Abstract: The present invention provides a traffic information processing apparatus and method, the apparatus comprises a format unifying device which unifies input traffic information with different formats to traffic information with unified format; and a traffic information integrating device which corrects and/or complements the traffic information with unified format based on a knowledge base to obtain traffic information which is consistent with each other, so as to integrate the traffic information, wherein the knowledge base is external to the apparatus or internal to the apparatus. The traffic information processing apparatus and method according to the present invention can process traffic information with spatial inconsistence, temporal inconsistence and semantic inconsistence so as to integrate effectively the traffic information from a variety of heterogeneous information sources and ensure the accuracy, completeness and reliability of traffic data.

Abstract: The present invention provides an apparatus for expanding a query requirement, comprising: a query requirement understanding device which generates an explicit query requirement according to a user query request; and a query requirement expanding device which generates an implicit query requirement associated with the explicit query requirement. The query requirement understanding device generates an explicit query requirement including a query concept and a question type by searching a knowledge base and a language base, and the query requirement expanding device generates an implicit query requirement including a query concept and a question type by searching the knowledge base, the language base and a relevancy database. The present invention further provides a method for expanding a query requirement. The apparatus and method for expanding a query requirement according to the present invention can facilitate a user's query and provide the user with an accurate, comprehensive query answer.

Abstract: A hypertext checking apparatus comprises: a hypertext database 21 which stores the information about a page and a link; an information collecting unit 11 which collects an information about the page and the link in the hypertext obtained from the hypertext database 21; a condition detecting unit 13 which refers to the hypertext database 21 to detect a part including logically mismatched link; a candidate providing unit 12 that provides a correction candidate related to the parts detected by the condition detecting unit 13; and a correction reflecting unit 14 which corrects the hypertext based on the part detected by the condition detecting unit 13 and the correction candidate provided by the correction providing unit 12.

Abstract: A natural language based location query system and a method thereof. The system comprises a receiving device which receives a request for natural language query from a user terminal; an access device which accesses a location ontology base and a location query language base that are external to the system or internal in the system, wherein the location ontology base comprising knowledge descriptions about the field of a location service, and the location query language base comprising a language model for the location service query; a natural language query processing device which performs at least one of a fuzzy processing and an indirection processing on the received request for natural language query by searching the location ontology base and the location query language base with the access device, retrieves location information corresponding to the request from a location database; and a sending device which sends the location information to the user terminal.

Abstract: A place name information extraction apparatus in which not only a place name expression appeared in a text is extracted but also the type of the extracted place name expression can be judged, and a place name information extraction method of the apparatus, and a storing medium stored place name information extraction programs of the method, and a map information retrieval apparatus used the place name information extraction apparatus are provided. The place name information extraction apparatus provides a place name expression detecting means that detects a place name expression appeared in a text and its position appeared the place name expression in the text, and a place name type judging means that judges a place name type, which signifies a meaning role of the place name expression appeared in the text, by analyzing before and after the position appeared the place name expression in the text.

Abstract: A named entity discriminating system capable of discriminating names entities such as location names, personal names, and organization names in text with a high degree of accuracy is provided. A reading means reads text from a hypertext database. A single text analyzing means analyzes each text read by the reading means and detects candidates for the named entity in the text. A complex text analyzing means estimates the likelihood of the candidate named entity detected by the single text analyzing means by an analysis with reference to referring link text or linked text of the text in which the candidate named entity appears.

Abstract: A hypertext checking apparatus comprises: a hypertext database 21 which stores the information about a page and a link; an information collecting unit 11 which collects an information about the page and the link in the hypertext obtained from the hypertext database 21; a condition detecting unit 13 which refers to the hypertext database 21 to detect a part including logically mismatched link; a candidate providing unit 12 that provides a correction candidate related to the parts detected by the condition detecting unit 13; and a correction reflecting unit 14 which corrects the hypertext based on the part detected by the condition detecting unit 13 and the correction candidate provided by the correction providing unit 12.

