KR101982990B1 - Method and apparatus for questioning and answering using chatbot - Google Patents

Abstract

Disclosed are a method and an apparatus for questioning and answering using a chatbot. The method for questioning and answering using a chatbot comprises the following steps: receiving a user input including a target of a question through a user interface; determining whether the target of the question is image data; performing image data pre-processing for image data, when the target of the question is the image data; detecting a character from the image data in which the image data pre-processing is performed; selecting an answer message corresponding to the image data from candidate answer messages stored in a database, based on a character extracted from the image data; and providing the selected answer message to a user.

Description

[0001] METHOD AND APPARATUS FOR QUESTIONING AND ANNSWERING USING CHATBOT [0002]

The following embodiments relate to a technique for performing a query response using a chatbot.

Chatbot is an interactive messenger that allows AI to analyze questions and provide appropriate answers when a question is typed like chatting on a messenger. In recent years, leading domestic and foreign companies have introduced chatbot as a customer support service to reduce the manpower required for customer service and to improve the quality of customer support service by processing the response quickly 24 hours a day.

On the other hand, since the query object to which the chatbot can recognize and respond is limited to the text data, a user having difficulty in providing the query of the text data may have a great difficulty in utilizing the chatbot function. To solve these problems, there is a need for technical means for developing a chatbot that can provide a wider range of quality of response by recognizing various types of data.

A query response method using a chatbot according to an embodiment includes: receiving a user input including a query object through a user interface; Determining whether the query object is image data; Performing image data preprocessing on the image data when the query object is the image data; Detecting a character in the image data in which the image data preprocessing has been performed; Selecting a response message corresponding to the image data among the candidate response messages stored in the database based on the characters extracted from the image data; And providing the selected response message to a user.

The step of performing the image data preprocessing may include performing at least one of resolution adjustment of the image data, change of the color of the image data to grayscale, and binarization of the image data.

The step of detecting a character in the image data may include detecting a character included in the image data using optical character recognition.

The query response method using the chatbot according to an exemplary embodiment of the present invention includes: tokenizing the entire character string when the number of character strings detected in the image data is equal to or less than a preset threshold value; And listing the entire tokenized string as a token list.

The query response method using a chatbot according to an exemplary embodiment of the present invention includes: tokenizing the entire character string when the number of character strings extracted from the image data is greater than a preset threshold value; Extracting a number of tokenized strings based on the threshold value; And listing the arbitrarily extracted tokenized string as a token list.

The step of selecting the response message may include performing morpheme analysis on the token list; And comparing the morpheme analysis result with candidate response messages stored in the database, and selecting a response message corresponding to the image data based on the comparison result.

The step of performing morpheme analysis may include extracting words included in the character string through morphological analysis of the character string included in the token list and removing duplicated words from the extracted words.

The step of selecting the response message may include calculating a similarity between words included in candidate response messages stored in the database and words extracted from a string included in the token list; And selecting, as a response message corresponding to the image data, a candidate response message in which the similarity satisfies a predetermined condition among the candidate response messages.

And providing the user with a response message including a response unavailable message if the similarity does not satisfy a predetermined condition.

A query response method using a chatbot according to an embodiment includes: receiving a user input including a query object through a user interface; Determining whether the query object is image data; Detecting a character in the image data when the query object is the image data; Generating a token list by tokenizing the entire character string when the number of character strings detected in the image data is equal to or less than a preset threshold value; Calculating a degree of similarity between words included in candidate response messages stored in a database and words extracted from a string included in the token list; Selecting a response message corresponding to the image data among the candidate response messages based on the similarity; And providing the selected response message to a user.

The query response method using a chatbot according to an exemplary embodiment of the present invention includes: tokenizing the entire character string when the number of character strings extracted from the image data is greater than a preset threshold value; Extracting a number of tokenized strings based on the threshold value; And listing the arbitrarily extracted tokenized string as a token list.

The step of selecting the response message may include calculating a similarity between words included in candidate response messages stored in the database and words extracted from a string included in the token list; And selecting, as a response message corresponding to the image data, a candidate response message in which the similarity satisfies a predetermined condition among the candidate response messages.

The query response method using the chatbot according to an exemplary embodiment may further include providing a response message including a response unavailable message to the user when the similarity does not satisfy a predetermined condition.

