KR102603767B1 - Method and system for generating knowledge graphs automatically - Google Patents

Abstract

The present disclosure provides a method for automatically generating a knowledge graph, which is performed by at least one processor. The method includes receiving an input data set, identifying a domain associated with the input data set, using a machine learning model associated with the domain, to generate a local knowledge graph based on the input data set, and the local knowledge graph. Based on this, it includes the step of building a global knowledge graph.

Description

Knowledge graph automatic generation method and system {METHOD AND SYSTEM FOR GENERATING KNOWLEDGE GRAPHS AUTOMATICALLY}

This disclosure relates to a method and system for automatically generating a knowledge graph, and specifically, to identify a domain associated with a received input data set, generate a local knowledge graph using a machine learning model associated with the domain, and create a global knowledge graph. It is about construction methods and systems.

As network and information processing technology develops, various data can be collected and used to provide various services to users. Here, in order to utilize this data, the data needs to be processed and refined by organizing, standardizing, and integrating the collected data. Servers that provide services utilize knowledge graphs for various categories to provide more appropriate services to users. Here, a knowledge graph is a method of structuring and expressing information and knowledge, and may mean expressing in the form of a graph how a concept is connected to other concepts.

On the other hand, because the concept of knowledge includes a semantic perspective, there are limitations in the program's mechanical processing when first constructing a knowledge graph. Accordingly, in the prior art, a person directly converted a knowledge document into a graph data structure and input it to create a knowledge graph. However, this prior art has the problem that it takes a lot of time and money to represent large amounts of data as a knowledge graph.

The present disclosure provides a method and system (device) for automatically generating a knowledge graph to solve the above problems.

The present disclosure may be implemented in various ways, including as a method, device (system), or computer program stored in a readable storage medium.

According to an embodiment of the present disclosure, a method for automatically generating a knowledge graph includes receiving an input data set, identifying a domain associated with the input data set, and using a machine learning model associated with the domain to base the knowledge graph on the input data set. This may include generating a local knowledge graph and building a global knowledge graph based on the local knowledge graph.

According to an embodiment of the present disclosure, the machine learning model identifies a plurality of entities associated with the input data and relationships between the plurality of entities based on meta data extracted from the input data. Can be pre-trained to generate

According to an embodiment of the present disclosure, a machine learning model may be learned using a knowledge base document in which a predetermined domain is annotated.

According to an embodiment of the present disclosure, generating a local knowledge graph includes generating a plurality of entities and relationships between a plurality of entities associated with an input data set using a machine learning model, and a plurality of entities and a plurality of entities. It may include generating a local knowledge graph associated with the domain based on the relationships between the domains.

According to an embodiment of the present disclosure, the step of constructing a global knowledge graph includes extracting relationships between entities within a predetermined range centered on instance nodes of the local knowledge graph and based on the relationships between the extracted entities. Thus, it may include the step of building a global knowledge graph by integrating the local knowledge graph.

According to an embodiment of the present disclosure, the method may further include generating an index corresponding to each of a plurality of entities included in the global knowledge graph.

According to an embodiment of the present disclosure, the step of generating an index includes embedding each of a plurality of entities included in the global knowledge graph into a vector and mapping the embedded vectors to the global knowledge graph. It may include steps.

According to an embodiment of the present disclosure, the step of embedding into a vector may be performed asynchronously by sequentially recording changes in the global knowledge graph in a log.

In order to execute the method according to an embodiment of the present disclosure on a computer, a computer program stored in a computer-readable recording medium may be provided.

A system according to an embodiment of the present disclosure includes a communication module, a memory, and at least one processor connected to the memory and configured to execute at least one computer-readable program included in the memory, wherein the at least one program is an input Receive a data set, identify the domain associated with the input data set, use machine learning models associated with the domain to generate a local knowledge graph based on the input data set, and based on the local knowledge graph, create a global knowledge graph. It may contain commands for building.

According to some embodiments of the present disclosure, a knowledge graph can be easily created by performing semantic processing on an input data set using a machine learning model. Accordingly, since people do not directly input data into the knowledge graph, the time and cost required to convert massive amounts of data into the knowledge graph can be significantly reduced.

According to some embodiments of the present disclosure, components and data that perform functions in an information processing system may be distributed. Accordingly, the speed of processing vast amounts of data to create a knowledge graph is greatly improved, and system expansion to process vast amounts of data can be very easy.

According to some embodiments of the present disclosure, a global knowledge graph may indicate which local knowledge graph a plurality of entities including entities and/or relationships are associated with. Accordingly, a domain corresponding to a plurality of entities including a specific entity and/or relationship can be easily searched.

According to some embodiments of the present disclosure, an index may be created by embedding entities and relationships between entities in a knowledge graph as vectors. Accordingly, by numerically expressing the data in the knowledge graph, the data you are looking for can be quickly searched and processed. Additionally, the performance of systems using knowledge graphs can be significantly improved.

The effects of the present disclosure are not limited to the effects mentioned above, and other effects not mentioned are clear to a person skilled in the art (referred to as “a person skilled in the art”) in the technical field to which the present disclosure pertains from the description of the claims. It will be understandable.

