KR102473155B1 - Method for providing interactive information service and apparatus therefor - Google Patents

Abstract

The present invention relates to an interactive information providing service method and apparatus for providing searched information to a user based on user selection response information for an interactive question. An information providing apparatus according to the present invention includes a tree generator for generating a question tree based on attribute information defined for each question; When an interactive information providing service is requested from a user terminal, hierarchical questions formed in the question tree are sequentially provided to the user terminal, but a sub-question of the next level is selected based on response information to the question and sent to the user terminal. a question providing unit to transmit; and an information providing unit extracting information corresponding to the response information of the final question and providing the extracted information to the user terminal when response information to the final question is received from the user terminal.

Description

Interactive information providing service method and apparatus therefor

The present invention relates to an information providing service method, and more particularly, to an interactive information providing service method and apparatus for providing searched information to a user based on user selection response information for an interactive question.

Today, due to the development of communication devices and mobile communication networks, a vast amount of data exists on the Internet, and users sometimes acquire desired information through a search function.

However, in this passive search method, deviations occur depending on the search ability of each user. Users with good search ability may obtain desired information immediately, and users with poor search ability may obtain desired information over a long period of time.

Meanwhile, a technology for searching for information within a specific category and providing it to a user has emerged. The following patent documents disclose a search method and system using a category identifier.

However, this category-based information search method also has a problem in that accurate information is provided to the user only when the user inputs an appropriate keyword and inaccurate information is provided when the keyword is inappropriate. In addition, the conventional category-based information search method has a problem accompanied by the inconvenience of continuously changing keywords when inaccurate information is searched for.

Korean registered patent 10-0882437

The present invention has been proposed to solve these conventional problems, and an object of the present invention is to provide an interactive information providing service method and apparatus capable of providing user with convenient and accurate search information.

Other objects and advantages of the present invention can be understood by the following description, and will be more clearly understood by the examples of the present invention. It will also be readily apparent that the objects and advantages of the present invention may be realized by means of the instrumentalities and combinations indicated in the claims.

An information providing apparatus according to a first aspect of the present invention for achieving the above object includes a tree generator for generating a question tree based on attribute information defined for each question; When an interactive information providing service is requested from a user terminal, hierarchical questions formed in the question tree are sequentially provided to the user terminal, but a sub-question of the next level is selected based on response information to the question and sent to the user terminal. a question providing unit to transmit; and an information providing unit extracting information corresponding to the response information of the final question and providing the extracted information to the user terminal when response information to the final question is received from the user terminal.

To achieve the above object, a method for performing an interactive information providing service in an information providing apparatus according to a second aspect of the present invention includes generating a question tree based on attribute information defined for each question; Receiving a request for an interactive information providing service from a user terminal; sequentially providing hierarchical questions formed in the question tree to the user terminal, selecting a sub-question of a next level based on response information to the question, and transmitting the selected sub-question to the user terminal; and when response information to the final question is received from the user terminal, extracting information corresponding to the response information to the final question and providing the extracted information to the user terminal.

The present invention has an advantage of improving convenience when searching for information by extracting data based on user response information to a plurality of multiple-choice questions and providing the extracted data to the user.

In addition, the present invention creates a question tree based on the attribute information of the question, sequentially provides questions with a high correlation to the user based on the question tree, and provides information to the user based on the user's selection response to the question. Since it is provided, there is an effect that the user can accurately search for the requested information.

The following drawings attached to this specification illustrate preferred embodiments of the present invention, and serve to further understand the technical idea of the present invention together with specific details for carrying out the invention, so the present invention is described in such drawings should not be construed as limited to
1 is a diagram illustrating a communication system according to an embodiment of the present invention.
2 is a diagram showing the configuration of an information providing device according to an embodiment of the present invention.
3 is a diagram illustrating a question including attribute information according to an embodiment of the present invention.
4 is a flowchart illustrating a method of generating a question tree in an information providing apparatus according to an embodiment of the present invention.
5 is a diagram illustratively illustrating a process of bipartite clustering of questions.
6 is a diagram illustrating a process of generating a question tree by way of example.
7 is a flowchart illustrating a method of providing an interactive information providing service to a user based on a question tree according to an embodiment of the present invention.

