TWI745878B - Chat robot system and chat robot model training method - Google Patents
Chat robot system and chat robot model training method Download PDFInfo
- Publication number
- TWI745878B TWI745878B TW109107231A TW109107231A TWI745878B TW I745878 B TWI745878 B TW I745878B TW 109107231 A TW109107231 A TW 109107231A TW 109107231 A TW109107231 A TW 109107231A TW I745878 B TWI745878 B TW I745878B
- Authority
- TW
- Taiwan
- Prior art keywords
- training
- corpus
- model
- entity
- answer
- Prior art date
Links
Images
Landscapes
- Machine Translation (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
- Electrically Operated Instructional Devices (AREA)
Abstract
Description
本發明是關於一種互動式機器人系統,特別是關於一種聊天機器人系統及聊天機器人模型訓練方法。The invention relates to an interactive robot system, in particular to a chat robot system and a chat robot model training method.
在使用者瀏覽網頁時,有些網頁可開啟互動性視窗,讓使用者輸入訊息,互動式視窗可依據使用者輸入訊息顯示回覆資訊。此外,使用者也可以將問題以文字或語音方式輸入到具有使用者介面的機器人,機器人可應用使用者介面回應使用者的問題。When a user browses a webpage, some webpages can open an interactive window for the user to input a message, and the interactive window can display reply information based on the user's input message. In addition, the user can also input questions into a robot with a user interface in text or voice, and the robot can use the user interface to respond to the user's question.
傳統的網頁伺服器或機器人都需要大量的訓練語料作機器學習,當使用者輸入訊息與訓練語料符合時,才能找到對應的回覆資訊。Traditional web servers or robots require a large amount of training corpus for machine learning. When the user input information matches the training corpus, the corresponding reply information can be found.
然而,同樣的使用者意圖(例如為開燈)可以有多種表達方式(例如為我想開燈、覺得很暗、幫我開燈…等等),傳統的網頁伺服器或機器人無法窮舉出所有使用者可能使用的用語,以作為訓練語料。即使採用大量的訓練語料,亦可能導致系統的運算量提升,需要硬體升級或是花費較多的時間成本。因此,如何有效率的產生聊天機器人的訓練模型已成為本領域需解決的問題之一。However, the same user's intention (for example, to turn on the light) can be expressed in multiple ways (for example, I want to turn on the light, feel dark, turn on the light for me... etc.), which traditional web servers or robots cannot exhaust All the words that users may use are used as training corpus. Even if a large amount of training corpus is used, it may lead to an increase in the amount of calculations of the system, requiring hardware upgrades or costly time. Therefore, how to efficiently generate a training model of a chat robot has become one of the problems to be solved in this field.
為了解決上述的問題,本揭露內容之一態樣提供了一種聊天機器人系統。聊天機器人系統包含一儲存裝置以及一處理器。儲存裝置用以儲存一知識庫,該知識庫用以記錄一意圖與一實體之組合與一答案之間的關聯。處理器用以分析複數個訓練語料中的意圖與實體,並將利用一機器學習模型的一泛化(generalization)能力將此些訓練語料中的複數個同義字分離,並將此些同義字從此些訓練語料移除後,以取得一語料集,將語料集輸入一類神經網路模型後,取得一訓練模型,測試訓練模型,以取得一測試結果。其中,當處理器從測試結果中以一預先定義規則分析測試結果,以產生一分析結果,並依據分析結果產生一新版訓練語料。In order to solve the above-mentioned problems, one aspect of the present disclosure provides a chat robot system. The chat robot system includes a storage device and a processor. The storage device is used for storing a knowledge base for recording the association between a combination of an intention and an entity and an answer. The processor is used to analyze the intentions and entities in a plurality of training corpus, and use a generalization ability of a machine learning model to separate the plural synonyms in these training corpus, and to separate these synonyms After the training corpus is removed, a corpus is obtained. After the corpus is input to a neural network model, a training model is obtained, and the training model is tested to obtain a test result. Wherein, when the processor analyzes the test result from the test result using a predefined rule to generate an analysis result, and generates a new version of the training corpus according to the analysis result.
