KR102422325B1 - Method and apparatus for managing knowledge graph - Google Patents

Abstract

Provided are a method and device for managing a knowledge graph. The method for managing the knowledge graph according to one embodiment of the present invention comprises: a step of identifying an associative relation strength between a first entity and a second entity in a knowledge graph generated using one or more datasets; a step of displaying the knowledge graph, and visualizing and displaying a connection line representing the associative relation between the first entity and the second entity as a first graphic representation indicating the identified associative relation strength; and a step of displaying the first raw data corresponding to the first entity and the second raw data corresponding to the second entity in response to a selection of the visualized connection line.

Description

Knowledge graph management method and apparatus {METHOD AND APPARATUS FOR MANAGING KNOWLEDGE GRAPH}

The present invention relates to a knowledge graphic management method. More particularly, it relates to a knowledge graph management method and apparatus for displaying a knowledge graph including various graphic representations so that a user can intuitively check the strength of a relationship between entities.

A knowledge graph is a graphical representation of structured knowledge about a subject. The knowledge graph has been developed and applied in various fields such as interactive search and voice command execution.

In the past, knowledge graphs were created through a series of manual tasks such as extracting entities from original data and establishing relationships between entities. Such a graph generation operation was previously performed manually, but in recent years, it is also automatically created using an algorithm of a computing device.

However, in the knowledge graph automatically generated through the algorithm of the computing device, the association relationship of each entity may be inaccurate. In this case, a manager (ie, an expert) who can correct the relationship of the knowledge graph identifies the relationship of each entity and corrects the wrong relationship. In this case, when the administrator determines the accuracy of the association relationship between the entities, the manager searches and verifies the raw data one by one in the database, and determines whether the association relationship between the entities using the raw data is correct.

However, the work method through data retrieval not only slows the work speed, but also requires a lot of labor. In addition, if an administrator erroneously retrieves data referenced to establish an association relationship in a database, an inaccurate determination may be made on the object association relationship. In addition, through the existing knowledge graph, the manager could not intuitively check the degree of relationship between entities.

Korean Patent Publication No. 10-2011-0064833 (published on June 15, 2011)

SUMMARY The technical problem to be solved by the present invention is to provide a knowledge graph management method and apparatus that supports intuitively checking the degree and type of relation between entities in the knowledge graph.

Another technical problem to be solved by the present invention is to provide a knowledge graph management method and apparatus capable of easily modifying the knowledge graph.

Another technical problem to be solved by the present invention is to provide a knowledge graph management method and apparatus for easily providing detailed information of raw data referenced when a relationship of the knowledge graph is established.

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

In order to solve the above technical problem, a knowledge graph management method according to an embodiment of the present invention includes the steps of identifying the strength of a relationship between a first entity and a second entity in a knowledge graph generated using one or more datasets; , displaying the knowledge graph, and visualizing and displaying a connection line indicating the association relationship between the first object and the second object as a first graphic representation indicating the identified association relationship strength, and the visualized connection In response to the line being selected, the method may include displaying first raw data corresponding to the first object and second raw data corresponding to the second object.

In an embodiment, the displaying of the first raw data corresponding to the first entity and the second raw data corresponding to the second entity may include displaying a numerical value for the strength of the association relationship. .

In an embodiment, the step of visualizing and displaying the first graphical representation includes: identifying a type of a relationship between the first entity and the second entity; based on the identified type, a type of the connection line may include the step of determining

In an embodiment, the determining of the type of the connection line may include determining the connection line as a first line when the type of the relation between the first entity and the second entity is a spatial relation; determining the connection line as a second line when the type of association between the first entity and the second entity is a temporal correlation, and when the type of association between the first entity and the second entity is an observational association , determining the connection line as a third line.

In an embodiment, the step of visualizing and displaying the first graphic representation includes: determining the thickness of the connecting line so that the thickness of the connecting line becomes thicker in proportion to the strength of the association relationship; 1 may include a step of visualizing and displaying the graphic representation.

