KR20190086126A - Manual retrieval service providing server and method using chatbot - Google Patents

Abstract

The present invention provides a manual search service providing server using a chatbot, and a manual search service providing method thereof. The manual search service providing server comprises: a communication interface unit which communicates with a user terminal providing a messenger service through a mobile messenger application; a memory which stores a chatbot program for providing the user terminal with a chatbot service, and keywords extracted from an inputted manual; and a processor which executes the chatbot program stored in the memory to provide the chatbot service to the user terminal having requested the chatbot service, extracts the keywords from questions inputted from the user terminal through the chatbot, compares the extracted question keywords with stored manual keywords, searches the manual for answers related to the questions, and provides the same to the user terminal. Therefore, the present invention can allow a user to freely ask questions on home appliances by using the chatbot and to receive responses with optimal answers.

Description

[0001] The present invention relates to a manual search service providing server and a method for providing a manual search service using the chatbot,

The present invention relates to a manual search service providing server and a method of providing a manual search service using the chatbot. More particularly, the present invention relates to a manual search service providing server and a method of providing a manual search service using the chatbot. The present invention relates to a manual search service providing server using a chatbot and a method for providing a manual search service.

With the development of SNS (Social Networking Service), a messenger service for communicating with other parties through various messengers such as Kakao Talk, Line, and Facebook Messenger is widely used. In recent years, there has been an increasing interest in chatbot technology, in which a user-to-robot conversation is performed not by a user but by a user via a messenger.

A chatbot is a combination of chat and robot, which means a program that talks to people through text. In general, the chatbot function is implemented so that it can be answered by the user through the messenger based on the predetermined response rule. For example, if chatbot is set as a conversation, it can be used to answer questions of consumers in home shopping, internet shopping mall, insurance company, bank, food delivery, accommodation reservation, etc. or recommending suitable products based on the tendency of existing consumers .

However, the function provided by the existing chatbot requests the other party (i.e., user) to select the number of the inquiry contents after listing the inquiry contents in the dialog window, and when the other party selects the number of inquiry contents, Or through the process of displaying a sub-question of the content of the inquiry or requesting input of specific information (for example, a resident registration number). In other words, when using a conventional chatbot, only passive conversation by a predefined procedure is possible in the chatbot rather than the user's initiative.

For example, if you want to inquire about household appliances using chatbots related to household appliances, existing chatbots display a list of questions related to household appliances and provide predetermined and uniformized answers only for the questions you select.

Accordingly, the user feels limitations in freely asking a user a desired question, and as a result, it takes a lot of time and effort to get a desired answer or to obtain a desired answer.

Domestic registered patent No. 10-1811751 (registered on Dec. 18, 2017)

SUMMARY OF THE INVENTION The present invention has been made in view of the above problems, and it is an object of the present invention to provide a method and apparatus for a user to freely inquire about a method of using a home appliance and troubles related to a home appliance using a chatbot, A method for providing a manual search service using a chatbot and a method for providing a manual search service.

The solution of the present invention is not limited to those mentioned above, and other solutions not mentioned can be clearly understood by those skilled in the art from the following description.

According to an aspect of the present invention, there is provided a manual search service providing server using a chatbot, comprising: a communication interface unit communicating with a user terminal providing a messenger service through a mobile messenger application; A chatbot program for providing a chat service to the user terminal, a memory for storing key words (hereinafter, referred to as 'manual key words') extracted from the input manual, And a chatbot program stored in the memory to execute a chatbot service to provide a chatbot service to a user terminal requesting the chatbot service, extract key words (hereinafter, referred to as query key words) from the query input from the user terminal through the chatbot, And a processor for comparing the extracted query keywords with the stored manual keyword to search for an answer related to the query in the manual and provide the query to the user terminal.

The processor extracts the query keywords from the query input through the chatbot, compares the extracted query keywords with the stored manual keywords, identifies the same key word (hereinafter, referred to as the " same key word "), It is possible to process a sentence having the largest number of the same key words among the manuals as a response to the inquiry to the user terminal.

