KR102578257B1 - Chatbot service construction and maintenance system - Google Patents

Abstract

The present invention relates to a chatbot service construction and maintenance system that includes a chatbot management server that builds an artificial intelligence-based chatbot model and periodically updates the chatbot model based on big data.

Description

Chatbot service construction and maintenance system {Chatbot service construction and maintenance system}

The present invention relates to a chatbot service construction and maintenance system, and more specifically, to a chatbot service construction and maintenance system that builds an artificial intelligence-based chatbot model and periodically updates the chatbot model based on big data. .

Today, with the development of computers and other information and communication technologies, artificial intelligence (AI) technology has also gradually developed and is currently being applied to various fields. One of the technologies that applies artificial intelligence (AI) is chatbot.

A conventional chatbot is an interactive messenger that provides answers through artificial intelligence (AI), which talks to people in everyday language based on big data analysis, when you enter a question as if chatting on a corporate messenger. Competition among IT companies is intensifying because while providing corporate messenger services, natural language processing capabilities can be improved by analyzing usage patterns of business smartphones/PCs or collecting big data such as languages commonly used at work. Corporate messengers that adopt this chatbot function have the advantage of being able to use it as a platform to connect various functions because they can check and process information in the chat window without running a separate app.

Meanwhile, the above-mentioned background technology is technical information that the inventor possessed for deriving the present invention or acquired in the process of deriving the present invention, and cannot necessarily be said to be known technology disclosed to the general public before filing the application for the present invention. .

Korean Patent No. 10-2445519

One aspect of the present invention provides a chatbot service construction and maintenance system that builds an artificial intelligence-based chatbot model and periodically updates the chatbot model based on big data.

The technical problem of the present invention is not limited to the technical problem mentioned above, and other technical problems not mentioned will be clearly understood by those skilled in the art from the description below.

The chatbot service construction and maintenance system according to an embodiment of the present invention includes a chatbot management server that builds an artificial intelligence-based chatbot model and periodically updates the chatbot model based on big data.

The chatbot management server is,

Question data is extracted from queries in the form of voice or text received from the user terminal, and the extracted question data is transmitted to a network-connected external search engine and external chatbot to display response data received from the external search engine and external chatbot separately. A chatbot service provider that builds a chatbot model that does the following; and

It includes a chatbot update unit that periodically updates the chatbot model built by the chatbot construction unit.

The chatbot service provider is,

The reliability score for each response data received from an external search engine and an external chatbot is calculated using the following equation, and only response data where the calculated reliability score is higher than a preset standard value is displayed.

[Equation]

Here, TS is the reliability score, v_a is the embedding vector for the keyword extracted from the question data, v_ri is the embedding vector for keyword i among the plurality of keywords extracted from the response data, t is the response delay time, u is the inappropriateness index, w is a weight that is set differently for each external search engine and external chatbot.

According to one aspect of the present invention described above, it is possible to build a chatbot model that provides reliable answers to user inquiries, and by periodically updating this chatbot model, the time and cost required for maintenance can be minimized.

Figure 1 is a diagram illustrating the schematic configuration of a chatbot service construction and maintenance system according to an embodiment of the present invention.
FIG. 2 is a diagram showing the specific configuration of the chatbot management server shown in FIG. 1.

The detailed description of the present invention described below refers to the accompanying drawings, which show by way of example specific embodiments in which the present invention may be practiced. These embodiments are described in sufficient detail to enable those skilled in the art to practice the invention. It should be understood that the various embodiments of the present invention are different from one another but are not necessarily mutually exclusive. For example, specific shapes, structures and characteristics described herein may be implemented in one embodiment without departing from the spirit and scope of the invention. Additionally, it should be understood that the location or arrangement of individual components within each disclosed embodiment may be changed without departing from the spirit and scope of the invention. Accordingly, the detailed description that follows is not intended to be taken in a limiting sense, and the scope of the invention is limited only by the appended claims, together with all equivalents to what those claims assert, if properly described. Similar reference numbers in the drawings refer to identical or similar functions across various aspects.