Abstract: A place name information extraction apparatus in which not only a place name expression appeared in a text is extracted but also the type of the extracted place name expression can be judged, and a place name information extraction method of the apparatus, and a storing medium stored place name information extraction programs of the method, and a map information retrieval apparatus used the place name information extraction apparatus are provided. The place name information extraction apparatus provides a place name expression detecting means that detects a place name expression appeared in a text and its position appeared the place name expression in the text, and a place name type judging means that judges a place name type, which signifies a meaning role of the place name expression appeared in the text, by analyzing before and after the position appeared the place name expression in the text.

Abstract: A named entity discriminating system capable of discriminating names entities such as location names, personal names, and organization names in text with a high degree of accuracy is provided. A reading means reads text from a hypertext database. A single text analyzing means analyzes each text read by the reading means and detects candidates for the named entity in the text. A complex text analyzing means estimates the likelihood of the candidate named entity detected by the single text analyzing means by an analysis with reference to referring link text or linked text of the text in which the candidate named entity appears.

Abstract: A full-text data base retrieving device retrieves a data base in accordance with a query. A full-text index has character location information representative of location of each of key character sequences of N characters that appear in the data base, where N is a positive integer. A query memory memorizes the query as a retrieval key character sequence. A separating section separates the retrieval key character sequence into a plurality of retrieval key character sequences of N characters to extract contexts as extracted contexts from the retrieval key character sequence in accordance with the retrieval key character sequences. A context classifying section classifies the extracted contexts into classified contexts having the classification numbers, respectively. An index retrieving section retrieves the full-text index in accordance with the sorts of the retrieval key character sequences and the classified contexts to read the character location information as a retrieval result out of the full-text index.

Abstract: A character strings reading device for reading character strings from input image data comprises cut-out recognition means for cutting out a segment corresponding to one character from the image data to perform individual character recognition every segment, a recognition result buffer for storing a recognition result of the cut-out recognition means, word searching means for searching a word string candidate corresponding to a combination of character candidates in the recognition result buffer, a word string candidate buffer for storing a search result of the word searching means, check portion determining means for determining a check target portion and a presumed character string of the check target portion on the basis of the result in the word string candidate buffer, and check means for judging the possibility of existence of the presumed character string on the check portion.

Abstract: A full-text data base retrieving device retrieves a data base in accordance with a query. A full-text index has character location information representative of location of each of key character sequences of N characters that appear in the data base, where N is a positive integer. A query memory memorizes the query as a retrieval key character sequence. A separating section separates the retrieval key character sequence into a plurality of retrieval key character sequences of N characters to extract contexts as extracted contexts from the retrieval key character sequence in accordance with the retrieval key character sequences. A context classifying section classifies the extracted contexts into classified contexts having the classification numbers, respectively. An index retrieving section retrieves the full-text index in accordance with the sorts of the retrieval key character sequences and the classified contexts to read the character location information as a retrieval result out of the full-text index.

Abstract: A character string input system includes an input storage portion for temporarily storing input character string with an incomplete input indicative signs. There is also a word dictionary storing words. An incomplete word supplementing portion compares the character string with the word stored in the word dictionary. Also, there is a neglected word supplementing portion for predicting a word to be supplemented at the position of the incomplete input indicative sign representing an omitted word. A supplementing candidature storage portion temporarily stores candidate character strings for the incomplete word supplementing portion and the neglected word supplementing portion. A supplementing control portion controls the incomplete word supplementing portion and the neglected word supplementing portion on the basis of the incomplete input indicative sign, and retrieves the candidate character string corresponding to the position of the incomplete input indicative sign in the character string.

Abstract: A character string input system includes a direct character string buffer 50 storing character coded direct character string, a character string predicting portion 60 generating a predicted character string immediately following character string in the direct character string buffer 50, a predicted character string buffer 70 storing the predicted character string generated by the character string predicting portion, a display control portion 100 and a display portion 110 for displaying the direct character string stored in the direct character string buffer 50 and the predicted character string stored in the predicted character string buffer 70, a selection command input portion 30 for selecting a desired character string among the predicted character strings stored in the predicted character string, and a learning control portion 130 and a learning portion 140 storing hysteresis information which is made reference to upon generation of the character string candidates by the character string predicting portio