Abstract: User authentication is provided. A most recent user secret block of a set of unprocessed user secret blocks corresponding to a user is retrieved from a blockchain. The user is challenged using a question and answer pair contained in the most recent user secret block of the set of unprocessed user secret blocks corresponding to the user. It is determined whether the user successfully passed the challenge using the question and answer pair contained in the most recent user secret block of the set of unprocessed user secret blocks corresponding to the user. The user is authenticated to access a decentralized service in response to determining that the user did successfully pass the challenge using the question and answer pair contained in the most recent user secret block of the set of unprocessed user secret blocks corresponding to the user. The user is allowed to access the decentralized service.

Abstract: Provided are a computer program product, system, and method for determining play speeds for rendering video content in a video player. A determination is made of segment complexity scores of segments of a video are determined. A determination is made of user comprehension score for a viewer of the video with respect to a category of the video. A preferred speed predictor machine learning model receives input comprising the segment complexity scores and the user comprehension scores for the categories of the video to output predicted play speeds for the segments of the video. The segments of the video in the video player are rendered according to the predicted play speeds of the segments.

Abstract: Provided are a computer program product, system, and method for analyzing user activity data to generate activity information for use by generative artificial intelligence (AI) to generate reports. Activity data includes information on an activity in which a monitored user engages, including a time period during which the monitored user was engaged in the activity and a description of the activity. An activity categorizer comprising a machine learning model classifier processes the time period and the description of the activity; to output an activity category. A status report generator generates a status report for the activity category, including the activity category of the activity and key attributes of the activity category including the time spent on the activity category and information on the activity. The status report is updated to a database.

Abstract: A computer-implemented method to send targeted messages based on a driver's intent. The method includes identifying, by a sending vehicle, one or more additional vehicles in the vicinity of the sending vehicle, including a first vehicle. Monitoring a set of data related to a current scenario for the sending vehicle and determining, based on a current scenario, an intent score for the sending vehicle. The method includes activating a horn device associated with the sending vehicle. The method further includes determining, in response to the activating, the intent score is above an intent threshold for the first vehicle. The method includes generating, in response to the intent score being above the intent threshold, a message; and sending, to a target vehicle, the message. Further aspects of the present disclosure are directed to systems and computer program products containing functionality consistent with the method described above.

Abstract: Provided are a computer program product, system, and method for data analysis of interaction information for interacting participants to determine a connection intention. An audio and/or a visual feed collected at an event is processed to determine whether interacting participants at the event are engaged in an interaction. A duration of the interaction, attributes of the interaction, and personal profile information of the interacting participants are determined. The duration of the interaction, the attributes of the interaction, and the personal profile information are processed to determine a connection intention indicating whether the interacting participants should connect or should not connect. Requests for the interacting participants to connect are transmitted in response to determining the connection intention indicates the interacting participants should connect.

Abstract: A computer-implemented method to send targeted messages based on a driver's intent. The method includes identifying, by a sending vehicle, one or more additional vehicles in the vicinity of the sending vehicle, including a first vehicle. Monitoring a set of data related to a current scenario for the sending vehicle and determining, based on a current scenario, an intent score for the sending vehicle. The method includes activating a horn device associated with the sending vehicle. The method further includes determining, in response to the activating, the intent score is above an intent threshold for the first vehicle. The method includes generating, in response to the intent score being above the intent threshold, a message; and sending, to a target vehicle, the message. Further aspects of the present disclosure are directed to systems and computer program products containing functionality consistent with the method described above.

Abstract: An index is provided of content at timestamps of frames in a video. A search request is received with search content. A determination is made of matching content in the index, associated with a timestamp, matching the search content. A computer addressable link to the timestamp in the index associated with the matching content is returned to the search request. Selection of the computer addressable link causes the video to play from the timestamp.

Abstract: An event at a location is identified. An event risk of the event can be calculated based on risk characteristics of both the location of the event (“location risk characteristics”) and the event itself (“personnel risk characteristics”). Location risk characteristics can include a visitor history of the location. Personnel risk characteristics can be based on attendees of the event, such as a number of attendees. The overall event risk, once calculated, can be compared to a threshold. Depending on the comparison, a risk mitigation policy can be implemented.

Abstract: A method, computer system, and a computer program product for modifying a user interface. Attributes of a source object identified by a user in connection with a user input for storing the source object are determined. Attributes of one or more target storage locations are determined. A target storage location for storing the source object is predicted, along with a confidence value associated with the prediction. The prediction is made using a machine learning model that predicts the predicted target storage location and associated confidence value based on the determined attributes of the source object. A plurality of target storage location usage patterns are determined. The user interface is modified based on the predicted target storage location.