Embodiments of the present disclosure will be described with reference to the accompanying drawings described below, in which like reference numerals indicate like elements, but are not limited thereto.
Figure 1 shows an example in which a knowledge graph is automatically generated according to an embodiment of the present disclosure.
Figure 2 is a schematic diagram showing a configuration in which an information processing system is connected to communicate with a plurality of user terminals in order to generate a knowledge graph according to an embodiment of the present disclosure.
Figure 3 is a block diagram showing the internal configuration of a user terminal and an information processing system according to an embodiment of the present disclosure.
Figure 4 is a diagram illustrating an example of learning a machine learning model according to an embodiment of the present disclosure.
FIG. 5 is a diagram illustrating an example of the functional configuration of an information processing system for generating a knowledge graph according to an embodiment of the present disclosure.
FIG. 6 is a diagram illustrating an example of a knowledge graph generator generating a knowledge graph according to an embodiment of the present disclosure.
FIG. 7 is a diagram illustrating an example in which an index corresponding to an entity of a knowledge graph is created according to an embodiment of the present disclosure.
Figure 8 is a flowchart showing an example of a method according to an embodiment of the present disclosure.

Hereinafter, specific details for implementing the present disclosure will be described in detail with reference to the attached drawings. However, in the following description, detailed descriptions of well-known functions or configurations will be omitted if there is a risk of unnecessarily obscuring the gist of the present disclosure.

In the accompanying drawings, identical or corresponding components are given the same reference numerals. Additionally, in the description of the following embodiments, overlapping descriptions of identical or corresponding components may be omitted. However, even if descriptions of components are omitted, it is not intended that such components are not included in any embodiment.

Advantages and features of the disclosed embodiments and methods for achieving them will become clear by referring to the embodiments described below in conjunction with the accompanying drawings. However, the present disclosure is not limited to the embodiments disclosed below and may be implemented in various different forms. The present embodiments are merely provided to ensure that the present disclosure is complete and that the present disclosure does not convey the scope of the invention to those skilled in the art. It is provided only for complete information.

Terms used in this specification will be briefly described, and the disclosed embodiments will be described in detail. The terms used in this specification are general terms that are currently widely used as much as possible while considering the function in the present disclosure, but this may vary depending on the intention or precedent of a technician working in the related field, the emergence of new technology, etc. In addition, in certain cases, there are terms arbitrarily selected by the applicant, and in this case, the meaning will be described in detail in the description of the relevant invention. Accordingly, the terms used in this disclosure should be defined based on the meaning of the term and the overall content of the present disclosure, rather than simply the name of the term.

In this specification, singular expressions include plural expressions, unless the context clearly specifies the singular. Additionally, plural expressions include singular expressions, unless the context clearly specifies plural expressions. When it is said that a certain part includes a certain element throughout the specification, this does not mean excluding other elements, but may further include other elements, unless specifically stated to the contrary.

Additionally, the term 'module' or 'unit' used in the specification refers to a software or hardware component, and the 'module' or 'unit' performs certain roles. However, 'module' or 'unit' is not limited to software or hardware. A 'module' or 'unit' may be configured to reside on an addressable storage medium and may be configured to run on one or more processors. Thus, as an example, a 'module' or 'part' refers to components such as software components, object-oriented software components, class components and task components, processes, functions and properties. , procedures, subroutines, segments of program code, drivers, firmware, microcode, circuits, data, databases, data structures, tables, arrays, or variables. Components and 'modules' or 'parts' may be combined into smaller components and 'modules' or 'parts' or further components and 'modules' or 'parts'. Could be further separated.

According to an embodiment of the present disclosure, a 'module' or 'unit' may be implemented with a processor and memory. 'Processor' should be interpreted broadly to include general-purpose processors, central processing units (CPUs), microprocessors, digital signal processors (DSPs), controllers, microcontrollers, state machines, etc. In some contexts, 'processor' may refer to an application-specific integrated circuit (ASIC), programmable logic device (PLD), field programmable gate array (FPGA), etc. 'Processor' refers to a combination of processing devices, for example, a combination of a DSP and a microprocessor, a combination of a plurality of microprocessors, a combination of one or more microprocessors in combination with a DSP core, or any other such combination of configurations. You may. Additionally, 'memory' should be interpreted broadly to include any electronic component capable of storing electronic information. 'Memory' refers to random access memory (RAM), read-only memory (ROM), non-volatile random access memory (NVRAM), programmable read-only memory (PROM), erasable-programmable read-only memory (EPROM), May also refer to various types of processor-readable media, such as electrically erasable PROM (EEPROM), flash memory, magnetic or optical data storage, registers, etc. A memory is said to be in electronic communication with a processor if the processor can read information from and/or write information to the memory. The memory integrated into the processor is in electronic communication with the processor.

In the present disclosure, 'system' may include at least one of a server device and a cloud device, but is not limited thereto. For example, a system may consist of one or more server devices. As another example, a system may consist of one or more cloud devices. As another example, the system may be operated with a server device and a cloud device configured together.

In this disclosure, 'display' may refer to any display device associated with a computing device, e.g., any display device capable of displaying any information/data controlled by or provided by the computing device. can refer to.