A query response apparatus using a chatbot according to an exemplary embodiment includes a user interface for receiving a user input including a query target; A determination unit determining whether the query object is image data; An image data preprocessing unit for preprocessing image data on the image data when the query object is the image data; A character detector for detecting a character in the image data subjected to the image data preprocessing; A processing unit for selecting a response message corresponding to the image data among the candidate response messages stored in the database based on the characters extracted from the image data; And an output unit for providing the selected response message to a user.

The image data preprocessing unit may perform at least one of resolution adjustment of the image data, change of the color of the image data to grayscale, and binarization of the image data.

The character detecting unit may detect a character included in the image data by using optical character recognition.

If the number of character strings detected in the image data is equal to or less than a preset threshold value, the character detecting unit may tokenize the entire character string and list the entire tokenized character string as a token list.

Wherein the character detection unit is configured to tokenize the entire character string if the number of character strings extracted from the image data is greater than a preset threshold value and to randomly extract a number of the tokenized character strings based on the threshold value, The arbitrary extracted tokenized character string may be listed in a token list.

Wherein the processing unit calculates a degree of similarity between words included in candidate response messages stored in the database and words extracted from a character string included in the token list and if the degree of similarity satisfies a predetermined condition among the candidate response messages May be selected as a response message corresponding to the image data.

The processing unit may select a response message including a response unavailable message if the similarity does not satisfy a preset condition.

According to one embodiment, in a query response method using a chatbot, a query object is not limited to text data but can provide a response to a query object including image data, thereby enabling various types of query responses.

According to one embodiment, a query object including image data is received, and a character included in the image data is detected. Based on the detected character, a candidate response message having the highest degree of similarity among the candidate response messages stored in the database of the chat- It is possible to provide appropriate response data for the query object including the image data.

FIG. 1 is a diagram showing the overall configuration of a question and answer system using a chatbot according to an embodiment.
2 is a flowchart illustrating an operation of a query response method using a chatbot according to an exemplary embodiment.
FIG. 3 and FIG. 4 are flowcharts for explaining an example of a query response method using a chatbot according to an embodiment.
5 is a diagram showing a configuration of a question answering device using a chatbot according to an embodiment.

In the following, embodiments will be described in detail with reference to the accompanying drawings. However, various modifications may be made in the embodiments, and the scope of the patent application is not limited or limited by these embodiments. It is to be understood that all changes, equivalents, and alternatives to the embodiments are included in the scope of the right.

The terms used in the examples are used for descriptive purposes only and are not to be construed as limiting. The singular expressions include plural expressions unless the context clearly dictates otherwise. In this specification, the terms "comprises" or "having" and the like refer to the presence of stated features, integers, steps, operations, elements, components, or combinations thereof, But do not preclude the presence or addition of one or more other features, integers, steps, operations, elements, components, or combinations thereof.

Unless defined otherwise, all terms used herein, including technical or scientific terms, have the same meaning as commonly understood by one of ordinary skill in the art to which this embodiment belongs. Terms such as those defined in commonly used dictionaries are to be interpreted as having a meaning consistent with the contextual meaning of the related art and are to be interpreted as either ideal or overly formal in the sense of the present application Do not.

In the following description of the present invention with reference to the accompanying drawings, the same components are denoted by the same reference numerals regardless of the reference numerals, and redundant explanations thereof will be omitted. In the following description of the embodiments, a detailed description of related arts will be omitted if it is determined that the gist of the embodiments may be unnecessarily blurred.

FIG. 1 is a diagram showing the overall configuration of a question and answer system using a chatbot according to an embodiment.

Referring to FIG. 1, a query response device 100 using a chatbot is a device that provides a response corresponding to a query to a user using a chatbot when receiving a query from a user. For example, the Q & A apparatus 100 may receive not only a text form query but also an image form query, analyzing each query, and deriving an optimal response suitable for the query and providing the query to the user.

The Q & A apparatus 100 includes an image data analyzing unit 105 for analyzing image data, a morpheme analyzing unit 110 for analyzing morphemes, a response message providing unit 115 for selecting and providing a response message to a user, And a user interface 160 that can receive the data.

In one embodiment, the image data analyzing unit 105 includes an image data preprocessing unit 120 for preprocessing image data on the received image data, a character detecting unit 125 for detecting a character in image data subjected to image data preprocessing, And a tokenization performing unit 130 for tokenizing the character string of the detected character and listing the tokenized character string as a token list.