In an embodiment, the method for managing the knowledge graph includes: receiving correction information on a relationship between the first entity and the second entity; based on the correction information, the first entity and the second entity The method may further include correcting a relationship between the two groups, and displaying a knowledge graph in which the modified relationship is reflected.

In an embodiment, the first entity may indicate a first column of the dataset, and the second entity may indicate a second column of the dataset.

In an embodiment, the identifying the strength of the association relationship between the first entity and the second entity includes: at least one of the first raw data included in the first column and at least one of the second data included in the second column The method may include calculating a relationship strength between the first entity and the second entity by using the similarity between the raw data.

In an embodiment, each of the first raw data and the second raw data may include a plurality of location data. In this case, the step of identifying the strength of the association relationship between the first entity and the second entity includes: Measuring a distance between the position median value of the first raw data and the position median value of the second raw data; Numericalizing the strength of the association relationship between the first entity and the second entity based on the measured distance may include.

In an embodiment, each of the first raw data and the second raw data may include a plurality of temporal data. In this case, the step of identifying the association relationship strength between the first entity and the second entity includes: calculating a time difference between the median or average value of the first raw data and the median or average value of the second raw data; and quantifying the strength of the association relationship between the first entity and the second entity based on the calculated time difference.

In an embodiment, each of the first raw data and the second raw data may include a plurality of observation data. In this case, the step of identifying the strength of the association between the first entity and the second entity includes: 1 Calculating a difference between the median or average value of the raw data and the median or average value of the second raw data, and quantifying the strength of the association relationship between the first entity and the second entity based on the calculated difference may include steps.

Computing device according to another embodiment of the present invention for solving the above technical problem, comprising one or more processors, a memory for loading a program executed by the processor, and a storage in which the program is stored, The program includes an operation of identifying the strength of a relationship between a first entity and a second entity in a knowledge graph generated using one or more datasets, and displaying the knowledge graph, wherein the association between the first entity and the second entity is performed. visualizing and displaying a connecting line representing the relationship as a first graphical representation indicating the identified association relationship strength, and in response to the visualized connecting line being selected, first raw data corresponding to a first object; It may include instructions for performing an operation of displaying the second raw data corresponding to the second object.

In accordance with another embodiment of the present invention for solving the above technical problem, a computer-readable non-transitory storage medium including instructions, when the instructions are executed by a processor, causes the processor to use one or more data sets. identifying the strength of the association relationship between the first entity and the second entity in the knowledge graph generated by Visualizing and displaying the first graphical representation indicating the strength of the association relationship, and in response to the visualized connecting line being selected, first raw data corresponding to the first object and second raw data corresponding to the second object Operations including displaying data may be performed.

1 is a flowchart illustrating a knowledge graph management method according to an embodiment of the present invention.
2 is a diagram illustrating a knowledge graph.
FIG. 3 is a view for explaining in detail step S400 of FIG. 2 .
4-6 are diagrams illustrating knowledge graphics including various graphical representations.
7 is a diagram for explaining in detail step S430 of FIG. 3 .
8 to 10 are diagrams illustrating graphic representations displayed according to types of association relationships between objects.
11 is a diagram for explaining in detail step S600 of FIG. 2 .
12 is a diagram illustrating a knowledge graph modified according to an input.
13 is an exemplary hardware configuration diagram that may implement a computing device in various embodiments.

Hereinafter, preferred embodiments of the present invention will be described in detail with reference to the accompanying drawings. Advantages and features of the present invention and methods of achieving them will become apparent with reference to the embodiments described below in detail in conjunction with the accompanying drawings. However, the technical idea of the present invention is not limited to the following embodiments, but may be implemented in various different forms, and only the following embodiments complete the technical idea of the present invention, and in the technical field to which the present invention belongs It is provided to fully inform those of ordinary skill in the art of the scope of the present invention, and the technical spirit of the present invention is only defined by the scope of the claims.