The above-described objects, features and advantages will become more apparent through the following detailed description in conjunction with the accompanying drawings, and accordingly, those skilled in the art to which the present invention belongs can easily implement the technical idea of the present invention. There will be. In addition, in describing the present invention, if it is determined that a detailed description of a known technology related to the present invention may unnecessarily obscure the subject matter of the present invention, the detailed description will be omitted. Hereinafter, a preferred embodiment according to the present invention will be described in detail with reference to the accompanying drawings.

1 is a diagram illustrating a communication system according to an embodiment of the present invention.

As shown in FIG. 1, the communication system according to an embodiment of the present invention includes a user terminal 100 and an information providing device 200, and the user terminal 100 and the information providing device 200 are network They communicate with each other through (300). The network 300 includes a mobile communication network and a wired Internet network, and since it corresponds to well-known and used technology of the present invention, detailed description thereof will be omitted.

The user terminal 100 is a communication device possessed by a user, and is provided with an interactive information service by accessing the information providing device 200 . In particular, the user terminal 100 accesses the information providing device 200, sequentially receives multiple choice questions, and receives a data group corresponding to the response from the information providing device 200 in response to each of the multiple choice questions. do. The choice type question is a multiple-choice type question such as a multiple-choice type including a plurality of selection information and a two-way type in which one of yes and no can be selected. In addition, the data group is information in which one or more pieces of data are aggregated, for example, an API data group in which APIs (application programming interfaces) are aggregated according to purpose, a department data group divided by department, a travel destination data group classified according to travel destinations, etc. to be. The user terminal 100 may be a mobile communication terminal such as a smart phone or a personal computer such as a desktop computer.

The information providing apparatus 200 classifies and stores a question to which attribute information is defined and encoding information is assigned and a data group corresponding to the question by data type. In addition, the information providing device 200 separates each question into optimal clusters using a genetic algorithm, and creates a question tree for each data type based on the separated clusters.

The genetic algorithm is a calculation model developed based on the natural evolutionary process and is one of the techniques used to derive an optimal solution. The genetic algorithm derives an optimal solution for a specific problem through selection operation, crossover operation, and mutation operation. In an embodiment of the present invention, while the information providing device 200 sets each question as a node and repeatedly performs a selection operation, crossover operation, mutation operation, and fitness evaluation using the encoding information assigned to each question. , each question is separated into a certain number of optimal clusters. Here, the encoding information represents identification information of a certain number of digits assigned to each question, corresponds to genetic information (eg, chromosome information) in the genetic algorithm, and is generated in advance and assigned to each question. In the encoding information, a number of a certain number of digits corresponding to a decimal number is recorded. Optionally, data in various formats such as binary, octal, hexadecimal, and the like may be recorded in the encoding information.

The information providing device 200 provides a question to the user terminal 100, continuously provides another related question based on the response information selected by the user terminal 100, and then provides final question response information. Information corresponding to is extracted and provided to the user terminal 100 . The information providing device 200 may provide the user terminal 100 with any one of an API data group, a department data group classified by department, and a travel destination data group classified according to a travel destination as information.

2 is a diagram showing the configuration of an information providing device according to an embodiment of the present invention.

As shown in FIG. 2 , the information providing device 200 according to an embodiment of the present invention includes a question providing unit 210, a storage unit 220, a tree generating unit 230 and an information providing unit 240. Including, these components may be implemented in hardware or software, or through a combination of hardware and software.

The question provider 210 performs a function of providing a question including a plurality of options and questions to the user terminal 100 based on the question tree formed in the tree generator 230 . The question providing unit 210 provides a question corresponding to a root road to the user terminal 100 as an initial question. In addition, the question providing unit 210 extracts a question of a child node corresponding to the selection response information from child nodes of the current question node based on the selection response information of the user terminal 100 and provides the extracted question to the user terminal 100. do.

The storage unit 220 is a storage medium such as a memory or a disk device, and stores a plurality of multiple-choice questions for each data type and also stores information corresponding to the questions (ie, a data group). Also, the storage unit 220 stores a question tree for each data type. In the question, attribute information is defined, encoding information is allocated, and a plurality of option information is included in the question. In addition, information on whether or not there is correlation for each data group is recorded in the attribute information. The attribute information is used to calculate the degree of fitness for cluster separation.

3 is a diagram illustrating a question including attribute information according to an embodiment of the present invention.