The morpheme analysis unit 110 includes a processing unit 2 (135) for performing morpheme analysis on a string listed in the token list to detect a word and removing duplicated words when the query subject included in the user input is image data, And a processing unit 1 140 for classifying the sentence component analysis result through morphological analysis on the text data and adding the tag information to the text data when the inquiry object included in the user input is text data . The response message providing unit 115 includes a processing unit 145 for calculating a similarity between the morpheme analysis result received from the morpheme analysis unit 110 and the candidate response message and selecting a candidate response message satisfying a preset similarity condition as a response message, A database 150 for storing a candidate response message, and an output unit 155 for providing a response message to a user.

In the above embodiment, when the query object included in the user input received from the user is image data, the image data preprocessing unit 120 may pre-process the image data received from the user. The image data preprocessing unit 120 performs image data preprocessing so that the character detection unit 125 can detect characters included in the image data. The image data preprocessing unit 120 may adjust the resolution of the image data and convert the color of the image data into grayscale to perform binarization of the image data. The character detecting unit 125 can detect a character in image data subjected to image data preprocessing. The character detecting unit 125 can detect a character in the preprocessed image data by utilizing an optical character recognition function for converting a character included in the image data into a machine-readable character. The character string detected by the character detecting unit 125 may be tokenized in the tokenizing unit 130, and the tokenized character string may be listed in the token list.

After the image data preprocessing is performed in the image data analyzing unit 105, the characters are detected, and the tokenizing is performed, the token list of the listed strings is subjected to morphological analysis in the processing unit 2 135 included in the morpheme analysis unit 110 Can be performed. The processing unit 2 (135) can extract the words included in the character string through morphological analysis of the character string included in the token list. The similarity between the candidate response messages stored in the database 150 in the processing unit 145 included in the response message providing unit 115 may be calculated. The processing unit 145 may calculate the similarity between the words included in the morpheme analysis result and the words included in the candidate response message and select the candidate response message satisfying the preset similarity condition as a response message. If there is no candidate response message satisfying the similarity condition, the processing unit 145 may select the response-disabled message as a response message. The output unit 155 may provide the user with a response message selected by the processing unit 145 through the user interface.

In another embodiment, when the inquiry object included in the user input received from the user is text data, the user can access the morphological analysis unit 110 of the question answering machine 100 using the chatbot and the response message providing unit 115 You can be provided with answers related to the query subject. The text data is analyzed by morphological analysis in the processing unit 1 140 included in the morpheme analysis unit 110, and tag information is added to the text data by classifying the sentence component analysis result into a tag. The analysis result of the sentence component through the morpheme analysis can determine whether or not the sentence structure pattern matches the candidate response messages stored in the database 150 in the processing unit 150 included in the response message providing unit 115. If it is determined that there is a candidate response message whose pattern matches the morpheme analysis result, the processor 150 may select a candidate response message having a pattern identical to the morpheme analysis result as a response message. If there is no candidate response message having the same pattern as the morpheme analysis result, or if there are two or more candidate response messages, the processing unit 150 may select a response-disabled message as a response message. The response message selected by the processing unit 150 may be provided to the user through the output unit 155. [

Hereinafter, a query response method using a chatbot will be described in more detail with reference to the drawings.

2 is a flowchart illustrating an operation of a query response method using a chatbot according to an exemplary embodiment. The query response method using the chatbot can be performed by the query response apparatus using the chatbot described in this specification.

Referring to FIG. 2, in step 210, the query response device may receive user input including a query object via a user interface. In one embodiment, the chatbot may receive, as user input, a query subject that includes data in the form of images, text, and the like.

In step 220, the query response device may determine whether the query object is image data. If it is determined that the query object contained in the user input is image data, the query response apparatus can perform image data preprocessing on the image data in step 230. [ In one embodiment, the query response device may perform resolution adjustment of image data received at the user input, change the color of the image data to grayscale, and binarize the image data.

In step 240, the question answering device can detect a character in the image data subjected to image data preprocessing through resolution adjustment, color change to grayscale, and binarization based on a preset threshold value.