In the present disclosure, 'each of a plurality of A' or 'each of a plurality of A' may refer to each of all components included in a plurality of A, or may refer to each of some components included in a plurality of A. .

In this disclosure, 'knowledge graph' may refer to any graph structure that represents or characterizes knowledge in the real world. The knowledge graph can structure and connect information by expressing entities and relationships between entities as nodes and edges, respectively. Additionally, in the present disclosure, for example, a local knowledge graph is a small-scale knowledge graph used for a specific topic or field, and can express information within a limited range. Additionally, a global knowledge graph is a large-scale knowledge graph used in a variety of topics and fields and can represent a wide range of information.

In the present disclosure, 'domain' may represent or characterize a specific scope or area, such as a specific topic, field, or surrounding environment, in a knowledge graph. For example, these domains can be used to limit and refine the scope of content covered within the knowledge graph.

In this disclosure, 'machine learning model' may include any model used to infer an answer to a given input. According to one embodiment, the machine learning model may include an artificial neural network model including an input layer (layer), a plurality of hidden layers, and an output layer. Here, each layer may include multiple nodes. In this disclosure, each of the plurality of machine learning models is described as a separate machine learning model, but the present invention is not limited thereto, and some or all of the plurality of machine learning models may be implemented as one machine learning model. Additionally, one machine learning model may include multiple machine learning models. In this disclosure, the terms machine learning model and artificial neural network model may be used interchangeably to refer to the same or similar model.

In this disclosure, 'Large Language Model (LLM)' may refer to a language model capable of inference without fine-tuning using methods such as few-shot learning, It can have more than 10 times as many parameters (for example, more than 100 billion parameters) compared to existing general language models. In this disclosure, 'language model' may include a very large language model.

Figure 1 shows an example in which the knowledge graph 150 is automatically generated according to an embodiment of the present disclosure. In one embodiment, an information processing system (not shown) may receive input data set 110. Here, the input data set 110 may include data extracted from text documents, web pages, databases, etc. Additionally, the information processing system may identify the domain associated with the input data set 110. For example, the information processing system may analyze the input data set 110 and determine that the input data set 110 is related to the field of autonomous driving. Alternatively, the information processing system may use a pre-trained machine learning model (e.g., language model, etc.) to identify the domain associated with the input data set 110.

In one embodiment, the information processing system may generate a knowledge graph 150 based on the input data set 110 using a machine learning model 120 associated with the identified domain. Specifically, the information processing system may generate a plurality of entities 130 and relationships 140 between the plurality of entities associated with the input data set 110 using a machine learning model 120 associated with the identified domain. Here, the machine learning model 120 may be a pre-trained model that receives the input data set 110 and outputs a plurality of entities 130 and relationships 140 between the plurality of entities. Alternatively, the machine learning model 120 may be a pre-trained model that receives a domain extracted or identified from the input data set 110 and outputs a plurality of entities 130 and relationships 140 between the plurality of entities. . In contrast, the machine learning model 120 receives the input data set 110 and the domain extracted or identified from the input data set 110, and outputs a plurality of entities 130 and relationships 140 between the plurality of entities. It may be a pre-trained model to do so.

Additionally, the information processing system may generate a local knowledge graph associated with the identified domain based on the generated plurality of entities 130 and relationships 140 between the plurality of entities. Additionally, the information processing system can extract relationships between entities within a predetermined range centered on instance nodes of the generated local knowledge graph. The information processing system can build a global knowledge graph by integrating multiple local knowledge graphs, including a local knowledge graph, based on relationships between extracted entities.

In one embodiment, the machine learning model 120 may be pre-trained using a knowledge base document annotated with a predetermined domain. Here, the machine learning model 120 may be a large language model (LLM), but is not limited thereto. An example of how such a domain-specific machine learning model is learned will be described in detail later with reference to FIG. 4.

In one embodiment, the information processing system may create an index database that integrates a knowledge graph layer consisting of a local knowledge graph and a global knowledge graph associated with the created domain. Specifically, the information processing system may generate an index corresponding to each of a plurality of entities included in the global knowledge graph. As the index corresponds to the domain and/or entity of the global knowledge graph, specific data can be easily searched using the index in the knowledge graph.

With this configuration, a knowledge graph can be easily created by performing semantic processing on the input data set using a machine learning model. Accordingly, since people do not directly input data into the knowledge graph, the time and cost required to convert massive amounts of data into the knowledge graph can be significantly reduced.

Figure 2 is a schematic diagram showing a configuration in which the information processing system 230 is connected to enable communication with a plurality of user terminals 210_1, 210_2, and 210_3 in order to generate a knowledge graph according to an embodiment of the present disclosure. As shown, a plurality of user terminals 210_1, 210_2, and 210_3 may be connected to the information processing system 230 that can provide a knowledge graph creation service through the network 220. Here, the plurality of user terminals 210_1, 210_2, and 210_3 may include terminals of users who are provided with a knowledge graph creation service.

In one embodiment, information processing system 230 is one or more server devices and/or databases capable of storing, providing, and executing computer-executable programs (e.g., downloadable applications) and data associated with providing knowledge graph creation services, etc. , or may include one or more distributed computing devices and/or distributed databases based on cloud computing services.