In adding reference numerals to the components of each drawing, it should be noted that the same components are given the same reference numerals as much as possible even though they are indicated on different drawings. In addition, in describing the present invention, if it is determined that a detailed description of a related known configuration or function may obscure the gist of the present invention, the detailed description thereof will be omitted.

Unless otherwise defined, all terms (including technical and scientific terms) used herein may be used with the meaning commonly understood by those of ordinary skill in the art to which the present invention belongs. In addition, terms defined in a commonly used dictionary are not to be interpreted ideally or excessively unless clearly defined in particular. The terminology used herein is for the purpose of describing the embodiments and is not intended to limit the present invention. In this specification, the singular also includes the plural, unless specifically stated otherwise in the phrase.

In addition, in describing the components of the present invention, terms such as first, second, A, B, (a), (b), etc. may be used. These terms are only for distinguishing the elements from other elements, and the essence, order, or order of the elements are not limited by the terms. When it is described that a component is “connected”, “coupled” or “connected” to another component, the component may be directly connected or connected to the other component, but another component is between each component. It should be understood that elements may be “connected,” “coupled,” or “connected.”

As used herein, "comprises" and/or "comprising" refers to the presence of one or more other components, steps, operations and/or elements mentioned. or addition is not excluded.

Hereinafter, some embodiments of the present invention will be described with reference to the drawings.

1 is a flowchart illustrating a knowledge graph management method according to an embodiment of the present invention.

Each step of the method illustrated in FIG. 1 may be performed by a computing device. In other words, each step of the method may be implemented with one or more instructions executed by a processor of a computing device. The first steps included in the method may be performed by the first computing device, and the second steps of the method may be performed by the second computing device. Hereinafter, the description is continued assuming that each step of the method is performed by a computing device, but the subject performing each step is merely an example, and the present invention is not limited by the following description, for convenience of description For this purpose, the description of the operating subject of some steps included in the method may be omitted.

Referring to FIG. 1 , the computing device may collect one or more data sets by interworking with one or more of a database and an external server ( S100 ). The dataset may be a dataset in which rows and columns are configured, such as a CSV (Comma Separated Values) file, an Excel file, or the like. In an embodiment, when the format of the collected dataset does not match the format of the rows and columns, the computing device may change the format, form, data arrangement state, etc. of the collected dataset to conform to the format. In some embodiments, when data included in the collected data set does not conform to a preset data format, the computing device may change the corresponding data to conform to the data format. For example, when data included in a specific column of a dataset is coordinates for latitude and longitude, and the standard format of location data is an administrative address, the latitude and longitude coordinates may be changed to an administrative address format including street names. For another example, if the data included in a specific column of the dataset is date and time data recorded in the order of month, day, and year, and the standard format of the date and time data is in the format of year, month, day, date, month, day, year, date, and date of year, month, day data can be changed.

Next, the computing device may select an artificial intelligence model corresponding to a domain of the one or more datasets from among the already built customized artificial intelligence models ( S200 ). In an embodiment, a plurality of artificial intelligence models having different domains may be built in advance, and an artificial intelligence model corresponding to the domain of the dataset may be selected from among them. Here, the domain is a related field or topic in which the artificial intelligence model is used, and may be, for example, a disaster type such as flooding, fine dust, earthquake, and the like. For example, when the domain of the dataset is an earthquake, an artificial intelligence model having an earthquake domain may be selected, and when the domain of the dataset is flooding, an AI model having a submersion domain may be selected. Each AI model can be trained and built in advance.

Next, the computing device may generate a knowledge graph in which entities are connected to form a relationship using the selected artificial intelligence model ( S300 ). FIG. 2 is a diagram illustrating a knowledge graph. The knowledge graph illustrated in FIG. 2 includes entities from entity A to entity E, and the relationship between the entities is expressed as a connecting line. The entity may be represented as a node in the knowledge graph. Here, the computing device may select a column name included in each data set as an entity, and connect entities having a relation with each other as a connection line. The entities connected by the connecting line may be entities selected from the same dataset or entities selected from different datasets.