In one embodiment, the Q ' response device can detect characters contained in image data using optical character recognition (OCR). Here, optical character recognition may mean a function of converting a character included in image data into a machine-readable character. The characters detected in the image data through optical character recognition can be tokenized based on the whitespace character of the string, and when the amount of the character string exceeds a certain reference value, that is, a predetermined threshold value, The number of strings can be arbitrarily extracted based on the number of bases. For example, if the number of character strings is less than or equal to a preset threshold value, the entire string may be tokenized and the entire tokenized string may be listed as a token list. On the other hand, if the number of character strings is greater than a preset threshold value, the entire character string can be tokenized and the tokenized character string can be extracted as many as five times as many as the threshold value among the tokenized strings. In addition, the arbitrarily extracted tokenized character string can be listed in the token list.

In step 250, the query response device may select a response message corresponding to the image data, among the candidate response messages stored in the database, based on the characters extracted from the image data.

In one embodiment, the query response device may perform morphological analysis on a token list comprised of tokenized strings. Here, morpheme analysis can mean tokenized strings are categorized into the smallest unit of words with their meanings. Also, the morphological analysis may include a process of extracting words included in a character string through morphological analysis of a string included in the token list, and removing duplicated words from the extracted words. The query response device can calculate the similarity between the words extracted from the character string and the words included in the candidate response messages stored in the database through morphological analysis. The query response apparatus can select a response message corresponding to the image data as the candidate response message in which the degree of similarity calculated in the candidate response messages satisfies predetermined conditions. At this time, if there is no candidate response message corresponding to the degree of similarity satisfying the predetermined condition, the QA device can select the response message including the response-disabled message.

At step 260, the query response device may provide the user with a selected response message.

In another embodiment, in step 220, the query response device determines in step 270 that the query object is not image data as a result of determining whether the query object is image data, Can be detected.

3 and 4 are flowcharts for explaining an example of a query response method according to an embodiment.

Referring to FIG. 3, in step 305, the query response device may receive user input including a query object from a user via a user interface. According to one embodiment, the user input may include image data and text data.

In step 310, the query response device may determine whether the query target contained in the user input is image data. If the query object included in the user input is determined to be text data in step 310, the query response apparatus classifies the results of the sentence component analysis through morphological analysis into tags and adds the tag information to the text data in step 350 .

Alternatively, if the query object contained in the user input is determined to be image data, the QA device may perform image data preprocessing on the image data received in step 315. In the course of performing the image data preprocessing, the query response apparatus can adjust the resolution of the image data to a resolution that facilitates character extraction, and changes the color of the image data to grayscale so that the image data is converted into grayscale by adaptive thresholding Binarization can be performed. The image data preprocessing unit performs the binarization of the image data through the adaptive alerting process in which the binarization is performed for each zone by dividing the image data into zones, It is possible to perform binarization of image data that is easy to extract.

In step 320, the query response device may detect the character in the image data. In one embodiment, the QA device may utilize Optical Character Recognition functionality to detect characters in the image data.

With respect to the character detected in step 320, the query response device in step 325 may determine whether the number of characters in the character string is greater than or equal to a predetermined threshold value. If it is determined in step 330 that the number of detected strings is greater than a preset threshold value, the QA device can tokenize the entire string based on the space character of the string, and the N of the tokenized strings A tokenized string can be arbitrarily extracted as many as the number of times (N is a natural number). If it is determined that the number of detected strings is less than or equal to a predetermined threshold value, then in step 335, the query response device can tokenize the entire string based on the whitespace character of the string.

In step 340, the query response device may list the tokenized strings in step 330 and step 335 into a token list.

At step 345, the query response device may perform a morphological analysis on the string included in the token list. Through a morphological analysis, for example, the sentence "I have read a book" can be analyzed as "withdrawn / read / read / read / read". In one embodiment, the question answering device can extract words from the strings sorted through the morphological analysis and remove redundant words from the extracted words.

Based on the word extracted from the string as a result of step 345 and the text data analyzed as a result of performing step 350, the query response apparatus can generate a morphological analysis result in step 355.

Thereafter, referring to FIG. 4, based on the morpheme analysis result generated in step 355 of FIG. 3, in step 405, the QA device may determine whether the query object is image data. If the query object is determined to be image data, the query response device may calculate the similarity between the morpheme analysis result and the candidate response message stored in the database in step 410.

