Abstract: Methods and apparatuses are described for detecting vulnerabilities associated with a software application build. A server generates a software application build based upon a source code repository, including determining application dependencies of the software application build. The server identifies vulnerabilities associated with the application dependencies. For each identified vulnerability, the server creates an aspect class based upon a package file associated with the vulnerability, the aspect class comprising vulnerability logging code. The server integrates the created aspect classes into libraries of the application dependencies, generates a new package file based upon the application dependencies, and integrates the new package file into the software application build. The server executes the software application build, including generating log statements by calling the aspect classes in the new package file.

Abstract: Methods and apparatuses are described for analyzing unstructured computer text for identification and classification of complaint-specific interactions. A computer data stores unstructured text. A server computing device splits the unstructured text into phrases of words. The server generates a set of tokens from each phrase and removes tokens that are stopwords. The server generates a normalized sentiment score for each set of tokens. The server uses a rules-based classification engine to generate a rules-based complaint score for each set of tokens. The server uses an artificial intelligence machine learning model to generate a model-based complaint score for each set of tokens. The server determines determine whether each set of tokens corresponds to a complaint-specific interaction based upon the rules-based complaint score and the model-based complaint score.

Abstract: Methods and apparatuses are described for automated computer text classification and routing using artificial intelligence transfer learning. A server trains a word embedding model using one-hot vectors of word pairs from a filtered first corpus of unstructured computer text and a filtered second corpus of unstructured computer text, using an artificial intelligence neural network. The server trains a long short-term memory model using vector matrices that correspond to sentences in the filtered second corpus of unstructured computer text, and labels. The server receives a message, generates a matrix for each sentence in the message by applying the trained word embedding model, generates one or more labels, and a probability for each label, for each sentence in the message by applying the trained long short-term memory model, and routes the message to a second client computing device based upon an assigned label.

Abstract: A computerized method of authenticating a user includes receiving, by a computing device, first biometric data from the user via a first biometric input device; extracting one or more first features from the first biometric data; generating a first vector based on the first features; computing a first similarity score reflecting a geometric distance between the first vector and a first reference vector stored in memory; receiving second biometric data from the user via a second biometric input device; extracting one or more second features from the second biometric data; generating a second vector based on the second features; computing a second similarity score reflecting a geometric distance between the second vector and a second reference vector stored in memory; computing a confidence score based on the first and second similarity scores; and determining a right of the user to access restricted information based on the confidence score.

Abstract: A computer-implemented method of training, using a computer log file, an application error prediction engine to identify one or more application errors includes parsing the computer log file into a plurality of data sets. Each data set is associated with a unique computing session having a session identifier and ending in an application or. The method also includes extracting, from each data set, values for a specified set of parameters in each data set. The method also includes encoding the extracted values for each data set into a corresponding data structure. The method also includes generating, for each data structure, a corresponding vector, the corresponding vectors collectively forming a matrix. The method also includes calculating, based on the matrix, a set of clusters, each cluster corresponding to a known error type, the set of clusters used to create a model used to identify new error types.

Abstract: The Firmware Extension for Secure Cryptocurrency Key Backup, Restore, and Transaction Signing Platform Apparatuses, Methods and Systems (“SFTSP”) transforms transaction signing request, key backup request, key recovery request inputs via SFTSP components into transaction signing response, key backup response, key recovery response outputs. A key backup request that includes an encrypted master key associated with a hosting HSM is received by a backup HSM from a backup utility. A private key decryption key corresponding to a public key encryption key previously provided by the backup HSM to the backup utility for the hosting HSM is retrieved from the backup HSM's tamper-proof storage and used to decrypt the encrypted master key. A specified number of master key shares to generate for the decrypted master key is determined and generated using a secret sharing method. The generated master key shares are provided to the backup utility.

