Abstract: In a remote technical support system, a technical support controller receives an indication of a maximum number of support sessions to be serviced by a remote technician. Thereafter, the technical support controller receives a service request for a user device, which service request is classified into a category and added to a preliminary queue corresponding to the category. The technical support controller determines if handling of the service request by the remote technician would cause the number of support sessions currently being handled by the remote technician to exceed the previously-indicated maximum number of support sessions. If not, the service request is added to a work queue for the remote technician and removed from the preliminary queue.

Abstract: Implementations directed to managing resources executing in one or more RPA platforms, and include actions of receiving process data representative of two or more processes executed by resources in a RPA platform, and resource data representative of the resources in the RPA platform, determining a process rank for each of the two or more processes, respectively, for at least one process, calculating a number of resources required to complete the process in conformance with a SLA governing the process, and transmitting instructions through a platform adapter to provision at least one additional resource to execute the process within the RPA platform, the platform adapter being specific to the RPA platform, and being one of a plurality of platform adapters.

Abstract: A multi-layer resource aggregation (RA) stack may generate prescriptive activation timetables for controlling activation states for computing resources. To facilitate operator control and adjustment, the RA stack may, at an aggregation engine layer, aggregate the computing resource into one or more resource aggregates. The computing resources within the resource aggregates may have similar individual activation prescription patterns. Machine learning techniques may be used by the RA stack to identify these related individual activation prescription patterns and aggregate the computing resources accordingly. Once aggregated, the RA stack may make a uniform activation determination for the aggregates as single units. Therefore, the computing resources within the aggregate may be controlled and/or adjust together. Thus, the RA stack increases the scalability of implementation of prescriptive computing resource activation state determinations.

Abstract: A system and method for extracting structured information from image documents is disclosed. An input image document is obtained, and the input image document may be analyzed to determine a skeletal layout of information included in the input image document. A measure of similarity between the determined skeletal layout and each of the document templates may be determined. A document template may be selected as a matched template, based on the determined measure of similarity. Box areas from the input image document may be cropped out, and optical character recognition (OCR) may be performed on the box areas. Obtained recognized text may be automatically processed using directed search to correct errors made by the OCR. Statistical language modeling may be used to classify the input image document into a classification category, and the classified input image document may be processed according to the classification category.

Abstract: A system and method for filling containers with a precise amount of fluid is disclosed. The system and method use artificial neural network logic to sense conditions and to control the two-valve dispensing unit based on the sensed conditions to fill containers with a precise amount of fluid. Using neural network logic combined with sensors and controllers for equipment eliminates the significant human effort and human errors associated with manually filling containers with fluid. Furthermore, the neural network can log data quicker and with more accuracy than a human manually logging data. The system and method use a two-valve dispensing unit to precisely fill and to prevent and clear clogs caused by fluid solidifying within the dispensing unit.

Abstract: A system includes a blockchain operation stack which may control access to reading and writing operations for a blockchain. The blockchain operation stack may include a credential authority layer that may control permissions for profiles maintained by the credential authority layer. When the permissions are granted by the credential authority layer, a presentation layer may generate a display that may include information on the blockchain structure. The presentation layer may provide tools to facilitate write layer operations to rewrite and append to the blockchain.

Abstract: Implementations of the present disclosure include methods, systems, and computer-readable storage mediums for utilizing multiple AI service providers by a dialog management system. The dialog management system can include a dispatcher bot, multiple worker bots, and multiple AI adapters that are each associated with a different cloud-based AI service provider. In response to receiving a query, the dispatcher bot selects a particular worker bot to handle the query. The particular worker bot is assigned to a particular AI service provider. An AI adapter associated with the particular AI service provider, generates a query message based on the query. The AI adapter sends the query message to the particular AI service provider and receives a response message. The dialog management system sends a representation of the response message to the particular worker bot, receives an answer for the query from the particular worker bot, and provides the answer for output.

Abstract: Implementations include receiving, by a DDT platform, computer-readable files including test data, the test data including data to execute at least one transaction during testing of a software system that is at least partially hosted by a vendor back-end system, the software system being configured for customer use, providing, by the DDT platform, one or more test scenarios for execution by the software system on the vendor back-end system, the one or more test scenarios including a set of activities to conduct transactions by the software system using at least a portion of the test data, scheduling, by a scheduler of the DDT platform, execution of the one or more test scenarios using a test harness of the DDT platform, receiving, by the DDT platform, test results from the vendor back-end system, and comparing, by the DDT platform, the test results to expected results to provide a comparison as output.

Abstract: Implementations are directed to methods, systems, apparatus, and computer programs for generation of a three-dimensional (3D) animation by receiving a user input defining a two-dimensional (2D) representation of a plurality of elements, processing, by the one or more processors, the 2D representation to classify the plurality of elements in symbolic elements and action elements, generating, by the one or more processors, based on the symbolic elements, the action elements, and a set of rules a 3D animation corresponding to the 2D representation, and transmitting, by the one or more processors, the 3D animation to an extended reality device for display.

Abstract: A device receives images of a field on a farm, and filters the images of the field to generate filtered images. The device isolates planting lanes in the filtered images, where the planting lanes include lanes formed by crops in the field, and the planting lanes are isolated via a masking technique or a sliding windows technique. The device identifies plant gaps in the planting lanes, where the plant gaps correspond to portions of the planting lanes that are missing crops, the plant gaps are identified based on a heat map when the masking technique is utilized to isolate the planting lanes, and the plant gaps are identified based on sliding windows when the sliding windows technique is utilized to isolate the planting lanes. The device superimposes the plant gaps over the images to generate a visual representation of stressed areas in the field, and performs an action based on the visual representation of the stressed areas.

Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for controlling access to physical areas. One of the methods includes receiving first data, determining, using the first data, whether each of the passengers for a vehicle is authorized to cross a border, storing second data in a data set of pre-registered border crossers, receiving third data identifying the vehicle and indicating entry of the vehicle into a border crossing station, comparing the third data with data from the data set of pre-registered border crossers, determining that the third data and the second data both identify the vehicle, collecting, for each current passenger in the vehicle, fourth data representing the current passenger, determining whether the current passengers in the vehicle and the passengers identified in the second data are the same people, and providing instructions to guide the vehicle to a lane at the border crossing station.

Abstract: A device may perform a static analysis of a codebase associated with a software application to determine a structure of the codebase and one or more metrics associated with the codebase. The device may generate a structured format of the codebase based on the structure of the codebase. The device may generate a domain specific language format of the codebase based on the structured format of the codebase and the one or more metrics associated with the codebase. The device may generate an extended reality rendered view of the domain specific language format of the codebase. The device may provide, to an extended reality device, the extended reality rendered view of the domain specific language format of the codebase.

Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for generating multiple distinct test plans using a computing system. The system merges the each of the test plans to produce a first test plan and obtains performance data about automated execution of the first test plan by a robotics system. The system generates learned inferences for determining predictions about execution of the first test plan based on analysis of the performance data and adjusts the first test plan based on the learned inferences. The system generates a second test plan for execution by the computing system based on adjustments to the first test plan and performs the second test plan to test multiple devices using the robotics system.

Abstract: A device may receive data associated with an event. The device may identify a context of the event based on receiving the data. The device may identify a similar event based on performing a comparison of the context of the event and a context of the similar event. The device may determine a set of pre-events associated with the event based on identifying a pre-event that occurred before the similar event. The set of pre-events may include at least one pre-event similar to the pre-event that occurred before the similar event. The device may determine a set of post-events associated with the event based on determining the set of pre-events and identifying a post-event that occurred after the similar event. The set of post-events may include at least one post-event similar to the post-event. The device may perform an action based on the set of post-events.

Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for detecting higher level events based on lower level events. In one aspect, a method includes receiving a stream model that defines elements of a data domain. A stream mapping that defines sensor identifiers for real-world sensors and associates each sensor identifier with a respective element of the data domain is received. A user-specified stream matching pattern is received. The stream matching pattern specifies respective sensor identifiers of sensor identifiers of the real-world sensors, and for each sensor identifier, a tuple of data elements of the stream model and, for each tuple of data elements, co-occurrence criteria including at least one time window. A stream of events is obtained from the real-world sensors. A determination is made that two or more events co-occur within the time window and whether the one or more co-occurrence criteria are satisfied.

Abstract: A system and method to detect fraudulent documents is disclosed. The system uses a generative adversarial network to generate synthetic document data including new fraud patterns. The synthetic document data is used to train a fraud classifier to detect potentially fraudulent documents as part of a document validation workflow. The method includes extracting document features from sample data corresponding to target regions of the documents, such as logo regions and watermark regions. The method may include updating a cost function of the generators to reduce the tendency of the system to generate repeated fraud patterns.

Abstract: Complex computer system architectures are described for analyzing data elements of a knowledge graph, and predicting new surprising or unforeseen facts from relational learning applied to the knowledge graph. This discovery process takes advantage of the knowledge graph structure to improve the computing capabilities of a device executing a discovery calculation by applying both training and inference analysis techniques on the knowledge graph within an embedding space, and generating a scoring strategy for predicting surprising facts that may be discoverable from the knowledge graph.

Abstract: The systems and methods described herein may generate multi-modal embeddings with sub-symbolic features and symbolic features. The sub-symbolic embeddings may be generated with computer vision processing. The symbolic features may include mathematical representations of image content, which are enriched with information from background knowledge sources. The system may aggregate the sub-symbolic and symbolic features using aggregation techniques such as concatenation, averaging, summing, and/or maxing. The multi-modal embeddings may be included in a multi-modal embedding model and trained via supervised learning. Once the multi-modal embeddings are trained, the system may generate inferences based on linear algebra operations involving the multi-modal embeddings that are relevant to an inference response to the natural language question and input image.

Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for a touchless testing platform employed to, for example, create automated testing scripts, sequence test cases, and implement determine defect solutions. In one aspect, a method includes the actions of receiving a log file that includes log records generated from a code base; processing the log file through a pattern mining algorithm to determine a usage pattern; generating a graphical representation based on an analysis of the usage pattern; processing the graphical representation through a machine learning algorithm to select a set of test cases from a plurality of test cases for the code base and to assign a priority value to each of the selected test cases; sequencing the set of test cases based on the priority values; and transmitting the sequenced set of test cases to a test execution engine.

Abstract: A system may receive, from a first device associated with a patient, a request for an ambulance. The system may determine, based on a location associated with the first device, an available ambulance to be dispatched to the patient. The system may provide, to a second device associated with an ambulance operator of the available ambulance, information that identifies the location associated with the first device. The system may identify a hospital to which the patient is to be delivered. The system may provide, to a third device associated with the hospital, information associated with the available ambulance or the patient.