Abstract:
One or more problems may be detected in an executing application by retrieving runtime execution information from the application executing on one or more computers. The runtime information is transformed into a temporal sequence of events. A knowledgebase is searched for a dialog that has nodes in an order that match the temporal sequence of events according to a threshold degree. Responsive to finding the dialog in the knowledgebase, the dialog is launched on a user interface to interact with a user and guide the user through a problem identification and solution. Responsive to not finding the dialog, additional instrumenter is enabled in the application.
Abstract:
One or more problems may be detected in an executing application by retrieving runtime execution information from the application executing on one or more computers. The runtime information is transformed into a temporal sequence of events. A knowledgebase is searched for a dialog that has nodes in an order that match the temporal sequence of events according to a threshold degree. Responsive to finding the dialog in the knowledgebase, the dialog is launched on a user interface to interact with a user and guide the user through a problem identification and solution. Responsive to not finding the dialog, additional instrumenter is enabled in the application.
Abstract:
One or more problems may be detected in an executing application by retrieving runtime execution information from the application executing on one or more computers. The runtime information is transformed into a temporal sequence of events. A knowledgebase is searched for a dialog that has nodes in an order that match the temporal sequence of events according to a threshold degree. Responsive to finding the dialog in the knowledgebase, the dialog is launched on a user interface to interact with a user and guide the user through a problem identification and solution. Responsive to not finding the dialog, additional instrumenter is enabled in the application.
Abstract:
Diagnosing and detecting causes of an incident may comprise classifying the incident by keywords, searching for co-occurring and reoccurring group of incidents, summarizing commonalities in the group of incidents, correlating the group of incidents with causes, defining association rules between the commonalities, and predicting potential problems based on the correlated group of incidents with causes.
Abstract:
Recommending problem resolution knowledge, in one aspect, may comprise determining a given product information associated with a product by searching an information network. The given product information may comprise a type of the given product, one or more features associated with the given product, and temporal information associated with the given product. One or more related products may be retrieved from the knowledge base. Related product information associated with each of the one or more related products may be determined, e.g., by searching the information network. At least one related product is selected that has the related product information that most closely matches the given product information. A dialog network from the knowledge base associated with the at least one related product is presented for the problem resolution of the given product.
Abstract:
A computer-implemented method is provided for processing a set D of conversation logs. The method includes learning, by a processor device, a set R of entity relation mining rules from a set K of known entity utterances uttered by known entities. The method further includes automatically recommending, by the processor device, extended utterances of the known entities from unrecognized ones of the known entities based on the set R.
Abstract:
A method, apparatus and computer program product for presenting a user interface for a conversational system is described. A unified contextual graph for use by the conversational system, the unified contextual graph comprising components based on database queries of the conversational system and a user dialog between a user and the conversational system. For each of a set of user utterances produced in a dialog with the conversational system, a semantic meaning representation is determined. The semantic meaning representations are converted to respective sentential concept graphs. The unified contextual graph is updated based on new sentential concept graphs while the dialog with the conversational system progresses.
Abstract:
One or more problems may be detected in an executing application by retrieving runtime execution information from the application executing on one or more computers. The runtime information is transformed into a temporal sequence of events. A knowledgebase is searched for a dialog that has nodes in an order that match the temporal sequence of events according to a threshold degree. Responsive to finding the dialog in the knowledgebase, the dialog is launched on a user interface to interact with a user and guide the user through a problem identification and solution. Responsive to not finding the dialog, additional instrumenter is enabled in the application.
Abstract:
Building, reusing and calibrating network of authored content, in one aspect, may comprise clustering a plurality of problem tickets into one or more clusters. The clusters may be associated to one or more FAQ nodes in a FAQ network. The associated one or more FAQ nodes may be checked to determine whether the nodes are part of a broken branch. If the one or more FAQ nodes leads to a broken branch, a user may be notified to update the branch, e.g., with an answer or resolution to the one or more FAQ nodes.
Abstract:
A computer-implemented method is provided for processing a set D of conversation logs. The method includes learning, by a processor device, a set R of entity relation mining rules from a set K of known entity utterances uttered by known entities. The method further includes automatically recommending, by the processor device, extended utterances of the known entities from unrecognized ones of the known entities based on the set R.