Abstract: Method, system and computer program product for transaction evaluation based on a potential impact of the potential transaction on defined plans. In one embodiment, the method comprises receiving at a financial analysis computer system specified interactions intercepted when a person uses a client computing device to identify a potential transaction, and the analysis computer system processing these interactions for determining a potential impact of said transaction on one or more defined goals of the person. Before the person commits to the transaction, the analysis computer system generates a client guidance signal based on this determining, and sends the client guidance signal to the client computing device to instruct that device to convey guidance to the specified about the transaction. The specified interactions received at the financial analysis computer system data may identify a transaction context and activity of the person.

Abstract: Provided is a method, computer program product, and system for leveraging spatial scanning data of an environment collected by a robotic vacuum to generate recommendations for improving environmental conditions. A robotic vacuum may collect cleanliness data relative to an environment. The robotic vacuum may store the cleanliness data over a plurality of cleaning cycles. The robotic vacuum may analyze the cleanliness data over the plurality of cleaning cycles to identify one or more cleanliness trends. The robotic vacuum may generate a recommendation for improving an environmental condition relative to the environment based on the identified one or more cleanliness trends. The robotic vacuum may provide the recommendation to a user.

Abstract: Provided is a method, computer program product, and system for leveraging spatial scanning data of an environment collected by a robotic vacuum to generate recommendations for improving environmental conditions. A robotic vacuum may collect cleanliness data relative to an environment. The robotic vacuum may store the cleanliness data over a plurality of cleaning cycles. The robotic vacuum may analyze the cleanliness data over the plurality of cleaning cycles to identify one or more cleanliness trends. The robotic vacuum may generate a recommendation for improving an environmental condition relative to the environment based on the identified one or more cleanliness trends. The robotic vacuum may provide the recommendation to a user.

Abstract: A combined translation request is obtained that includes content of a first language to be translated to a second language combined with translation context information of a user for which translation is to be performed. The content is translated, using machine translation, from the first language to the second language based on the translation context information to provide a translation. The translation is adjusted based on one or more identified translation factors selected based on user feedback to provide an adjusted translation. The adjusted translation is provided to the user.

Abstract: A tool for providing a secure communication channel during three-way communications. The tool initiates a three-way communication from a user device, wherein the three-way communication is a connection between a user, a third-party interpreter, and a service provider. The tool enables a passthrough function of a secured switch for transmitting non-privileged data during the three-way communication. The tool determines whether privileged data is to be transmitted during the three-way communication. Responsive to a determination that privileged data is to be transmitted during the three-way communication, the tool mutes an audio communication component. The tool activates a bypass function of the secured switch for transmitting the privileged data on an alternate audio communication component.

Abstract: A processor may receive congregation data. The congregation data may be associated with a particular area. The processor may analyze the congregation data. The processor may generate a social movement model of the particular area. The processor may generate one or more routes from a first location to a second location in the particular area based on the social movement model. The one or more routes may reduce the level of exposure to an infectious disease.

Abstract: A method, computer system, and a computer program product for modifying a user interface. Attributes of a source object identified by a user in connection with a user input for storing the source object are determined. Attributes of one or more target storage locations are determined. A target storage location for storing the source object is predicted, along with a confidence value associated with the prediction. The prediction is made using a machine learning model that predicts the predicted target storage location and associated confidence value based on the determined attributes of the source object. A plurality of target storage location usage patterns are determined. The user interface is modified based on the predicted target storage location.

Abstract: An event at a location is identified. An event risk of the event can be calculated based on risk characteristics of both the location of the event (“location risk characteristics”) and the event itself (“personnel risk characteristics”). Location risk characteristics can include a visitor history of the location. Personnel risk characteristics can be based on attendees of the event, such as a number of attendees. The overall event risk, once calculated, can be compared to a threshold. Depending on the comparison, a risk mitigation policy can be implemented.

Abstract: A method for facilitating identification of navigation regions in a web page based on document object model (DOM) analysis is provided. In one embodiment, the method includes analyzing the web page for features. The features include at least one of: interactive elements, content regions, link region roots, or landmarks. The method also includes representing the features in a tree structure and analyzing the tree structure for a link density to identify non-main landmarks, a reading order, and main content roots. The method further includes enabling a region navigation for the web page based on the identified non-main landmarks, reading order, and main content roots.

Abstract: Input data for a computing device is received from one or more input devices. Whether there is visual hacking of the computing device is determined based on the input data. A user interface of the computing device is modified in response to determining there is visual hacking of the computing device.

Abstract: According to one embodiment, a computer-implemented method includes collecting data corresponding to an image of one or more objects captured by a user on an image capture device, wherein the data comprises biometric data, emotion data, image quality data, and context data. In addition, the computer-implement method includes determining an image quality (IQ) value based on the image quality data, determining an emotion (E) value based on at least one of the biometric data and the emotion data, and determining a relationship (R) value between the one or more objects and the user based on the context data. The computer-implement method includes calculating an Overall Emotional Image Quality Score (OEIQS) for the image based on the IQ value, the E value, and the R value, and categorizing the image into at least one of a plurality of predefined categories.