The computing device may use an artificial intelligence model or may calculate and quantify the strength of the association of related entities through an algorithm.

In an embodiment, the computing device may use an artificial intelligence model to cluster one or more of a dataset name, a column name, and column data, and determine a relationship between entities using the clustered result. In an embodiment, when the first column name and the second column name are names (eg, address, place, etc.) related to space, the first entity indicating the first column name and the second entity indicating the second column name are related to each other may have a relationship, and a spatial median value (ie, a position median value) of a plurality of first column data corresponding to the first column name and a spatial median value of a plurality of second column data corresponding to a second column name ( That is, the distance between the positions may be measured, and the strength of the association between the first entity and the second entity may be quantified based on the measured distance. Here, the spatial median value may be an median value of a plurality of column data (ie, a plurality of spatial data). The computing device may quantify the strength of the association relationship between the first entity and the second entity to have a higher numerical value as the measured distance is shorter.

In an embodiment, when the third column name and the fourth column name are names related to time (eg, date and time, date, etc.), the third entity indicating the third column name and the fourth entity indicating the fourth column name are related to each other may have a relationship, and a time median value (or average value) of a plurality of third column data corresponding to the third column name and a temporal median value (or average value) of a plurality of fourth column data corresponding to the fourth column name A time difference may be calculated between the two, and the strength of a relationship between the third entity and the fourth entity may be quantified based on the calculated time difference. The computing device may quantify the strength of the association between the third entity and the fourth entity to have a higher numerical value as the time difference is shorter.

In another embodiment, when the fifth column name and the sixth column name are names related to the same type of observation value (eg, precipitation amount, inundation amount, etc.), the fifth entity indicating the fifth column name and the sixth column name are indicated. The sixth entity may have a relationship with each other, and an observation median (or average value) of a plurality of fifth column data corresponding to the fifth column name and observation of a plurality of sixth column data corresponding to the sixth column name A difference between the median values (or average values) may be calculated, and the strength of the association between the fifth individual and the sixth individual may be quantified based on the difference between the calculated observation values. The computing device may quantify the strength of the association relationship between the fifth entity and the sixth entity to have a higher numerical value as the difference between the calculated observation values is smaller.

In addition, the computing device may quantify the relationship of each entity through various methods.

Next, the computing device may express the relation between the entities in various graphic representations, and then display the knowledge graphic in which the relation is expressed as a graphic representation ( S400 ). Step S400 will be described in more detail with reference to FIG. 3 .

The computing device may receive correction information from the manager while displaying the knowledge graph (S500). Here, the correction information may be correction information on a relationship between entities. The manager may select a connection line included in the knowledge graph and input correction information for the selected connection line. In this case, the computing device may receive the correction information from the administrator.

When correction information is input, the computing device may change and display the knowledge graph based on the correction information (S600). Step S600 will be described in more detail with reference to FIG. 11 .

Subsequently, the computing device may monitor whether additional correction information for the knowledge graph is input, and when it is input, change and display the knowledge graph again based on the additional correction information.

Hereinafter, step S400 of FIG. 1 will be described in detail with reference to FIGS. 3 to 10 .

The computing device may identify the entities in the association relationship and identify the strength of the association relationship between the entities ( S410 ). In an embodiment, the strength of the association of the entities may be quantified, and the computing device may identify the strength of the quantified association.

Then, the computing device may visualize the strength of the relationship between the objects by first graphic representation ( S420 ). In an embodiment, the thickness of the connection line may be determined so that the thickness of the connection line is increased in proportion to the strength of the association relationship, and the determined thickness of the line may be visualized as a first graphic representation. In another embodiment, the computing device may highlight and visualize a connection line having a certain association strength.

