Abstract: The disclosed system and method for software testing provide a strategy for testing new software functionalities in a sequence that detects defects according to a testing strategy designed to accomplish a predetermined objective. Providing a pre-testing stage generates test execution results for test cases designed to find defects related to new functionalities. Using machine learning clustering techniques to identify which test cases are similar to one another facilitates organizing test cases in a sequence appropriate for accomplishing a predetermined objective.

Abstract: A device may receive site data identifying a site associated with a telecommunications network. The device may receive RF drive test data identifying signal strengths of the site at different location points. The device may receive network KPI data and throughput data associated with the site. The device may assign unique identifiers to the different location points. The device may determine, based on the site data, the RF drive test data, the network KPI data, and the unique identifiers, at least one of reference signal strength data for each of the different location points or downlink channel data for each of the different location points. The device may determine degraded signal strength data identifying a degraded signal strength of each of the different location points, if the site is decommissioned and based on the at least one of the reference signal strength data or the downlink channel data.

Abstract: Automated computing machinery that agnostically augments a customer relationship management (“CRM”) application, including an agent hub comprising a module of the automated computing machinery configured with computer memory that associates an identity of a tele-agent, the tele-agent's qualifications, and an indication whether the tele-agent is logged on to the agent hub; and the agent hub operatively coupled for data communications to a browser, the browser bearing a browser extension through which a sales template for a sales campaign to which the tele-agent is assigned to work is operatively exposed as an overlay upon a graphical user interface of the browser, the overlay overlaid upon a web page of the CRM application.

Abstract: A device may receive historical cloud data associated with resources of a cloud computing environment, and may receive historical customer data associated with requested resource usage by customers of the cloud computing environment. The device may determine a usage growth profile based on the historical cloud data and the historical customer data, and may determine, based on the historical cloud data and the historical customer data, usage deviation data indicating deviations between actual and planned resource usage. The device may train a model, with the usage growth profile and the usage deviation data, to generate a trained model, and may receive a request for new resource usage by a customer associated with the cloud computing environment. The device may process the request for the new resource usage, with the trained model, to generate projected resource usage data, and may perform actions based on the projected resource usage data.

Abstract: Methods, systems, and apparatus for transmitting qubits encoding quantum information with reduced risk of interception from an eavesdropper. In one aspect, a method includes encoding quantum information into an information qubit; encrypting the information qubit, comprising performing i) a parity operation on the information qubit and a parity control qubit and ii) a phase operation on the information qubit and a phase control qubit; performing, by a sender party, a sequence of one or more quantum logic gates on the phase control qubit; sending the information qubit, parity control qubit, and phase control qubit to a recipient party; and sending data identifying the sequence of one or more quantum logic gates to the recipient party, wherein the recipient party obtains the quantum information encoded into the information qubit using the information qubit, parity control qubit, phase control qubit, and data identifying the sequence of one or more quantum logic gates.

Abstract: A device may communicate with a client device to provide, via a user interface of the client device, a set of prompts regarding an entity. The device may detect one or more user interactions with the user interface associated with indicating a set of responses to the set of prompts. The device may process data identifying the set of responses to the set of prompts to generate a set of scores for a set of recommendations based on processing the data identifying the set of responses to the set of prompts. The device may determine a ranking of the set of recommendations based on the set of scores. The device may select one or the set of recommendations based on the ranking. The device may communicate with the client device to provide information associated with the set of recommendations based on selecting the set of recommendations.

Abstract: Complex computer system architectures are described for analyzing data elements of a knowledge graph, and predicting new facts from relational learning applied to the knowledge graph. This discovery process includes converting the knowledge graph into a set of candidate embeddings spaces to apply further analysis to rank the set of candidate embeddings spaces, where the top ranked candidate embeddings spaces are further processed to identify the new facts.

Abstract: Implementations include actions of providing a first transaction hash including a digital representation of a digital record between a first peer and a second peer within a digital records platform, the platform provided by the first peer as a host peer, and the transaction hash being generated based on one or more documents underlying the digital record, receiving one or more edits to at least one document from the second peer, updating the first transaction hash to provide: a second transaction hash, and a transaction hash history including the first transaction hash and the second transaction hash, receiving approval of the digital record from each of the first peer and the second peer, and executing a consensus protocol by a notary service of a third node to update transaction objects across the first node and the second node, the updating indicating that the transaction objects are consistent.

Abstract: A device may receive time series data from one or more data sources. The device may pre-process the time series data to generate a respective time series chart for multiple classifications included in the time series data. The device may randomly select a pair of respective time series charts and a correlation detection technique after pre-processing the time series data. The device may determine a correlation for the pair of respective time series charts based on using the correlation detection technique. The device may determine a score for the pair of respective time series charts based on the correlation of the pair of respective time series charts. The score may indicate an extent to which the pair of respective time series charts is correlated with each other. The device may perform one or more actions after determining the score for the pair of respective time series charts.

Abstract: This document describes multi-modal platforms that receive multi-modal inputs and generates interactive experiences based on the inputs. In one aspect, a method includes receiving input data comprising one or more images of an area of a sports venue. A person is detected in the one or more images. Apparel information including at least one of a team identifier or player identifier on athletic apparel of the person is identifier in the one or more images. An interactive experience that includes a particular sports-related character is selected based at least on the apparel information. The interactive experience is initiated on an interactive display. The interactive experience includes video of the particular sports-related character delivering a message to the person.