The knowledge graph creation service provided by the information processing system 230 is provided to users through a knowledge graph creation service application, web browser, web browser extension, etc. installed on each of the plurality of user terminals 210_1, 210_2, and 210_3. It can be. For example, the information processing system 230 may provide information corresponding to a knowledge graph creation request received from the user terminals 210_1, 210_2, and 210_3 through a knowledge graph creation service application or perform corresponding processing. .

A plurality of user terminals 210_1, 210_2, and 210_3 may communicate with the information processing system 230 through the network 220. The network 220 may be configured to enable communication between a plurality of user terminals 210_1, 210_2, and 210_3 and the information processing system 230. Depending on the installation environment, the network 220 may be, for example, a wired network such as Ethernet, a wired home network (Power Line Communication), a telephone line communication device, and RS-serial communication, a mobile communication network, a wireless LAN (WLAN), It may consist of wireless networks such as Wi-Fi, Bluetooth, and ZigBee, or a combination thereof. The communication method is not limited, and may include communication methods utilizing communication networks that the network 220 may include (e.g., mobile communication networks, wired Internet, wireless Internet, broadcasting networks, satellite networks, etc.) as well as user terminals (210_1, 210_2, 210_3). ) may also include short-range wireless communication between

In Figure 2, the mobile phone terminal (210_1), tablet terminal (210_2), and PC terminal (210_3) are shown as examples of user terminals, but they are not limited thereto, and the user terminals (210_1, 210_2, 210_3) use wired and/or wireless communication. This is possible and may be any computing device on which a knowledge graph creation service application or a web browser, etc. can be installed and executed. For example, user terminals include AI speakers, smartphones, mobile phones, navigation, computers, laptops, digital broadcasting terminals, PDAs (Personal Digital Assistants), PMPs (Portable Multimedia Players), tablet PCs, game consoles, It may include wearable devices, IoT (internet of things) devices, VR (virtual reality) devices, AR (augmented reality) devices, set-top boxes, etc. In addition, in Figure 2, three user terminals (210_1, 210_2, 210_3) are shown as communicating with the information processing system 230 through the network 220, but this is not limited to this, and a different number of user terminals are connected to the network ( It may be configured to communicate with the information processing system 230 through 220).

In Figure 2, a configuration in which the user's request is transmitted to the information processing system 230 through the user terminals 210_1, 210_2, and 210_3 is shown as an example, but the present invention is not limited thereto, and the user's request is transmitted to the information processing system 230 through the user terminals 210_1, 210_1, and 210_3. It may be provided to the information processing system 230 through an input device associated with the information processing system 230 without going through 210_2, 210_3), and the result of processing the user's request may be sent to an output device associated with the information processing system 230 ( For example, it may be provided to the user through a display, etc.).

Figure 3 is a block diagram showing the internal configuration of the user terminal 210 and the information processing system 230 according to an embodiment of the present disclosure. The user terminal 210 may refer to any computing device capable of executing applications, web browsers, etc. and capable of wired/wireless communication, for example, the mobile phone terminal 210_1, tablet terminal 210_2 of FIG. 2, It may include a PC terminal (210_3), etc. As shown, the user terminal 210 may include a memory 312, a processor 314, a communication module 316, and an input/output interface 318. Similarly, information processing system 230 may include memory 332, processor 334, communication module 336, and input/output interface 338. As shown in FIG. 3, the user terminal 210 and the information processing system 230 are configured to communicate information and/or data through the network 220 using respective communication modules 316 and 336. It can be. Additionally, the input/output device 320 may be configured to input information and/or data to the user terminal 210 through the input/output interface 318 or to output information and/or data generated from the user terminal 210.

Memories 312 and 332 may include any non-transitory computer-readable recording medium. According to one embodiment, the memories 312 and 332 are non-permanent mass storage devices such as read only memory (ROM), disk drive, solid state drive (SSD), flash memory, etc. It can be included. As another example, non-perishable mass storage devices such as ROM, SSD, flash memory, disk drive, etc. may be included in the user terminal 210 or the information processing system 230 as a separate persistent storage device that is distinct from memory. Additionally, an operating system and at least one program code may be stored in the memories 312 and 332.

These software components may be loaded from a computer-readable recording medium separate from the memories 312 and 332. This separate computer-readable recording medium may include a recording medium directly connectable to the user terminal 210 and the information processing system 230, for example, a floppy drive, disk, tape, DVD/CD- It may include computer-readable recording media such as ROM drives and memory cards. As another example, software components may be loaded into the memories 312 and 332 through the communication modules 316 and 336 rather than computer-readable recording media. For example, at least one program is loaded into memory 312, 332 based on a computer program installed by files provided over the network 220 by developers or a file distribution system that distributes installation files for applications. It can be.

The processors 314 and 334 may be configured to process instructions of a computer program by performing basic arithmetic, logic, and input/output operations. Instructions may be provided to the processors 314 and 334 by memories 312 and 332 or communication modules 316 and 336. For example, the processors 314 and 334 may be configured to execute instructions received according to program codes stored in a recording device such as the memory 312 and 332.

