The past decades have witnessed the rapid advancements of computational intelligence techniques， including big data， machine learning， and knowledge engineering， in both industrial and academic communities. Specifically， with the diffusion of some computing paradigms such as natural language processing， knowledge graph， reasoning decision， it promotes the computer-assisted diagnosis and treatment in Traditional Chinese Medicine (TCM). Through the integration of our research achievements in the field of intelligent information processing on TCM over the last decade， this book introduces the data processing technologies in TCM medical records and TCM medication， the medical records-based knowledge acquisition， the text-based knowledge acquisition， and the applications of TCM knowledge. We would like to provide a guidance for graduate students， university teachers and professional technicians engaged in knowledge engineering and TCM informatization.
1 Data Processing Technology in TCM Records 1
1.1 Structural Technology Research on Symptom Data 1
1.1.1 Analyze the Symptoms 2
1.1.2 Structure the Symptoms 4
1.1.3 Conclusions 7
1.2 Semantic Feature Expansion Technology Based on Knowledge Graph 7
1.2.1 Knowledge Graph and Feature Acquisition Analysis 8
1.2.2 Symptom Normalization in TCM 9
1.2.3 Acquisition of Semantic Features Based on Knowledge Path 13
1.2.4 Experiment Analysis 16
1.2.5 Conclusions 21
1.3 Medical Case Retrieval Method Based on Machine Learning 22
1.3.1 Medical Record Representation 22
1.3.2 Case Retrieval Based on Learning Ranking 25
1.3.3 Experiment and Analysis 28
1.3.4 Conclusions 32
2 Data Processing Technology in TCM Medication 33
2.1 An Intelligent Medication Matching Method for TCM 33
2.1.1 Measure the Correlation between Medications 33
2.1.2 Random Walk Similarity of Nodes 37
2.1.3 The Graph Clustering 39
2.1.4 Experiment 39
2.2 The Core Medications Analysis Based on Social Network Analysis 41
2.2.1 The Social Network Construction about Semantic Relations of
TCM Records 41
2.2.2 Core Medications Analysis Based on Social Network Analysis 42
2.2.3 The Implementation of Core Medications Algorithms 46
2.2.4 Conclusions 48
2.3 Analysis and Mining of Core Prescription Using Fuzzy Cognitive Map 48
2.3.1 Construction of Fuzzy Cognitive Map 49
2.3.2 Realization of Core Prescription Mining 51
2.3.3 Systematic Review 55
2.3.4 Conclusions 57
3 The Medical Records-based Knowledge Acquisition 59
3.1 Centrality Research on the Traditional Chinese Medicine Network 59
3.1.1 Basic Thought and Concept 60
3.1.2 Method to Calculate Betweenness Centrality 62
3.1.3 Betweenness Centrality Algorithm 63
3.1.4 Example Analyses 64
3.1.5 Conclusions 66
3.2 Cognitive Induction Based Knowledge Acquisition 66
3.2.1 Data Preprocessing 66
3.2.2 Inductive Logic Based Inductive Learning Algorithm 68
3.2.3 Graph-based Inductive Learning Algorithm 71
3.2.4 Application of Inductive Learning Algorithm 73
3.3 Analysis on Interactive Structure of Knowledge Acquisition 77
3.3.1 Relevant Work 78
3.3.2 Structural Modeling Analyzing 79
3.3.3 Construction of Structural Model 81
3.3.4 Algorithms 81
3.3.5 Verification & Application 82
3.3.6 Conclusions 84
3.4 Application of Structural Analysis in Knowledge Acquisition of
Traditional Chinese Medicine 84
3.4.1 Structural Modeling 85
3.4.2 Arithmetic and Analysis 87
3.4.3 Application Example 88
3.4.4 Conclusions 91
4 Text-based Knowledge Acquisition 93
