Abstract: Embodiments focus on the real-time processing and analysis of event-related images posts on social media. By computing the most posted images and grouping them in accordance to their similarity, these images can be organized in a visual interface to provide the users an image-driven social media topic detection system. The groups of images with the highest frequency represent the most prominent topics. By keeping track of the temporal occurrence of the images, it is possible to visualize the temporal evolution of the topics.

Abstract: A method for surveilling a monitored environment includes classifying an individual detected in the monitored environment according to a role fulfilled by the individual within the monitored environment, generating a trajectory that illustrates movements and locations of the individual within the monitored environment, and detecting when the trajectory indicates an event that is inconsistent with an expected pattern for the role.

Abstract: A method for surveilling a monitored environment includes classifying an individual detected in the monitored environment according to a role fulfilled by the individual within the monitored environment, generating a trajectory that illustrates movements and locations of the individual within the monitored environment, and detecting when the trajectory indicates an event that is inconsistent with an expected pattern for the role.

Abstract: In reply to a requester's credit request, a plurality of the requester's debtors are selected, each of which has a payment due to the requester during the repayment period. Repayment information for is retrieved for each debtor as is the requester's cash flow. A repayment probability score per debtor is computed based on the debtor's repayment history and the debtors are ranked based on the repayment probability score and an amount of the debtor's payments due. Debtors are further selected in order of rank until a total of their payment amounts at least equals a payment amount per installment. The computed repayment probability scores of the further selected debtors are aggregated into a bundle score, and a new credit score is computer for the credit request based on at least the bundle score, without reliance on information that may be used to identify any of the debtors.

Abstract: A method for surveilling a monitored environment includes classifying an individual detected in the monitored environment according to a role fulfilled by the individual within the monitored environment, generating a trajectory that illustrates movements and locations of the individual within the monitored environment, and detecting when the trajectory indicates an event that is inconsistent with an expected pattern for the role.

Abstract: The invention relates to a rim insert system for a rim having at least one opening which forms a rim channel that tapers in a funnel-like manner, and at least one funnel-like rim insert releasably engaged in the opening. The rim insert has a peripheral catch edge which engage behind an internally arranged opening edge of the rim channel in an inserted position. A first catch projection is in abutment with an inclined portion of the opening edge. The inclined portion and the inner face of the rim channel are disposed at an angle of approximately from 200°-240° in cross-section. A second catch projection is substantially diametrically opposed to the first catch projection and engages behind the opening edge in a positive-locking manner. The inner face of the rim channel and the opening edge form an angle of approximately from 270° to 290°.

Abstract: A method for surveilling a monitored environment includes classifying an individual detected in the monitored environment according to a role fulfilled by the individual within the monitored environment, generating a trajectory that illustrates movements and locations of the individual within the monitored environment, and detecting when the trajectory indicates an event that is inconsistent with an expected pattern for the role.

Abstract: A method for surveilling a monitored environment includes classifying an individual detected in the monitored environment according to a role fulfilled by the individual within the monitored environment, generating a trajectory that illustrates movements and locations of the individual within the monitored environment, and detecting when the trajectory indicates an event that is inconsistent with an expected pattern for the role.

Abstract: A method for indexing a user interface test recording includes capturing, during a session, a recording of a plurality of interactions with the user interface, capturing, during the session, an event stream including a plurality of user interface events, synchronizing, in time, the plurality of interactions and the plurality of user interface events, identifying a point of interest in the event stream, wherein the point of interest is correlated to a time in the recording by the synchronization, and annotating the recording at a time correlated to when the point of interest occurred.

Abstract: A method for determining significant words or phrases within social media data includes receiving a stream of data from at least one social media source. The stream includes one or more words or phrases along with corresponding time stamps indicating when the word/phrase was used. One or more words/phrases to be analyzed is determined from the stream. A time period of interest is identified. The time period is divided into a plurality of non-overlapping time windows. The stream is analyzed within the time period of interest to determine how many instances of each words/phrases have timestamps within each time window. One or more of the words/phrases are identified as significant based on a level of co-occurrence of the words/phrases related to the determination as to how many instances of each words/phrases have timestamps within each window.

