a valid account, the method authorizes a transaction associated with the identifier. Based on a determination that the identifier is not associated with a valid account, the method denies the transaction. The first neural network classifies the electronic image into one of multiple valid document types and an invalid document type.

Abstract: The technical solutions described herein relate to a method, system, and non-transitory computer-readable medium for forecasting (e.g., predicting) and reporting trends in crime. A method includes: filtering, by one or more processors coupled with memory, employment data and act data for a plurality of locations; identifying, by the one or more processors using a machine-learning model trained on a historic employment data and historic act data, a relationship between the employment data and the crime data; predicting, by the one or more processors based on the relationship identified by the machine-learning model, trends in acts for the plurality of locations; and generating, based on the predicted trends, a request for a preventive measure in a first location of the plurality of locations.

Abstract: A method of latent intent clustering is provided. The method comprises encoding identified features in a number of electronic user reports in a database. A binary matrix is created, wherein each row of the binary matric represents a different report and each column represents a different available feature. A 1 is placed in each cell of the matrix that matches a feature present in a user report. Cosine similarities are calculated for the user reports, and a similarity matrix is created, wherein each row and column of the binary matrix represents a different report, and wherein the cosine similarities of the reports are placed in corresponding cells of the matrix. The reports are clustered according to the cosine similarities. Features common to reports in each cluster are identified, and an intent of each report cluster is labeled according to the common features.

Abstract: A method, computer system, and computer program manage revisions in a document. The document is displayed in a graphical user interface. The document comprises a structured data object composed from a set of tiles, wherein each tile corresponds to one or more data nodes. The tiles are composable according to a domain-specific language of an integrated development environment. One or more revisions to the structured data object are received in sequence. The revisions to each data node of the set of tiles composing the structured data object are independently managed, enabling each revision to be independently reverted to a prior state irrespective of the sequence and revisions to other data nodes of the set of tiles and without reverting the other data nodes of the structured data object to their prior state.

Abstract: A method, apparatus, system, and computer program code for onboarding client information for provisioning multiple software services. On a first page of the graphical user interface, client location data is received in a consolidated manner for the multiple services. Within the first page of the graphical user interface, each of the multiple software services is configured using a plurality of guided question. The client location data is organized according to Federal Employer Identification Number. Groups of client location data, organized per FEIN, are displayed on a second page of the graphical user interface, providing an easier onboarding process that reduces no-starts and enables a client to onboard services more quickly and accurately.

Abstract: Data digitization via custom integrated machine learning ensembles is provided. For example, a system integrates multiple trained machine learning ensembles to identify, extract, and map data. The system receives a data set from sources. The system identifies ensembles can include machine learning models that can determine an outcome. The system filters a subset of data from the data set. The system identifies a layout for the data set based on a vendor type, data type, and the data set. The system executes a block detection module to identify blocks of the layout. The system executes a header detection module. The system executes a policy detection module to identify the headers as policies. The system transforms, based on the headers, the layout, the blocks, and the policies, the data set into a second file type, and presents the transformed data set for integration into a capital management system.

Abstract: A system for processing employment documents includes one or more processors, coupled with memory. The one or more processors are configured to receive an input document, determine that the input document is associated with a first field and a second field, extract a first extracted text string corresponding to the first field and a second extracted text string corresponding to the second field, generate a first generated text string associated with the first field based on the first extracted text string, and generate a second generated text string associated with the second field based on the second extracted text string.

Abstract: Aspects of the present disclosure relate to distributed transactions over a broadcast communication channel within a microservices environment. In embodiments, a method includes: receiving a request to process distributed transactions input in a data schema in order to perform a task of an application in a cloud computing environment; broadcasting to a plurality of microservices a multicast message requesting availability to execute the distributed transactions in the data schema; receiving confirmation of preparation from at least one of the plurality of microservices to execute one or more of the distributed transactions in the data schema; sending at least one unicast message to the at least one of the of the plurality of microservices to execute the one or more of the distributed transactions in the data schema; and receiving an acknowledgement of the execution of each of the distributed transactions in the data schema.