Abstract: Methods and apparatuses are described for generating and deploying customized application software containers. Software containers on a first server comprise an application software module and an end-user-specific data set. A second server receives input data from remote computing devices and stores the input data in a master data set. The second server determines end-user-specific data sets from the master data set. The second server encrypts each of the end-user-specific data sets with an encryption key. The second server generates the software containers by executing the application software module in separate processes and storing each of the encrypted data sets in a separate container. Client computing devices authenticate to the second server to access a software container. The client devices decrypt the end-user-specific data set stored in the software container using the encryption key, and use the application software module to interact with the end-user-specific data set.

Abstract: Described herein are methods and systems for secure communication of private audio data in a zero user interface computing environment. A server receives text generated from a first digital audio bitstream, the digital audio bitstream corresponding to speech captured by a zero user interface computing device from a user. The server analyzes the text to extract a set of keywords from the text. The server determines whether information responsive to the keywords comprises private data related to the user. If the information responsive to the set of keywords comprises private data: the server generates a text response to the set of keywords that includes the private data relating to the user, determines a personal audio playback device associated with the user, and transmits the generated text response to the personal audio playback device for playback as a second digital audio bitstream.

Abstract: A method of processing data by one or more data processing systems for classification of the processed data into one or more predefined classifications, the method comprising: receiving by one or more data processing systems social profile data; binding by the one or more data processing systems based on the input social profile data, values of one or more attributes included in the social profile data to one or more parameters of a classifier executing on the one or more data processing systems; classifying data representing the user into one or more predefined classifications; for one of the predefined classifications into which the data representing the user is classified, identifying by the one or more data processing systems a candidate action included in the predefined classification and unassociated with the user; and transmitting an alert to notify the user of the candidate action.

Abstract: Methods and apparatuses are described for analyzing unstructured computer text for domain-specific stopword identification and removal. A computer data store stores unstructured text. A server computing device splits the unstructured text into phrases and generates tokens from the phrases. The server computing device generates a set of bootstrap keywords using the tokens. An artificial intelligence neural network executing on the server computing device generates a stopword training model. The server computing device generates a first set of candidate stopwords using the bootstrap keywords and the stopword training model. The server computing device generates regular expressions using the bootstrap keywords, and generates a second set of candidate stopwords using the regular expressions. The server computing device stores the candidate stopwords in the data store, and removes stopwords from the unstructured text using the data store.

Abstract: A computer-implemented method is provided for authenticating an identity of a user requesting access to a computerized resource via a client computing device. The method includes receiving, by the client computing device, a request to authenticate the identity of the user, determining, by the client computing device, a time period of the request, determining, by the client computing device, an approximate geolocation of the user, and determining, by the client computing device, one or more network characteristics associated with a current network of the client computing device. The method further includes transmitting, by the client computing device to an authentication device, authentication data including the request, the time period of the request, the approximate geolocation of the user and the one or network characteristics.

Abstract: A computerized method of comparing documents includes a computing device: receiving a source document via a first automated document feed channel; receiving a target document via a second automated document feed channel; pre-processing the source document using a first comparison data structure operating on the computing device, thereby producing a pre-processed source document having a text array including text from the source document; pre-processing the target document using a second comparison data structure, thereby producing a pre-processed target document having a text array including text from the target document; determining, using a document comparison engine operating on the computing device, a set of differences between the pre-processed source document and the pre-processed target document with respect to a set of pre-specified criteria; and generating, a summary of the set of differences between the pre-processed source document and the pre-processed target document.

Abstract: Methods and apparatuses are described for dynamic generation of custom web analytics data. A computing device renders a webpage comprising a plurality of page elements, where the webpage is assigned one or more attributes and each page element is assigned one or more attributes. The computing device detects one or more interactions occurring with one or more of the plurality of page elements on the webpage. For each detected interaction, the computing device identify the page element with which the detected interaction occurred, captures at least one of the one or more attributes of the webpage, captures at least one of the one or more attributes of the identified page element, aggregates the captured attributes of the webpage and the captured attributes of the identified page element into a custom variable, and stores the custom variable in a local memory module of the computing device.