Hereinafter, preferred embodiments of the present invention will be described in more detail with reference to the drawings.

Figure 1 is a diagram illustrating the schematic configuration of a chatbot service construction and maintenance system according to an embodiment of the present invention.

The chatbot service construction and maintenance system according to the present invention builds an artificial intelligence-based chatbot model to provide reliable answers to user inquiries, and periodically updates this chatbot model to reduce maintenance costs. The goal is to minimize time and cost.

Specifically, the chatbot service construction and maintenance system according to the present invention includes a user terminal 100 and a chatbot management server 200.

The user terminal 100 is a terminal owned by a user who wishes to receive a chatbot service using the chatbot service construction and maintenance system according to the present invention, and is capable of wired and wireless communication with external devices and capable of inputting, outputting, and processing information. It may be an electronic device such as a smartphone, PC, laptop, tablet PC, wearable device, etc.

The chatbot management server 200 builds an artificial intelligence-based chatbot model and periodically updates the chatbot model based on big data.

Figure 2 is a diagram showing the specific configuration of this chatbot management server 200.

As shown, the chatbot management server 200 includes a chatbot service provision unit 210 and a chatbot update unit 220.

The chatbot service provider 210 extracts question data from a query in the form of voice or text received from the user terminal using an artificial neural network built with the Word2Vec algorithm.

The Word2Vec algorithm may include a neural network language model (NNLM). A neural network language model is basically a neural network consisting of an input layer, projection layer, hidden layer, and output layer. Neural network language models are used to vectorize words. Since the neural network language model is a known technology, a more detailed description will be omitted.

The Word2vec algorithm is for text mining and is an algorithm that determines proximity by looking at the front and back relationships between each word. The Word2vec algorithm is an unsupervised learning algorithm. As the name indicates, the Word2vec algorithm can be a quantitative technique that expresses the meaning of words in vector form. The Word2vec algorithm can express each word as a vector in a space of about 200 dimensions. Using the Word2vec algorithm, you can obtain the vector corresponding to the word for each word.

The Word2vec algorithm can enable dramatic improvements in precision in the field of natural language processing compared to other conventional algorithms. Word2vec can learn the meaning of words using the relationships between words and adjacent words in sentences in the input corpus. The Word2vec algorithm is based on an artificial neural network and starts from the premise that words with the same context have close meanings. The Word2vec algorithm learns through text documents, and for one word, other words that appear nearby (about 5 to 10 words before or after it) are taught to the artificial neural network as related words. Because words with related meanings are likely to appear close together in a document, two words may have increasingly closer vectors during repeated learning.

The learning methods of the Word2vec algorithm include the CBOW (Continuous Bag Of Words) method and the skip-gram method. The CBOW method predicts the target word using the context created by surrounding words. The skip-gram method predicts words that may come nearby based on one word. The skip-gram method is known to be more accurate in large datasets.

Therefore, in the embodiment of the present invention, the Word2vec algorithm using the skip-gram method is used. For example, if learning is successfully completed through the Word2vec algorithm, similar words can be located nearby in a high-dimensional space. According to the Word2vec algorithm as described above, the closer the distribution of surrounding words in a learning document is, the more similar the calculated vector values can be, and words with similar calculated vector values can be considered similar. Since the Word2vec algorithm is a known technology, detailed descriptions related to vector value calculation will be omitted.

In this way, the chatbot service provider 210 extracts question data by inputting a query in the form of voice or text received from the user terminal into an artificial neural network in which the Word2Vec algorithm is built. Such question data may be in the form of a single word, such as a keyword, but is not limited to this and may be in the form of a phrase or clause consisting of two or more consecutive words, or a single sentence.

