TWI688969B - Dialogue system for medical product recommendation - Google Patents
Dialogue system for medical product recommendation Download PDFInfo
- Publication number
- TWI688969B TWI688969B TW107137633A TW107137633A TWI688969B TW I688969 B TWI688969 B TW I688969B TW 107137633 A TW107137633 A TW 107137633A TW 107137633 A TW107137633 A TW 107137633A TW I688969 B TWI688969 B TW I688969B
- Authority
- TW
- Taiwan
- Prior art keywords
- unit
- sentence
- slot
- word
- intent
- Prior art date
Links
Images
Landscapes
- Medical Treatment And Welfare Office Work (AREA)
Abstract
Description
本發明是關於一種對話系統,特別是關於一種藥品選擇對話系統。The invention relates to a dialogue system, in particular to a dialogue system for drug selection.
近年來國人越來越注重身體健康及生活品質,市面上大量地出現新型之中西藥或是健康食品,這讓使用者在藥品及健康食品有著選擇上的困難,使得使用者多將該些藥品及健康食品帶至醫院或是診所詢問醫療人員,令原本醫療人員不足的問題更加嚴重。因此,如何利用AI人工智慧正確並快速地協助使用者得知自己之症狀可能對應之疾病為何,並給予使用者初步選擇藥品或健康食品的建議亦為AI人工智慧一個相當重要的應用。In recent years, Chinese people have paid more and more attention to physical health and quality of life. A large number of new Chinese and Western medicines or health foods have appeared on the market, which makes it difficult for users to choose medicines and health foods, which makes users take more medicines. Taking healthy foods to hospitals or clinics to ask medical staff, the problem of the shortage of medical staff is even more serious. Therefore, how to use AI artificial intelligence to correctly and quickly help users know what their symptoms may be corresponding to the disease, and give the user a preliminary choice of drugs or healthy food suggestions is also a very important application for AI artificial intelligence.
請參閱台灣專利申請號097136480「慢性疾病自我健康照護諮詢系統」,該慢性疾病自我健康照護諮詢系統藉由圖案及導引字句逐步地引導使用者進行健康諮詢,但由於該系統缺乏了與使用者之間的對話,除了讓諮詢較為單調外,也容易因為導引字句的限制讓健康諮詢較難快速地貼近使用者的實際問題,而導致傳統之人工智慧健康諮詢較為耗時。Please refer to Taiwan Patent Application No. 097136480 "Chronic Disease Self-Health Care Consultation System". The chronic disease self-health care consultation system gradually guides users to conduct health consultation through patterns and guide words, but due to the lack of the system In addition to making the consultation more monotonous, the dialogue between them also makes it difficult for the health consultation to quickly get close to the actual problems of the user due to the limitation of the guiding words, which causes the traditional artificial intelligence health consultation to be more time-consuming.
本發明的主要目的在於藉由對話理解模組之意圖偵測及槽填充理解使用者輸入之語句的含意,而能透過對話管理模組根據對話理解模組偵測之含意提供診斷結果及藥品選擇的建議。The main purpose of the present invention is to understand the meaning of the sentence entered by the user through the intention detection and slot filling of the dialogue understanding module, and to provide the diagnosis result and drug selection according to the meaning detected by the dialogue understanding module through the dialogue management module Suggestions.