4 is a diagram illustrating a knowledge graph visualized as a first graphic representation, and as illustrated in FIG. 4 , the strength of an association is visualized as a thickness of a connecting line. According to FIG. 4 , the strength of the association between entity A and entity B is “strong”, the strength of the association between entity B and entity D is “strong”, and the strength of the association between entity B and entity C is “medium”. “It is exemplified by Also, according to FIG. 4 , it is exemplified that the strength of the association between the entity A and the entity C is “weak” and the strength of the association between the entity A and the entity E is “weak”.

Subsequently, the computing device may group each object ( S430 ). In an embodiment, the computing device may group objects selected from the same dataset as objects of the same group. Each entity may be a column name of a dataset, as described above.

Next, the computing device may visualize objects belonging to the same group as a second graphic representation having the same shape or the same color ( S440 ).

5A is a diagram illustrating visualization of objects belonging to the same group with the same color. In FIG. 5A, a specific color is indicated by a hatched line. Referring to FIG. 5A , objects A, B, and C belong to a first group and may be visualized with a first color, and objects D and E may belong to a second group and may be visualized with a second color.

5B is a diagram illustrating visualization of an object belonging to the same group as a shape. Referring to FIG. 5B , objects A, B, and C belong to a first group and may be visualized in a circle shape, and objects D and E may belong to a second group and may be visualized in a circle shape.

Subsequently, the computing device may identify a causal relationship of each entity ( S450 ). In an embodiment, a causal relationship of each entity may be determined through the artificial intelligence model selected in step S200. That is, the computing device may use the artificial intelligence model to identify causal entities. For example, a rainfall entity and a submerged entity having a rainfall measurement value greater than or equal to a predetermined value may have a causal relationship.

Next, the computing device may visualize the objects in the causal relationship as a third graphic representation ( S460 ).

6 is a diagram illustrating visualization of a causal entity as a third graphic representation. According to FIG. 6 , a connection line between entity A and entity C in a causal relation may be visualized as a double line. Here, the double line may correspond to the third graph representation. In some embodiments, as the third representation, other types of lines may be used, or various graphic representation methods may be used.

Next, the connection line may be visualized as a separate graphic representation based on the preset association type ( S470 ).

Hereinafter, step S470 will be described in detail with reference to FIGS. 7 to 10 .

When objects have an association relationship, the computing device may identify a type of the association relationship ( S431 ). In an embodiment, the computing device may identify which type of association relation between entities corresponds to among a spatial relation, a temporal relation, an observation relation, and the like. Here, the spatial correlation relationship indicates a relationship in which spatial values (ie, location values) of objects are similar, the temporal correlation relationship indicates a relationship in which the temporal values of the objects are similar, and the observation relationship relationship indicates a relationship in which the observed values of the objects are similar. can indicate a related relationship.

Subsequently, the computing device may change the connection line of the objects having the spatial association relationship to the first line and visualize the object to display that the objects have the spatial association relationship ( S432 ).

Subsequently, the computing device may change the connection line of the objects having the temporal relationship to a second line and visualize it to display that the objects have the temporal relationship ( S433 ).

Next, the computing device may change the connection line of the objects having the observation relationship to a third line and visualize it to display that the objects have the observation relationship ( S434 ).

8 is a diagram illustrating a knowledge graph visualized according to the type of association relationship, and according to FIG. 8, object A and object E are visualized with a first line (ie, dotted line) indicating spatial association relationship do. In addition, according to FIG. 8 , the objects A and B exemplify the visualization with a second line (ie, a dotted square line) representing the temporal relationship, and the objects B and C are visualized with a third line (ie, the observation relationship) , broken line) is an example of visualization.

Referring back to FIG. 3 , the computing device may receive a selection of a specific connection line indicating a relationship from the manager ( S480 ).

