Recognition system method
View Patent ↗A method for a recognition system, for example for recognizing a location name according to a preset, spelled voice entry, in order to shorten the reaction time for a new start of a system in which data must first be transferred from a reading memory into a working memory via a connection at a low data rate. According to the method, the data are grouped in data blocks, corresponding to successive structural levels, with the data content being arranged in the manner of a branched tree structure, and with the data blocks in the hierarchical sequence of the associated structural branch levels being consecutively transferred from the reading to the working memory. The recognition has already begun, on the basis of the still-incomplete data set, after a plurality of levels is present, and is continued in real time with the transfer of further data blocks. The average processing time can be reduced further through an advantageous structuring and grouping of the data.
1. A method for character recognition for a character recognition system having a reading memory, a working memory, an entry device and a recognition device, with said method including the steps of: storing a data set of memory character sequences in the reading memory; transferring the character sequences from the reading memory into the working memory in a serial manner; in the recognition device, deriving an association of an entered-character sequence provided by the entry device with one of the transmitted memory character sequences by the linking of the supplied entered-character sequence with the contents of the working memory; and, wherein the stored character sequences are represented in a hierarchical branched structure having a plurality of branch levels, and, said step of transferring the character sequence data of the data set includes transmitting the partial data of successive structural branch levels one after another over time, and causing the recognition device to already receive the possible linking of a possibly-present entered-character sequence having the still-incomplete contents of the working memory before the transfer of the entire data set is complete.
2. The method defined in claim 1 , wherein the partial data of a structural branch level are arranged as a cohesive data block, and the data blocks are arranged in a hierarchy of successive structural levels as a linear data sequence in the reading memory.
3. The method defined in claim 2 , wherein the reading memory is a portable data carrier.
4. The method defined in claim 1 , wherein the reading memory is a portable data carrier.
5. The method defined in claim 1 , wherein the characters of the stored character sequences are at least one of individual symbols and sequences of symbols from a finite list of symbols.
6. The method defined in claim 1 , wherein the character sequences comprise alphanumeric symbols.
7. The method defined in claim 1 , wherein, for the characters of a structural level, the number of permissible subsequent characters of the next structural level is stored and transferred.
8. The method defined in claim 5 , wherein, for characters comprising a plurality of symbols, the number of symbols of the respective character is stored and transferred.
9. The method defined in claim 8 , wherein the entry device is a device for receiving and interpreting voices.
10. The method defined in claim 1 , wherein the entry device contains an intermediate memory for the entered-character sequence.