本發明之又一態樣係於提供一種聊天機器人模型訓練方法。聊天機器人模型訓練方法包含:藉由一知識庫記錄一意圖與一實體之組合與一答案之間的關聯;分析複數個訓練語料中的意圖與實體;利用一機器學習模型的一泛化(generalization)能力將此些訓練語料中的複數個同義字分離,並將此些同義字從此些訓練語料中移除,以取得一語料集;將語料集輸入一類神經網路模型,取得一訓練模型,測試訓練模型,以取得一測試結果;以及依據一預先定義規則分析測試結果,以產生一分析結果,並依據分析結果產生一新版訓練語料。Another aspect of the present invention is to provide a chat robot model training method. The chatbot model training method includes: using a knowledge base to record the association between the combination of an intention and an entity and an answer; analyzing the intentions and entities in a plurality of training corpus; using a generalization of a machine learning model ( generalization) Ability to separate plural synonymous characters in these training corpus, and remove these synonymous characters from these training corpora to obtain a corpus; input the corpus into a type of neural network model, Obtain a training model, test the training model to obtain a test result; analyze the test result according to a predefined rule to generate an analysis result, and generate a new version of the training corpus according to the analysis result.
本發明所示之聊天機器人系統及聊天機器人模型訓練方法,透過機器學習模型的泛化能力,將訓練語料中的同義字去除,以產生用於輸入類神經網路模型之語料集的大小,可以減少運算量並節省運算時間,透過分析訓練模型的方法,可依據分析結果產生新版訓練語料,透過新版訓練語料輸入類神經網路模型,以達到優化訓練模型的效果。The chat robot system and chat robot model training method shown in the present invention remove synonymous words in the training corpus through the generalization ability of the machine learning model to generate the size of the corpus used for the input neural network model , Which can reduce the amount of calculation and save time. By analyzing the training model, a new version of the training corpus can be generated based on the analysis result, and the new version of the training corpus can be input into the neural network model to achieve the effect of optimizing the training model.
以下說明係為完成發明的較佳實現方式,其目的在於描述本發明的基本精神,但並不用以限定本發明。實際的發明內容必須參考之後的權利要求範圍。The following description is a preferred implementation of the invention, and its purpose is to describe the basic spirit of the invention, but not to limit the invention. The actual content of the invention must refer to the scope of the claims that follow.
必須了解的是,使用於本說明書中的”包含”、”包括”等詞,係用以表示存在特定的技術特徵、數值、方法步驟、作業處理、元件以及/或組件,但並不排除可加上更多的技術特徵、數值、方法步驟、作業處理、元件、組件,或以上的任意組合。It must be understood that the words "including", "including" and other words used in this specification are used to indicate the existence of specific technical features, values, method steps, operations, elements, and/or components, but they do not exclude Add more technical features, values, method steps, job processing, components, components, or any combination of the above.
於權利要求中使用如”第一”、"第二"、"第三"等詞係用來修飾權利要求中的元件,並非用來表示之間具有優先權順序,先行關係,或者是一個元件先於另一個元件,或者是執行方法步驟時的時間先後順序,僅用來區別具有相同名字的元件。Words such as "first", "second", and "third" used in the claims are used to modify the elements in the claims, and are not used to indicate that there is an order of priority, antecedent relationship, or an element Prior to another element, or the chronological order of execution of method steps, is only used to distinguish elements with the same name.