Abstract: A method, an apparatus and an article of manufacture for classifying customer activity in an automated customer support system. The method includes obtaining input from the automated customer support system, wherein the input comprises an observable measurement of customer activity in the automated customer support system, computing a probability that the input corresponds to one of one or more probabilistic models, and using the computed probability to classify the customer activity in the automated customer support system by considering the probabilistic model corresponding to a highest computed probability.

Abstract: Systems and articles of manufacture for characterizing statistical time-bounded incident management systems include generating an expected distribution of multiple work requests in an incident management system across multiple characterization classes based on a target service level agreement for each of the multiple work requests and one or more probability distribution values, analyzing the multiple work requests in the incident management system to determine an actual distribution of the multiple work requests across the multiple characterization classes, and comparing the expected distribution of the multiple work requests to the actual distribution of the multiple work requests for each of the multiple characterization classes to characterize performance of the incident management system.

Abstract: Techniques, systems, and articles of manufacture for characterizing statistical time-bounded incident management systems. A method includes generating an expected distribution of multiple work requests in an incident management system across multiple characterization classes based on a target service level agreement for each of the multiple work requests and one or more probability distribution values, analyzing the multiple work requests in the incident management system to determine an actual distribution of the multiple work requests across the multiple characterization classes, and comparing the expected distribution of the multiple work requests to the actual distribution of the multiple work requests for each of the multiple characterization classes to characterize performance of the incident management system.

Abstract: A method of simulating an online social network (OSN) includes modeling behavior data of a user, the behavior data including sampled real data, and simulating a behavior of the OSN using the modeled data.

Abstract: The invention relates to a rim insert system for a rim having at least one opening which forms a rim channel that tapers in a funnel-like manner, and at least one funnel-like rim insert releasably engaged in the opening. The rim insert has a peripheral catch edge which engage behind an internally arranged opening edge of the rim channel in an inserted position. A first catch projection is in abutment with an inclined portion of the opening edge. The inclined portion and the inner face of the rim channel are disposed at an angle of approximately from 200°-240° in cross-section. A second catch projection is substantially diametrically opposed to the first catch projection and engages behind the opening edge in a positive-locking manner. The inner face of the rim channel and the opening edge form an angle of approximately from 270° to 290°.

Abstract: Techniques for characterizing a time-bounded incident management system. A method includes receiving a plurality of work requests into a time-bounded incident management system, each work request having a time-to-service requirement, determining an assignment delay and a resolution delay for each work request, and characterizing the time-bounded incident management system by classifying each work request into one of multiple classes according to assignment delay and resolution delay.

Abstract: A system and an article of manufacture for characterizing a time-bounded incident management system, which includes receiving a plurality of work requests into a time-bounded incident management system, each work request having a time-to-service requirement, determining an assignment delay and a resolution delay for each work request, and characterizing the time-bounded incident management system by classifying each work request into one of multiple classes according to assignment delay and resolution delay.

Abstract: Techniques for automatically providing flood warnings to individuals are provided. The techniques include receiving a message regarding a water level observed in connection with a totem display at a geographic area, using the message and one or more items of available data to generate a flood level prediction for the geographic area, and sending a flood warning to one or more registered individuals if the flood level prediction for the geographic area exceeds a predetermined threshold.

Abstract: Techniques are disclosed for projecting an image onto a surface suitable for interaction with a user while avoiding user occlusion, and while correcting for distortion due to oblique projection. The displayed image moves to a suitable surface at a suitable size and orientation as a user moves around an environment, resulting in a user-following interface. Surfaces are selected in which the projected interface is not occluded by the user or other objects in the environment. Displayed images may be interactive, and moved into an interaction area on a suitable surface that is convenient for the user. The interaction area may or may not coincide with the display area. Adaptation of the projected interface is allowed so that the content of the display and the style of interaction widgets are modified based on distance from the user and orientation of the user with respect to a projected interface.

Abstract: A method, an apparatus and an article of manufacture for classifying customer activity in an automated customer support system. The method includes obtaining input from the automated customer support system, wherein the input comprises an observable measurement of customer activity in the automated customer support system, computing a probability that the input corresponds to one of one or more probabilistic models, and using the computed probability to classify the customer activity in the automated customer support system by considering the probabilistic model corresponding to a highest computed probability.