The communication modules 316 and 336 may provide a configuration or function for the user terminal 210 and the information processing system 230 to communicate with each other through the network 220, and may provide a configuration or function for the user terminal 210 and/or information processing. The system 230 may provide a configuration or function for communicating with other user terminals or other systems (for example, a separate cloud system, etc.). For example, a request or data (e.g., a knowledge graph creation request, etc.) generated by the processor 314 of the user terminal 210 according to a program code stored in a recording device such as the memory 312 is sent to the communication module 316. It may be transmitted to the information processing system 230 through the network 220 under the control of . Conversely, a control signal or command provided under the control of the processor 334 of the information processing system 230 is transmitted through the communication module 316 of the user terminal 210 through the communication module 336 and the network 220. It may be received by the user terminal 210.

The input/output interface 318 may be a means for interfacing with the input/output device 320. As an example, input devices may include devices such as cameras, keyboards, microphones, mice, etc., including audio sensors and/or image sensors, and output devices may include devices such as displays, speakers, haptic feedback devices, etc. You can. As another example, the input/output interface 318 may be a means for interfacing with a device that has components or functions for performing input and output, such as a touch screen, integrated into one. For example, the processor 314 of the user terminal 210 uses information and/or data provided by the information processing system 230 or another user terminal when processing instructions of a computer program loaded in the memory 312. A service screen, etc. configured as such may be displayed on the display through the input/output interface 318. In FIG. 3 , the input/output device 320 is shown not to be included in the user terminal 210, but the present invention is not limited to this and may be configured as a single device with the user terminal 210. Additionally, the input/output interface 338 of the information processing system 230 may be connected to the information processing system 230 or means for interfacing with a device (not shown) for input or output that the information processing system 230 may include. It can be. In FIG. 3, the input/output interfaces 318 and 338 are shown as elements configured separately from the processors 314 and 334, but the present invention is not limited thereto, and the input/output interfaces 318 and 338 may be configured to be included in the processors 314 and 334. there is.

The user terminal 210 and information processing system 230 may include more components than those in FIG. 3 . However, there is no need to clearly show most prior art components. In one embodiment, the user terminal 210 may be implemented to include at least some of the input/output devices 320 described above. Additionally, the user terminal 210 may further include other components such as a transceiver, a global positioning system (GPS) module, a camera, various sensors, and a database. For example, if the user terminal 210 is a smartphone, it may include components generally included in a smartphone, such as an acceleration sensor, a gyro sensor, a microphone module, a camera module, and various physical devices. Various components such as buttons, buttons using a touch panel, input/output ports, and vibrators for vibration may be implemented to be further included in the user terminal 210.

While a program or application for a knowledge graph creation service, etc. is operated, the processor 314 uses input devices such as a touch screen, a keyboard, a camera including an audio sensor and/or an image sensor, and a microphone connected to the input/output interface 318. Input or selected text, image, video, voice and/or motion can be received, and the received text, image, video, voice and/or motion can be stored in the memory 312 or stored in the communication module 316 and network. It can be provided to the information processing system 230 through (220).

The processor 314 of the user terminal 210 manages, processes, and/or stores information and/or data received from the input/output device 320, other user terminals, the information processing system 230, and/or a plurality of external systems. It can be configured to do so. Information and/or data processed by processor 314 may be provided to information processing system 230 via communication module 316 and network 220. The processor 314 of the user terminal 210 may transmit information and/or data to the input/output device 320 through the input/output interface 318 and output the information. For example, the processor 314 may output or display the received information and/or data on a screen associated with the user terminal 210.

The processor 334 of the information processing system 230 may be configured to manage, process, and/or store information and/or data received from a plurality of user terminals 210 and/or a plurality of external systems. Information and/or data processed by the processor 334 may be provided to the user terminal 210 through the communication module 336 and the network 220.

In Figures 2 and 3, an environment in which a user terminal and an information processing system communicate with each other in order to automatically generate a knowledge graph is described as an example, but it is not limited thereto, and input/output to the information processing system is performed without communication with the user terminal. An environment where interfaces and/or input/output devices are connected may be provided.

Figure 4 is a diagram illustrating an example of learning a machine learning model according to an embodiment of the present disclosure. In one embodiment, a machine learning model may be pre-trained to create a knowledge graph. Here, the machine learning model may be pre-trained to create a plurality of entities associated with the input data and relationships between the plurality of entities based on meta data extracted from the input data. there is. Here, the machine learning model may be a large language model (LLM), but is not limited to this.

In one embodiment, the domain specific machine learning model 430 may be created by fine tuning the pre-trained machine learning model 410. Specifically, data in the database 420 associated with the content management system may be used as learning data. Here, data in the database 420 may be annotated in advance with a domain corresponding to the data. Accordingly, the pre-trained machine learning model 410 is fine-tuned through data from a specific domain (e.g., autonomous driving field, medical field, etc.), thereby creating a domain-specific machine learning model 430 optimized for the specific domain. can be created. Additionally, this learning may be performed periodically according to a preset time. Accordingly, a machine learning model specialized for each of the plurality of predetermined domains may be created, and the plurality of predetermined domains may be added as the amount of data increases.