請參照第1~2圖,第1圖係依照本發明一實施例繪示整合聊天機器人系統100之方塊圖。第2圖係依照本發明一實施例繪示聊天機器人模型訓練方法200之流程圖。Please refer to FIGS. 1 and 2. FIG. 1 is a block diagram of the integrated chat robot system 100 according to an embodiment of the present invention. FIG. 2 is a flowchart of a chat robot
於一實施例中,如第1圖所示,整合多平台登入系統100包含一儲存裝置10及一處理器20。於一實施例中,儲存裝置10耦接於處理器20。In one embodiment, as shown in FIG. 1, the integrated multi-platform login system 100 includes a
於一實施例中,聊天機器人系統100可以是筆記型電腦、桌機、平板、手機或其它電子裝置。於一實施例中,聊天機器人系統100包含一使用者介面及一螢幕,使用者可以透過使用者介面輸入訊息,螢幕可顯示使用者輸入訊息及處理器20輸出的回覆訊息。例如,使用者使用筆記型電腦打開一網頁後,網頁連結到聊天機器人系統100後,開啟一訊息視窗,用以接收使用者的輸入訊息,例如,使用者在訊息視窗中輸入「東京的維修中心在哪?」,聊天機器人系統100透過執行聊天機器人模型訓練方法200後找到答案,在訊息視窗中回覆位於東京的維修中心的地址。In an embodiment, the chat robot system 100 may be a notebook computer, a desktop computer, a tablet, a mobile phone, or other electronic devices. In one embodiment, the chat robot system 100 includes a user interface and a screen through which the user can input messages, and the screen can display user input messages and reply messages output by the
於一實施例中,儲存裝置10可被實作為唯讀記憶體、快閃記憶體、軟碟、硬碟、光碟、隨身碟、磁帶、可由網路存取之資料庫或熟悉此技藝者可輕易思及具有相同功能之儲存媒體。In one embodiment, the
於一實施例中,處理器20可以由體積電路如微控制單元(micro controller)、微處理器(microprocessor)、數位訊號處理器(digital signal processor)、特殊應用積體電路(application specific integrated circuit,ASIC)或一邏輯電路來實施。In one embodiment, the
請參閱第2圖,以下敘述聊天機器人模型訓練方法200。Please refer to Figure 2, the chat robot
於步驟210中,儲存裝置10儲存一知識庫,知識庫用以記錄一意圖(question type)與一實體(entity)之組合與一答案之間的關聯。In step 210, the
於一實施例中,使用者輸入的句子可能對應到相同或不同的意圖,意圖是指使用者想要進行的操作或是問題的種類,藉由聊天機器人系統100或人工可以將使用者輸入的句子進行意圖的分類。句子與意圖的例子如下表一所示。
於一實施例中,聊天機器人系統100還需要句子中的重要的單詞,稱為實體(或關鍵字),例如在句子“where is the repair center in Tokyo”與“where is the repair center in Taipei”中,此種句型的“Tokyo”與“Taipei”稱為實體。因為相同的意圖可能發生在不同的實體上,所以聊天機器人系統100會學習辨識出句子中的實體。In one embodiment, the chat robot system 100 also needs important words in sentences, called entities (or keywords), for example, in the sentences "where is the repair center in Tokyo" and "where is the repair center in Taipei" In this sentence, "Tokyo" and "Taipei" are called entities. Because the same intention may occur on different entities, the chatbot system 100 will learn to recognize the entities in the sentence.
於一實施例中,聊天機器人系統100可應用命名實體識別(Named Entity Recognition,NER)的技術以識別實體,其中,此技術用到的演算法為條件隨機域(conditional random field, CRF),是一種鑑別式機率模型,常用於標記或分析序列資料,如自然語言文字,藉此可預測句子中的標籤(tag)。於一實施例中,聊天機器人系統100藉由句子的前後文可判斷出實體的標籤,例如在介詞“in”的後面通常會是地點,因此將“in”後面所接的“Tokyo”標記為地點,並將地點“Tokyo”視為實體。In one embodiment, the chatbot system 100 can apply a named entity recognition (Named Entity Recognition, NER) technology to identify entities, where the algorithm used in this technology is a conditional random field (CRF), which is A discriminative probability model, often used to mark or analyze sequence data, such as natural language text, to predict tags in sentences. In one embodiment, the chatbot system 100 can determine the tag of the entity by the context of the sentence. For example, the place after the preposition "in" is usually the place, so the "Tokyo" following the "in" is marked as Location, and treat the location "Tokyo" as an entity.