In one embodiment, the method of calculating the similarity between the words included in the morpheme analysis result and the candidate response message stored in the database may be as follows. The query response apparatus can detect words included in each candidate response message stored in the database and list them in a list corresponding to each candidate response message. The number of words matching each other among the words included in the morpheme analysis result and the words corresponding to the candidate response message included in the list is divided into the number of words included in the list corresponding to the candidate response message and included in the morpheme analysis result And the similarity between candidate words and the candidate response message stored in the database can be calculated.

In step 415, the query response apparatus can determine whether there is a candidate response message satisfying a condition of a predetermined degree of similarity among the similarities corresponding to the candidate response messages stored in the database. The predetermined similarity condition may be, for example, a case where there is only one candidate response message corresponding to the maximum value among the calculated similarities. If there are two or more candidate response messages corresponding to the maximum value of the similarity degree, or if there are 0, it can be determined that there is no candidate response message satisfying the predetermined similarity condition.

If there is a candidate response message satisfying a predetermined similarity condition, the query response device may select the corresponding candidate response message as a response message in step 420. On the other hand, if there is no candidate response message satisfying the predetermined similarity condition, the query response device can select the response unavailable message in the response message corresponding to the query object in step 425. [

If the query object is not determined to be image data, the query response apparatus determines whether there is a candidate response message whose pattern matches the morphological analysis result based on the morpheme analysis result of the text data corresponding to the query object in step 435 It can be judged.

If it is determined that there is a candidate response message in which the morpheme analysis result and the sentence structure pattern coincide with each other, the query response apparatus can select a candidate response message in which the morpheme analysis result and the sentence structure pattern coincide with each other as a response message in step 440 . Alternatively, if it is determined that there is no candidate response message that matches the morpheme analysis result and the sentence structure pattern, the QA device can select the non-response message in the response message in step 425.

In step 430, the query response device may provide the selected response message to the user in response to the query subject.

5 is a diagram showing a configuration of a question answering device using a chatbot according to an embodiment.

5, the Q & A apparatus 500 includes a user input interface 510, a determination unit 520, an image data preprocessing unit 530, a character detection unit 540, a processing unit 550, an output unit 560, And a database 570.

The user input interface 510 may receive a user input that includes a query object from a user. The determination unit 520 may determine whether the query object included in the user input received from the user input interface 510 is image data. If the query object is determined to be image data, the image data preprocessing unit 530 may perform image data preprocessing on the image data. Here, the image data preprocessing may include a process of adjusting the size of the image data to an appropriate size for extracting characters from the image data, changing the color of the image data to grayscale, and binarizing the image data based on a predetermined threshold value have.

The character detecting unit 540 can detect a character in image data subjected to image data preprocessing. The character detecting unit 540 can detect a character included in the image data using optical character recognition. The characters detected in the image data through the optical character recognition are classified into a case where the number of character strings is less than or equal to a predetermined threshold value and a case where the number of character strings is greater than a predetermined threshold value to tokenize the character string in a different manner, As shown in FIG.

If the number of characters of the character detected in the image data is smaller than or equal to a preset threshold value, the character detecting unit 540 can tokenize the entire character string and list the entire tokenized character string as a token list. On the other hand, when the number of character strings of the character detected in the image data is larger than a predetermined threshold value, the character detecting unit 540 tokenizes the entire character string, and randomly generates a token from the tokenized character string Can be extracted. The extracted tokenized strings may be listed in a token list. The number based on the threshold value can be, for example, five times the threshold value.

The processing unit 550 can select a response message corresponding to the image data among the candidate response messages stored in the database 570 based on the characters extracted from the image data.

In one embodiment, the processing unit 550 may perform morphological analysis on the list of tokens listed in the character detection unit 540. As a result of the morphological analysis performed by the processing unit 550, redundant words among the extracted words can be removed. The processing unit 550 may calculate similarities with the words included in the candidate response messages stored in the database 570 from the words extracted from the token list. A candidate response message corresponding to the degree of similarity having the highest value among the calculated similarities may be selected as a response message. If there is not one similarity having the highest value, the processing unit 550 can select the response-disabled message as a response message. The output unit 560 may provide the selected response message to the user.