The chatbot service provider 210 transmits the extracted question data to an external search engine and an external chatbot connected to a network to build a chatbot model that distinguishes and displays response data received from the external search engine and external chatbot.

In one embodiment, the chatbot service provider uses Equation 1 below to select only reliable response data among a plurality of response data received from each of the external search engine and external chatbot. Reliability scores are calculated for each response data.

[Equation 1]

Here, TS is the reliability score, v_a is the embedding vector for the keyword extracted from the question data, v_ri is the embedding vector for keyword i among the plurality of keywords extracted from the response data, t is the response delay time, u is the inappropriateness index, w is a weight that is set differently for each external search engine and external chatbot.

In this way, the chatbot service provider 210 calculates a reliability score for each response data and displays only response data where the calculated reliability score is greater than or equal to a preset reference value.

When there is a plurality of response data with reliability scores greater than the standard value, the chatbot service provider 210 displays the response data separately by external search engine and external chatbot.

For example, the chatbot service provider 210 converts the response data to the query ‘Tell me about a restaurant in my area’ into ‘Recommend restaurant A as a Google search result, and recommend restaurant B as a Naver search result. , Chat GPT inquiry results can be answered in the form of ‘I recommend restaurant C’.

Meanwhile, the nonconformity index is characterized by being calculated by Equation 2 below.

[Equation 2]

Here, U is the misfit index, s_m is the number of words included in the negative keyword list, s_o is the number of words included in the positive keyword list, s_t is the total number of words, and bs is the distance between embedding vectors for multiple keywords extracted from response data. The average distance (radians), n is the number of keywords extracted from the response data, and σ is the variance of bs.

For example, if the total number of words that make up the response data is 20, and among the words, 5 words are negative keywords and 7 words are positive keywords, n is 12, and bs is 3, when σ is 0.2, u is -2.07, and the smaller the value of u, the lower the reliability score may be.

In this way, the chatbot service provider 210 can calculate the unsuitability index using Equation 2 described above, thereby reducing the reliability score of response data that is inappropriate for the answer and ultimately improving the reliability of the analysis results.

The chatbot update unit 220 periodically updates the chatbot model built by the chatbot construction unit.

To this end, the chatbot update unit 220 can train an artificial neural network or use a trained artificial neural network. The processor can train or execute an artificial neural network stored in memory, and the memory can store a trained artificial neural network. The electronic device that trains the artificial neural network and the electronic device that uses it may be the same, but may also be separate. Artificial intelligence is a computer system that implements some of the functions of the human brain and can learn, guess, and make decisions on its own. As learning progresses, the probability of extracting an answer may increase. Artificial intelligence can be composed of learning and elemental technologies using it. Artificial intelligence learning is an algorithmic technology that classifies and learns features based on input data, and elemental technologies may be technologies that implement some of the functions of the human brain using learning algorithms.

Artificial intelligence is a technology that makes it easy to approach problems that can have multiple answers probabilistically, and can logically and probabilistically infer the optimal cycle, method, and plan according to any input data. Artificial intelligence's inference technology can include judging input data, optimization predictions, knowledge and probability-based reasoning, and preference-based planning.

Artificial neural network is one of the learning algorithms in the machine learning field and is a program that implements the connection between neurons and synapses in the brain. Artificial neural networks can be created through a program to create a neural network structure and then learn it to have the desired function. Although there may be errors, it is possible to learn based on huge data and output appropriate output data with input data. It has the advantage of being able to obtain output data with statistically good results and being similar to human reasoning.

The chatbot update unit 220 can build a question/answer dataset required for learning using an artificial intelligence algorithm built based on big data, and may include a number of artificial neural networks that have been trained in advance for this purpose.

In this embodiment, the relay server may include a number of pre-trained artificial neural networks to perform machine learning algorithms. With machine learning, you can output output data based on input data and use the results to learn on your own, which can improve your own data processing ability. Artificial neural networks can extract features based on input data, infer regularities, and output result data. As this process accumulates, the reliability of the result data increases.