本發明一種藥品選擇對話系統包含一預處理模組、一對話理解模組及一對話管理模組,該預處理模組具有一語句處理單元及一詞嵌入單元,該語句處理單元具有一斷詞元件及一停用詞元件,該斷詞元件接收一輸入語句,且該斷詞元件用以將該輸入語句斷詞為複數個詞彙,該停用詞元件耦接該斷詞元件以接收該些詞彙,該停用詞元件用以將屬於至少一停用詞之該詞彙刪除而輸出一處理語句,該詞嵌入單元耦接語句處理單元,該詞嵌入單元用以將該處理語句轉換為一語句向量,該對話理解模組耦接該預處理模組,該對話理解模組具有一意圖偵測單元及一槽填充單元,該意圖偵測單元接收該語句向量,該意圖偵測單元用以根據一意圖資料庫偵測該語句向量之一意圖,該槽填充單元接收該語句向量及該意圖,且該槽填充單元用以根據該意圖將該語句向量填充於一填充槽中,該對話管理模組耦接該對話理解模組,該對話管理模組具有一診斷單元及一藥品選擇單元,該診斷單元耦接該槽填充單元,以根據該填充槽及一診斷症狀權重資料庫診斷該語句向量對應之一疾病,該藥品選擇單元耦接該診斷單元,以根據該疾病及一藥品選擇資料庫輸出一建議藥品。The medicine selection dialogue system of the present invention includes a preprocessing module, a dialogue understanding module and a dialogue management module. The preprocessing module has a sentence processing unit and a word embedding unit, and the sentence processing unit has a word breaker Element and a stop word element, the word breaker element receives an input sentence, and the word breaker element is used to break the input sentence into plural words, and the stop word element is coupled to the word breaker element to receive the words Vocabulary, the stop word component is used to delete the vocabulary belonging to at least one stop word to output a processing sentence, the word embedding unit is coupled to the sentence processing unit, and the word embedding unit is used to convert the processing sentence into a sentence Vector, the dialogue understanding module is coupled to the pre-processing module, the dialogue understanding module has an intention detection unit and a slot filling unit, the intention detection unit receives the sentence vector, and the intention detection unit is used for An intention database detects an intention of the sentence vector, the slot filling unit receives the sentence vector and the intention, and the slot filling unit is used to fill the sentence vector in a filling slot according to the intention, the dialog management mode The group is coupled to the dialogue understanding module. The dialogue management module has a diagnosis unit and a drug selection unit. The diagnosis unit is coupled to the slot filling unit to diagnose the sentence vector based on the filling slot and a diagnosis symptom weight database. Corresponding to a disease, the drug selection unit is coupled to the diagnosis unit to output a recommended drug based on the disease and a drug selection database.
本發明藉由該預處理模組對該輸入語句進行處理,而能以該對話理解模組之該意圖偵測單元偵測該輸入語句之該意圖,並以該對話理解模組之該槽填充單元將該其填入該填充槽中,最後即可透過該對話管理模組判斷使用者的該疾病並建議其使用之藥品,達成以人工智慧的方式進行疾病診斷的功效。In the present invention, the input sentence is processed by the preprocessing module, and the intent detection unit of the dialogue understanding module can detect the intention of the input sentence and fill the slot of the dialogue understanding module The unit fills it into the filling tank, and finally, through the dialog management module, the user can judge the disease and recommend the medicine to be used, so as to achieve the effect of disease diagnosis in the manner of artificial intelligence.
