Abstract: Methods, systems, and computer-readable storage media for a multimodal machine learning image and text combined search method. One example method includes processing items that each have an associated image and a textual description. A first image feature vector is generated by processing a first image using a first machine learning model. A first textual feature vector is generated by processing a first textual description using a second machine learning model. The first image feature vector and the first textual feature vector are combined to generate a first combined feature vector for a first item. Similarity lists of similar items are generated for the first item based on similarities between the first image feature vector, the first text feature vector, the first combined feature vector and respective corresponding vectors of other items. The similarity lists for the first item are combined to generate a combined similarity list for the first item.

Abstract: Some embodiments may be associated with a cloud computing environment. A computer processor of a traffic prediction server may retrieve performance stack trace logs from a traffic performance stack trace log repository that stores traffic information of the cloud computing environment. The traffic prediction server parses the performance stack trace logs as an objects list including parent/child object relationships and stores the parsed objects list in a graph database. The traffic prediction server may then transform the graph database into training data including spatial and temporal information and use the transformed training data to train a transformer model. According to some embodiments, the traffic prediction server also provides previous traffic input data to the transformer model when generates predicted traffic output data based on the previous traffic input data (e.g., to facilitate cloud load management).

Abstract: Various examples are directed to systems and methods for characterizing natural language text units. A plurality of text units may be used to train a bidirectional model. A bidirectional model may be applied to a set of annotated text units to generate a plurality of span context vectors. The plurality of span context vectors may be used to train a span prediction model. The span prediction model may be applied to at least a portion of the plurality of text units to generate a plurality of span characterizations, a first span characterization corresponding to a first span indicating that the first span describes a first job skill.

Abstract: A computer-implemented method can receive a software update for a software application deployable on a target system and perform an automatic performance test of the software application incorporating the software update on the target system. The automatic performance test can be integrated in a continuous integration and continuous delivery (CI/CD) pipeline. The method can collect a plurality of performance metrics measured when performing the automatic performance test and determine a performance score based on the plurality of performance metrics. Responsive to detecting the performance score is below a predefined performance threshold, the method can cause the CI/CD pipeline to reject the software update to the software application.

Abstract: Requests are received for handling by a cloud computing environment which are then executed by the cloud computing environment. While each request is executing, performance metrics associated with the request are monitored. A vector is subsequently generated that encapsulates information associated with the request including the text within the request and the corresponding monitored performance metrics. Each request is then assigned (after it has been executed) to either a normal request cluster or an abnormal request cluster based on which cluster has a nearest mean relative to the corresponding vector. In addition, data can be provided that characterizes requests assigned to the abnormal request cluster. Related apparatus, systems, techniques and articles are also described.

Abstract: A query is received that requests issues relevant to a user. Thereafter, a plurality of issues responsive to the query are retrieved. The retrieved issues are ranked using a first machine learning model to result in a first subset of the retrieved issues. The first subset of the retrieved issues are then ranked using a second, different machine learning model to result in a second subset of the retrieved issues which are a subset of the first subset of the retrieved issues. Data can then be provided which is responsive the query and includes at least a portion of the second subset of the retrieved issues. Related apparatus, systems, techniques and articles are also described.

Abstract: The present disclosure provides systems and methods for generating a graph of microservices of a software application. Source code for the application may be parsed using one or more method identifiers to identify a plurality of methods of the software application. Names and path values for the plurality of methods may be stored in a graph database as nodes and edges. The graph database may be queried to determine dependencies of a method, including the microservice that the method belongs to any remote methods called by the method. In addition, properties of the nodes may be transformed into a set of vectors to provide searching of the graph and recommendations.

Abstract: The present disclosure provides systems and methods for generating a graph of microservices of a software application. Source code for the application may be parsed using one or more method identifiers to identify a plurality of methods of the software application. Names and path values for the plurality of methods may be stored in a graph database as nodes and edges. The graph database may be queried to determine dependencies of a method, including the microservice that the method belongs to any remote methods called by the method. In addition, properties of the nodes may be transformed into a set of vectors to provide searching of the graph and recommendations.

Abstract: Requests are received for handling by a cloud computing environment which are then executed by the cloud computing environment. While each request is executing, performance metrics associated with the request are monitored. A vector is subsequently generated that encapsulates information associated with the request including the text within the request and the corresponding monitored performance metrics. Each request is then assigned (after it has been executed) to either a normal request cluster or an abnormal request cluster based on which cluster has a nearest mean relative to the corresponding vector. In addition, data can be provided that characterizes requests assigned to the abnormal request cluster. Related apparatus, systems, techniques and articles are also described.

Abstract: Supervised learning creates and trains a model to predict resource consumption by a remote system. Historical time-series data (e.g., monitor logs of CPU consumption, memory consumption) are collected from systems called upon to perform a task. This raw data is transformed into a labeled data set ready for supervised learning. Using the labeled data set, a model is constructed to correlate the input data with a resulting load. The constructed model may be a Sequence to Sequence (Seq2Seq) model based upon Gated Recurrent Units of a Recurrent Neural Network. After training, the model is saved for re-use to predict future load based upon an existing input. For example, the existing input may be data from a most recent 24 hour period (hour0-hour23), and the output of the model may be the load predicted for the next 24 hour period (hour24-hour47). This prediction promotes efficient reservation remote server resources.

Abstract: A query is received that requests issues relevant to a user. Thereafter, a plurality of issues responsive to the query are retrieved. The retrieved issues are ranked using a first machine learning model to result in a first subset of the retrieved issues. The first subset of the retrieved issues are then ranked using a second, different machine learning model to result in a second subset of the retrieved issues which are a subset of the first subset of the retrieved issues. Data can then be provided which is responsive the query and includes at least a portion of the second subset of the retrieved issues. Related apparatus, systems, techniques and articles are also described.

Abstract: Testing script files are received including a load test scenario file, a parameters file, and action file. These testing script files are all in a first programming language compatible with a first testing application and are collectively used to simulate actions of a large number of users interacting with a cloud-based application. Subsequently, each of the load test scenario file, the parameters file, and the action file are individually parsed to extract data therefrom. This extracted data is then used to populate an object. The data in this object is then converted to a converted testing script in a second programming language compatible with a second testing application. Related apparatus, systems, techniques and articles are also described.

Abstract: Data is received that encapsulates each of a plurality of resource requests that each specify a time interval and a requested resource. Thereafter, an array can be generated that includes a plurality of elements such that, for each request, there is a first element corresponding to the start time and a second element corresponding to the end time. The array can then be time sorted and after such sorting the array can be iterated through to identified, for each element in the array, a number of overlapping requests to generate a respective request count. Elements of the array can be updated based on the iterating to include the respective request counts. A capacity balance is then calculated for each element in the array based on available resource capacity and the corresponding respective request count. Data can then be provided that indicates capacity consumption levels for each requested time interval.

Abstract: Systems and methods for monitoring and improving software development quality are described herein. In accordance with one aspect of the present disclosure, an occurrence of a monitoring task related to source code is monitored. The source code is compiled and tested to produce a test result. The test result is analyzed. The test result analysis includes quality analysis to assess the quality of the source code.