In this embodiment, the artificial neural network may be an algorithm that outputs response data from at least one of the type of question, length of question, number of keywords, and importance of question. Artificial neural networks can infer the best output data using big data as input data or after going through a processing process to organize unnecessary data.

ve Bayes Classifier, Hidden Markov Model, K-Means Clustering 등이 사용될 수 있다.Depending on the type of learning, artificial intelligence machine learning models include Super Viser Learning, UnSuper Viser Learning, Semisupervised Learning, and Reinforcement Learning. And machine learning algorithms include Decision Tree, K-Nearest Nearest Bor, Artificial Neural Network, Support Vector Machine, Ensemble Learning, Gradient Descent, Na

ve Bayes Classifier, Hidden Markov Model, K-Means Clustering, etc. can be used.

The artificial neural network may be pre-trained on various input values that may be included in the input data. An artificial neural network may be an artificial neural network that is learned according to reinforcement learning, one of the learning methods. Reinforcement learning is a method of gradually increasing the probability of obtaining the correct result by setting rewards and limits. Artificial neural networks can also be modeled based on Convelutional Neural Network (CNN) or Recurrent Neural Network (RNN).

In this way, the chatbot update unit 220 can periodically update the chatbot model using big data and artificial neural networks.

As such, the technology according to the present invention may be implemented as an application or in the form of program instructions that can be executed through various computer components and recorded on a computer-readable recording medium. The computer-readable recording medium may include program instructions, data files, data structures, etc., singly or in combination.

The program instructions recorded on the computer-readable recording medium may be those specifically designed and configured for the present invention, or may be known and usable by those skilled in the computer software field.

Examples of computer-readable recording media include magnetic media such as hard disks, floppy disks and magnetic tapes, optical recording media such as CD-ROMs and DVDs, and magneto-optical media such as floptical disks. media), and hardware devices specifically configured to store and perform program instructions, such as ROM, RAM, flash memory, etc.

Examples of program instructions include not only machine language code such as that created by a compiler, but also high-level language code that can be executed by a computer using an interpreter or the like. The hardware device may be configured to operate as one or more software modules to perform processing according to the invention and vice versa.

Although the above has been described with reference to embodiments, those skilled in the art will understand that various modifications and changes can be made to the present invention without departing from the spirit and space of the present invention as set forth in the following patent claims. You will be able to.

210: Chatbot service provision department
220: Chatbot update unit

Claims (3)

In a chatbot service construction and maintenance system that includes a chatbot management server that builds an artificial intelligence-based chatbot model and periodically updates the chatbot model based on big data,
The chatbot management server is,
Question data is extracted from queries in the form of voice or text received from the user terminal, and the extracted question data is transmitted to a network-connected external search engine and external chatbot to display response data received from the external search engine and external chatbot separately. A chatbot service provider that builds a chatbot model that does the following; and
It includes a chatbot update unit that periodically updates the chatbot model built by the chatbot service provider,
The chatbot service provider is,
Building and maintaining a chatbot service, characterized by calculating a reliability score for each response data received from an external search engine and an external chatbot using Equation 1 below, and displaying only response data where the calculated reliability score is higher than a preset standard value. system.

[Equation 1]

Here, TS is the reliability score, v_a is the embedding vector for the keyword extracted from the question data, v_ri is the embedding vector for keyword i among the plurality of keywords extracted from the response data, t is the response delay time, and u is the following Equation 2 The nonconformity index calculated by , w, is a weight set differently for each external search engine and external chatbot.

[Equation 2]


Here, u is the misfit index, s_m is the number of words included in the negative keyword list, s_o is the number of words included in the positive keyword list, s_t is the total number of words, and bs is the distance between embedding vectors for multiple keywords extracted from response data. The average distance (radians), n is the number of keywords extracted from the response data, and σ is the variance of bs.

delete delete