藉由上述方法,當使用者輸入“where is the repair center in Tokyo”, 聊天機器人系統100可以理解語意,將此句子資訊簡化成意圖為“find repair center”,實體為“Tokyo”。接著,知識庫可以記錄意圖(例如“find repair center”)與實體(例如“Tokyo”)之與一答案(例如“shinjuku”(新宿))之間的關聯。換言之,知識庫將意圖與實體視為一組索引,透過索引可關聯(或查找)到答案。With the above method, when the user enters "where is the repair center in Tokyo", the chatbot system 100 can understand the semantic meaning and simplify the sentence information to the intention "find repair center", and the entity is "Tokyo". Then, the knowledge base can record the association between an intent (for example, "find repair center") and an entity (for example, "Tokyo") and an answer (for example, "shinjuku" (Shinjuku)). In other words, the knowledge base regards the intent and the entity as a set of indexes, through which the answers can be associated (or searched).
於步驟220中,處理器20分析複數個訓練語料中的意圖與實體。In
於一實施例中,表一中的句子可視為訓練語料,處例器20透過詞向量演算法或是意圖分類演算法分析出句子的意圖。In one embodiment, the sentences in Table 1 can be regarded as training corpus, and the
於一實施例中,處理器20透過命名實體識別的技術以識別實體。In one embodiment, the
於步驟230中,處理器20利用一機器學習模型的一泛化(generalization)能力將此些訓練語料中的複數個同義字分離,並將此些同義字從此些訓練語料中移除,以取得一語料集。In
於一實施例中,同義字可以由使用者事先定義。In one embodiment, the synonymous characters can be defined by the user in advance.
第3圖係依照本發明一實施例繪示聊天機器人模型訓練方法之示意圖。以下請一併參閱第3圖,在前處理310(pre-process)階段,處理器20將訓練語料30去除同義字32後,產生語料集34,作為後續訓練的資料。FIG. 3 is a schematic diagram of a chat robot model training method according to an embodiment of the present invention. Please also refer to Figure 3 below. In the pre-process stage, the
於一實施例中,機器學習模型可以由邏輯迴歸、線性迴歸、最近鄰演算法、K-Means聚類、類神經網路等等方式實現之。In one embodiment, the machine learning model can be implemented by logistic regression, linear regression, nearest neighbor algorithm, K-Means clustering, neural network, etc.
於一實施例中,泛化能力是指機器學習模型對新鮮樣本(例如訓練語料30)的適應能力。學習的目的是學到隱含在對背後的規律,對具有同一規律的訓練語料30以外的資料,經過訓練的網路也能給出合適的輸出,此能力稱為泛化能力。In one embodiment, generalization ability refers to the adaptability of the machine learning model to fresh samples (for example, training corpus 30). The purpose of learning is to learn the rules behind the pairing. For data other than the
舉例而言,在句子“where is the repair center in Tokyo”與“where is the repair center in Taipei”中,此種句型的“Tokyo”與“Taipei”為實體,即視為重要的關鍵字,且標記為地點,當新的一筆資料輸入時,例如為“where is the repair center in Beijing”,即使此資料沒有出現過,機器學習模型的泛化能力仍可以依據規律(例如句型、介詞或其他規律)判斷出“Beijing”為實體,且標記為地點。For example, in the sentences "where is the repair center in Tokyo" and "where is the repair center in Taipei", the sentence patterns "Tokyo" and "Taipei" are entities, which are regarded as important keywords. And mark it as a location. When a new piece of data is entered, such as "where is the repair center in Beijing", even if the data has not appeared before, the generalization ability of the machine learning model can still be based on rules (such as sentence patterns, prepositions, or Other rules) It is determined that "Beijing" is an entity and marked as a location.
