Abstract: A computer-implemented method, a computer program product, and a computer system for using computer vision to automatically generate a unit test case. A computer converts a text file of a source code to an image file of the source code. A computer inputs the image file to a neural network having been trained with source code images. The neural network identifies elements in the image file. The neural network generates a resulting image including identified elements in the image file. A computer extracts the identified elements from the resulting image. A computer generates a text file including a key value map of the identified elements. A computer generates a scaffold of a unit test case, based on the key value map.

Abstract: Mitigating mistranscriptions resolves errors in a transcription of the audio portion of a video based on a semantic matching with contextualized data electronically garnered from one or more sources other than the audio portion of the video. A mistranscription is identified using a pretrained word embedding model that maps words to an embedding space derived from the contextualizing data. A similarity value for each vocabulary word of a multi-word vocabulary of the pretrained word embedding model is determined in relation to the mistranscription. Candidate words are selected based on the similarity values, each indicating a closeness of a corresponding vocabulary word to the mistranscription. The textual rendering is modified by replacing the mistranscription with a candidate word that, based on average semantic similarity values, is more similar to the mistranscription than is each other candidate word.

Abstract: Computer-based provision of recommendations includes determining an item of interest to a user and a geographic region of the user. The item, as available from different e-commerce websites (websites) of geographic regions that are different from the geographic region of the user are aggregated within blockchain. Social network data for the user is retrieved and processed using natural language processing to determine contacts of the user located in the geographic regions of the websites. A likelihood of each contact traveling to the geographic region of the user is determined based on the social networking data. A website is selected that offers the item and that corresponds to a geographic region of a selected contact. The selected contact of the user has at least a minimum likelihood of traveling to the geographic region of the user. The selected website is presented to the user as an option for obtaining the item.

Abstract: A computer-implemented method for avatar rendering of virtual presentations is disclosed. The computer-implemented method includes extracting visual content from a presentation. The computer-implemented method further includes extracting audio content from the presentation. The computer-implemented method includes correlating the visual content with the audio content of the presentation. The computer-implemented method includes generating a virtual avatar to dynamically render a virtual presentation to a viewer, based at least in part, on the correlated visual content and audio content of the presentation.

Abstract: Generating safety level scores of travel parking spots by an AI model trained by supervised learning using labeled online source data and static and dynamic IoT data, determining a current location and travel route of a vehicle, identifying potential travel parking spots within the geospatial area of the current location and travel route of the vehicle, receiving data from online sources and static and dynamic data of IoT devices in the vicinity of the travel parking spots, generating by the AI model, safety level scores for the travel parking spots within a geospatial area of the vehicle, and sending a listing of the safety level scores to a computing device associated with the vehicle.

Abstract: A computer implemented method processes alerts. A computer system creates a representation of an alert received for processing. The computer system determines a similarity of the alert with previously processed alerts using the representation of the alert and representations of the previously processed alerts. A first evaluator in the computer system evaluates an alert level for the alert based on previously processed similar alerts in response to the similarity being above a similarity threshold for similar alerts. A second evaluator in the computer system evaluates, the alert level for the alert using a machine learning model in response to the similarity not being above the similarity threshold.

Abstract: A method of generating a virtual reality (“VR”) experience includes detecting, using external sensors, a real-world spectator that is in a spectator space that is adjacent to a user that is wearing a VR headset and experiencing a VR space. The method also includes detecting a real-world physical state of the spectator, and rendering, in response to detecting, the spectator in the VR space as an avatar that reflects the real-world physical state of the spectator.

Abstract: Systems, methods and/or computer program products for managing the temperature of datacenter during a period of malfunction or inoperability of the cooling system responsible for maintaining temperatures within the datacenter. Temperatures of the datacenter's computing systems are monitored by thermal imaging systems and/or sensors. Computing systems are also monitored for how frequently the systems are accessed during a defined period of time and the number of mission critical deployments by each computing system. Collected parameters, including temperature, frequency of access and number of running mission critical applications are imputed into a scoring algorithm which uses the collected parameters and weightings to generate a ranking of computing systems to shutdown sequentially in response to rising temperatures.

Abstract: A method includes determining a presence of one or more people around a user and determining, based on the presence of the one or more people, an exposure level. The method also includes receiving a message for the user, the message comprising a first portion and a second portion and removing, based on the exposure level, the first and second portions from the message to produce a first message. The method further includes removing, based on the exposure level, the first portion from the message to produce a second message and presenting, based on the exposure level, the first message to the user. The method also includes receiving, from the user, feedback about the first message and presenting the second message to the user in response to the feedback.

Abstract: Methods, computer program products, and systems are presented for warranty tracking and transactions based on usage metrics by use of blockchain. The methods include, for instance: obtaining a usage report of an IoT device in a predefined format. The usage report is recorded in a blockchain network, and a warranty balance, also recorded in the blockchain network, is updated in the amount corresponding to the usage report on the IoT device. A warranty claim is resolved based on records of the usage report and the warranty balance for the IoT device as recorded in the blockchain network.

