Abstract: A conversation support apparatus 10 includes: an utterance reception unit 11 that receives an utterance in an on-going conversation; an utterance position estimation unit 12 that, for each node in a conversation tree in which at least one of a label and a topic is provided to each node, collates the at least one of the label and the topic provided to the node and the received utterance, and estimates a node that is most related to the received utterance; and a display unit 13 that adds a visual characteristic representation to the estimated node and displays the conversation tree on a screen.

Abstract: A display format determination apparatus is provided with a display number prediction unit that calculates, for each of a plurality of display formats for displaying choices, a predicted value representing a prediction of the number of display items displayed until one of the choices is selected, on the basis of an index value representing, for each choice, a magnitude of a probability that each choice is selected; and a display format determination unit that selects one of the display formats on the basis of the calculated predicted value.

Abstract: A question responding apparatus is provided with a type determination unit that determines, on the basis of a question from a user, the type of answer to the question; a path selection unit that selects one path among paths from a current position node selected from among nodes in a hierarchical structure of information to matching nodes that match the type of answer; and a choices processing unit that presents information that indicates a node included in the selected path to the user as a choice.

Abstract: An addition unit 11, with regard to data indicating a conversation history including one or more sets of sentences formed from a problem sentence being a sentence indicating one problem, a question sentence being a sentence indicating a question for the one problem, and an answer sentence being a sentence indicating an answer to the question, adds a label indicating a problem state to the problem sentence within the data, a label indicating a question state to the question sentence within the data, and a label indicating an answer state to the answer sentence within the data. An extraction unit 12 extracts, from the data, a set of sentences with which the states indicated by the labels have been associated according to a state transition model that is a model configured from the one problem state, question state, and answer state, and that represents a transition of the states.

Abstract: A conversation support apparatus 10 includes: an utterance reception unit 11 that receives an utterance in an on-going conversation; an utterance position estimation unit 12 that, for each node in a conversation tree in which at least one of a label and a topic is provided to each node, collates the at least one of the label and the topic provided to the node and the received utterance, and estimates a node that is most related to the received utterance; and a display unit 13 that adds a visual characteristic representation to the estimated node and displays the conversation tree on a screen.

Abstract: A data structuring device 1 includes an acquisition unit 2 and a modeling unit 3. The acquisition unit 2 acquires branch expression data. Branch expression data is data that includes a branch expression, which is an utterance expression in a conversation for which multiple mutually different replies can be assumed. The conversation data is converted to a graph structure in which the content of the conversation is divided into multiple nodes, and the multiple nodes are connected by means of edges. On the basis of the branch expression data obtained by the acquisition unit 2, the modeling unit 3carries out a process on the multiple items of conversation data in the graph structure in which nodes that share a common branch expression are combined in one node, thereby modeling the multiple items of conversation data in one tree structure.

Abstract: Provided is an information processing system for detecting a project risk more preferably with fewer input information. The system includes: feature representation totalizing means that totalizes an occurrence frequency of a feature representation related to each process based on a set of a message and a time of occurrence of the message, and on feature representation information indicating the feature representation related to the process; and discrepancy determination means that outputs information about discrepancy between ideal and actual states of the process based on an occurrence rate calculated from the occurrence frequency related to the process and on a detection rule that defines a position of the occurrence rate on a time axis.