发明名称 Method for recommending best information in real time by appropriately obtaining gist of web page and user's preference
摘要 Disclosed is an information recommendation method for providing a construction method for a classified word database capable of rapidly accommodating changes in associations between words. The disclosed information recommendation method basically is based on the finding that, by analyzing occurrence frequency information of an arbitrary word in a Web site having an arbitrary classified word in real-time and obtaining the real-time degree of similarity between the classified word and the arbitrary word, it is possible to construct a database that is capable of being sensitive in responding to changes in associations between words. The disclosed information recommendation method relates to a method of extracting classified words indicating a main idea of text included in a Web page, accumulating the classified words, and constructing a real-time tag database; an information recommendation method for using the tag database to reflect the main idea of the Web page in real-time; and an information matching method of advertisements for using the tag database to reflect the main idea of the Web page and tastes of users in real-time.
申请公布号 US8812505(B2) 申请公布日期 2014.08.19
申请号 US201013518065 申请日期 2010.12.24
申请人 TAGGY, Inc. 发明人 Ishigami Yutaka
分类号 G06F17/30 主分类号 G06F17/30
代理机构 Posz Law Group, PLC 代理人 Posz Law Group, PLC
主权项 1. An information recommending method with a computer using a database storing multiple classification words displayed as a tag or a category in a web site, one or more words related to each of the multiple classification words, and a numerical value of the relationship of one or more words with the classification word in association with each other, wherein the tag is text information displayed on the web page as which is representing the gist of a word group included in sentences of the web site, the method comprises a step of establishing the database, wherein the step for establishing the database comprises: a web site selecting step in which the computer selects multiple web sites having a certain classification word from web sites connected to the computer via an electronic communication circuit; a word group extracting step in which the computer extracts the word group included in the sentences in the web sites selected in the web site selecting step; a numeric conversion step in which the computer measures, in the web sites selected in the web site selecting step, a frequency of each word included in the word group extracted in the word group extracting step, and performs numerical conversion on a relationship between the certain classification word and each word to determine the numerical value; and a storage step in which the computer stores, to the database, the numerical value obtained in the numeric conversion step for each word included in the word group and each word of the word group included in the sentences of the web sites selected in the web site selecting step in relation to the certain classification word, a first word extracting step of extracting words included in each of multiple web pages; a first classification word extracting step of accessing the database using the words extracted in the first word extracting step, and extracting a classification word from the database, and thereby extracting the classification word related to each of the web pages; a related classification word storing step of storing access information to each of the web pages and the classification word related to each of the web pages extracted in the first classification word extracting step in association with each other; a second word extracting step of extracting words used for a search of the Internet by a certain client or words included in web pages viewed by the certain client; a second classification word extracting step of accessing the database using the words extracted in the second word extracting step, and extracting a classification word from the database, and thereby extracting the classification word related to each client; a web page selecting step of obtaining a web page having a classification word related to the classification word extracted in the second classification word extracting step using the classification word extracted in the second classification word extracting step and the classification word extracted in the first classification word extracting step; and an access information displaying step of reading out the access information to the web page obtained in the web page selecting step from the access information stored in the related classification word storing step, and displaying the access information read out on the client; therefore, the preference of a user of the client that can be read from the certain client and the web page suitable for the preference can be matched.
地址 Tokyo JP