The processor extracts the manual key words from the input manual using a word extraction algorithm, saves the sentence containing the extracted manual key words (hereinafter, referred to as 'manual sentences') in the memory, Counting the number of the same key words included in each of the manual sentences stored in the memory, sorting the manual sentences in descending order according to a result of the counting, and outputting a topmost manual sentence to the inquiry item It can be set as an answer.

Wherein the processor calculates a weight of each of the manual sentences from a result of counting the number of the same key words for each of the manual sentences and a result of counting the number of repetitions of the same key words for each of the manual sentences, The user can sort the manual sentences in descending order according to the calculated weight, and determine the topmost manual sentence as a reply to the query.

According to another embodiment of the present invention, there is provided a method for providing a manual search service using a chatbot in a server, the method comprising the steps of: (A) searching the key word extracted from the inputted manual (hereinafter referred to as' Storing; (B) receiving, by the manual search server, a query item from the user terminal through a chatbot of a user terminal providing a messenger service; (C) extracting key words (hereinafter referred to as 'query key words') from the query items received through the chatbot, by the manual search server; And (D) comparing, by the manual search server, the extracted query key words with the stored manual key words, searching for answers related to the query in the manual, and providing the answer to the user terminal have.

In the step (D), the manual search server compares the extracted query keywords with the stored manual keyword to identify the same key word (hereinafter, referred to as " same key word "), And may provide the user terminal with the sentence most included in the query as the answer to the query.

According to the present invention, it is possible for a user to freely inquire about a usage method of a household appliance and a trouble related to a home appliance using a chatbot, so that a user can ask questions without limitation of a format and can obtain a more accurate answer .

Further, according to the present invention, when a query item is input from a user, a key word extracted from a manual related to a query item (for example, a manual of a home appliance) is compared with a key word included in the query item, You can provide answers.

The effects of the present invention are not limited to those mentioned above, and other effects not mentioned can be clearly understood by those skilled in the art from the following description.

1 illustrates a system for providing a manual search service using a chatbot according to an embodiment of the present invention;
2A is a diagram illustrating an example of a query input by a user through a chatbot in a user terminal,
FIG. 2B is a diagram illustrating an example of a response to a query item retrieved according to an embodiment of the present invention displayed on a user terminal;
3 is a flowchart illustrating a method of generating search data through manual input according to an embodiment of the present invention,
4 is a flowchart illustrating a method for generating search data through a manual search service providing input using a chatbot according to an embodiment of the present invention.

BRIEF DESCRIPTION OF THE DRAWINGS The above and other objects, features, and advantages of the present invention will become more readily apparent from the following description of preferred embodiments with reference to the accompanying drawings. However, the present invention is not limited to the embodiments described herein but may be embodied in other forms. Rather, the embodiments disclosed herein are provided so that the disclosure can be thorough and complete, and will fully convey the scope of the invention to those skilled in the art.

Herein, when it is mentioned that the first element (or component) is operated or executed on the second element (or component) ON, the first element (or component) ) Is operated or executed in an environment in which it is operated or executed, or it is operated or executed through direct or indirect interaction with the second element (or component).

It is to be understood that when an element, component, apparatus, or system is referred to as comprising a program or a component made up of software, it is not explicitly stated that the element, component, (E.g., memory, CPU, etc.) or other programs or software (e.g., drivers necessary to run an operating system or hardware, etc.)

It is also to be understood that the elements (or elements) may be implemented in software, hardware, or any form of software and hardware, unless the context requires otherwise.

Also, terms used herein are for the purpose of illustrating embodiments and are not intended to limit the invention. In the present specification, the singular form includes plural forms unless otherwise specified in the specification. The terms "comprises" and / or "comprising" used in the specification do not exclude the presence or addition of one or more other elements.

Also, in this specification, a DB may mean functional and structural combination of software and hardware for storing information corresponding to each DB. The DB may be implemented as at least one table, and may further include a separate DBMS (Database Management System) for searching, storing, and managing information stored in the DB. In addition, it can be implemented in various ways such as a linked-list, a tree, and a relational DB, and includes all data storage media and data structures capable of storing information corresponding to the DB.

DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS Hereinafter, the present invention will be described in detail with reference to the accompanying drawings. In describing the specific embodiments below, various specific details have been set forth in order to explain the invention in greater detail and to assist in understanding it. However, it will be appreciated by those skilled in the art that the present invention may be understood by those skilled in the art without departing from such specific details.

In some instances, it should be noted that portions of the invention that are not commonly known in the description of the invention and are not significantly related to the invention do not describe confusing reasons for explaining the present invention.

Each of the configurations of the manual search service providing server 100 using the chatbot shown in FIG. 1 indicates that it can be divided into functions and logically, and each configuration may be divided into separate physical devices or written in separate codes The average expert in the field of the present invention can easily reasonably deduce that the term " a "

The manual search service providing server 100 using the chatbots may be installed in a predetermined data processing apparatus to implement the technical idea of the present invention.

The manual search service providing server 100 using the chatbot according to the embodiment of the present invention may be provided with a program such as a desktop PC (personal computer), a server, a laptop PC (Laptop PC), a netbook computer Lt; RTI ID = 0.0 > and / or < / RTI >

1 is a diagram illustrating a system for providing a manual search service using a chatbot according to an embodiment of the present invention.

Referring to FIG. 1, a system for providing a manual search service using a chatbot according to an embodiment of the present invention may include a user terminal 10 and a manual search service providing server 100.

The user terminal 10 may provide a messenger service through a mobile messenger application, or may be a device capable of installing and executing an application such as a smart phone. Messenger services include Kakao Talk, Facebook Messenger, line, and telegram.

The user can use the messenger service to register a desired party to chat and then perform a chat. In particular, in recent years, as a person who wants to communicate, it is also possible to chat with a chatbot after registering not only a person but also an intangible chatbot.

The manual search service providing server 100 using the chatbot according to the embodiment of the present invention can provide the user terminal 10 with a chatbot service related to the manual search service. The manual can be one of a variety of manuals, such as manuals for multiple products, manuals for specific instructions, and so on.

In addition, the manual search service providing server 100 using the chatbot may be a server provided by a specific household appliance manufacturer, or may be an independent server providing only a manual search service. In the former case, the manual search service providing server 100 can only provide a manual search service of home appliances provided by a specific home appliance manufacturer. In the latter case, the manual search service providing server 100 can operate independently of a specific home appliance manufacturer and provide a search service for various manuals provided by a plurality of companies.

For this, a manual search service providing server 100 using a chatbot according to an embodiment of the present invention receives a manual for providing a chat service and extracts key words from the manual and stores the keyword, The user terminal 10 can provide a response to the inquiry, that is, an answer, using the received query and the previously stored keyword.

Referring to FIG. 1, a manual search service providing server 100 using a chatbot according to an exemplary embodiment of the present invention may include a communication interface 110, a memory 120, and a processor 130.

The communication interface unit 110 is a device for wireless communication between the user terminal 10 and the manual search service providing server 100. For example, the communication interface unit 110 may receive a query related to providing a manual search service from the user terminal 10 through the chatbot.

In addition, the communication interface unit 110 may transmit one or more sentences (sentences retrieved from the manual) to the user terminal 10 through the chatbot as a response to the received query items.

The memory 120 may include one or more volatile memory and / or non-volatile memory. In order to implement and / or provide the operations, functions, and the like provided by the manual search service providing server 100, the memory 120 stores instructions or data related to the components, one or more programs and / or software, .

Various manuscripts can be stored in the memory 120, and a keyword including a keyword extracted from each manual (hereinafter, referred to as a 'manual key word') and a manual key word can be mapped and stored. Once the mapping has been saved, the manual may be deleted.

The program stored in the memory 120 extracts a key word (hereinafter referred to as a query key word) from the query items received from the user terminal 10 and uses the extracted query key words and manual keyword words And a chatbot program including a plurality of commands for providing a chatbot service for searching an answer to the chatbot program.