請參閱第1圖,其為本發明之一實施例,一種藥品選擇對話系統100的功能方塊圖,該藥品選擇對話系統100包含一預處理模組110、一對話理解模組120及一對話管理模組130,其中該對話理解模組120耦接該預處理模組110,該對話管理模組130耦接該對話理解模組120。Please refer to FIG. 1, which is a functional block diagram of a medicine
請參閱第2圖,該預處理模組110具有一語句處理單元111及一詞嵌入單元112,該語句處理單元111接收一輸入語句,該輸入語句可選自為以一麥克風接收使用者之語音後轉換而得,或是使用者直接以文字輸入。其中,該語句處理單元111具有一斷詞元件111a及一停用詞元件111b,由於中文之語句中,單字與單字之間並非如外文語法包含有空格,而較難將有字義的字詞一一區分出來,例如「我今天早起有點頭痛」中的「我今」、「天早」、「起有」並不具有意義,而須藉由該斷詞元件111a擷取該輸入語句中有意義之字詞。在本實施例中,該斷詞元件111a接收該輸入語句,且該斷詞元件111a將該輸入語句斷詞為複數個詞彙,在本實施例中,該斷詞元件111a是以一Jieba中文斷詞系統111c對該輸入語句進行斷詞,例如「我今天早起有點頭痛」被斷詞為「我 / 今天 / 早起 / 有點 / 頭痛」,令每個詞彙皆具有意義。但其他實施例亦可使用其他斷詞系統對該輸入語句進行斷詞,本發明並不在此限。Referring to FIG. 2, the
此外,由於該些詞彙中包含了許多不能代表該輸入語句之語意的停用詞,例如上述之斷詞結果「我 / 今天 / 早起 / 有點 / 頭痛」中的「我」、「今天」及「有點」都屬於不能代表該輸入語句之語意的停用詞,因此須藉由該停用詞元件111b將該些停用詞刪除,其中,該停用詞元件111b耦接該斷詞元件111a以接收該些詞彙,該停用詞元件111b用以將屬於停用詞之該詞彙刪除而輸出一處理語句。在本實施例中,該停用詞元件111b具有一停用詞資料庫111d,該停用詞資料庫111d儲存有複數個該停用詞,且該停用詞元件111b用以比對該輸入語句之該些詞彙與各該停用詞,以將屬於各該停用詞之該詞彙刪除。In addition, because these words contain many stop words that can not represent the semantic meaning of the input sentence, such as the "me", "today" and "today" and "today" in the word breaking result "me/today/early rise/a bit/headache" "Some points" are stop words that cannot represent the semantics of the input sentence, so these stop words must be deleted by the
請參閱第2圖,由於電腦系統並不如人腦能夠辨識該些詞彙的意義,而若將詞彙與詞彙一一進行比對則相當耗時,且每個字義可能以不同之詞彙表示,導致直接以文字進行比對在相似度的計算上可能會面臨無法收斂的問題,因此,本實施例藉由該詞嵌入單元112耦接語句處理單元111,以透過該詞嵌入單元112將該處理語句轉換為一語句向量,在本實施例中,該詞嵌入單元112具有一word2vec模組112a,且該word2vec模組112a先以一文集進行訓練,可讓具有近似意義之詞彙以相近之向量表示,使該詞嵌入單元112可藉由word2vec模組112a將該處理語句轉換為該語句向量。Please refer to Figure 2. Because computer systems are not as capable of recognizing the meaning of these words as the human brain, comparing words with words one by one is quite time-consuming, and the meaning of each word may be expressed in different words, resulting in direct The comparison by text may face the problem of non-convergence in calculating the similarity. Therefore, in this embodiment, the
請參閱第1及3圖,該對話理解模組120具有一意圖偵測單元121及一槽填充單元122,該意圖偵測單元121接收該語句向量,該意圖偵測單元121用以根據一意圖資料庫121a偵測該語句向量之一意圖,在本實施例中,該意圖資料庫121a中儲存有複數個意圖字彙,該些意圖字彙對應為一症狀診斷意圖及一藥品選擇意圖,該意圖偵測單元121藉由餘弦相似性(Cosine similarity)計算該語句向量與各該意圖字彙之間的一相似度,以測得該語句向量之該意圖為該症狀診斷意圖或該藥品選擇意圖。Referring to FIGS. 1 and 3, the dialogue understanding
請參閱第3圖,該槽填充單元122接收該語句向量及該意圖,且該槽填充單元122用以根據該語句向量之該意圖將該語句向量填充於一填充槽122a中,在本實施例中,該填充槽122a包含一症狀槽122b及一藥品槽122c,若該語句向量之該意圖為該症狀診斷意圖,代表著該些語句向量屬於症狀之詞彙,該槽填充單元122將該語句向量填充於該症狀槽122b,若該語句向量之該意圖為該藥品選擇意圖,代表著該些語句向量屬於藥品選擇之詞彙,該槽填充單元122將該語句向量填充於該藥品槽122c,以提高後續之該對話管理模組130的疾病診斷及藥品選擇的運算速度。Referring to FIG. 3, the
請參閱第1及4圖,該對話管理模組130具有一診斷單元131及一藥品選擇單元132,該診斷單元131耦接該槽填充單元122,在本實施例中,該診斷單元131具有一第一判斷元件131a、一分數計算元件131b、一第二判斷元件131c、一問診元件131d及一診斷症狀權重資料庫131e。Please refer to FIGS. 1 and 4, the
請參閱第4圖,該第一判斷元件131a耦接該槽填充單元122,以判斷該症狀槽122b中被填充的槽之數量是否大於一槽門檻值,在本實施例中,該第一判斷元件131a判斷該症狀槽122b中被填充的槽之數量是否大於2,也就是判斷該症狀槽122b中是否已有足夠之症狀來進行疾病的分析,若是則至該分數計算元件131b計算該疾病分數,若否則至該問診元件131d,讓該問診元件131d詢問使用者更多的該症狀。Please refer to FIG. 4, the first determining