藉此,即使不用大量的訓練語料30,應用機器學習模型的泛化能力,也能夠判斷出新資料的實體及其標籤。In this way, even if a large amount of
由於好的機器學習模型能作到一定程度的泛化,換言之,即使某些字詞不需要特別訓練,機器學習模型也能將此些字詞辨識出來,因此可以利用機器學習的泛化能力將同義字32從訓練語料30中分離出來。Since a good machine learning model can generalize to a certain degree, in other words, even if certain words do not require special training, the machine learning model can recognize these words, so the generalization ability of machine learning can be used to
其中,同義字32例如為“wifi”、“wi-fi”、“wireless”,此三個字詞出現在句子中有相當高的程度代表相同的意思,因此,此三個字詞可取“wifi”作為關鍵字保留下來,而“wi-fi”、“wireless”則從訓練語料30中移除,移除掉同義字32(僅保留一個關鍵字)的訓練語料30稱為語料集34。於一實施例中,“wifi”、“wi-fi”、“wireless”可被稱為一組同義字集。Among them, the
藉由移除掉重複意義的同義字32,語料集34的資料量降低,可以大幅減低後續訓練語料集34所需的運算量。By removing the
於步驟240中,處理器20將語料集34輸入一類神經網路模型36,取得一訓練模型38,測試訓練模型38,以取得一測試結果44。In
於一實施例中,如第3圖所示,在訓練階段320中,語料集輸入類神經網路模型36,神經網路模型36中會依序進行卷積(convolution)層、ReLU層、卷積層、ReLU層、池化(pooling)層、ReLU層、卷積層、ReLU層、池化層及全連接(fully connected)。然而,神經網路模型36中各層運算可以依實作調整,不限於此。經過一連串的運算後,神經網路模型36輸出一訓練模型38。In one embodiment, as shown in Figure 3, in the
於一實施例中,測試資料40的意圖及實體是已知的,意圖及實體與其對應的結果也是已知的。在測試階段330中,將測試資料40輸入訓練模型38後,訓練模型38輸出測試結果44。In one embodiment, the intent and entity of the
於一實施例中,處理器20將測試資料40及同義字32輸入訓練模型38,藉此測試訓練模型38是否能正確的判斷出同義字32,並取得對應同義字32的答案,訓練模型38輸出測試結果44。In one embodiment, the
接著,處理器20分析測試結果44以驗證訓練模型38的準確性。Then, the
於步驟250中,處理器20依據一預先定義規則46分析測試結果44,以產生一分析結果48,並依據分析結果48產生新版訓練語料50。In
於一實施例中,如第3圖所示,在分析階段340中,處理器20將測試結果44輸入分析模組45中,分析模組45可以由電路、韌體或軟體實現,分析模組45中儲存預先定義規則46,測試結果44經由預先定義規則46進行一連串的判斷後,分析模組45輸出分析結果48,並依據分析結果48產生新版訓練語料50。In one embodiment, as shown in FIG. 3, in the
於一實施例中,請參閱第4圖,第4圖係依照本發明一實施例繪示應用預先定義規則46分析測試結果44的方法400之流程圖。In one embodiment, please refer to FIG. 4, which is a flowchart of a
於步驟410中,處理器20讀取測試結果44。In
於一實施例中,測試結果44包含測試一結果與測試二結果,預先定義規則46定義測試一為比較預測結果44是否等於預期的標籤,預先定義規則46定義測試二為用訓練模型38輸出的意圖及實體到知識庫中找答案。於一實施例中,測試結果44如表二所示。
於一實施例中,若測試一的結果與測試二的結果皆通過,代表測試結果44沒有錯誤,無須進行後續步驟。若測試一的結果與測試二的結果其中一者有錯誤,則進入步驟420。In one embodiment, if both the result of test 1 and the result of test 2 pass, it means that the
於步驟420中,處理器20藉由預先定義規則46分析錯誤型態。In
於一實施例中,錯誤型態包含一缺乏同義字型態、一缺乏答案型態或一其他錯誤型態。In one embodiment, the error type includes a lack of synonymous word type, a lack of answer type, or another error type.