Meanwhile, the processor 130 controls the overall operation of the manual search service providing server 100 by executing one or more programs stored in the manual search service providing server 100.

For example, the processor 130 receives a manual, and extracts a keyword consisting of words, that is, a manual keyword, using a term frequency-inverted document frequency (TF-IDF) algorithm in a manual. The processor 130 may map the extracted key words and the sentence including the key word to store the key word in the memory 120.

Hereinafter, the manual of the refrigerator will be described as an example of the household appliance, and the contents as shown in the following [Table 1] are inputted as the refrigerator manual.

Refrigerator Manual The refrigerator generates heat during the process of creating cold. In order to cool the heat, a heat pipe is contained in the outer wall of the refrigerator, and heat is generated on the outer wall during operation. If you need a lot of cold, it gets a lot of heat. It can cause a lot of heat especially when it is hot during the summer or when the product is started up. The heat of the appearance that occurs when the cold air is in a normal state is not a product abnormality and can be used.

When the refrigerator manual as shown in [Table 1] is input, the processor 130 reads' refrigerator (2 times), cool air (4 times), heat (7 times), occurrence (4 times) '.

The processor 130 extracts a sentence (hereinafter, referred to as a 'manual sentence') from the refrigerator manual and extracts the sentence as three manual sentences, for example, as shown in Table 2 below. Then, it can be mapped to the manual key word extracted from each of the manual sentences and stored in the memory 120.

sentence Contents Manual Keyword Sentence 1 The refrigerator generates heat during the process of creating cold. In order to cool the heat, a heat pipe is contained in the outer wall of the refrigerator, and heat is generated on the outer wall during operation. Refrigerator: 2 times
Frost: 1 time
Heat: 3 times
Occurrence: 2 times
Outer wall: 2 times Sentence 2 If you need a lot of cold, it gets a lot of heat. Cool: 2 times
Heat: 2 times Sentence 3 It can cause a lot of heat when it is hot during the summer or when the product starts up. The heat of the appearance that occurs when the cold air is in a normal state is not a product abnormality and can be used. Frost: 1 time
Heat: 2 times
Occurrence: 2 times

Through the above-described process, manual key words and manual sentences can be extracted for every manual, and can be mapped with manual key words extracted for each manual sentence.

In addition, the processor 130 may execute the chatbot program stored in the memory 120 and provide the chatbot service to the user terminal 10 requesting the chatbot service. The processor 130 extracts key words (i.e., query key words) from the query items received from the user terminal 10 through the chatbot, compares the extracted query key words with the manual keyword stored in the memory 120, It may search for an answer related to the inquiry and provide it to the user terminal 10.

More specifically, when the user of the user terminal 10 executes the messenger and attempts to chat with the chatbot, the user terminal 10 inputs the inquiry to the manual search service providing server 100 send.

The processor 130 extracts query keywords from query items received from the user terminal 10 via the chatbot and compares the extracted query keywords with the manual keyword stored in the memory 120 to obtain the same key word Quot;), and can process a manual sentence including the largest number of the same key words among the manuals to provide the user terminal 10 with a chatbot as a reply to the inquiry.

That is, when a query item is received through the chatbot, the processor 130 counts the number of key words included in each of the manual sentences stored in the memory 120, arranges the manual sentences in descending order according to the count result, The sentence can be set as an answer to the question. This is because the greater the number of the same key words, the greater the degree of matching (or similarity) between the key words.

For example, when the query received from the user terminal 10 is "heat is generated at the side of the refrigerator" as shown in FIG. 2A, the processor 130 executes the chatbot program, Refrigerator, side, heat, generation "can be extracted.

The processor 130 then compares the extracted query keywords (refrigerator, side, column, generator) with the manual keywords (refrigerator, refrigerator, heat, generator, exterior wall) stored in the memory 120, , Heat, occurrence). The processor 130 determines the number of the same key words in the manual sentences such as Table 2 stored in the memory 120 when there are a plurality of identified identical key words (refrigerator, You can count.