Referring to FIG. 3 as an example, the question includes attribute information in the form of multi-dimensional coordinates. For example, the question “Is it related to land transportation?” includes attribute information of (1,1,1,1,1,1,1,1,1,0,0,0,0), and “Is it related to sea transportation?” Do you have it?' includes attribute information of (0,0,0,0,0,0,0,0,0,1,0,0,0) Each attribute information is expressed as a multidimensional coordinate value '0' or '1' is recorded as a detailed value, where '1' is flag information indicating that it is related to the corresponding data group, and '0' is flag information indicating that it is not related to the corresponding data group. According to the attribute information included in the question "Is it related to maritime traffic?" in Fig. 3, the question is related to the "ship operation" data group and has no relation to other data groups.

The tree generator 230 separates each question into a predetermined number of optimum clusters using a genetic algorithm, generates a question tree for each data type based on the separated clusters, and stores the data type in the storage unit 220 . That is, the tree generator 230 generates a question tree having a hierarchical structure according to the relation of questions using a genetic algorithm and stores it in the storage 220 .

Specifically, the tree generator 230 initially separates a plurality of questions into a predetermined number of optimal clusters based on factors such as question attribute information and question encoding information. At this time, the tree generator 230 divides the questions into a certain number of random clusters, calculates internal similarity and external similarity for the clusters using Equations 1 and 2 described later, and determines whether the internal similarity and internal similarity are After calculating the multiplied final similarity, the selection operation, crossover operation, mutation operation, and fitness evaluation (i.e., final similarity convergence evaluation) are repeated until the final similarity converges, and the questions are initially separated into optimal clusters.

The selection operation selects a crossover target question among questions, and an equal proportional roulette wheel selection method, a tournament selection method, a rank-based selection method, and the like may be used. The crossover operation is a process of generating a new object (ie, encoding information) by crossing selected questions, and the gene (ie, part of the encoding information) of a parent is inherited by the new object created through crossing over. In the crossing operation, a cycle crossing operation, an order crossing operation, an arithmetic intersection operation, a heuristic intersection operation, and the like may be used. The mutation operation represents a process of deriving a mutant object by changing some data of the encoding information of a newly created object to data (ie, a number) not inherited from a parent (ie, a question selected in the selection operation). . The data to be changed may be generated through a random number generator.

The object for which the mutation operation has been completed (ie, encoding information) is changed to the encoding information of a specific questionnaire. At this time, the tree generator 230 may identify a question having encoding information most similar to the object for which the mutation operation has been completed, and change the encoding information of the question to the encoding information for which the mutation has been completed.

When one cycle according to the selection operation, crossover operation, and mutation operation is completed, encoding information of a specific question is updated. Then, the tree generator 230 substitutes the attribute information of the question belonging to the currently separated cluster into Equations 1 and 2, calculates the final similarity of the currently separated cluster, and determines whether the similarity is converging. If convergence is occurring, the currently separated cluster is determined as the optimal cluster and cluster separation is stopped.

When the optimal cluster is initially separated, the tree generator 230 creates a question having attribute information corresponding to a distance close to the center value of the first cluster as a root load. Also, the tree generator 230 generates a specific question included in the initially separated second cluster as a second child node of the root load. At this time, the tree generator 230 may generate a question having attribute information corresponding to the closest distance to the center value of the second cluster as the second child node of the root road.

In addition, the tree generator 230 separates a predetermined number of sub-clusters from each of the separated first and second clusters through a selection operation, crossover operation, and mutation operation of a genetic algorithm. Similarly, the tree generator 230 divides the optimally separated clusters into arbitrary sub-clusters, calculates the internal similarity and external similarity of the sub-clusters using Equations 1 and 2, and then determines the internal similarity and external similarity. The multiplied final similarity is calculated, and by repeating the cluster separation through the genetic algorithm until the final similarity converges, the separated clusters are again separated into optimal sub-clusters.