Abstract: A computer-implemented method, a computer system and a computer program product manage disruption between activities in a common area environment. The method includes capturing activity data from the common area environment, where the activity data is selected from a group consisting of: video data, audio data and biometric data and text data. The method also includes identifying a plurality of current activities in the activity data. Each current activity is associated with a device and includes a context with respect to other current activities in the plurality of current activities. In addition, the method includes determining a disruption score for each current activity in the plurality of current activities based on the context with respect to the other current activities. Lastly, the method includes transmitting a notification response to the device associated with a current activity when the disruption score for the current activity is above a threshold.

Abstract: Presenting content history to a user added to a group chat may include: receiving a request from a user to join an existing group chat session, wherein the requesting user is associated with user data describing the requesting user’s persona; performing an analysis of content of the group chat session prior to the requesting user joining the group chat session; and adding the requesting user to the group chat session, including: generating a modified version of the content of the group chat session based on the content analysis and the user data; and presenting the modified version of the content of the group chat session to the requesting user.

Abstract: Computer-implemented methods, computer program products, and computer systems for detecting and resolving fraudulent calls. The computer-implemented methods include one or more processors configured for receiving voice call data corresponding to an incoming telephone call placed to a user device, wherein the voice call data comprises caller voice data. Further, the computer-implemented methods may include one or more processors configured for converting the caller voice data to caller text data comprising one or more text phrases. Further embodiments of the computer-implemented method include processors configured for determining that the one or more text phrases satisfies a first condition, and responsive to determining that the one or more text phrases satisfies the first condition, transmitting a user alert to the user device.

Abstract: Methods, computer program products, and/or systems are provided that perform the following operations: identifying two or more distinct elements in an image; generating a sub-image for each of the two or more distinct elements; generating adjectives descriptive of content associated with a distinct element for each sub-image; displaying a response list including the adjectives associated with the distinct element of a selected sub-image in response to an interaction with the image; obtaining annotation data based in part on the response list displayed for the distinct element of the selected sub-image; and assigning the annotation data to the distinct element of the selected sub-image, wherein the annotation data is displayed in response to an interaction with the distinct element in the image.

Abstract: A computer-implemented method according to one embodiment includes applying a predetermined augmentation to the sample set of training data to create an augmented sample set, training a model with the augmented sample set, determining a performance of the trained model, and assigning a weight to the predetermined augmentation for the training data set based on the determined performance. A determination is made as to whether to apply the predetermined augmentation to a larger training data set before the training data set is applied to the model, based on the weight assigned to the predetermined augmentation.

Abstract: Computer technology for leveraging crowd sourced data to create an experience scoring based itinerary that outputs an itinerary of POI's (points of interest) based on relevancy to the person's interest, scoring experience, weather conditions and other factors relevant to setting the destinations, order and/or scheduling of the traveler's itinerary (for example, a daily schedule for a family on holiday). Also, computer technology for filtration of a set of images unique to a person's profile and taste and stitching these images to suggest a personalized route specific to that person's understanding.

Abstract: A method for managing edge resource processing includes identifying a plurality of data sources, wherein each sensor from a plurality of sensors associated with the plurality of data sources produce data for processing by a plurality of edge devices. In response to sampling a data feed from each data source form the plurality of data sources to establish context, the method also includes determining contextual priority for each data source. The method also includes identifying the plurality of edge devices at the location for performing computations on the data produced by the plurality of data sources. In response to identifying a type of computation for the plurality of edge devices, the method also includes determining a computation plan for the edge devices based on the contextual priority for each data source from the plurality of data sources and deploying the computation plan for the plurality of edge devices.

Abstract: A computer implemented method and system are disclosed for dynamically enabling a first user device operated by a first user to provide wireless hotspot capability for a wireless hotspot session to a second user device operated by a second user. The wireless hotspot session is accepted based at least on urgency and bandwidth requirement of the second user device. When the first user device accepts a connection to the second user device to provision a wireless hotspot for the wireless hotspot session, the first user restricts use of the second user device in the wireless hotspot session, based on bandwidth and context of use of the second user device. The first user device may refuse a connection by rejecting the wireless hotspot session request wireless hotspot session transactions information is provided as blockchain ledgers.

Abstract: Real-time resource deployment and integration can include determining one or more performance priorities for a user computer system based on a plurality of system-generated processing metrics. Based on the one or more performance priorities, a candidate cloud-based service can be determined among one or more previously unanalyzed cloud-based services identified by an automated watcher configured to search a plurality of communication network sites. The current performance of the user computer system can be compared to a potential performance of the user computer system were the candidate cloud-based service deployed. A script can be generated in response to determining, based on the comparing, that deploying the candidate cloud-based service improves performance of the user computer system with respect to the performance priorities. The script reconfigures the user computer system in real-time by automatically deploying the candidate cloud-based service.

Abstract: A method, computer program, and computer system are provided for validating document submissions. A data entry in a data entry field associated with a document associated with a user is identified. A set of validation rules associated with the document is accessed. A determination is made as to whether the identified data entry complies with the accessed set of validation rules. Based on determining that at least a portion of the identified data entry does not comply with a subset of validation rules from among the set of validation rules, feedback is provided to the user corresponding to the portion of the identified data entry that does not comply with the subset of validation rules.