pchen
e6a29bcdfd
c_NlpNgramGraph: 基于 n 个已经出现的词，预估后续可能出现的词 c_NlpLanguageModel: 如果有的词组合形式没有出现过，找到之前学习过最长类似的词句进行预测
39 lines
1.7 KiB
C
39 lines
1.7 KiB
C
#ifndef INCLUDED_C_NLPLANGUAGEMODEL_H
|
|
#define INCLUDED_C_NLPLANGUAGEMODEL_H
|
|
|
|
#ifndef INCLUDED_C_NLPNGRAMGRAPH_H
|
|
#include <c_NlpNgramGraph.h>
|
|
#endif /*INCLUDED_C_NLPNGRAMGRAPH_H*/
|
|
|
|
|
|
typedef struct {
|
|
c_NlpNgramGraph_t* levels; /* Array of N-gram graphs sorted from highest order down to 2-gram */
|
|
c_size_t max_n; /* The maximum configuration order N of the model (e.g., 3 for Trigram) */
|
|
double backoff_alpha; /* Proportional smoothing decay factor (typically 0.4) used per back-off step */
|
|
} c_NlpLanguageModel_t;
|
|
|
|
/**
|
|
* @brief Initializes a multi-tier cascaded Language Model environment supporting back-off smoothing.
|
|
* @param self Pointer to the uninitialized language model structure.
|
|
* @param max_n Maximum model order threshold (e.g., 3 creates a Trigram + Bigram cascading mesh).
|
|
* @param bucket_count Main hash allocation array size mapped down to sub-graphs.
|
|
* @return c_err_t C_ERR_OK on successful initialization, or dynamic memory OOM codes.
|
|
*/
|
|
c_err_t c_NlpLanguageModel_Init(c_NlpLanguageModel_t* self, c_size_t max_n, c_size_t bucket_count);
|
|
|
|
/**
|
|
* @brief Core Prediction: Evaluates histories and executes automated back-off smoothing cascades.
|
|
*/
|
|
c_err_t c_NlpLanguageModel_PredictSmooth(c_NlpLanguageModel_t* self, const c_ucs4_t* history_context, c_size_t history_len,
|
|
c_ucs4_t* out_next_char, double* out_confidence);
|
|
|
|
/**
|
|
* @brief Destroys and flushes all cascaded hierarchy sub-graphs completely.
|
|
*/
|
|
void c_NlpLanguageModel_Destroy(c_NlpLanguageModel_t* self);
|
|
|
|
|
|
c_err_t c_NlpLanguageModel_Train(c_NlpLanguageModel_t* self, const c_ucs4_t* unicode_array, c_size_t length);
|
|
|
|
#endif /*INCLUDED_C_NLPLANGUAGEMODEL_H*/
|