4.1 Knowledge Acquisition Based on Open Data Source 93
4.2 Unsupervised TCM Text Segmentation Combined with Domain Dictionary 101
4.2.1 Related Work 102
4.2.2 Method 103
4.2.3 Experience 106
4.2.4 Conclusions 109
4.3 A Phrase Mining Method for TCM 110
4.3.1 Methods 110
4.3.2 Results 115
4.3.3 Conclusions 117
4.4 Improving Distantly-Supervised Named Entity Recognition 117
4.4.1 Related work 119
4.4.2 NER Scheme 120
4.4.3 Experiment 127
4.4.4 Relation Extraction Frame 132
4.5 Nested Named Entity Recognition Method 133
4.5.1 Methodology 135
4.5.2 Experiments 137
4.5.3 Conclusions 141
5 Application of Knowledge of TCM 143
5.1 Fuzzy Ontology Constructing and its Application in TCM 143
5.1.1 Structure of Fuzzy Ontology 143
5.1.2 Application of Fuzzy Ontology 147
5.1.3 Conclusions 150
5.2 Personalized Diagnostic Modal Discovery of TCM Knowledge Graph 150
5.2.1 Access to Medical Data and Normalization 150
5.2.2 Obtain the Medical Records Node and Get the Path and Storage 153
5.2.3 Overlay All Medical Path Results 157
5.2.4 Using the Template 159
5.2.5 Result Analysis 160
5.2.6 Conclusions 168
5.3 Assistant Diagnostic Method of TCM 168
5.3.1 Data Pretreatment 169
5.3.2 Research on Integrated Diagnosis Based on Multi Classification 170
5.3.3 Conclusions 176
5.4 Auxiliary Diagnosis Based on the Knowledge Graph of TCM Syndrome 177
5.4.1 Related Work 177
5.4.2 TCM Diagnosis Path Discovery 181
5.4.3 Meta-path Based on Reasoning Strategy 182
?
5.4.4 Experiment 186
5.4.5 Conclusions 189
References 191
Figure List 195
Table List 199
內容試閱：
Preface
The past decades have witnessed the rapid advancements of computational intelligence techniques， including big data， machine learning， and knowledge engineering， in both industrial and academic communities. Specifically， with the diffusion of some computing paradigms such as natural language processing， knowledge graph， reasoning decision， it promotes the computer-assisted diagnosis and treatment in Traditional Chinese Medicine (TCM). Through the integration of our research achievements in the field of intelligent information processing on TCM over the last decade， this book introduces the data processing technologies in TCM medical records and TCM medication， the medical records-based knowledge acquisition， the text-based knowledge acquisition， and the applications of TCM knowledge. We would like to provide a guidance for graduate students， university teachers and professional technicians engaged in knowledge engineering and TCM informatization.
We thank AI Dongmei，CHEN Hongyun， CHEN Xingxing， CHEN Yujia， FAN Yumei， FENG Jim， GAO Lixin， HA Shuang， HU Liangyuan， HU Xiaohui， JIA Qi， LI Cheng， LI Daole， LI Jianyuan， LIU Kan， LIU Jianming， LUO Xiong， MA Yuekun， QIAN Yanxuan， SHAN Ping， SONG Zihao， SUN Yi， XIA Chao， XU Cong， XU Yan， XU Yang， YAN Chang， YAN Yuyang， YANG Shibing， ZANG Honglei， ZHANG Huansheng， ZHANG Jing， ZHANG Yuanyu， ZHAO Yincheng， ZHOU Yuchao and ZHOU Yue for helping us accomplish the work.
Thanks to the graduate students in the laboratory: ZHAN Yuxiao， FAN Xinxin， LI Jia， LI Xuliang， TAO Hu， TU Ruwei， XU Haifeng， YANG Lijia and YANG Juwang， for their work on data compilation.
This work is funded by the Ministry of Science and Technology of Peoples Republic of China (National Key Research and Development Program of China: 2017YFB1002304).
購物車/收銀台(
0
) | 在線留言板
| 付款方式
| 運費計算
| 聯絡我們
| 幫助中心 |
加入書簽
HOME
新書上架
