METHOD computer classification unsegmented text in the language C ideographic writing system

摘要

1.a computer classification u043du0435u0441u0435u0433u043cu0435u043du0442u0438u0440u043eu0432u0430u043du043du044bu0445 texts on u00a0u0437u044bu043au0435 with u0438u0434u0435u043eu0433u0440u0430u0444u0438u0447u0435u0441u043au043eu0439 writing system, comprising a u0441u0435u0431u00a0 method u0441u0443u043cu043cu0438u0440u043eu0432u0430u043du0438u00a0 u043au043bu0430u0441u0441u0438u0444u0438u043au0430 development of chinese characters u0434u043bu00a0 u043eu043fu0440u0435u0434u0435u043bu0435u043du0438u00a0 background text to a certain class, u043eu0442u043bu0438u0447u0430u044eu0449u0438u0439u0441u00a0 so that as the basic elements of the analysis use t signs of writing systems u0438u0434u0435u043eu0433u0440u0430u0444u0438u0447u0435u0441u043au0438u0445 u00a0u0437u044bu043au043eu0432 - hieroglyphicsin this u0434u043bu00a0 each symbol in the text on the special database u043eu043fu0440u0435u0434u0435u043bu00a0u044eu0442 u0432u0435u0441u043eu0432u043eu0435 importance u0434u043bu00a0 each version of the classification, the u0437u043du0430u0447u0435u043du0438u00a0 all u0438u0435u0440u043eu0433 u043bu0438u0444u043eu0432 each option classification u0441u0443u043cu043cu0438u0440u0443u044eu0442, u043fu043eu043bu0443u0447u0430u00a0 weighting u0437u043du0430u0447u0435u043du0438u00a0 u0434u043bu00a0 text for each potential option classificationfurther, the u0437u043du0430u0447u0435u043du0438u00a0 compared and on the basis of the maximum u0437u043du0430u0447u0435u043du0438u00a0 conclude that belong to a particular class.;2. method for u043eu0442u043bu0438u0447u0430u044eu0449u0438u0439u0441u00a0 1, however, that in addition to the characters for the unit of analysis are the signs u043fu0440u0435u043fu0438u043du0430u043du0438u00a0.;3. method for u043eu0442u043bu0438u0447u0430u044eu0449u0438u0439u0441u00a0 1, however, that in addition to the characters for the unit of analysis are the signs u00a0u043fu043eu043du0441u043au043eu0433u043e alphabet, kana.;4. method for u043eu0442u043bu0438u0447u0430u044eu0449u0438u0439u0441u00a0 1, however, that in addition to the characters for the unit of analysis u043fu0440u0438u043du0438u043cu0430u044eu0442u0441u00a0 other written signs u00a0u0437u044bu043au0430 (figures, innovative signs u043fu0440u0435u043fu0438u043du0430u043d u0438u00a0 "emoticons" and others).;5. method for u043eu0442u043bu0438u0447u0430u044eu0449u0438u0439u0441u00a0 1, so that the u0441u0443u043cu043cu0438u0440u0443u044eu0442 only u0437u043du0430u0447u0435u043du0438u00a0 more 1.;6. method for u043eu0442u043bu0438u0447u0430u044eu0449u0438u0439u0441u00a0 1, so that the u0437u043du0430u0447u0435u043du0438u00a0 less than 1 are from the sum of the weight u0437u043du0430u0447u0435u043du0438u00a0 equal 1 does not take into account.