Abstract: Systems and methods for cognitive object and object use recognition using digital images are disclosed. In embodiments, a computer-implemented method comprises: receiving, by a computing device, a plurality of digital images; extracting, by the computing device, image objects depicted in the plurality of digital images and metadata associated with the plurality of digital images; performing, by the computing device, contextual analysis of each of the image objects; and generating, by the computing device, relationship data based on the contextual analysis including a relationship between each of the image objects and one or more usages of the image object.

Abstract: A computer-implemented method comprises: monitoring, by a user device, user gesture and user input activity by a user of the user device; detecting, by the user device, that the user has entered a thinking state based on the monitoring; determining, by the user device, subject content based on content displayed on a display of the user device based on the detecting; determining, by the user device, relevant content associated with the subject content; and presenting, by the user device, the relevant content to the user via the display.

Abstract: Methods, computer program products, and systems are presented. The methods include, for instance: collecting user data from the user, analyzing a context of an event including one or more actions from the user data; identifying subsequent actions of the event based on the context of the event, creating one or more context-personality-cognitive state (CPC) mapping, building up a knowledgebase by machine learning, and predicting a cognitive state of the user based on the knowledgebase. The method generates an alarm for a subsequent action based on the predicted first cognitive state of the user and notifying the generated alarm to the user.

Abstract: Adjusting a business intelligence report is provided. An identification of an input data source corresponding to content of the business intelligence report is received from a client device via a network. An unstructured text stream is extracted from the input data source. A set of parameter values that are contextually-related to the content of the business intelligence report is identified. The business intelligence report is adjusted using the set of parameter values that are contextually-related to the content of the business intelligence report.

Abstract: Methods, systems, and computer program products are provided for remediating an instance of a visual notification interfering with an output of an application on a display device of an electronic device. An instance of a visual notification is identified on a display device. The visual notification is determined to be interfering with the output of the application on the display device. User response to the output of the application is monitored. An assessment is made, based on the monitoring, of an effectiveness of the output of the application. It is determined, based on the assessment, that there exists a failure of the effectiveness of the output of the application. A remediation action is performed in response to the determined failure. The remediation action may include removal of the instance of the visual notification, terminating a parent process of the instance of the visual notification, or restarting the electronic device.

Abstract: An optimization model is selected to reduce a number of passengers adversely affected by a delay of an aircraft. A cascade boundary is determined for a length of the delay, which projects the delay at the plurality of airports. Using the optimization model, a probability curve is computed at an airport from the plurality of airports, which outputs a second length of the delay experienced at the airport responsive to the cascade boundary projecting the delay on the airport. The length is adjusted in the optimization model such that a count of passengers adversely affected by the delay at the airport at the elapse of the second length is minimized. A target system is caused to configure the aircraft to be delayed by the adjusted length.

Abstract: For a task that has been partially executed, a residual complexity index is computed, the task being of a complexity that cannot be ascertained prior to executing the task. An evaluation is made whether the residual complexity index exceeds a cost of a resource that should be considered for allocation to the task. When the evaluation is affirmative, a priority of the task is established relative to a second task. The resource is scheduled to perform the task according to a timing, the timing being determined using the cost of the resource. The resource is allocated to the task according to the timing.

Abstract: A graph is constructing using a user node of a user and a set of connection nodes corresponding to connections in a social network of the user. The graph is overlaid on a risk map, which is a mapping of a geo-social risk characteristic of a geographical area. A first and a second risk indices are determined for a first and a second connection in the set of connections. Using the risk map, a first and a second risk diffusion boundary of the first and the second risk index are computed. When the first risk diffusion boundary includes the user node, a first risk contribution from the first connection node to the user node is computed using the first risk index. Using the first risk contribution, a risk index of the user is determined to accounts for a risk attributable to the user due to the user's social network.

Abstract: Aspects automatically minimize marketing rates as a function of optimized response rate models. Response rates are estimated from marketing offers targeted from a first entity to topic-entity pairs at respective specified marketing rates as a function of relative differences in their consumer sentiment scores. Marketing offers are targeted to a subset of the topic-entity pairs that each have estimated response rates meeting a threshold response rate constraint. Respective costs and actual rates of response from consumers are determined for the targeted offers. Response rates are modeled to determine modeled response parameters for the topics and entities of the subset topic-entity pairs as regressions of minimized differences in value between estimated and actual response rates. Marketing rates of the subset entity-topic pairs are minimized to meet the threshold response rate constraint and a marketing cost constraint as a function of the modeled response parameters.

Abstract: Methods, computer program products, and systems are presented. The methods include, for instance: obtaining input data regarding to a market for a branded product subject to loss of exclusivity scheduled. A dynamic half-life of a market value for the branded product is estimated to predict a market share erosion rate of the branded product at a point of time after the loss of exclusivity.

Abstract: Methods, computer program products, and systems are presented. The methods include, for instance: evaluating a brand value as a function of numerous parameters as formulated by brand value dynamics, and by use of input data for accurate prediction of the brand value. A brand equity is estimated based on the brand value and brand values of all brands competing in the market.