該分數計算元件131b耦接該第一判斷元件131a及該診斷症狀權重資料庫131e以計算一疾病分數,其中,該診斷症狀權重資料庫131e中儲存有複數種疾病,各該疾病對應有多個症狀,因此,該分數計算元件131b可根據該症狀槽122b所填充之語句向量計算各該疾病的該疾病分數。該第二判斷元件131c耦接該分數計算元件131b,用以判斷各該疾病分數是否大於一分數門檻值,若其中之一該疾病分數大於該分數門檻值,代表著該疾病的症狀出現在使用者身上已經足夠,因此該第二判斷元件131c即可判斷該疾病診斷完成,而輸出大於該分數門檻值的該疾病至該藥品選擇單元132,若否則至該問診元件131d,讓該問診元件131d詢問使用者更多的該症狀。The
該問診元件131d耦接該第一判斷元件131a、該分數計算元件131b及該第二判斷元件131c,在該第一判斷元件131a判斷被填充的槽之數量小於或等於該槽門檻值及該第二判斷元件131c判斷該疾病分數小於或等於該分數門檻值時,該問診元件131d輸出一問診訊號,以透過語音或文字表示的方式詢問使用者更多關於疾病症狀的描述,將使用者回覆之症狀向量化後填入該症狀槽122b中,並重新藉由該分數計算元件131b計算該疾病分數。The
請參閱第4圖,該藥品選擇單元132耦接該診斷單元131之該第二判斷單元131c以接收該疾病,以根據該疾病及一藥品選擇資料庫132a輸出一建議藥品。Referring to FIG. 4, the
本發明藉由該預處理模組110對該輸入語句進行處理,而能以該對話理解模組120之該意圖偵測單元121偵測該輸入語句之該意圖,並以該對話理解模組120之該槽填充單元122將該其填入該填充槽122a中,最後即可透過該對話管理模組130判斷使用者的該疾病並給予該建議藥品,達成以人工智慧的方式進行疾病診斷的功效。In the present invention, the input sentence is processed by the
本發明之保護範圍當視後附之申請專利範圍所界定者為準,任何熟知此項技藝者,在不脫離本發明之精神和範圍內所作之任何變化與修改,均屬於本發明之保護範圍。The scope of protection of the present invention shall be subject to the scope defined in the attached patent application. Any changes and modifications made by those who are familiar with this skill without departing from the spirit and scope of the present invention shall fall within the scope of protection of the present invention. .
100:藥品選擇對話系統100: Drug selection dialogue system
110:預處理模組110: pre-processing module
111:語句處理單元111: sentence processing unit
111a:斷詞元件111a: word breaking component
111b:停用詞元件111b: stop word component
111c:Jieba中文斷詞系統111c: Jieba Chinese word breaker system
111d:停用詞資料庫111d: Stopword database
112:詞嵌入單元112: word embedding unit
112a:word2vec模組112a: word2vec module
120:對話理解模組120: Dialogue Understanding Module
121:意圖偵測單元121: Intent detection unit
121a:意圖資料庫121a: Intent database
122:槽填充單元122: slot filling unit
122a:填充槽122a: filling tank
122b:症狀槽122b: symptom slot
122c:藥品槽122c: Medicine tank
130:對話管理模組130: Dialogue management module
131:診斷單元131: Diagnostic unit
131a:第一判斷元件131a: the first judgment element
131b:分數計算元件131b: Score calculation component
131c:第二判斷元件131c: Second judgment element
131d:問診元件131d: Interrogation element
131e:診斷症狀權重資料庫131e: Diagnosis symptom weight database
132:藥品選擇單元132: Drug selection unit
132a:藥品選擇資料庫132a: Drug selection database
第1圖: 依據本發明之一實施例,一種藥品對話系統之功能方塊圖。 第2圖: 依據本發明之一實施例,一預處理模組之功能方塊圖。 第3圖: 依據本發明之一實施例,一對話理解模組之功能方塊圖。 第4圖: 依據本發明之一實施例,一對話管理模組之功能方塊圖。Figure 1: According to one embodiment of the present invention, a functional block diagram of a drug dialogue system. Figure 2: A functional block diagram of a pre-processing module according to an embodiment of the invention. Figure 3: According to an embodiment of the present invention, a functional block diagram of a dialogue understanding module. Figure 4: According to an embodiment of the present invention, a functional block diagram of a dialog management module.