FIG. 5 is a diagram illustrating an example of the functional configuration of the information processing system 230 for generating a knowledge graph according to an embodiment of the present disclosure. In one embodiment, the information processing system 230 may include a domain-specific machine learning model 510 trained in the manner described above in FIG. 4 . Alternatively, the learned domain-specific machine learning model 510 may be included in a device accessible by wired and/or wirelessly by the information processing system 230. Additionally, the information processing system 230 may access and receive the distributed data set 550 through the data pipeline 520. In this case, the information processing system 230 may preprocess the distributed data set 550, extract metadata from the distributed data set 550, and transmit it to the domain-specific machine learning model 510.

In one embodiment, domain-specific machine learning model 510 can identify entities from input data and define relationships between the entities. Accordingly, the information processing system 230 may transmit the relationships between entities generated by the domain-specific machine learning model 510 to the knowledge graph generator 530. In this case, the knowledge graph generator 530 may generate a knowledge graph based on entities and relationships between entities. An example of how the knowledge graph generator generates a knowledge graph will be described in detail later with reference to FIG. 6. Additionally, the generated knowledge graph may be stored in a database 540 associated with the knowledge graph.

Although not shown in FIG. 5, the information processing system 230 may further include an index generator that generates an index corresponding to an entity in the knowledge graph. An example of the information processing system 230 generating an index using an index generator will be described in detail later with reference to FIG. 7 .

Through this configuration, the configuration and data that perform functions in the information processing system can be distributed. Accordingly, the speed of processing vast amounts of data to create a knowledge graph is greatly improved, and system expansion to process vast amounts of data can be very easy.

FIG. 6 is a diagram illustrating an example of the knowledge graph generator 530 generating a knowledge graph according to an embodiment of the present disclosure. In one embodiment, the knowledge graph generator (or 530 in FIG. 5) 530 may generate a local knowledge graph 620 based on a plurality of entities and relationships between the plurality of entities generated from a domain-specific machine learning model. there is. Here, the generated local knowledge graph 620 may be associated with a domain in which the corresponding machine learning model is specialized. In this case, the local knowledge graph 620 may be a knowledge graph with a plurality of entities as nodes and relationships between the plurality of entities as edges.

In one embodiment, the knowledge graph generator 530 may build the global knowledge graph 630 based on the generated local knowledge graph 620. Specifically, the knowledge graph generator 530 may collect instance nodes from the local knowledge graph 620 associated with a specific domain. Additionally, the knowledge graph generator 530 may extract relationships between entities within a predetermined range centered on the collected instance nodes. That is, the knowledge graph generator 530 can extract the relationship between the instance nodes of the local knowledge graph and the nodes of the existing global knowledge graph within a predetermined range centered on the instance nodes. Here, the instance node may be determined based on the purpose and scope of the domain associated with the local knowledge graph, availability of data, etc. Additionally, the knowledge graph generator 530 can build the global knowledge graph 630 by connecting and integrating the extracted entities with the existing global knowledge graph based on the relationships between the extracted entities. This process of building a global knowledge graph can be performed automatically at predetermined intervals. Additionally, the generated local knowledge graph 620 and the constructed global knowledge graph 630 may be transmitted and stored in the database 640 associated with the knowledge graph.

By this configuration, the global knowledge graph can indicate which local knowledge graph a plurality of entities including entities and/or relationships are related to. Accordingly, a domain corresponding to a plurality of entities including a specific entity and/or relationship can be easily searched.

FIG. 7 is a diagram illustrating an example in which indexes corresponding to entities of the knowledge graphs 720 and 730 are created according to an embodiment of the present disclosure. In one embodiment, the index generator 740 stores each of a plurality of entities included in the knowledge graph based on the local knowledge graph 720 and the global knowledge graph 730 stored in the first database 710 associated with the knowledge graph. A corresponding index can be created. Here, the index generator 740 may be included in the information processing system 230. Specifically, the index generator 740 may embed each of a plurality of entities included in the knowledge graphs 720 and 730 into a vector. Here, any embedding algorithm already known in the field related to vector embedding can be used to embed the entity into the vector. Additionally, the index generator 740 may map the embedded vector to a vector space corresponding to the knowledge graphs 720 and 730. Accordingly, the embedded vector can be used as an index, and the similarity between embedded vectors can be calculated using cosine similarity, Euclidean distance, etc.

In one embodiment, the embedded vector (or index) may be stored in the second database 750 associated with the index. If the entities or relationships between entities in the knowledge graphs 720 and 730 change, the changes may be sequentially recorded in the log. Additionally, the changes recorded in the log are asynchronously transmitted to the index generator 740, so that an index based on the changes can be created.

With this configuration, an index can be created by embedding entities and relationships between entities in a knowledge graph as vectors. Accordingly, by numerically expressing the data in the knowledge graph, the data you are looking for can be quickly searched and processed. Additionally, the performance of systems using knowledge graphs can be significantly improved.

8 is a flow chart illustrating an example method 800 according to one embodiment of the present disclosure. In one embodiment, method 800 may be performed by at least one processor. Method 800 may begin with a processor receiving an input data set (S810). Thereafter, the processor may identify the domain associated with the input data set (S820).