As a result of counting, it is confirmed that the same key words (refrigerator, heat, generation) are included in sentence 1 in all three, in sentence 2 in one, and in sentence 3 in two. The processor 130 may assign a high weight to a large number of sentences including the same key word and sort in descending order based on the weight.

Accordingly, the processor 130 may assign the largest weight to the sentence 1 including three of the same key words, and sequentially assign weights to the sentence 3 and the sentence 2 including two and one of the same key words.

If the numbers of the same key words included in the sentences 2 and 3 are the same, that is, the weights are the same, the processor 130 uses the mutex technique of the genetic algorithm to add a new weight to the sentences 2 and 3 Ranking) can be given.

If the same key word does not exist in both sentence 2 and sentence 3, the processor 130 calculates the match degree of the word of the sentence 2 with the word of the sentence 2, and gives a higher weight to the sentence having a high degree of match .

Thus, when sentence 1 is arranged as a top-level manual sentence, and sentence 3 and sentence 2 are sequentially arranged as a next-ranked manual sentence, processor 130 sends sentence 1 to user terminal 10 as an answer to the inquiry The communication interface unit 110 can be controlled. Thus, the sentence 1 can be displayed in the chat chat window of the user terminal 10 as shown in FIG. 2B.

In addition, the processor 130 may cause the sentence 3 and the sentence 2 to be transmitted to the user terminal 10 so as to be displayed as auxiliary information of the chatbot.

Alternatively, according to the embodiment of the present invention, the processor 130 may use a result of counting the numbers including the same key words for each of the manual sentences, counting the number of times the same key word is repeated for each manual sentence, Can be calculated. That is, the processor 130 can calculate a value (degree of similarity or similarity) between how the keyword of the query and the keyword is equivalent to the value (the degree of repetition) of how many key words are included in the sentence. The higher the weighted manual sentence for similarity and repeatability, the more likely it is to be an optimal answer to the query. Accordingly, the processor 130 may sort the manual sentences in descending order according to the calculated weight, and then determine the topmost manual sentence as a reply to the query. In this case, the processor 130 compares the degree of similarity between the keywords and the degree of repetition, and calculates the weight. Therefore, the processor 130 can more accurately provide the manual search service.

3 and 4 are flowcharts for explaining a manual search service providing method using a chatbot of the manual search server 100 according to an embodiment of the present invention.

3 and 4 can be implemented by the manual search server 100 described with reference to FIGS. 1 to 2B, and thus a detailed description thereof will be omitted.

3 is a flowchart illustrating a method for generating search data through manual input according to an embodiment of the present invention.

Referring to FIG. 3, the manual search server 100 may extract a keyword consisting of words using a TF-IDF algorithm, that is, a manual keyword, at step S320, when a manual is input at step S310.

The manual search server 100 maps the manual key words extracted in step S320 and the sentence including the manual key word to the memory 120 of the server 100 as shown in Table 2 at step S330.

Thus, the search data for all the manuals provided by the manual search server 100 is generated and stored, so that the manual search server 100 provides services for various manuals using one chatbot or a chatbot created for each manual . When one chatbot is used, a specific name of the manual (e.g., household appliance type, manufacturing number, etc.) is requested to the user terminal 10, and the service can be provided using the search data of the corresponding manual .

4 is a flowchart illustrating a method for generating search data through a manual search service providing input using a chatbot according to an embodiment of the present invention.

4, when the manual search server 100 receives a query item from the user terminal 10 through the chatbot (S410), it can extract key words (that is, query key words) from the received query items ).

The manual search server 100 may compare the extracted query keywords with the manual keyword extracted and stored in step S320 to identify the same keywords (S430).

The manual search server 100 may count the number of key words included in the manual sentences stored in the memory 120 in step S440 if the same key words are found in step S430. The counting result may be used as a weight. That is, the greater the counted number, the more likely it is to be a response to the query.

In step S440, the manual search server 100 counts the number of times that the same keyword is repeated for each manual sentence (i.e., the degree of matching) and the number of repetitions of the same keyword for each manual sentence The weight of each of the manual sentences can be calculated. The higher the weighted weights for each of the manual sentences, the more likely it is that they are the best answers to the query.