100:藥品選擇對話系統 100: Drug selection dialogue system
110:預處理模組 110: pre-processing module
120:對話理解模組 120: Dialogue Understanding Module
130:對話管理模組 130: Dialogue management module
Claims (8)
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
TW107137633A TWI688969B (en) | 2018-10-24 | 2018-10-24 | Dialogue system for medical product recommendation |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
TW107137633A TWI688969B (en) | 2018-10-24 | 2018-10-24 | Dialogue system for medical product recommendation |
Publications (2)
Publication Number | Publication Date |
---|---|
TWI688969B true TWI688969B (en) | 2020-03-21 |
TW202016945A TW202016945A (en) | 2020-05-01 |
Family
ID=70766985
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
TW107137633A TWI688969B (en) | 2018-10-24 | 2018-10-24 | Dialogue system for medical product recommendation |
Country Status (1)
Country | Link |
---|---|
TW (1) | TWI688969B (en) |
Citations (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN101246474A (en) * | 2008-02-18 | 2008-08-20 | 刘树根 | Sentence component equipment, component production and method for reading foreign language by mother tongue base on the same |
TWI521467B (en) * | 2014-08-05 | 2016-02-11 | Pei-Hong Liao | Nursing decision support system |
CN106991284A (en) * | 2017-03-31 | 2017-07-28 | 南华大学 | Intelligent child-rearing knowledge services method and system |
-
2018
- 2018-10-24 TW TW107137633A patent/TWI688969B/en not_active IP Right Cessation
Patent Citations (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN101246474A (en) * | 2008-02-18 | 2008-08-20 | 刘树根 | Sentence component equipment, component production and method for reading foreign language by mother tongue base on the same |
TWI521467B (en) * | 2014-08-05 | 2016-02-11 | Pei-Hong Liao | Nursing decision support system |
CN106991284A (en) * | 2017-03-31 | 2017-07-28 | 南华大学 | Intelligent child-rearing knowledge services method and system |
Also Published As
Publication number | Publication date |
---|---|
TW202016945A (en) | 2020-05-01 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
Mathias et al. | Cognitive functioning in Alzheimer’s and vascular dementia: A meta-analysis. | |
Kassian et al. | Proto-Indo-European-Uralic comparison from the probabilistic point of view | |
Davletcharova et al. | Detection and analysis of emotion from speech signals | |
Das | A comparison of multiple classification methods for diagnosis of Parkinson disease | |
Clough et al. | Fluent or nonfluent? Part A. Underlying contributors to categorical classifications of fluency in aphasia | |
Martinc et al. | Tackling the ADReSS Challenge: A Multimodal Approach to the Automated Recognition of Alzheimer's Dementia. | |
Pérez-Toro et al. | Influence of the Interviewer on the Automatic Assessment of Alzheimer's Disease in the Context of the ADReSSo Challenge. | |
CN111274400B (en) | Construction method, device, equipment and storage medium of medical term system | |
WO2022257630A1 (en) | Risk detection method and apparatus based on multi-modal concealed information test | |
WO2021184802A1 (en) | Blood pressure classification prediction method and apparatus | |
CN106485085A (en) | A kind of intellect service robot health identification system and method | |
CN107066798A (en) | A kind of health of heart quality pre-alert system and its method for early warning | |
KR20220079789A (en) | Disease occurrence prediction system linked with biometric equipment | |
Chandra et al. | Natural language Processing and Ontology based Decision Support System for Diabetic Patients | |
TWI688969B (en) | Dialogue system for medical product recommendation | |
Martin et al. | Using reading mistakes as features for sleepiness detection in speech | |
Nahas et al. | Right-to-left shunt is common in chronic migraine | |
Beh et al. | Machine-Aided PPG Signal Quality Assessment (SQA) for Multi-Mode Physiological Signal Monitoring | |
CN115836847A (en) | Blood pressure prediction device and equipment | |
CN115565655A (en) | Enhanced auxiliary inquiry method | |
Scott et al. | Corpus Annotation as a Scientific Task. | |
US20230032536A1 (en) | Privacy preservation in a queryable database built from unstructured texts | |
CN113343686A (en) | Text multi-feature ambiguity resolution method and system | |
KR20210150063A (en) | A method and apparatus for postoperative pain assessment using differential index of photoplethysmogram | |
Yendri et al. | Application of Expert System with Smartphone-based Certainty Factor Method for Hypertension Risk Detection |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
MM4A | Annulment or lapse of patent due to non-payment of fees |