於一實施例中,若預先定義規則46判斷測試一結果為錯誤,且測試二結果也為錯誤,則代表訓練模型38無法識別預先定義好的字,且此字也不在同義字集中,也無法用訓練模型38標記的意圖與實體在知識庫中找到關聯的答案。預先定義規則46判斷此種錯誤型態為缺乏同義字型態。例如,表二中的句子“why my wifi is not working”,預先定義規則46判斷測試一結果為錯誤,且測試二結果也為錯誤,則代表訓練模型38可能是無法識別出“wifi”,且此字也不在同義字集中,因此也無法在知識庫中找到關聯的答案。In one embodiment, if the
於一實施例中,若預先定義規則46判斷測試一結果為通過,測試二結果為錯誤,則代表訓練模型38可正確的辨識出句子的意圖及實體,但無法將意圖及實體作為索引查找知識庫關聯到的答案。預先定義規則46判斷此種錯誤型態為缺乏答案型態。例如,表二中的句子“I want to find a repair center in Taipei city”,預先定義規則46判斷測試一結果為通過,且測試二結果為錯誤,則代表訓練模型38可能無法將意圖及實體作為索引查找知識庫關聯到的答案。In one embodiment, if the
於一實施例中,其他錯誤型態是指未知的錯誤,例如類神經網路的神經元不夠,層數不夠,或演算法出錯,需要資料工程師協助調整。In one embodiment, other error types refer to unknown errors, such as insufficient neurons in a neural network, insufficient number of layers, or an algorithm error, which requires the assistance of a data engineer to adjust.
處理器20依據上述方法分析出來的錯誤型態可視為分析結果48,並於後續步驟對應不同的錯誤型態進行不同的操作,例如依據分析結果48及語料集34產生新版訓練語料50。The error pattern analyzed by the
於步驟430中,處理器20判斷錯誤型態為缺乏同義字型態或缺乏答案型態。當處理器20判斷錯誤型態為缺乏同義字型態時,進入步驟440。當處理器20判斷錯誤型態為缺乏答案型態時,進入步驟450。另外,當處理器20判斷錯誤型態為其他錯誤型態時,結束此流程。In
於步驟440中,當處理器20分析測試結果44中的至少一錯誤型態為缺乏同義字型態時,代表一特定同義字(例如為“wifi”)無法被訓練模型38分析出來,則處理器20將特定同義字(例如為“wifi”)加入語料集34,以更新語料集34,將更新的語料集34(即,新版訓練語料50)輸入類神經網路模型36,以產生一新版訓練模型。In
藉此,聊天機器人系統100可以使沒有被辨識出來的同義字加入語料集34,避免再次發生錯誤。經過多次重複流程320~340,可以不斷的優化訓練模型。In this way, the chat robot system 100 can add unrecognized synonyms to the
於步驟450中,當處理器20分析測試結果44中的意圖及實體判斷正確,但至少一錯誤型態為缺乏答案類型,代表意圖(例如為解決“wifi”壞損問題)及實體(例如為“wifi”)之組合與答案(例如為重新啟動)之間的關聯沒有被建立,則處理器20依據實體及意圖作為索引查找知識庫關聯到的答案(例如實體“wifi”與“wireless”為同義字,可以由“wireless”與意圖作為索引查出知識庫關聯到的答案),將實體及意圖與答案建立關聯,以更新知識庫。In
本發明所示之聊天機器人系統及聊天機器人模型訓練方法,透過機器學習模型的泛化能力,將訓練語料中的同義字去除,以產生用於輸入類神經網路模型之語料集的大小,可以減少運算量並節省運算時間,透過分析訓練模型的方法,可依據分析結果產生新版訓練語料,透過新版訓練語料輸入類神經網路模型,以達到優化訓練模型的效果。The chat robot system and chat robot model training method shown in the present invention remove synonymous words in the training corpus through the generalization ability of the machine learning model to generate the size of the corpus used for the input neural network model , Which can reduce the amount of calculation and save time. By analyzing the training model, a new version of the training corpus can be generated based on the analysis result, and the new version of the training corpus can be input into the neural network model to achieve the effect of optimizing the training model.