The tree generator 230 performs the representative question of the sub-cluster having the highest frequency of the association flag (ie, '1') among the sub-clusters of the first cluster (ie, attribute information corresponding to the closest distance to the central value of the sub-cluster). question) is created as the first child node (eg, right child node) of the root node. In addition, the tree generator 230 determines the representative question of the sub-cluster having the lowest frequency of the association flag (ie, '0') among the sub-clusters of the first cluster (ie, the closest distance to the central value of the sub-cluster). A question having attribute information) is created as a child node of the first child node. In addition, the tree generator 230 selects the representative question of the sub-cluster having the highest frequency of the association flag (ie, '1') among the sub-clusters of the second cluster as a child node of the second child node (eg, the right child node). , and a representative question in a sub-cluster in which the relevance flag (ie, '0') has a low frequency among the sub-clusters of the first cluster is created as another child node of the second child node.

While repeating the process of dividing each question into sub-clusters until each question is generated as a node in the question tree, the tree generator 230 continues the process of generating child nodes for parent nodes.

Meanwhile, the number of child nodes is generated corresponding to the number of selection information of the question. That is, in the case of a question with either-or-type selection information such as 'yes' and 'no', a maximum of two child nodes can be generated, and in the case of a question with three selection information, a maximum of three child nodes can be generated. It can be.

When response information for the last question is received from the user terminal 100, the information provider 240 extracts information (ie, a data group) corresponding to the last question and response information to the storage 220, Information is provided to the user terminal 100 .

4 is a flowchart illustrating a method of generating a question tree in an information providing apparatus according to an embodiment of the present invention.

5 is a diagram illustratively illustrating a process of bipartite clustering of questions.

6 is a diagram illustrating a process of generating a question tree by way of example.

In the following description with reference to FIGS. 4 and 6 , it is assumed that the questions are either-or-type questions and thus a binary tree is formed. In addition, questions with high relevance to the parent node are created in the left child node (ie, child nodes corresponding to positive responses), and questions with low relevance are created in the right child node (ie, child nodes corresponding to negative responses). assume that

Referring to FIGS. 4 to 6 , the tree generator 230 initially separates a plurality of questions into two optimal clusters through selection operation, crossover operation, mutation operation, and fitness evaluation of the genetic algorithm (S401). The tree generator 230 performs crossover and mutation operations on each question using encoding information assigned to each question. In addition, the tree generator 230 separates the questions into two arbitrary clusters using a genetic algorithm, and calculates the internal similarity and external similarity of the randomly separated clusters using Equations 1 and 2 below, Cluster separation is repeatedly performed until the final similarity multiplied by the internal similarity and the external similarity converges, and the questions are initially separated into optimal bipartite clusters. In other words, the tree generator 230 separates clusters by performing selection, crossover, and mutation operations using the encoding information assigned to each question as genetic information, and uses the final similarity as a fitness evaluation index.

Here, Fit _intra means internal similarity, k is the number of clusters, C _k is the center value of the k-th cluster, and X _i represents the attribute information (ie, multi-dimensional coordinate values) of the i-th question belonging to the same cluster. .

Here, Fit _inter means external similarity, k is the number of clusters, C _k is the center value of the k-th cluster, X _i is the attribute information of the i-th question belonging to each other cluster (i.e., multi-dimensional coordinate values), d means the maximum k value.

Next, when a plurality of questions are initially divided into optimal bipartite clusters, the tree generator 230 selects one of the initially separated clusters A and B as the root target cluster. At this time, the tree generator 230 may select a cluster having a high frequency of the related flag information '1' (ie, the total number of 1's) in the attribute information as the root target cluster, and conversely, the frequency of the related flag information '0' A cluster with less is selected as the root target cluster. In the description with reference to FIGS. 4 to 6 , it is explained that cluster A is selected as the route target cluster.

5 is a diagram in which multi-dimensional questions are simplified into two dimensions, and it means that the frequency of the related flag information '1' increases as it is closer to the left with respect to the X coordinate axis. Referring to FIG. 5 as an example, the tree generation unit 230 forms A cluster with questions 1 to 4 for a total of 7 questions, and questions 5 to 7 are grouped together. By forming the B cluster, the questions are separated into two clusters, and among them, the A cluster can be selected as the root target cluster.

Subsequently, the tree generator 230 checks the center value of the selected route target cluster (ie, cluster A), and asks a question having attribute information (ie, multidimensional coordinate information) corresponding to the closest distance to the center value. It is created by root load (S403). Referring to FIG. 5(a) and FIG. 6(b), question number 3 closest to the center value of cluster A, which is the root target cluster, is created as a root load.