Abstract: The SECTOR-BASED PORTFOLIO CONSTRUCTION PLATFORM APPARATUSES, METHODS AND SYSTEMS (“SPC”) transform user data request via SPC components into sector-based portfolio investment transaction records. In one implementation, the SPC may provide an electronic user interface (UI) (e.g., web-based, mobile, etc.) for a user to construct a sector-based investment portfolio, to obtain performance prediction for the portfolio's allocation strategies by performance back-testing of selected sector funds and indices.

Abstract: A computer-implemented method is provided for facilitating live communication between a potential customer and an enterprise in relation to a product. The method includes causing to display, by a computing device on a webpage over a communications network, an interactive banner located on the webpage that includes advertisement content related to the product. The advertisement content includes an offer to the potential customer to communicate live with the enterprise about the product. The method includes adding to the context information, by the computing device, information related to an interaction over the communications network between the potential customer and the interactive banner. The method further includes adjusting, by the computing device over the communications network, the advertisement content in the interactive banner on the webpage if the potential customer accepts the offer.

Abstract: The Database, Data Structure and Framework Transformer Apparatuses, Methods and Systems (“DDSFT”) transforms variable list request, population selection, base table transform extract data inputs via DDSFT components into transformed, merged data outputs. The DDSFT includes a database structure that stores data used in the framework operations. A macro-tool includes one or more macros that control a sequence of database queries that extract the data from the database structure and then perform transformations on the extracted data. The macro-tool includes a series of binary flags indicative of whether or not statements are executed.

Abstract: Methods and apparatuses are described for automated computer text classification and routing using artificial intelligence transfer learning. A server captures historical story data from an Agile development tracking system. For each completed story, the server generates a vector based upon story-specific features and assigns a label to the vector based upon a cycle time associated with the story. The server trains a classification model using a neural network on the vectors and labels. The server captures new story data from the Agile development tracking system. For each new story, the server generates a vector based upon story-specific features and executes the trained model on the vector to generate a cycle time prediction for the new story. Based upon the cycle time prediction, the server identifies deficiencies in the new story and generates an alert message.

Abstract: Methods and apparatuses are described for intelligent automation of computer software testing log aggregation, analysis, and error remediation. A client device generates test log files for software automation testing tools, each test log file comprising errors generated by execution of test scripts. The client device creates an archive file with the log files and transmits the files to a server. The server extracts the files from the archive file and parses each of the files to identify errors. The server aggregates errors from at least two of the files and transmits the aggregated errors to a log management message queue and a development message queue. The server generates a user interface and transmits the user interface to a remote device. The server also generates development change orders that, when executed by the server, create tasks in a development tracking system to resolve errors by changing development source code.

Abstract: Methods and apparatuses are described for of recognizing handwritten characters in digital images using context-based machine learning. A server captures an image of a document that comprises one or more handwritten data fields, the document associated with a user identifier. The server identifies a field type for each handwritten data field in the image. The server creates a pixel intensity array for each character in each handwritten data field and determines whether a user-specific character map exists for the user identifier. If a map exists, the server retrieves the map and generates digital form data by executing a user-specific handwriting classifier using the map, the pixel intensity arrays, and the field types. If a map does not exist, the server builds a map based upon the pixel intensity arrays and generates digital form data by executing a baseline handwriting classifier using the map, the pixel intensity arrays, and the field types.

Abstract: The Social Aggregated Fractional Equity Transaction Partitioned Acquisition Apparatuses, Methods and Systems, (“SAFETPA”) transforms fractional equity ownership purchase request inputs via SAFETPA components into transaction confirmation outputs. A Fractional Order Generation component receives a purchase request for a fractional order of an equity via a data communication network interface from a client terminal of a client having a source of funds and having a public encryption key, determines a purchase price for the fractional order of the equity by retrieving a quote for a price of a share of the equity, confirms that the source of funds contains at least the purchase price; and generates a trade order for the share of the equity.