Subsequently, the computing device may display detailed information about the connection line of the selected association relationship ( S490 ). In an embodiment, the computing device may display raw data of entities used to establish the selected association relationship by including it in the detailed information. The raw data may include a name of a dataset, a column name, and column data. In addition, the computing device may display a numerical value of the strength of the association in the detailed information. Accordingly, the administrator can check the raw data that is the basis for establishing the association relationship, and can verify whether the object relationship and the entity relationship are properly set based on the raw data.

9 illustrates detailed information displayed when the connecting line 11 between the object A and the object B is selected. As illustrated in FIG. 9 , when the connecting line 11 is selected, a numerical value (70%) for the strength of the association relationship between the entity A and the entity B, the raw data of the entity A (ie, the raw data of the first entity) and detailed information including raw data of the entity B (ie, raw data of the second entity) may be displayed. Here, the numerical value may indicate the degree of similarity of each individual, and a higher number may mean stronger strength.

10 illustrates detailed information displayed when the connecting line 12 of the object B and the object D is selected. As illustrated in FIG. 10 , when the connecting line 12 is selected, the numerical value (72%) of the association relationship strength between the entity B and the entity D, the raw data of the entity B (ie, the raw data of the second entity) and detailed information including raw data of the entity D (ie, raw data of the fourth entity) may be displayed.

According to the present embodiment, the administrator can intuitively check the relation of entities in the knowledge graph through various graphic representations. In addition, by selecting a connection line, the administrator can check the raw data of each entity used to establish the association and the numerical value of the strength of the association.

Hereinafter, step S600 of FIG. 1 will be described in detail with reference to FIGS. 11 and 12 .

In response to receiving the correction information on the association from the manager, the computing device may change the association strength based on the input correction information ( S610 ). The manager may modify data on the relationship while checking the detailed information as shown in FIGS. 9 and 10 . In this case, the administrator may modify the numerical value of the strength of the association relationship. The administrator can input the numerical value as '0%' if there is no correlation at all. In addition, the administrator may modify other data through detailed information.

Then, the computing device may change the numerical value of the association strength for the selected entities based on the modified numerical value of the association strength, and also change the corresponding connection line in the knowledge graph according to the changed numerical value (S620). ). In an embodiment, the computing device may change the thickness of the connection line according to a change in the numerical value. In addition, when the numerical value is modified to '0%' (ie, when input from an administrator as having no correlation), the computing device may remove the connecting line connecting the corresponding objects.

12 is a diagram illustrating a state in which the knowledge graph is modified as the numerical value of the correlation strength is changed. According to FIG. 12 , in response to a change in the strength of the association relationship between the entity B and the entity D to 10%, the knowledge graph may be changed such that the thickness of the connection line 13 between the entity B and the entity D becomes thinner.

Next, the computing device may separately tag raw data of entities related to the modified association strength so that the modified association strength can be used as training data in the artificial intelligence model ( S630 ). For example, when the association relationship strength between the entity B and the entity D is corrected, the numerical value of the modified association relationship strength, the raw data of the entity B, and the raw data of the entity D may be separately tagged as additional training data. The additional training data tagged in this way is input to the AI model and trained, so that the accuracy of the AI model can be improved.

As described above, according to an embodiment of the present invention, it is possible to provide a knowledge graph in which the relation between entities can be intuitively understood. In addition, according to the present embodiment, the raw data used to establish the relationship can be obtained through the administrator selecting the connection line, so that the correction of the knowledge graph can be performed more quickly and easily. In addition, according to the present embodiment, by providing the manager with raw data used to set the correlation through simple input, it is possible to minimize errors in the knowledge graph correction operation.

13 is an exemplary hardware configuration diagram that may implement a computing device in various embodiments.