Afterwards, the processor may generate a local knowledge graph based on the input data set using a machine learning model associated with the domain (S830). Specifically, the processor may use a machine learning model to generate a plurality of entities associated with an input data set and relationships between the plurality of entities. Additionally, the processor may generate a local knowledge graph associated with the domain based on the plurality of entities and relationships between the plurality of entities. Here, the machine learning model may be pre-trained to create a plurality of entities associated with the input data and relationships between the plurality of entities based on meta data extracted from the input data. . Additionally, the machine learning model can be learned using a knowledge base document annotated with a predetermined domain.

Afterwards, the processor may build a global knowledge graph based on the local knowledge graph (S840). Specifically, the processor can extract relationships between entities within a predetermined range centered on instance nodes of the local knowledge graph. Additionally, the processor may build a global knowledge graph by integrating the local knowledge graph based on relationships between extracted entities.

In one embodiment, the processor may generate an index corresponding to each of a plurality of entities included in the global knowledge graph. Specifically, the processor can embed each of a plurality of entities included in the global knowledge graph as a vector. Additionally, the processor can map the embedded vector to the global knowledge graph. Here, the step of embedding into a vector can be performed asynchronously by sequentially recording changes in the global knowledge graph to the log.

The above-described method may be provided as a computer program stored in a computer-readable recording medium for execution on a computer. Media may be used to continuously store executable programs on a computer, or may be temporarily stored for execution or download. In addition, the medium may be a variety of recording or storage means in the form of a single or several pieces of hardware combined. It is not limited to a medium directly connected to a computer system and may be distributed over a network. Examples of media include magnetic media such as hard disks, floppy disks, and magnetic tapes, optical recording media such as CD-ROMs and DVDs, magneto-optical media such as floptical disks, and There may be something configured to store program instructions, including ROM, RAM, flash memory, etc. Additionally, examples of other media include recording or storage media managed by app stores that distribute applications, sites or servers that supply or distribute various other software, etc.

The methods, operations, or techniques of this disclosure may be implemented by various means. For example, these techniques may be implemented in hardware, firmware, software, or a combination thereof. Those skilled in the art will understand that the various illustrative logical blocks, modules, circuits, and algorithm steps described in connection with the disclosure herein may be implemented in electronic hardware, computer software, or combinations of both. To clearly illustrate this interchange of hardware and software, various illustrative components, blocks, modules, circuits, and steps have been described above generally in terms of their functionality. Whether such functionality is implemented as hardware or software depends on the specific application and design requirements imposed on the overall system. Skilled artisans may implement the described functionality in varying ways for each particular application, but such implementations should not be interpreted as causing a departure from the scope of the present disclosure.

In a hardware implementation, the processing units used to perform the techniques may include one or more ASICs, DSPs, GPUs, digital signal processing devices (DSPDs), or programmable logic devices. ; PLDs), field programmable gate arrays (FPGAs), processors, controllers, microcontrollers, microprocessors, electronic devices, and other devices designed to perform the functions described in this disclosure. It may be implemented within electronic units, a computer, or a combination thereof.

Accordingly, the various illustrative logical blocks, modules, and circuits described in connection with this disclosure may be general-purpose processors, DSPs, ASICs, FPGAs or other programmable logic devices, discrete gate or transistor logic, discrete hardware components, or It may be implemented or performed as any combination of those designed to perform the functions described in. A general-purpose processor may be a microprocessor, but in the alternative, the processor may be any conventional processor, controller, microcontroller, or state machine. A processor may also be implemented as a combination of computing devices, such as a DSP and a microprocessor, a plurality of microprocessors, one or more microprocessors in conjunction with a DSP core, or any other configuration.

For firmware and/or software implementations, techniques include random access memory (RAM), read-only memory (ROM), non-volatile random access memory (NVRAM), and PROM ( on computer-readable media such as programmable read-only memory (EPROM), electrically erasable PROM (EEPROM), flash memory, compact disc (CD), magnetic or optical data storage devices, etc. It may also be implemented as stored instructions. Instructions may be executable by one or more processors and may cause the processor(s) to perform certain aspects of the functionality described in this disclosure.

When implemented in software, the techniques may be stored on or transmitted through a computer-readable medium as one or more instructions or code. Computer-readable media includes both computer storage media and communication media, including any medium that facilitates transfer of a computer program from one place to another. Storage media may be any available media that can be accessed by a computer. By way of non-limiting example, such computer readable media may include RAM, ROM, EEPROM, CD-ROM or other optical disk storage, magnetic disk storage or other magnetic storage devices, or the desired program code in the form of instructions or data structures. It can be used to transfer or store data and can include any other media that can be accessed by a computer. Additionally, any connection may suitably be made to a computer-readable medium.

