Method and apparatus for automatically analyzing natural language to extract useful information,申请号US201113300573-传众专利搜索

Method and apparatus for automatically analyzing natural language to extract useful information

申请公布号：US8903713(B2)

申请号：US201113300573

申请日期：2011.11.19

申请公布日期：2014.12.02

发明人：Peterson Richard L.

分类号：G06F17/27

主分类号：G06F17/27

代理机构：

Mersenne Law LLP

代理人：Mersenne Law LLP

摘要：An automatic language-processing system uses a human-curated lexicon to associate words and word groups with broad sentiments such as fear or anger, and topics such as accounting fraud or earnings projections. Grammar processing further characterizes the sentiments or topics with logical (“is” or “is not”), conditional (probability), temporal (past, present, future), quantitative (larger/smaller, higher/lower, etc.), and speaker identification (“I” or “He” or “Alan Greenspan”) measures. Information about the characterized sentiments and topics found in electronic messages is stored in a database for further analysis, display, and use in automatic trading systems.

主权项：1. A non-transitory computer-readable medium containing instructions to cause a programmable processor to perform operations comprising: analyzing a plurality of natural-language messages to identify predetermined words in the messages, said predetermined words including a company name and a financial assertion; applying a heuristic to attribute the financial assertion to a speaker making the financial assertion; and emitting a signal if the speaker is a member of a management team of a company having the company name, wherein the financial assertion refers to higher earnings.