The computing device 1000 according to the present embodiment includes one or more processors 1100 , a system bus 1600 , a communication interface 1200 , and a memory for loading a computer program 1500 executed by the processor 1100 . 1400 and a storage 1300 for storing the computer program 1500 may be included. In Fig. 13, only the components related to the embodiment are shown. Accordingly, those skilled in the art to which the embodiments of the present specification pertain can know that other general-purpose components other than the components shown in FIG. 13 may be further included.

The processor 1100 controls the overall operation of each component of the computing device 1000 . The processor 1100 includes at least one of a central processing unit (CPU), a micro processor unit (MPU), a micro controller unit (MCU), a graphic processing unit (GPU), or any type of processor well known in the art. may be included. In addition, the processor 1100 may perform an operation on at least one application or program for executing the method/operation according to various embodiments. The computing device 1000 may include two or more processors.

The memory 1400 stores various data, commands, and/or information. The memory 1400 may load one or more programs 1500 from the storage 1300 to execute methods/operations according to various embodiments of the present specification. An example of the memory 1400 may be a RAM, but is not limited thereto.

The communication interface 1200 may communicate with an external communication device such as a mobile communication terminal, a personal computer, or a server using a network such as a mobile communication network or a wired Internet network. The communication interface 1200 may receive input information from a communication device.

The system bus 1600 provides a communication function between components of the computing device 1000 . The system bus 1600 may be implemented as various types of buses such as an address bus, a data bus, and a control bus.

The storage 1300 may non-temporarily store one or more computer programs 1500 . The storage 1300 may include a non-volatile memory such as a flash memory, a hard disk, a removable disk, or any type of computer-readable recording medium well known in the art to which embodiments of the present specification pertain. . In addition,

The computer program 1500 may include one or more instructions in which methods/operations according to various embodiments of the present specification are implemented. When the computer program 1500 is loaded into the memory 1400 , the processor 1100 may execute the one or more instructions to perform methods/operations according to various embodiments of the present specification.

In an embodiment, the computer program 1500 performs an operation of identifying the strength of an association relationship between a first entity and a second entity in a knowledge graph generated using one or more datasets, and displaying the knowledge graph, wherein the first entity visualizing and displaying a connecting line representing an association relationship between an entity and the second object as a first graphical representation indicating the identified association strength; in response to the visualized connecting line being selected, the first object may include instructions for performing an operation of displaying the first raw data corresponding to and second raw data corresponding to the second object.

So far, various embodiments of the present invention and effects according to the embodiments have been described with reference to FIGS. 1 to 13 . Effects according to the technical spirit of the present invention are not limited to the above-mentioned effects, and other effects not mentioned will be clearly understood by those skilled in the art from the following description.

The technical ideas of the present invention described with reference to FIGS. 1 to 13 may be implemented as computer-readable codes on a computer-readable medium. The computer-readable recording medium may be, for example, a removable recording medium (CD, DVD, Blu-ray disk, USB storage device, removable hard disk) or a fixed recording medium (ROM, RAM, computer-equipped hard disk). can The computer program recorded in the computer-readable recording medium may be transmitted to another computing device through a network such as the Internet and installed in the other computing device, thereby being used in the other computing device.

In the above, even though all the components constituting the embodiment of the present invention are described as being combined or operating in combination, the technical spirit of the present invention is not necessarily limited to this embodiment. That is, within the scope of the object of the present invention, all of the components may operate by selectively combining one or more.

Although acts are shown in a particular order in the drawings, it should not be understood that the acts must be performed in the specific order or sequential order shown, or that all depicted acts must be performed to obtain a desired result. In certain circumstances, multitasking and parallel processing may be advantageous. Moreover, the separation of the various components in the embodiments described above should not be construed as necessarily requiring such separation, and the program components and systems described may generally be integrated together into a single software product or packaged into multiple software products. It should be understood that there is

Although embodiments of the present invention have been described above with reference to the accompanying drawings, those of ordinary skill in the art to which the present invention pertains can practice the present invention in other specific forms without changing the technical spirit or essential features. can understand that there is Therefore, it should be understood that the embodiments described above are illustrative in all respects and not restrictive. The protection scope of the present invention should be interpreted by the claims below, and all technical ideas within the equivalent range should be interpreted as being included in the scope of the technical ideas defined by the present invention.