Next, the tree generator 230 checks the center value of cluster B, which is not selected as the root target cluster, and creates a question having attribute information closest to the center value of this cluster as the first right child node of the root node. Do (S405). Here, the right child node is a node having a low correlation with the parent node and is a question node corresponding to a negative response. Referring to FIG. 5(a) and FIG. 6(a), question number 7 closest to the center value of cluster B, which is not selected as the root target cluster, is created as the right child node of the root road.

Next, the tree generator 230 separates each initially separated cluster into two optimal sub-clusters using a genetic algorithm (ie, selection operation, crossover operation, mutation operation) (S407). At this time, the tree generator 230 separates the initially separated cluster into two sub-clusters, and calculates internal similarity and external similarity of the sub-clusters using Equations 1 and 2 above. Then, the tree generator 230 calculates the final similarity multiplied by the internal similarity and the external similarity, and repeats the process of re-executing cluster separation through a genetic algorithm until the final similarity converges, thereby optimizing the separated clusters. Separate each into sub-clusters of .

Subsequently, the tree generator 230 proceeds with a process of generating questions included in the separated sub-cluster as child nodes (S409). That is, the tree generator 230 identifies a sub-cluster having the highest frequency of the association flag (ie, '1') among the sub-clusters (ie, cluster A-1 and A-2) included in the root target cluster, and , A representative question of this sub-cluster (that is, a question having attribute information corresponding to the closest distance to the center value of the sub-cluster) is created as the first left child node of the root node. In addition, a representative question of a sub-cluster with a low frequency of the association flag (ie, '0') among sub-clusters included in the root target cluster (ie, a question having attribute information corresponding to the closest distance to the center value of the sub-cluster) is created as a right child node of the first left child node. At this time, the tree generator 230 selects and creates child nodes from questions that are not selected as nodes.

Next, the tree generator 230 provides a representative question of the sub-cluster having the highest frequency of the association flag (ie, '1') among the sub-clusters of cluster B (ie, cluster B-1 and cluster B-2). 1 Created as a left child node of a right child node (ie, a right child node of the root node), and a representative question of a sub-cluster having a low frequency of the association flag (ie, '0') among sub-clusters of cluster B is selected as the first right child node. It is created as the right child node of a child node.

Referring to (b) of FIG. 5 and (b) of FIG. 6 , cluster A is divided into clusters A-1 and A-2, and cluster B is divided into clusters B-1 and B-2. Among clusters A-1 and A-2, question 2, which is the node closest to the center value of cluster A-1, which is the sub-cluster with the highest association flag frequency, is the left child node of the root node (ie, question 3). is created with In addition, question 4, which is a node close to the center value of cluster A-2, which is the sub-cluster with the lowest association flag frequency, is created as a right child node of question 2. In addition, among clusters B-1 and B-2, question 5, which is the node closest to the center value of cluster B-1, which is the sub-cluster with the highest association flag frequency, is the right child node of the root node (i.e., question 7 ) is created as the left child node of In addition, question 6, which is a node close to the center value of cluster B-2, which is the sub-cluster with the lowest association flag frequency, is created as a right child node of the right child node of the root node (ie, question 7).

Next, the tree generator 230 determines whether a node is formed in the tree in response to the end condition and the number of all questions (S411). generate Referring to (c) of FIG. 5 and (c) of FIG. 6 , the tree generation unit 230 proceeds again from step S407 and divides cluster A-1 into two sub-clusters (ie, A-1-1 and A-1). -2), and a question close to the central value of A-1-1 with a high associated flag frequency among A-1-1 and A-1-2 clusters is formed as the right child node of question 2.

Through this iterative process, a question tree is formed. The tree creation unit 230 receives a data type (eg, API programming, company, etc.) from an administrator, stores the input data type and the formed question tree together in the storage unit 220, and accordingly the storage unit In 220, a question tree for each data type is stored.

Meanwhile, in the above embodiment, the question tree has been described as being a binary tree, but a question tree having three or more child nodes may be formed. For example, the tree generator 230 may generate up to three child nodes for a plurality of questions having three selection information. In this case, the tree generation unit 230 assigns the question with the highest correlation with the parent node to the leftmost (or rightmost) child node, and the question with the second highest correlation with the parent node to the middle child node or parent node. The lowest question can be created as a rightmost (or leftmost) child node, respectively.