Abstract: A system and method for using, training, building, and managing a question and answer engine to automatically generate responses to an end-user is disclosed. Specifically, the method and system make use of a topic builder that uses cluster predictions to generate and identify a list of topics and subtopics. A question and answer database may then be sorted by topic and subtopic using a similarity scorer. New user utterances may be analyzed to identify questions, with a cluster predictor identifying the corresponding topic and subtopics for each question, and a similarity scorer may identify the closest known question for the user's question to a recommender as an answer. Analytics of new user utterances are tracked to update the historical utterance database and question and answer database, thus allowing continuous improvement of the engine.

Abstract: A system and method that improves the efficiency and accuracy of template selection process by applying machine learning to perform natural language processing (NLP) to automatically interpret the intent of the test scenarios and to match the intent of the test scenarios to appropriate test template(s). The system and method can use keyphrases and part-of-speech (POS) tokens to accurately capture the intent of test scenarios and templates. The system and method can additionally use machine learning to perform NLP to identify information from the test scenario(s) that relates to fields in templates to automatically fill in fields in the selected test template(s). In situations where the processing of the test scenario(s) does not provide all of the information necessary to fill every field of a template, the system and method can use machine learning to perform NLP to automatically create and execute a search statement to find the missing information related to empty fields in an application database.

Abstract: The disclosed intelligent virtual agent provides a single, unified platform for completing a variety of diverse complex business transactions including a series of interactions between multiple people and the performance of multiple tasks occurring at different points in time.

Abstract: Implementations are directed to detecting bypass of an authentication system of a web application with actions including receiving one or more webpage logs including web traffic associated with a web application during a defined time period, receiving one or more authentication logs associated with one or more authentication appliances providing authentication services for the web application, determining, based on the one or more webpage logs, one or more webpage log entries corresponding to a user and the defined time period, determining, based on the one or more authentication logs, a total number of correct authentication factors provided by the user during the defined time period, and determining, based on the one or more webpage log entries corresponding to the user and the defined time period and the total number of correct authentication factors provided by the user, that the user bypassed an authentication system of the web application.

Abstract: An artificial intelligence based system and method for predicting and preventing illicit behavior is disclosed. The system and method may include obtaining search strings used by multiple users, as well as the clickstream data of such users. The search terms included in the search strings may be preprocessed and analyzed for inclusion of suspicious words, e.g., words related to illicit behavior, provided in a corpus of suspicious words. Information associated with the search strings containing suspicious words may be analyzed to identify users associated with the same search strings. The clickstream of the identified users may be analyzed to determine whether the users are likely to engage in illicit behavior. Preventive measures may be taken to prevent such users from engaging in such illicit behavior.

Abstract: Implementations include receiving sample data, the sample data being generated as digital data representative of a sample of the product, providing a set of features by processing the sample data through multiple layers of a residual network, a first layer of the residual network identifying one or more features of the sample data, and a second layer of the residual network receiving the one or more features of the first layer, and identifying one or more additional features, processing the set of features using a CNN to identify a set of regions, and at least one object in a region of the set of regions, and determine a type of the at least one object, and selectively issuing an alert at least partially based on the type of the at least one object, the alert indicating contamination within the sample of the product.

Abstract: This document describes a computer-implemented method that includes receiving, over a network, at least one of text, audio, image, or video data associated with an entity of interest; identifying, based on the received data, a set of entity-specific candidate features; loading a feature library comprising a plurality of features that are each assigned to one or more feature spaces; and selecting, using a feature selection engine, one or more features from each of the feature spaces based on the set of entity-specific candidate features.

Abstract: Methods, systems, and apparatus, including computer programs encoded on computer-storage media, for performing autonomous self-healing of test scripts. One example process includes the actions of recording data that reflects user interactions with multiple user interface objects of a first user interface, and, for each interaction, generating a natural language statement that reflects an intent of the interaction with an associated user interface object. The process also includes storing the natural language statements in a test script, autonomously self-healing the test script for execution on a second user interface, and executing the autonomously self-healed test script on a second user interface.

Abstract: A system for issue prediction based on multidimensional data analysis includes a model generator that receives a resolved data item relating to a service issue. The resolved data item includes different attributes corresponding to multiple data dimensions and adjusts a population of attributes based on a statistical data model and a deep learning data model operating independent of each other. The statistical data model operates on the attributes for providing a predictive feature and the deep learning data model operates on the attributes for providing a predictive label based on performance metrics related to the data dimensions. The predictive feature and the predictive label collectively define training data. The model generator also trains a classification model based on the training data for predicting a potential issue related to an unresolved data item. The trained data model provides a trigger based on the potential issue being related to the performance metrics.

Abstract: The proposed system and method provide streamlined procedures for automatically identifying and resolving computing errors that improve efficiency and accuracy by providing a way to automatically monitor log files, automatically find and identify errors in the log files, automatically find solutions the identified errors from a variety of sources, and automatically implement the found solutions. The system and method further provide streamlined procedures that use cognitive learning (e.g., machine learning) to learn new solutions that are manually defined and implemented by a user to resolve the automatically found and identified errors, and then automatically finding and implementing the new solutions in subsequent cycles.