Abstract: A computerized method of routing customer interactions (call and chats) includes the following steps performed by a server computing device: creating a database with a document for every agent with a set of attributes identifying the types of customer interactions they service, receiving a set of call attributes associated with an incoming call; formulating a query of the call attributes against all agent profiles and returning a matching score for all available agents using Elastic Search; and routing the incoming call to a target agent with the highest score in the set of available agents, if there is at least one available agent; or a customer waiting queue, if there is no suitable agent achieving at least a minimum score.

Abstract: Systems and methods for identifying data strings in electronic documents using pattern recognition. The method includes receiving a first data string corresponding to an electronic reference document from a first database and a second data string corresponding to an electronic legal document from a second database. The method also includes processing the first data string into a first processed data string and processing the second data string into a second processed data string. The method also includes calculating a cosine similarity between the first processed data string and the second processed data string. The method also includes receiving a feedback score from a user which corresponds to an accuracy of the calculated cosine similarity. The method also includes calculating an adjusted cosine similarity between the first processed data string and the second processed data string based on the calculated cosine similarity and the feedback score.

Abstract: Methods and apparatuses are described for session-based data storage for chat-based communication sessions. A computing device connects to a data storage area associated with an active chat-based communication session, the data storage area comprising data storage slots. The computing device identifies a first data event during the chat-based communication session, the first data event comprising one of a data capture event, a data retrieval event, or a data prefill event. The computing device identifies a data storage slot in the data storage area corresponding to the first data event, the data storage slot comprising a slot name and a slot value. The computing device selects data elements associated with the chat-based communication session for insertion into the data storage slot based upon the event type of the first data event. The computing device stores the selected data elements in the data storage slot for retrieval during the chat-based communication session.

Abstract: Methods and apparatuses are described for automatic generation of specifications for data access layer application programming interfaces (APIs). A server identifies an object-oriented data model comprising (i) a plurality of object structures containing one or more data elements and (ii) one or more relationships between at least two of the object structures. The server generates an API specification package using the object-oriented data model by identifying object structures to include in the API specification package, defining attributes for the API specification package, assigning data access operations to each identified object structure, creating data relationships between at least two of the identified object structures, and converting the identified object structures, the defined attributes for the API specification package, the assigned data access operations, and the created data relationships into one or more files that comprise the API specification package.

Abstract: Methods and apparatuses are described for digital content classification and recommendation based upon reinforcement learning. A server converts unstructured text corresponding to each digital content item into a content item feature set. The server generates a user context vector associated with a plurality of users. The server trains a linear multi-armed bandit (MAB) classification model based upon the user context vectors and historical user content recommendation information. The server receives a new user context vector associated with a new user. The server executes the MAB model using the new user context vector as input to generate content interaction prediction scores. The server selects the content interaction prediction scores above a predetermined threshold and identifies the associated digital content item. The server presents the identified digital content items on a client device and receives a response. The server updates linear UCB coefficient vectors of the MAB model based upon the response.

Abstract: Systems and methods are described for automating retrieval of application data prior to wireless network outages and rendering mobile device UIs during the outages. The system includes a server and database of data object files corresponding to features of applications executable on the mobile device. The mobile device receives a notification from the server before a predicted network outage, and sends back a request including parameters indicating resource status. The mobile device receives a response including a data object file from the database and automatically invokes a network bot, UI bot, and navigation bot. The network bot retrieves application data from a web server based on an object from the data object file. The navigation bot generates a navigation handle based on an object from the data object file, and the UI bot renders a UI based upon a UI object from the data object file and the navigation handle.

Abstract: Methods and apparatuses are described for building a knowledge base taxonomy from structured or unstructured computer text for use in automated user interactions. A server computing device receives one or more of structured text or unstructured text corresponding to historical user interaction data from a database. The server computing device extracts one or more terms from the received text that are most relevant to a subject matter domain. The server computing device organizes the extracted one or more terms into a taxonomy data structure.

Abstract: Systems and methods for aggregating a dependency structure based on application logging data, application metadata, customer intent and journey, organizational structure, and operational support information. The method includes receiving data using an application programming interface. The method further includes, for each user, determining a start point and an end point corresponding to user activity on a networked system. The method also includes, for each user, determining a task based on the start point and end point corresponding to the user activity. The method further includes, for each user, determining operations data corresponding to the user activity. The method also includes, for each user, determining a dependency structure based on the task and the operations data. The method also includes aggregating the dependency structure, the task, and the operations data into a visualization. The method further includes generating for display the visualization on a user device.

Abstract: Methods and apparatuses are described for automatic execution of subscription-based financial instrument trading strategies in real-time. A server receives a request to deploy a trading strategy with trading strategy parameters. The server determines that a trading strategy has already been created for other users based upon the parameters. The server generates a subscription to the trading strategy, which comprises indicators needed to deploy the trading strategy. The server identifies at least one indicator that has already been calculated and calculates any of the indicators that have not already been calculated. The server deploys the trading strategy using the identified and calculated indicators.

Abstract: Systems and methods for authenticating a user using an interactive voice response application. The method includes receiving data representing a spoken voice utterance corresponding to a user of an interactive voice response application. The method further includes processing the data representing the spoken voice utterance based on a length and a quality of the spoken voice utterance. The method also includes comparing the processed data representing the spoken voice utterance and a voiceprint associated with the user. The method further includes generating a security token in response to determining that the processed data representing the spoken voice utterance substantially matches the voiceprint associated with the user. The method also includes receiving the security token from the interactive voice application and validating the security token corresponding to the user in response to determining that the security token matches a security token generated by a server computing device.