7 is a flowchart illustrating a method of providing an interactive information providing service to a user based on a question tree according to an embodiment of the present invention.

Referring to FIG. 7 , the question provider 210 receives a request for an interactive service from the user terminal 100 . Then, the question providing unit 210 provides the data type list to the user terminal 100 and receives a specific data type selected by the user from the user terminal 100 (S701).

Subsequently, the question providing unit 210 checks the question tree corresponding to the specific data type in the storage unit 220 (S703), and sends a question corresponding to the highest level (ie, root) of the question tree to the user terminal. It is transmitted to (100) (S705). The question includes option information.

Subsequently, the question providing unit 210 receives selection response information for the question from the user terminal 100 (S707), identifies a child node of the next level (ie, level 2) corresponding to the selection response information, and , a question corresponding to this child node is provided to the user terminal 100 (S709). The question providing unit 210 may provide a question corresponding to a left (or right) child node of the root road to the user terminal 100 when the questionnaire is an either/or type question and the selection response information is an affirmative response. As another example, the question providing unit 210 provides a question corresponding to a right (or left) child node of the root rod to the user terminal 100 when the questionnaire is an either/or type question and the selection response information is a negative response. can do. As another example, the question providing unit 210 may provide a question corresponding to a child node located at the far left to the user terminal 100 when the questionnaire is a multiple-choice question and the selection response information is a response number 1. , If the selection response information is the second response, the child node located second from the left may be provided to the user terminal 100 .

Next, the question providing unit 210 receives selection response information for a question corresponding to a child node from the user terminal 100 (S711). Then, the question providing unit 210 determines whether the question has ended (S713), and instructs the information providing unit 240 to provide data if the question has ended (S713).

Then, the information providing unit 240 extracts information (ie, data group) corresponding to the last question and the selection response information to the storage unit 220, and stores this information (ie, data group) in the user terminal 100. Provided as (S715).

On the other hand, if it is determined that the question is not ended in step S713, the question providing unit 210 checks a child node of the next level corresponding to the selection response information, and sends a question corresponding to the child node to the user terminal 100. ) and proceeds again to step S709 provided.

As described above, the present invention improves convenience when searching for information by extracting and providing information to the user based on the user's response information to the plurality of multiple-choice questions. In addition, the present invention creates a question tree based on the attribute information of the question, sequentially provides related questions to the user based on the question tree, and provides information to the user based on the user's selection response to the question Because of this, it is possible to accurately search for the information requested by the user.

While this specification contains many features, such features should not be construed as limiting the scope of the invention or the claims. Also, features described in separate embodiments in this specification may be implemented in combination in a single embodiment. Conversely, various features that are described in this specification in a single embodiment may be implemented in various embodiments individually or in combination as appropriate.

Although actions are described in a particular order in the drawings, it should not be understood that such actions are performed in the specific order as shown, or that the actions are performed in a series of sequential order, or that all described actions are performed to achieve a desired result. . Multitasking and parallel processing can be advantageous in certain circumstances. In addition, it should be understood that the division of various system components in the above-described embodiments does not require such division in all embodiments. The program components and systems described above may generally be implemented as a package in a single software product or multiple software products.

The method of the present invention as described above may be implemented as a program and stored in a recording medium (CD-ROM, RAM, ROM, floppy disk, hard disk, magneto-optical disk, etc.) in a computer-readable form. Since this process can be easily performed by a person skilled in the art to which the present invention belongs, it will not be described in detail.

The present invention described above is capable of various substitutions, modifications, and changes without departing from the technical spirit of the present invention to those skilled in the art to which the present invention belongs, and thus the above-described embodiments and It is not limited by drawings.