本發明之方法,或特定型態或其部份,可以以程式碼的型態存在。程式碼可以包含於實體媒體,如軟碟、光碟片、硬碟、或是任何其他機器可讀取(如電腦可讀取)儲存媒體,亦或不限於外在形式之電腦程式產品,其中,當程式碼被機器,如電腦載入且執行時,此機器變成用以參與本發明之裝置。程式碼也可以透過一些傳送媒體,如電線或電纜、光纖、或是任何傳輸型態進行傳送,其中,當程式碼被機器,如電腦接收、載入且執行時,此機器變成用以參與本發明之裝置。當在一般用途處理單元實作時,程式碼結合處理單元提供一操作類似於應用特定邏輯電路之獨特裝置。The method of the present invention, or a specific type or part thereof, can exist in the form of code. The program code can be included in physical media, such as floppy disks, CDs, hard disks, or any other machine-readable (such as computer-readable) storage media, or not limited to external forms of computer program products. Among them, When the program code is loaded and executed by a machine, such as a computer, the machine becomes a device for participating in the present invention. The code can also be transmitted through some transmission media, such as wire or cable, optical fiber, or any transmission type. When the code is received, loaded and executed by a machine, such as a computer, the machine becomes used to participate in this Invented device. When implemented in a general-purpose processing unit, the program code combined with the processing unit provides a unique device that operates similar to the application of a specific logic circuit.
雖然本發明已以實施方式揭露如上,然其並非用以限定本發明,任何熟習此技藝者,在不脫離本發明之精神和範圍內,當可作各種之更動與潤飾,因此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。Although the present invention has been disclosed in the above embodiments, it is not intended to limit the present invention. Anyone who is familiar with the art can make various changes and modifications without departing from the spirit and scope of the present invention. Therefore, the protection of the present invention The scope shall be subject to the definition of the attached patent application scope.
100:聊天機器人系統 10:儲存裝置 20:處理器 200:聊天機器人模型訓練方法 210~250、410~450:步驟 310:前處理階段 30:訓練語料 32:同義字 34:語料集 320:訓練階段 330:測試階段 340:分析階段 36:類神經網路模型 38:訓練模型 40:測試資料 44:測試結果 45:分析模組 46:預先定義規則 48:分析結果 50:新版訓練語料 400:應用預先定義規則分析測試結果的方法 100: Chatbot system 10: Storage device 20: Processor 200: Chatbot model training method 210~250, 410~450: steps 310: Pre-processing stage 30: Training corpus 32: Synonyms 34: Corpus 320: Training phase 330: Test phase 340: Analysis phase 36: Neural Network Model 38: Training model 40: Test data 44: Test results 45: Analysis Module 46: Pre-defined rules 48: Analysis results 50: New version of training corpus 400: The method of applying pre-defined rules to analyze test results
第1圖係依照本發明一實施例繪示整合聊天機器人系統之方塊圖。 第2圖係依照本發明一實施例繪示聊天機器人模型訓練方法之流程圖。 第3圖係依照本發明一實施例繪示聊天機器人模型訓練方法之示意圖。 第4圖係依照本發明一實施例繪示應用預先定義規則分析測試結果的方法之流程圖。 FIG. 1 is a block diagram of an integrated chat robot system according to an embodiment of the present invention. Figure 2 is a flowchart of a chat robot model training method according to an embodiment of the present invention. FIG. 3 is a schematic diagram of a chat robot model training method according to an embodiment of the present invention. FIG. 4 is a flowchart of a method for analyzing test results by applying predefined rules according to an embodiment of the present invention.