The apparatus described above may be implemented as a hardware component, a software component, and / or a combination of hardware components and software components. For example, the apparatus and components described in the embodiments may be implemented within a computer system, such as, for example, a processor, a controller, an arithmetic logic unit (ALU), a digital signal processor, a microcomputer, a field programmable gate array (FPGA) , A programmable logic unit (PLU), a microprocessor, or any other device capable of executing and responding to instructions. The processing device may execute an operating system (OS) and one or more software applications running on the operating system. The processing device may also access, store, manipulate, process, and generate data in response to execution of the software. For ease of understanding, the processing apparatus may be described as being used singly, but those skilled in the art will recognize that the processing apparatus may have a plurality of processing elements and / As shown in FIG. For example, the processing unit may comprise a plurality of processors or one processor and one controller. Other processing configurations are also possible, such as a parallel processor.

The software may include a computer program, code, instructions, or a combination of one or more of the foregoing, and may be configured to configure the processing device to operate as desired or to process it collectively or collectively Device can be commanded. The software and / or data may be in the form of any type of machine, component, physical device, virtual equipment, computer storage media, or device , Or may be permanently or temporarily embodied in a transmitted signal wave. The software may be distributed over a networked computer system and stored or executed in a distributed manner. The software and data may be stored on one or more computer readable recording media.

The method according to an embodiment may be implemented in the form of a program command that can be executed through various computer means and recorded in a computer-readable medium. The computer-readable medium may include program instructions, data files, data structures, and the like, alone or in combination. The program instructions to be recorded on the medium may be those specially designed and configured for the embodiments or may be available to those skilled in the art of computer software. Examples of computer-readable media include magnetic media such as hard disks, floppy disks and magnetic tape; optical media such as CD-ROMs and DVDs; magnetic media such as floppy disks; Magneto-optical media, and hardware devices specifically configured to store and execute program instructions such as ROM, RAM, flash memory, and the like. Examples of program instructions include machine language code such as those produced by a compiler, as well as high-level language code that can be executed by a computer using an interpreter or the like. The hardware devices described above may be configured to operate as one or more software modules to perform the operations of the embodiments, and vice versa.

While the present invention has been particularly shown and described with reference to exemplary embodiments thereof, it is to be understood that the invention is not limited to the disclosed exemplary embodiments. For example, it is to be understood that the techniques described may be performed in a different order than the described methods, and / or that components of the described systems, structures, devices, circuits, Lt; / RTI > or equivalents, even if it is replaced or replaced.

Therefore, other implementations, other embodiments, and equivalents to the claims are also within the scope of the following claims.

Claims (21)