Claims (17)

A knowledge graph management method performed by a computer device, comprising:
identifying a strength of a relationship between a first entity and a second entity in a knowledge graph generated using one or more datasets;
displaying the knowledge graph, visualizing and displaying a connection line indicating a relationship between the first object and the second object as a first graphic representation indicating the identified relationship strength;
receiving correction information on a type of a relationship between the first entity and the second entity;
modifying an association relationship between the first entity and the second entity based on the correction information; and
generating learning data of the knowledge graph generation artificial intelligence model by tagging the revision information, first raw data corresponding to the first entity, and second raw data corresponding to the second entity;
Visualizing and displaying the first graphic representation comprises:
identifying a type of the association relationship between the first entity and the second entity; and
based on the identified type, determining the type of the connecting line;
The type of the association relationship between the entities is a spatial association relationship indicating that there is an association relationship between the positions of the first object and the second object, and that there is an association relationship between the time values of the first object and the second object. It is one of a temporal correlation indicating a temporal correlation and an observation correlation indicating that a correlation exists between the observation values of the first entity and the second entity,
The step of determining the type of the connection line,
determining the connection line as a first line when the type of the relation between the first entity and the second entity is the spatial relation;
determining the connection line as a second line when the type of the relation between the first entity and the second entity is the temporal relation; and
determining the connection line as a third line when the type of the association between the first entity and the second entity is the observation correlation;
How to manage the knowledge graph. According to claim 1,
The displaying of the first raw data corresponding to the first object and the second raw data corresponding to the second object may include:
Displaying a numerical value for the strength of the association relationship,
How to manage the knowledge graph. delete delete delete delete delete delete According to claim 1,
The first entity points to a first column of the dataset, and the second entity points to a second column of the dataset,
How to manage the knowledge graph. 10. The method of claim 9,
The step of identifying the strength of the association between the first entity and the second entity comprises:
calculating the strength of a relationship between the first entity and the second entity by using the similarity between the one or more first raw data included in the first column and the one or more second raw data included in the second column comprising steps,
How to manage the knowledge graph. 11. The method of claim 10,
Each of the first raw data and the second raw data includes a plurality of location data,
The step of identifying the strength of the association between the first entity and the second entity comprises:
measuring a distance between a position median value of the first raw data and a median position value of the second raw data; and
Comprising the step of quantifying the strength of the association relationship between the first entity and the second entity based on the measured distance,
How to manage the knowledge graph. 11. The method of claim 10,
Each of the first raw data and the second raw data includes a plurality of time data,
The step of identifying the strength of the association between the first entity and the second entity comprises:
calculating a time difference between the median or average value of the first raw data and the median or average value of the second raw data; and
Comprising the step of quantifying the strength of the association relationship between the first entity and the second entity based on the calculated time difference,
How to manage the knowledge graph. 11. The method of claim 10,
Each of the first raw data and the second raw data includes a plurality of observation data,
The step of identifying the strength of the association between the first entity and the second entity comprises:
calculating a difference between the median or average value of the first raw data and the median or average value of the second raw data; and
Comprising the step of quantifying the strength of the association relationship between the first entity and the second entity based on the calculated difference,
How to manage the knowledge graph. According to claim 1,
The step of visualizing and displaying the
Visualizing and displaying a plurality of objects generated from the same data set as a second graphic representation having the same shape or the same color,
How to manage the knowledge graph. According to claim 1,
The step of visualizing and displaying the
identifying a third entity that has a causal relationship with the first entity in the knowledge graph; and
Visualizing and displaying a causal relationship between the first entity and the third entity in a third graphical representation;
How to manage the knowledge graph. delete delete

Images