200:聊天機器人模型訓練方法 210~250:步驟 200: Chatbot model training method 210~250: Steps
Claims (6)
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
TW109107231A TWI745878B (en) | 2020-03-05 | 2020-03-05 | Chat robot system and chat robot model training method |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
TW109107231A TWI745878B (en) | 2020-03-05 | 2020-03-05 | Chat robot system and chat robot model training method |
Publications (2)
Publication Number | Publication Date |
---|---|
TW202135045A TW202135045A (en) | 2021-09-16 |
TWI745878B true TWI745878B (en) | 2021-11-11 |
Family
ID=78777487
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
TW109107231A TWI745878B (en) | 2020-03-05 | 2020-03-05 | Chat robot system and chat robot model training method |
Country Status (1)
Country | Link |
---|---|
TW (1) | TWI745878B (en) |
Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20110301441A1 (en) * | 2007-01-05 | 2011-12-08 | Myskin, Inc. | Analytic methods of tissue evaluation |
CN103000052A (en) * | 2011-09-16 | 2013-03-27 | 上海先先信息科技有限公司 | Man-machine interactive spoken dialogue system and realizing method thereof |
CN105393263A (en) * | 2013-07-12 | 2016-03-09 | 微软技术许可有限责任公司 | Feature completion in computer-human interactive learning |
TW201741948A (en) * | 2016-03-30 | 2017-12-01 | Alibaba Group Services Ltd | Resume assessment method and apparatus |
CN109101217A (en) * | 2013-03-15 | 2018-12-28 | 先进元素科技公司 | Method and system for purposefully calculating |
-
2020
- 2020-03-05 TW TW109107231A patent/TWI745878B/en active
Patent Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20110301441A1 (en) * | 2007-01-05 | 2011-12-08 | Myskin, Inc. | Analytic methods of tissue evaluation |
CN103000052A (en) * | 2011-09-16 | 2013-03-27 | 上海先先信息科技有限公司 | Man-machine interactive spoken dialogue system and realizing method thereof |
CN109101217A (en) * | 2013-03-15 | 2018-12-28 | 先进元素科技公司 | Method and system for purposefully calculating |
CN105393263A (en) * | 2013-07-12 | 2016-03-09 | 微软技术许可有限责任公司 | Feature completion in computer-human interactive learning |
TW201741948A (en) * | 2016-03-30 | 2017-12-01 | Alibaba Group Services Ltd | Resume assessment method and apparatus |
Also Published As
Publication number | Publication date |
---|---|
TW202135045A (en) | 2021-09-16 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
Lin et al. | Traceability transformed: Generating more accurate links with pre-trained bert models | |
Umer et al. | CNN-based automatic prioritization of bug reports | |
US11663409B2 (en) | Systems and methods for training machine learning models using active learning | |
US10599767B1 (en) | System for providing intelligent part of speech processing of complex natural language | |
US8972408B1 (en) | Methods, systems, and articles of manufacture for addressing popular topics in a social sphere | |
US20190347571A1 (en) | Classifier training | |
US9613093B2 (en) | Using question answering (QA) systems to identify answers and evidence of different medium types | |
US20150170051A1 (en) | Applying a Genetic Algorithm to Compositional Semantics Sentiment Analysis to Improve Performance and Accelerate Domain Adaptation | |
US20220083742A1 (en) | Man-machine dialogue method and system, computer device and medium | |
US20230259707A1 (en) | Systems and methods for natural language processing (nlp) model robustness determination | |
US20220414463A1 (en) | Automated troubleshooter | |
WO2021212681A1 (en) | Semantic role annotation method and apparatus, and computer device and storage medium | |
US11151117B2 (en) | Increasing the accuracy of a statement by analyzing the relationships between entities in a knowledge graph | |
CN112685550B (en) | Intelligent question-answering method, intelligent question-answering device, intelligent question-answering server and computer readable storage medium | |
US11809804B2 (en) | Text formatter | |
CN112101042A (en) | Text emotion recognition method and device, terminal device and storage medium | |
CN118093839B (en) | Knowledge operation question-answer dialogue processing method and system based on deep learning | |
JP5317061B2 (en) | A simultaneous classifier in multiple languages for the presence or absence of a semantic relationship between words and a computer program therefor. | |
US11922126B1 (en) | Use of semantic confidence metrics for uncertainty estimation in large language models | |
JP2019036210A (en) | FAQ registration support method using machine learning, and computer system | |
TWI745878B (en) | Chat robot system and chat robot model training method | |
TWI768513B (en) | Artificial intelligence training system and artificial intelligence training method | |
CN114357964A (en) | Subjective question scoring method, model training method, computer device, and storage medium | |
CN111627461A (en) | Voice quality inspection method and device, server and storage medium | |
CN114492397B (en) | Artificial intelligence model training system and artificial intelligence model training method |