100: user terminal 200: information providing device
210: question providing unit 220: storage unit
230: tree generation unit 240: information provision unit
300: network

Claims (14)

a tree generator for generating a question tree based on attribute information defined for each question;
When an interactive information providing service is requested from a user terminal, hierarchical questions formed in the question tree are sequentially provided to the user terminal, but a sub-question of the next level is selected based on response information to the question and sent to the user terminal. a question providing unit to transmit; and
When response information to the final question is received from the user terminal, an information providing unit extracting information corresponding to the response information of the final question and providing the extracted information to the user terminal;
The tree generator,
A plurality of questions are divided into a plurality of clusters, a first question included in a first cluster among the plurality of clusters is generated as a node, and a second question included in a second cluster among the plurality of clusters is generated as a node of the node. 1 An information providing device created as a child node. According to claim 1,
The tree generator,
Questions are initially separated into a certain number of clusters, a root target cluster is selected from among the separated clusters, representative questions included in the selected root target cluster are created as root nodes, and representative questions of non-selected root target clusters are generated. is created as a sub-node of the root node, and the process of re-separating each separated cluster into a certain number of sub-clusters is repeated, but the representative questions of the separated sub-clusters are created as sub-nodes. Device. According to claim 1,
The tree generator,
An information providing device generating a third question included in a first cluster among the plurality of clusters as a second child node of the node. According to claim 3,
The tree generator,
The first sub-cluster is divided into a plurality of sub-clusters, a first sub-cluster having the highest frequency of association flags is identified among the plurality of sub-clusters, and the third question included in the first sub-cluster is assigned to the second sub-cluster. An information providing device created as a child node. According to claim 4,
The tree generator,
Identifying a second sub-cluster having the lowest frequency of association flags among the plurality of sub-clusters, and generating a fourth question included in the second sub-cluster as a child node of the second child node. According to claim 1,
The tree generator,
An information providing device characterized by calculating a final similarity multiplied by an internal similarity and an external similarity for the separated clusters using the following equation, and repeatedly performing cluster separation until the final similarity converges.
(mathematical expression)

Here, Fit _intra means internal similarity, k is the number of clusters, C _k is the center value of the k-th cluster, and X _i is the attribute information of the i-th question belonging to the same cluster.

Here, Fit _inter means external similarity, k is the number of clusters, C _k is the center value of the k-th cluster, X _i is the attribute information of the ith question belonging to each other cluster, and d is the maximum value of k. According to claim 2,
The representative question is a question having attribution information corresponding to a closest distance from a central value of a cluster including the representative question. According to claim 3,
The question provider,
The information providing device characterized in that for checking a child node formed at a position corresponding to the response information, and transmitting a question corresponding to the child node to the user terminal. According to claim 3,
The tree generator,
An information providing device characterized in that the cluster is separated in proportion to the number of selection information of the question. According to claim 1,
The plurality of clusters,
An information providing device that is initially separated clusters or sub-clusters obtained by separating one of the initially separated clusters. A method for performing an interactive information providing service in an information providing device,
generating a question tree based on attribute information defined for each question;
Receiving a request for an interactive information providing service from a user terminal;
sequentially providing hierarchical questions formed in the question tree to the user terminal, selecting a sub-question of a next level based on response information to the question, and transmitting the selected sub-question to the user terminal; and
When response information to the final question is received from the user terminal, extracting information corresponding to the response information of the final question and providing the extracted information to the user terminal;
The step of generating the question tree is,
A plurality of questions are divided into a plurality of clusters, a first question included in a first cluster among the plurality of clusters is generated as a node, and a second question included in a second cluster among the plurality of clusters is generated as a node of the node. 1 Interactive information provision service method created as a child node. According to claim 11,
The step of generating the question tree is,
initially dividing questions into a certain number of clusters, and selecting a root target cluster from among the divided clusters;
generating a representative question included in the selected root target cluster as a root node, and generating a representative question of a non-selected root target cluster as a lower node of the root node; and
and repeating the process of re-separating each of the separated sub-clusters into the predetermined number of sub-clusters, and generating representative questions of the separated sub-clusters as lower nodes. According to claim 11,
Calculating the final similarity obtained by multiplying the internal similarity and the external similarity for the separated cluster using the equation below, and repeatedly performing cluster separation until the final similarity converges; Interactive informational service method.
(mathematical expression)

Here, Fit _intra means internal similarity, k is the number of clusters, C _k is the center value of the k-th cluster, and X _i is the attribute information of the i-th question belonging to the same cluster.

Here, Fit _inter means external similarity, k is the number of clusters, C _k is the center value of the k-th cluster, X _i is the attribute information of the i-th question belonging to the same and different clusters, and d is the maximum k represents a value. According to claim 11,
The step of transmitting to the user terminal,
and identifying a child node formed at a location corresponding to the response information, and transmitting a question corresponding to the child node to the user terminal.

Images