Then, the manual search server 100 can sort the manual sentences in descending order based on the counting result, that is, the weight (S450).

In step S460, the manual search server 100 determines a top-level manual sentence among the sorted manual sentences as a response to the inquiry, and transmits the top manual sentence to the user terminal 10 in step S460.

In addition, the manual search server 100 may further transmit a predetermined number of sub-manual sentences among the sub-manual sentences of the highest-level manual sentence to the user terminal 10 as auxiliary information (S470). Accordingly, the user of the user terminal 10 can receive various information in a short time by receiving a plurality of answers rather than a single answer.

According to the embodiment of the present invention described above, the user can use the chat service by using the existing messenger service without installing a separate application in the user terminal 10. In particular, without providing a uniform dialog window, the chattb service provided by the embodiment of the present invention allows a user to freely search a manual on the basis of a query, and to provide a search result as an answer to a query, The limitations of use that the user feels in searching the manual can be minimized.

Meanwhile, a method of providing a manual search service using a chatbot of the manual search service providing server 100 according to the present invention is a method of providing a manual search service using a chatbot, in which a program of instructions for implementing the program is tangibly embodied, Can be easily understood by a person skilled in the art.

That is, the method for providing the manual search service using the chatbot of the manual search service providing server 100 according to the present invention can be implemented in a form of a program that can be executed through various computer means, and can be recorded on a computer- The computer-readable recording medium may include program commands, data files, data structures, and the like, alone or in combination. The computer-readable recording medium may be any of various types of media such as magnetic media such as hard disks, optical media such as CD-ROMs and DVDs, and optical disks such as ROMs, RAMs, flash memories, And hardware devices specifically configured to store and execute program instructions.

Therefore, in order to implement a method for providing a manual search service using a chatbot of the manual search service providing server 100, the present invention provides a method for providing a manual search service providing server 100, Can be provided together.

While the present invention has been particularly shown and described with reference to exemplary embodiments thereof, it is to be understood that the present invention is not limited to the disclosed exemplary embodiments, but, on the contrary, It will be apparent to those skilled in the art that numerous modifications and variations can be made to the present invention without departing from the scope of the present invention. Accordingly, all such modifications and variations are intended to be included within the scope of the present invention. Accordingly, the true scope of the present invention should be determined by the technical idea of the appended claims.

10: user terminal 100: manual search service providing server
110: communication interface unit 120: memory
130: Processor

Claims (4)

A communication interface unit for communicating with a user terminal providing a messenger service through a mobile messenger application;
A chatbot program for providing a chat service to the user terminal, a memory for storing key words (hereinafter, referred to as 'manual key words') extracted from the input manual, And
A chatbot program stored in the memory is executed to provide a chat terminal service to a user terminal requesting the chat service, and key words (hereinafter referred to as query key words) are extracted from query entries input from the user terminal through the chat bots And a processor for comparing the extracted query keywords with the stored manual keyword to search for an answer related to the query in the manual and provide the query to the user terminal, . The method according to claim 1,
The processor comprising:
The query key words are extracted from the query items input through the chatbot, the extracted query key words are compared with the stored manual key words to identify the same key word (hereinafter, referred to as the " same key word "), And provides a sentence having the largest number of the same key words to the user terminal as a response to the query item. 3. The method of claim 2,
The processor comprising:
Extracts the manual key words from the input manual using a word extraction algorithm, and stores sentences including the extracted manual key words (hereinafter referred to as "manual sentences") in the memory,
Counting the number of the same key words included in each of the manual sentences stored in the memory, sorting the manual sentences in descending order according to a result of the counting, and outputting a topmost manual sentence to the inquiry item A server for providing a manual search service using a chatbot. The method of claim 3,
The processor comprising:
Calculating a weight of each of the manual sentences from a result of counting the number of the same key words for each of the manual sentences and a result of counting the number of repetitions of the same key words for each of the manual sentences, And the top-level manual sentence is determined as a response to the inquiry item after sorting the manual sentences in descending order.

Images