7 results about "Identification technology" patented technology

The invention discloses a conference record generation method based on a telephone conference and a device. The method comprises steps that voice content acquired by each conference terminal is acquired; the voice content is converted into text content; conference record is generated according to the text content, and the conference record is stored and/or is sent to a designated address. Through the method, the voice content recorded by each conference terminal is automatically converted into the text content by utilizing the voice identification technology, the conference record is generated according to the text content, so the conference record of the telephone conference is automatically generated, tediousness in manual conference recording can be avoided, operation efficiency is improved, and a telephone conference system is made to be more intelligent.

To provide an individual management system for managing products with the use of an automatic identification technology using a wireless communication device. In the individual management system, an individual management device is attached to a managed object, an individual identification device can wirelessly communicate with the individual management device, and an individual information management device can communicate with the individual identification device. The individual management device includes a detection portion such as a sensor. The individual identification device includes a position analysis portion which calculates a distance between the individual management device and the individual identification device. Information on the distance between the individual management device and the individual identification device, and information from the detection portion included in the individual management device are transmitted to the individual identification device. Accordingly, a system user can specify a position of the individual management device accurately.

The present invention provides a fingerprint direction feature obtaining method based on a striped pattern, and relates to the fingerprint automatic identification technology, etc. The method comprises three portions consisting of fingerprint image preprocessing, obtaining of three-dimensional single-base signals and obtaining of direction information. A fingerprint image is taken as a typical striped pattern, namely two-dimensional demodulated frequency modulation and amplitude modulation signals; two radian transition operators are employed to perform analysis solution of fingerprint signals to obtain three-dimensional single-base signals corresponding to the fingerprint signals; and according to the property of the single-base signals, the fingerprint direction information is obtained under polar coordinates. Compared to a traditional method, the fingerprint direction feature obtaining method based on the striped pattern eliminates the influence of noise and gray compensation values, has high anti-noise performance, and increases the credibility of a calculation result; and moreover, the operation of obtaining the fingerprint direction information in a frequency domain can directly eliminate the amplitude information in the fingerprint signals to obtain direction information representing the fingerprint uniqueness, avoid the problem that the modulation signals are not continuous in direction caused by the cosine function value restriction and reduce the unnecessary processing links so as to reduce the time cost of the identification system and effectively improve the identification efficiency of the system.

The invention relates to the technical field of text recognition, in particular to a text error correction method and device. The text error correction method comprises the following steps: identifying a to-be-corrected entity from a text sequence; determining a preset number of candidate entities from a target knowledge base according to the entity to be corrected; and executing preset processing on the entity to be corrected according to the similarity between the entity to be corrected and each candidate entity. According to the embodiment of the invention, the text error correction efficiency and accuracy are improved.

The invention discloses a switcher capable of automatically processing news simulcasting time extension. The switcher includes a base, a switcher main body is mounted at the top of the base; a coolingfan is mounted on one side of the power panel; a touch display panel is mounted on one side of the switcher main body; one end of the touch display panel is provided with a signal switching port. Oneside of the signal switching port is provided with a signal decoding port and a video image graph acquisition matching identification port. The invention discloses a switcher capable of automaticallyprocessing news simulcasting time extension. A CCTV1 signal is distributed into one path to be decoded to generate a video image picture; the system uses a video image identification technology. Firstly, news simulcasting corner mark identification and news simulcasting end identification of a fixed area in a news simulcasting picture are collected and stored, broadcasting and ending of news simulcasting are judged according to appearing and disappearing of corner mark and end identification graphs, and therefore complete rebroadcasting of news simulcasting and smooth broadcasting of subsequent programs are guaranteed.