Abstract:
The present invention relates to a mobile device and a method for classifying moving actions of a user and a method for creating a hierarchical tree model for the same. The mobile device comprises: an acceleration sensor; a buffer for collecting acceleration data outputted from the acceleration sensor according to a specific action of a user; an extraction unit for extracting a characteristic element about the specific action of the user based on the acceleration data collected in the buffer; and an action determination unit for classifying the specific action of the user into a certain action by inputting the characteristic element extracted by the extraction unit to a previously configured hierarchical tree model. The hierarchical tree model was constructed in advance based on an extracted characteristic element from each action. The characteristic element of each action is extracted based on a first frame group which is configured by dividing the selected acceleration data for each action by a predetermined time unit and a second frame group in which part of the acceleration data is constructed to overlap with the first frame group by separating the collected acceleration data for each action by a different time unit from the predetermined time unit.
Abstract:
The present invention relates to a method of recognizing user-context by using a multimodal sensor comprising an acceleration sorting step in which mobility feature candidates are extracted from user acceleration data collected through an acceleration sensor, at least one mobility feature is selected from the extracted mobility feature candidates based on relevancy and redundancy of the extracted mobility feature candidates, and a mobility type of a user is inferred from the selected mobility feature by using a first time sequential stochastic model.In an audio sorting step, surrounding environment features are extracted from audio data concerned about user surrounding environment and collected through an audio sensor and a type of surrounding environment is inferred from the extracted surrounding environment features by using a second time sequential stochastic model.Further, the method of recognizing user-context comprises a user-context recognizing step by which the user context is recognized by using at least one of the types of user motion and surrounding environment. [Reference numerals] (AA) Start; (BB) End; (S111) Collect acceleration data through acceleration sensor; (S113) Extract mobility feature candidate; (S115) Select mobility feature; (S117) Infer mobility type; (S131) Collect audio data through audio sensor; (S133) Extract surrounding environment feature; (S135) Infer surrounding environment feature; (S150) Recognize user context; (S170) Confirm validity; (S190) Valid user context is recognized?
Abstract:
PURPOSE: An indoor location tracking device and a recording medium therefor are provided to update a mobile model of a user by using static data by collecting the static data related to a moving path of each particle. CONSTITUTION: A user location tracking unit(104) samples a replacement particle again by using updated weighted values. The user location tracking unit repetitively executes a particle resampling process according to the movement of a user. The user location tracking unit estimates a real-location in which particles are finally converged by the location of the user. A mobile model learning unit(106) updates a mobile model by using static data for the movement path of the matched particle. [Reference numerals] (100) Sensor module; (102) Wireless communication unit; (104) User location tracking unit; (106) Mobile model learning unit
Abstract:
PURPOSE: A service supplying method of a mobile terminal and a supplying method thereof for supplying an HTN plan service are provided to automatically plan an execution order by analyzing requested service demand content and searching for optimal services. CONSTITUTION: If a service request signal is inputted from a user, a mobile terminal presently analyzes a demand of the user by using preference data and present situation data of the user(S110). The mobile terminal generates an input parameter for an HTN(Hierarchical Task Network) plan(S120). The mobile terminal plans a service suitable for a situation of the user through a cloud server in order to obtain a service which the input parameter demands(S130).
Abstract:
PURPOSE: A bus number extracting apparatus used for a mobile terminal and a method thereof are provided to learn a trace of a user repeated every day based on sensor information, thereby extracting a suitable service according to CR(Cognitive Recognition) based an usual behavior. CONSTITUTION: A movement trace storage(110) accumulates repetitive movement trace data of a user having a similar pattern. A bus section extracting unit(120) extracts bus section data indicating a section which moves from the trace data to a bus. A stop section extracting unit(130) extracts stop section data corresponding to a stop state of the bus among the bus section data every time the stop state happens. A substitute path extracting unit(140) extracts departure and arrival stations, corresponding to a departure and an arrival points, from a bus database and extracts a substitute path passing via the departure and arrival stations.
Abstract:
PURPOSE: A mobile personal assistant and an interactional plan execution method thereof are provided to flexibly execute plans of various types according to a goal of work, a change of an environment and a control of a user, thereby efficiently operating in a dynamic mobile computing environment. CONSTITUTION: A plan set storage(110) stores a plan set including an event-leading plan, a goal-leading plan and a command-leading plan. The sensor(120) senses events happening in the external environment. A world modeling unit(130) stores information about the events in a world model. A UI(User Interface) unit(140) receives a control command of a user through UI. An interpreter(150) decides a execution of the plan by interpreting the world model, the control command and the plan set. An executing unit(170) executes an operation corresponding to the plan.
Abstract:
PURPOSE: A system and a method for inferring ontology based on mobile are provided to be applied to various ubiquitous computing fields by processing context which is generated from a mobile terminal in real time. CONSTITUTION: An ontology input unit(110) changes context into ontology type context. A fact conversion unit(120) stores a knowledge base(150) by converting a subject, a predicate, and object which is extracted from ontology context into a inferable fact based on a fact template which is defied by corresponding to a triple syntax. An ontology extractor(130) infers the face which is stored in a knowledge base by matching with an inference rule.