For example, if the Software is transmitted from a website, server, or other remote source using coaxial cable, fiber optic cable, twisted pair cable, digital subscriber line (DSL), or wireless technologies such as infrared, radio, and microwave, , fiber optic cable, twisted pair, digital subscriber line, or wireless technologies such as infrared, radio, and microwave are included within the definition of medium. As used herein, disk and disk include CD, laser disk, optical disk, digital versatile disc (DVD), floppy disk, and Blu-ray disk, where disks are usually magnetic. It reproduces data optically, while discs reproduce data optically using lasers. Combinations of the above should also be included within the scope of computer-readable media.

A software module may reside in RAM memory, flash memory, ROM memory, EPROM memory, EEPROM memory, registers, hard disk, removable disk, CD-ROM, or any other form of storage medium known. An exemplary storage medium may be coupled to the processor such that the processor may read information from or write information to the storage medium. Alternatively, the storage medium may be integrated into the processor. The processor and storage medium may reside within an ASIC. ASIC may exist within the user terminal. Alternatively, the processor and storage medium may exist as separate components in the user terminal.

Although the above-described embodiments have been described as utilizing aspects of the presently disclosed subject matter in one or more standalone computer systems, the disclosure is not limited thereto and may also be implemented in conjunction with any computing environment, such as a network or distributed computing environment. . Furthermore, aspects of the subject matter of this disclosure may be implemented in multiple processing chips or devices, and storage may be similarly effected across the multiple devices. These devices may include PCs, network servers, and portable devices.

Although the present disclosure has been described in relation to some embodiments in this specification, various modifications and changes may be made without departing from the scope of the present disclosure as can be understood by a person skilled in the art to which the invention pertains. Additionally, such modifications and changes should be considered to fall within the scope of the claims appended hereto.

110: input data set
120: Machine learning model
130: Entity
140: Relationships
150: Knowledge Graph

Claims (10)

In a method for automatically generating a knowledge graph, performed by at least one processor,
Receiving an input data set;
Identifying a domain associated with the input data set, from among a plurality of predetermined domains, wherein a machine learning model specialized for each of the plurality of predetermined domains is created and the number of the plurality of predetermined domains increases as a given amount of data increases. ;
Generating a local knowledge graph based on the input data set using a machine learning model associated with the identified domain, wherein the machine learning model is fine-tuned periodically at a predetermined time using data associated with the domain. (fine tuned) -;
Building a global knowledge graph based on the local knowledge graph;
Embedding each of a plurality of entities included in the constructed global knowledge graph into a vector; and
Generating an index corresponding to the constructed global knowledge graph by mapping the embedded vector to a vector space.
Including,
The step of building the global knowledge graph is,
Extracting relationships between entities within a predetermined range centered on an instance node of the local knowledge graph - the instance node of the local knowledge graph determines the purpose, scope, and availability of data of the domain associated with the local knowledge graph. decided on the basis -; and
Integrating the local knowledge graph based on the relationships between the extracted entities to build the global knowledge graph,
The index is stored in an index database that integrates a knowledge graph layer consisting of the local knowledge graph and the global knowledge graph to enable data retrieval,
The step of embedding into the vector is performed asynchronously by sequentially recording changes in the global knowledge graph in a log.
According to paragraph 1,
The machine learning model is pre-trained to generate a plurality of entities associated with the input data and relationships between the plurality of entities based on meta data extracted from the input data, Method for automatically generating knowledge graphs.
According to paragraph 1,
The machine learning model is a method of automatically generating a knowledge graph, where the machine learning model is learned using a knowledge base document annotated with a predetermined domain.
According to paragraph 1,
The step of generating the local knowledge graph is,
generating a plurality of entities associated with the input data set and relationships between the plurality of entities using the machine learning model; and
Generating a local knowledge graph associated with the domain based on the plurality of entities and relationships between the plurality of entities.
Method for automatically generating a knowledge graph, including:
delete delete delete delete A computer program stored in a computer-readable recording medium for executing the method according to any one of claims 1 to 4 on a computer.
As a system,
communication module;
Memory; and
At least one processor connected to the memory and configured to execute at least one computer-readable program included in the memory,
The at least one program is,
Receive a set of input data,
Among the predetermined plurality of domains, identify a domain associated with the input data set - a machine learning model specialized for each of the predetermined plurality of domains is created and the number of the predetermined plurality of domains is increased as a given amount of data increases -
Using a machine learning model associated with the identified domain, a local knowledge graph is generated based on the input data set, and the machine learning model is fine-tuned periodically at a predetermined time using data associated with the domain. fine tuned -,
Based on the local knowledge graph, build a global knowledge graph,
Embedding each of the plurality of entities included in the constructed global knowledge graph as a vector,
Contains instructions for generating an index corresponding to the constructed global knowledge graph by mapping the embedded vector to a vector space,
Building the global knowledge graph involves:
Extracting relationships between entities within a predetermined range centered on an instance node of the local knowledge graph - the instance node of the local knowledge graph determines the purpose, scope, and availability of data of the domain associated with the local knowledge graph. determined on the basis -, and
Based on the relationships between the extracted entities, integrating the local knowledge graph to build the global knowledge graph,
The index is stored in an index database that integrates a knowledge graph layer consisting of the local knowledge graph and the global knowledge graph to enable data retrieval,
The step of embedding into the vector is performed asynchronously by sequentially recording changes in the global knowledge graph in a log.

Images