Abstract: The Shifting Substitution Cipher Based Efficient Vaultless Data Tokenization Apparatuses, Methods and Systems (“VDT”) transforms tokenized data storage request, detokenized data retrieval request, tokenized data retokenization request inputs via VDT components into tokenized data storage response, detokenized data retrieval response, tokenized data retokenization response outputs. A tokenized data storage request datastructure is obtained. Data type and data type instance of a plaintext data value are determined. A first data tokenization key token for the data type instance is determined. A first data shift position for the first data tokenization key token is calculated. A first tokenized data value is generated by translating the plaintext data value from a plaintext alphabet to a first shifted ciphertext data alphabet generated by shifting the first data tokenization key token using the first data shift position.

Abstract: A computer-implemented method is provided for permitting a user to manipulate data feeds via a graphical user interface. The method includes receiving, by a computing device, the data feeds over a communications network in real time from corresponding data sources and receiving from the user, by the computing device, via the graphical user interface an execution plan comprising a list of one or more actions to be performed on the data feeds. The method also includes sequentially executing, by the computing device, each of the actions in the execution plan on the real-time data feeds to generate one or more manipulated data feeds. The method further includes displaying, by the computing device, the manipulated data feeds to the user in a user-defined format via the graphical user interface.

Abstract: Methods and apparatuses are described for automated predictive analysis of user interactions to determine a modification based upon competing classification models. A server computing device receives first encoded text for prior user interactions and trains a plurality of classification models using the first text. The server determines a prediction cost for each of the models based upon the training. The server receives second encoded text for a current user interaction and executes the trained models using the second text to generate a prediction vector for each model that maximizes user engagement. The server selects one of the models based upon the prediction vectors, identifies a communication feature of the model, generates a user interaction modification, and transmits the user interaction modification to a client computing device.

Abstract: Methods and apparatuses are described for caching login sessions to access a software testing environment. A server identifies a test case for execution against an application in the software testing environment, the test case comprising one or more test steps. The server retrieves test data based upon the identified test case and generates a session key using the test data. The server requests an active session from a login session cache using the session key. When an active session exists in the login session cache, the server receives, from the login session cache, session data corresponding to the active session, establishes a connection to the application in the software testing environment using the session data and without first authenticating to the software testing environment, and executes one or more test steps of the test case against the application in the software testing environment using the test data.

Abstract: Methods and apparatuses are described in which unstructured computer text is analyzed for identification and classification of complaint-specific user interactions. A data store receives unstructured computer text corresponding to current user interactions. A server filters the unstructured computer text to identify messages that comprise a potential complaint.

Abstract: Methods and apparatuses are described for generation of a data model for identifying and classifying training needs of individuals. A computer data store stores unstructured text. A server computing device generates a vector for search queries in the unstructured text, and generates a training course classification data model that comprises a multi-layered neural network. The server computing device executes the training course classification model using the vectors as input to generate a training course recommendation output vector. The server computing device updates the training course classification data model based upon a rating value for a training course.

Abstract: A computer-implemented method is provided for electronically distributing content in a meeting to a participant of an enterprise. The method includes receiving information related to the meeting, including one or more risk definitions corresponding to one or more sections of the content of the meeting and determining a risk level for the participant. The method also includes comparing the one or more risk definitions of the meeting content with the risk level of the participant and filtering the meeting for the participant based on the comparing. The method further includes causing to present the filtered content personalized to the participant.

Abstract: Methods and apparatuses are described for intelligent smoothing of 3D alternative reality applications for secondary 2D viewing. A computing device receives a first data set corresponding to a first position of an alternative reality viewing device. The computing device generates a 3D virtual environment for display on the alternative reality viewing device using the first data set, and a 2D rendering of the virtual environment for display on a display device using the first data set. The computing device receives a second data set corresponding to a second position of the alternative reality viewing device after movement of the alternative reality viewing device. The computing device determines whether a difference between the first data set and the second data set is above a threshold. The computing device updates the 2D rendering of the virtual environment on the display device using the second data set, when the difference is above the threshold value.

Abstract: Systems and methods for establishing a secure connection between a client computing device and a server hosted website. The method includes requesting an HTTPS connection with a server hosted website. The method further includes receiving a certificate from the server hosted website. The certificate is signed by a certificate authority and certificate validators. The method also includes delivering the certificate to each of the certificate validators. The method further includes receiving a certificate status for each of the certificate validators. Each certificate status indicates whether the certificate is valid or has been revoked. The method also includes determining a quantity of valid certificate statuses received from the certificate validators.

Abstract: A computer-implemented method is provided for generating an access profile for a given user in a group of users. The method includes generating (i) a demographic similarity matrix of demographic similarity scores, each score measuring a degree of similarity between a pair of the users with respect to a demographic metric in a plurality of demographic metrics, and (ii) an access similarity matrix of access similarity scores, each score measuring a degree of similarity between a pair of the users with respect to an entitlement in a plurality of entitlements. The method also includes calculating a group similarity matrix based on a weighted average of the demographic and access similarity matrices. The method further includes creating the access profile for the given user based on the group similarity matrix. The access profile indicates access recommendations for the given user in relation to the plurality of entitlements.