Abstract: A method, apparatus, system, and computer program code for automatic data retrieval and validation. A computer system generates an audit file including a set of data objects. The computer system validates the data objects with a compliance policy by deploying a set of software bots to interact at a user level with a set of application programs. In response to validating the data objects, the computer system reflects validation results into a user interface.

Abstract: Aspects extract, from payroll data of employees of an organization, data historically associated to previous instances of certified tax credit eligibility; normalize the extracted data with respect to data type and data value; generate from the normalized extracted data via a neural network classifier multi-class outputs for each employee that indicate strengths of likelihood that each employee is currently eligible for each of a plurality of different tax credits; filter the normalized extracted data by removing portions associated to employees indicated within the multi-class outputs as having no currently eligible likelihood for the different tax credits, thereby generating a remainder set of normalized extracted data associated to remainder eligible ones of the employees; and prioritize application for the tax credits for the remainder eligible employees as a function of respective values and likelihoods of eligibility within the remainder set of normalized extracted data.

Abstract: Carbon emission reduction using machine learning is provided. A system receives data for profiles linked with locations of an entity. The system determines, based at least in part on data from a utility service provider system and the data indicative of energy consumption associated with the locations, a first value of a metric indicative of carbon emissions associated with the locations. The system determines, based on a comparison of the first value of the metric with a threshold, to invoke an automated process via the payroll processing system to reduce the metric. The system generates, generate, using one or more models trained with machine learning, an action to execute via the automated process. The system selects a first profile from that is compatible with the action, and commands the payroll processing system to execute the generated action to cause a reduction in the first value of the metric.

Abstract: A system can receive, from a client device, a request to execute an automatic repeating network operation using a profile data structure. The system can query a database to retrieve multiple source identifiers and corresponding computing infrastructure identifiers. The system can cause the client device to present a user interface comprising an interface object for each of the source identifiers. The interface object can be configured to display configurations for the automatic repeating network operation associated with a respective source identifier. The system can receive interactions corresponding to partial switches for the automatic repeating network operation for at least two of the multiple source identifiers. The system can generate one or more executable commands to cause a payroll processing system to update the profile data structure based on the interactions. The system can execute the automatic repeating network operation in accordance with the updated profile data structure.

Abstract: Analyzing chatbot/employee dialogs is provided. An analysis of a dialog between a chatbot manager and a plurality of employees regarding a current corporate topic is performed using an artificial intelligence component. Relevant information regarding the current corporate topic is extracted from the dialog based on the analysis. Insights corresponding to the relevant information regarding the current corporate topic are generated using the artificial intelligence component. The relevant information regarding the current corporate topic and the insights are displayed in a dashboard on a client device of a human resource agent.

Abstract: Configuring computing devices based on geographic pattern detection is provided. A system provides a first mapping application on computing devices. The first mapping application can display an approximate location of each computing device of the computing devices. The system provides interactive interface elements to the computing devices. The interactive interface elements adjust the approximate location having a first resolution to an actual location having a second resolution that is greater than the first resolution for each of the computing devices. The system receives the adjustments to the approximate locations, and categorizes an actual location received from the computing devices to generate a consolidated view of the actual location for each respective computing device. The system displays, via a second mapping application, a consolidated view of the actual locations of the computing devices.

Abstract: A system can include one or more processors coupled with memory. The one or more processors can determine that a first collection of resources is coupled with the first entity, detect that a second collection of resources has been decoupled from a second entity, cause a user interface to display a first element configured to receive an input to cause an aggregation of the second collection of resources into the first collection of resources based on the first collection of resources being coupled with the first entity, retrieve an electronic form associated with the aggregation of the second collection of resources into the first collection of resources, cause the user interface to display a second element configured to receive information for one or more fields included in the electronic form, and transmit one or more signals to provide the electronic form to a third entity.

Abstract: Dynamic session headers for a computing session via a remote dictionary are provided. A system establishes a session responsive to receiving a first request from a browser, the session authenticated using a cookie configured to access a first electronic record. The system stores data corresponding to the session in a remote dictionary server. The system identifies a second request to modify the session to access a second electronic record and accesses, using the cookie, the data corresponding to the session from the remote dictionary server. The system receives, using a reverse proxy technique, data to update the session. The system modifies the session by storing the second identifier in the remote dictionary server and provides the browser with access to the second electronic record via the session.