Abstract: Methods, computer program products, and systems are presented. The methods include, for instance: building model connections between models in a knowledgebase, which stores case data as model networks. An exploration probability stored in the knowledgebase indicates a likelihood of new connections based on a case data input to be employed for an analytical model of the case data input, which includes numerous stages and multiple model choices in each stage. Based on the new connections and model networks of the knowledgebase, paths are created and performance of respective paths/connections are evaluated. A predefined number of top performing paths are selected and the models and attributes that do not appear in the top performing paths are eliminated from the knowledgebase. Probabilities of model networks and a future case data input are updated accordingly and a best-fit model for the case data input is presented to a user.

Abstract: Methods, computer program products, and systems are presented. The methods include, for instance: predicting a market share based on consumer preference shift based on inputs of including sales data of respective branded products in a market, product feature data, and product event data. Feature cluster switch rates are first estimated and then brand switch rate within a subject feature cluster is estimated. Future market share of a branded product having the subject feature cluster is predicted and reported.

Abstract: Methods, computer program products, and systems are presented. The methods include, for instance: identifying a target customer population of a series product and dividing into segments by customer behaviors relevant to adoption of and compliance to a series of purchases of the series product. A marketing campaign strategy for each segment is devised and executed, and adoption rate and compliance rate is predicted by analytical modeling and later evaluated by actual sales data. Parameters used in predicting the adoption rate and the compliance rate are adjusted for accuracy.

Abstract: From a log of a machine, an entry is selected relating to providing a subservice in processing a service request from a requestor associated with a key. The log entry includes a subsequence of machines used and a cost of providing the subservice. A set of entries is selected from the log, an entry including the subsequence and a second cost of providing the subservice but in processing a different service request from a different requestor associated with a different key. A distance is computed between the cost and the second cost. A number of occurrences of the subsequence with the key is determined. Using the number and the distance for the subsequence, a value pair is computed. Responsive to an aggregate number in the value pair not exceeding a threshold count. The processing of the service request is output as a suspect for using an improper sequence of machines.

Abstract: An amount of time needed to fill a job requirement is forecasted. By executing a forecasting algorithm, a numerosity of resumes matching the job requirement during the amount of time is forecasted. Using the numerosity and the amount of time, a risk value is computed corresponding to the job requirement, the risk value being indicative of a probability that the job requirement will go unfulfilled in the amount of time. From a base tuple corresponding to the job requirement, a second tuple is constructed, the second tuple having a distance from the base tuple. In real-time a second risk value is computed corresponding to the second tuple. When the second risk value is less than the risk value, data of the second tuple is presented as a risk minimization option for the job requirement.

Abstract: Methods, computer program products, and systems are presented. The methods include, for instance: collecting user data from the user, analyzing a context of an event including one or more actions from the user data; identifying subsequent actions of the event based on the context of the event, creating one or more context-personality-cognitive state (CPC) mapping and building up a knowledgebase by machine learning, predicting a cognitive state of the user while performing a of the event based on the knowledgebase. The method generates the alarm for the subsequent action based on the predicted first cognitive state of the user and notifying the generated alarm to the user.

Abstract: A network of nodes is constructed from data obtained from a data source of a social medium. A node corresponds to a medical professional. From the data, a likelihood is determined of the node prescribing a product. From the data, for a period, a level of knowledge is computed of the node about the product. A change in the level of knowledge of the node from a previous period is determined. Using a change in a level of knowledge corresponding to each node in the network, an amount of knowledge reinforcement to be applied to each node in the network is computed. A knowledge reinforcement resource to perform knowledge reinforcement at a subset of the nodes is allocated according to a schedule, where the allocated knowledge reinforcement resource to the node has a correspondence with the change in the level of knowledge of the node.

Abstract: A set of factors affecting a sold volume of the product is collected at a store in a geographical portion of a geographical area. A subset of a set of area stores is identified having a corresponding sold volume of the product. An intrinsic capacity of the product is computed by adjusting the sold volume of an area store by a first volume where the first volume is due to a sale of a second product at the area store. A modified intrinsic capacity is computed by modifying an effect of a factor from the subset on the intrinsic capacity such that the effect is worse than an effect of the factor at the store. A virtual store is constructed using modified intrinsic capacities of a sub-subset of area stores. A target volume of the product is set at the store as the virtual intrinsic capacity at the virtual store.

Abstract: Aspects provide for selective location of supplies of goods based on dynamic population density and travel distance metrics. Consumer population density forecasts are determined for different geographic locations as functions of distances to different events having different population amounts and geographic population locations. A geographic maximal density location point is determined between geographic locations of the different events and that is located at different distances from the locations of different events as a function of differences in respective consumer population density forecasts for the events, and closer to an event location with a higher consumer population density forecast relative to the location of another event. A quantity of goods is allocated to a supply site that is located at the maximal density location point in an amount selected to maximize a business value of the goods as a function of a population distribution of the maximal density location point.