Generating finite state automata for recognition of organic compound names in Chinese

A device for generating a finite state automata, the device comprising:

• a memory;
• and
• a processor coupled to the memory and configured to:
• initializing to substitute representation constants of categories of character segments appearing in an organic compound name set into the organic compound name set to obtain a conversion name set;
• updating the conversion name set based on a conversion name segment which repeatedly appears in the conversion name set;
• and
• generating a finite state automata based on the updated conversion name set;
• wherein respective organic compound names in the organic compound name set are in Chinese,
• wherein the updating comprises:
• determining a conversion name segment of two adjacent representation constants in the conversion name set being different and setting a corresponding representation constant for the two adjacent representation constants as a binary representation to update a binary representation set, wherein respective binary representations in a binary representation set satisfy:
• a time for which a conversion name segment to which the binary representation corresponds appears in the conversion name set is greater than a first predetermined threshold;
• determining a conversion name segment in the conversion name set where the same representation constant continuously appears for n times or more than n times and setting a corresponding representation constant for the same representation constant as a repeated representation to update a repeated representation set, wherein each repeated representation in the repeated representation set is used for collectively representing a conversion name segment in which the same representation constant to which the repeated representation corresponds continuously appears, and n is equal to a second predetermined threshold;
• judging whether both the updated binary representation set with respect to a previous binary representation set and the updated repeated representation set with respect to the previous repeated representation set do not vary;
• and
• updating a conversion name set, when a judgment result of the judging is that at least one of the updated binary representation set and the updated repeated representation set varies, by substituting representation constants in the binary representation set and representation constants in the repeated representation set into the conversion name set.

A non-transitory computer-readable storage medium with a program stored thereon, where when the program is executed on an information processing apparatus, causes the information processing apparatus to implement operations comprising:

• initializing including substituting representation constants of categories of character segments appearing in an organic compound name set into the organic compound name set to obtain a conversion name set;
• updating the conversion name set based on a conversion name segment which repeatedly appears in the conversion name set;
• and
• generating finite state automata for recognizing a chemical name in a text, based on the updated conversion name set;
• wherein respective organic compound names in the organic compound name set are in Chinese,
• wherein the updating comprises:
• determining a conversion name segment of two adjacent representation constants in the conversion name set being different and setting a corresponding representation constant for the two adjacent representation constants as a binary representation to update a binary representation set, wherein respective binary representations in a binary representation set satisfy:
• a time for which a conversion name segment to which the binary representation corresponds appears in the conversion name set is greater than a first predetermined threshold;
• determining a conversion name segment in the conversion name set where the same representation constant continuously appears for n times or more than n times and setting a corresponding representation constant for the same representation constant as a repeated representation to update a repeated representation set, wherein each repeated representation in the repeated representation set is used for collectively representing a conversion name segment in which the same representation constant to which the repeated representation corresponds continuously appears, and n is equal to a second predetermined threshold;
• judging whether both the updated binary representation set with respect to a previous binary representation set and the updated repeated representation set with respect to the previous repeated representation set do not vary;
• and
• updating a conversion name set, when a judgment result of the judging is that at least one of the updated binary representation set and the updated repeated representation set varies, by substituting representation constants in the binary representation set and representation constants in the repeated representation set into the conversion name set.