In a query response method using a chatbot,
Receiving a user input including a query object via a user interface;
Determining whether the query object is image data;
Performing image data preprocessing on the image data when the query object is the image data;
Detecting a character in the image data in which the image data preprocessing has been performed;
Tokenizing the character string if the number of characters of the character detected in the image data is equal to or less than a preset threshold value;
Listing the tokenized string as a token list;
Selecting a response message corresponding to the image data among the candidate response messages stored in the database based on the token list and the character detected in the image data; And
Providing the selected response message to a user
/ RTI >
A query response method using chatbots. The method according to claim 1,
Wherein the performing the image data preprocessing comprises:
Adjusting the resolution of the image data, changing the color of the image data to grayscale, and performing at least one of binarizing the image data
/ RTI >
A query response method using chatbots. The method according to claim 1,
Wherein the step of detecting a character in the image data comprises:
Detecting a character included in the image data using optical character recognition
/ RTI >
A query response method using chatbots. delete In a query response method using a chatbot,
Receiving a user input including a query object via a user interface;
Determining whether the query object is image data;
Performing image data preprocessing on the image data when the query object is the image data;
Detecting a character in the image data in which the image data preprocessing has been performed;
Tokenizing the character string if the number of characters of the character detected in the image data is greater than a preset threshold value;
Extracting a number of tokenized strings based on the threshold value;
Listing the randomly extracted tokenized string in a token list;
Selecting a response message corresponding to the image data among the candidate response messages stored in the database based on the token list and the character detected in the image data; And
Providing the selected response message to a user
/ RTI >
A query response method using chatbots. 6. The method of claim 5,
The step of selecting the response message comprises:
Performing morpheme analysis on the token list; And
Comparing the morpheme analysis result with a candidate response message stored in the database, and selecting a response message corresponding to the image data based on the comparison result
/ RTI >
A query response method using chatbots. The method according to claim 6,
The step of performing the morpheme analysis comprises:
Extracting words included in the character string through morphological analysis of the string included in the token list, and removing words overlapping each other among the extracted words
/ RTI >
A query response method using chatbots. 8. The method of claim 7,
The step of selecting the response message comprises:
Calculating a degree of similarity between words included in the candidate response messages stored in the database and words extracted from a string included in the token list; And
Selecting a response message corresponding to the image data among the candidate response messages, the candidate response message satisfying the predetermined condition as the similarity degree;
/ RTI >
A query response method using chatbots. 9. The method of claim 8,
Providing a response message to the user including a response unavailable message if the similarity does not satisfy a predetermined condition
≪ / RTI >
A query response method using chatbots. In a query response method using a chatbot,
Receiving a user input including a query object via a user interface;
Determining whether the query object is image data;
Detecting a character in the image data when the query object is the image data;
Generating a token list by tokenizing the entire character string when the number of character strings detected in the image data is equal to or less than a preset threshold value;
Calculating a degree of similarity between words included in candidate response messages stored in a database and words extracted from a string included in the token list;
Selecting a response message corresponding to the image data among the candidate response messages based on the similarity; And
Providing the selected response message to a user
/ RTI >
A query response method using chatbots. 11. The method of claim 10,
If the number of character strings extracted from the image data is greater than a predetermined threshold, tokenizing the entire character string;
Extracting a number of tokenized strings based on the threshold value; And
Listing the randomly extracted tokenized string in a token list
≪ / RTI >
A query response method using chatbots. 11. The method of claim 10,
The step of selecting the response message comprises:
Calculating a degree of similarity between words included in the candidate response messages stored in the database and words extracted from a string included in the token list; And
Selecting a response message corresponding to the image data among the candidate response messages, the candidate response message satisfying the predetermined condition as the similarity degree;
/ RTI >
A query response method using chatbots. 13. The method of claim 12,
Providing a response message to the user including a response unavailable message if the similarity does not satisfy a predetermined condition
≪ / RTI >
A query response method using chatbots. A computer-readable recording medium having recorded thereon a program for causing a computer to execute the method according to any one of claims 1 to 3 and 5 to 13. A user interface for receiving user input including a query target;
A determination unit determining whether the query object is image data;
An image data preprocessing unit for preprocessing image data on the image data when the query object is the image data;
A character detector for detecting a character in the image data subjected to the image data preprocessing;
A processing unit for selecting a response message corresponding to the image data among the candidate response messages stored in the database, based on the character detected in the image data; And
And an output unit for providing the selected response message to a user,
Wherein the character detection unit comprises:
Tokenize the character string when the number of characters of the character detected in the image data is equal to or less than a preset threshold value,
Listing the tokenized string as a token list,
Query response device using chatbot. 16. The method of claim 15,
The image data pre-
Adjusting the resolution of the image data, changing the color of the image data to grayscale, and performing binarization of the image data.
Query response device using chatbot. 16. The method of claim 15,
Wherein the character detection unit comprises:
Detecting a character included in the image data using optical character recognition,
Query response device using chatbot. delete A user interface for receiving user input including a query target;
A determination unit determining whether the query object is image data;
An image data preprocessing unit for preprocessing image data on the image data when the query object is the image data;
A character detector for detecting a character in the image data subjected to the image data preprocessing;
A processing unit for selecting a response message corresponding to the image data among the candidate response messages stored in the database, based on the character detected in the image data; And
And an output unit for providing the selected response message to a user,
Wherein the character detection unit comprises:
If the number of character strings extracted from the image data is larger than a predetermined threshold value,
Extracting a number of the tokenized strings based on the threshold value,
And to list the tokenized strings in the token list,
Query response device using chatbot. The method according to claim 15 or 19,
Wherein,
Calculating similarities between words included in the candidate response messages stored in the database and words extracted from the strings included in the token list,
A candidate response message that satisfies a predetermined condition among the candidate response messages is selected as a response message corresponding to the image data
Query response device using chatbot. 21. The method of claim 20,
Wherein,
Selecting a response message including a response unavailable message if the similarity does not satisfy a predetermined condition,
Query response device using chatbot.

Images