KR20200086574A - Method and system for extracting new keyword by using keyword relation structure - Google Patents

Abstract

Disclosed are a method and system for extracting a novel keyword using a keyword relation structure. The method comprises the steps of: generating a multi-graph indicating a relationship between keywords in a product dictionary; analyzing at least one of product names related to a search query by using the multi-graph for the search query and other queries; and extracting a novel keyword not existing in the product dictionary from the search query based on the analyzed result.

Description

METHOD AND SYSTEM FOR EXTRACTING NEW KEYWORD BY USING KEYWORD RELATION STRUCTURE}

The following description relates to a technique for extracting a new keyword using relationship data between keywords.

In general, when a user wants to collect information through the Internet, it accesses a server that provides the information and obtains the information through a search.

If you want to purchase a specific product, you can use the search site to get information about prices, characteristics, etc., or you can go to a website that sells the product.

In order to search for products, a product registration process is required, including the process of matching product models and categories.

For example, Korean Patent Registration No. 10-0705410 (registration date April 03, 2007) discloses a technique for registering product information by automatically matching product models and categories.

Provided is a method and system for automatically extracting new keywords based on a multi-graph structure after constructing a multi-graph structure representing relationships between keywords for keywords extracted from product information.

Provides a method and system for automatically extracting new keywords that have been trended by analyzing product names and product related queries that correspond to recent popular queries based on a multi-graph structure.

A keyword extraction method executed in a computer system, the computer system comprising at least one processor configured to execute computer readable instructions contained in a memory, wherein the keyword extraction method comprises, by the at least one processor, a product Generating a multi-graph representing relationships between keywords in the dictionary; Analyzing, by the at least one processor, at least one of product names related to the search query and other queries using the multi-graph for the search query; And extracting, by the at least one processor, a new keyword that does not exist in the product dictionary from the search query based on the analyzed result.

According to an aspect, the generating step includes: converting product information matching a corresponding product into keywords for each product included in the product dictionary; And extracting relationship data between information matching the product from the product dictionary as relationship data between keywords.

According to another aspect, the analyzing may include selecting a query to be analyzed based on the number of query inputs among recently input search queries.

According to another aspect, the analyzing may include separating keywords included in the multigraph from the search query and determining the remaining keywords as candidate strings for extracting the new keywords.

According to another aspect, the analyzing may include separating keywords included in the multigraph from the search query and determining the remaining keywords as candidate strings; And after inputting the search query, analyzing an input pattern for the candidate string by using at least one of a clicked product name list, a different query list associated with each clicked product, and a tag list associated with each clicked product. have.

According to another aspect, in the extracting step, at least some of the candidate strings may be extracted as the new keyword.

According to another aspect, in the extracting step, a character string corresponding to the input pattern may be separated from the candidate character string to extract the separated character string as the new keyword.

According to another aspect, in the extracting step, a string of an input pattern having a probability of a predetermined level or higher among the input patterns for the candidate string may be extracted as the new keyword.

According to another aspect, the extracting may include extracting at least a part of the candidate strings as the new keyword based on an input pattern for the candidate strings; And additionally registering the new keyword in the multi-graph.

According to another aspect, the step of registering additionally may add a relationship between keywords appearing with the new keyword to at least one of the product name list, the query list, and the tag list among keywords on the multigraph.

There is provided a non-transitory computer-readable recording medium in which a program for executing the keyword extraction method on a computer is recorded.

A computer system, comprising: at least one processor configured to execute computer readable instructions contained in a memory, the at least one processor comprising: a graph generator that generates a multigraph representing relationships between keywords in a product dictionary; An analysis unit that analyzes at least one of product names related to the search query and other queries using the multi-graph for the search query; And a keyword extracting unit that extracts a new keyword that does not exist in the product dictionary from the search query based on the analyzed result.

According to embodiments of the present invention, after constructing a multi-graph structure representing a relationship between keywords for keywords extracted from product information, new keywords can be automatically extracted based on the multi-graph structure.

According to embodiments of the present invention, a new keyword that is trended may be automatically extracted by analyzing a product name and a product-related query corresponding to a recent popular query based on a multi-graph structure.

1 is a diagram showing an example of a network environment according to an embodiment of the present invention.
2 is a block diagram illustrating an internal configuration of an electronic device and a server according to an embodiment of the present invention.
3 is a block diagram illustrating an example of components that a processor of a server may include according to an embodiment of the present invention.
4 is a flowchart illustrating an example of a method that can be performed by a server according to an embodiment of the present invention.
5 shows an example of the configuration of a product dictionary for keyword management in an embodiment of the present invention.
6 is an exemplary diagram for explaining an example of a process of converting product information into keywords in an embodiment of the present invention.
7 is an exemplary diagram for explaining an example of a process of constructing a multi-graph showing a relationship between keywords in an embodiment of the present invention.
8 to 9 are exemplary views for explaining an example of a process of extracting a new keyword in an embodiment of the present invention.
10 is an exemplary diagram for explaining an example of a process of registering a new keyword in an embodiment of the present invention.

Hereinafter, embodiments of the present invention will be described in detail with reference to the accompanying drawings.

Embodiments of the present invention relates to a technique for automatically extracting new keywords using relationship data between keywords.

Embodiments including those specifically disclosed herein can build a multi-graph structure representing a relationship between keywords for keywords extracted from product information, and then extract new keywords based on the multi-graph structure, through which Significant advantages can be achieved in terms of management automation, reduced work resources, improved service quality, and expanded service.

1 is a diagram showing an example of a network environment according to an embodiment of the present invention. The network environment of FIG. 1 shows an example including a plurality of electronic devices 110, 120, 130, 140, a plurality of servers 150, 160, and a network 170. 1 is not limited to the number of electronic devices or the number of servers as an example for explaining the invention.

The plurality of electronic devices 110, 120, 130, and 140 may be fixed terminals or mobile terminals implemented as a computer system. For example, a plurality of electronic devices (110, 120, 130, 140), smart phones (smart phone), mobile phones, navigation, computers, notebooks, digital broadcasting terminal, PDA (Personal Digital Assistants), PMP (Portable Multimedia Player) ), tablet PCs, game consoles, wearable devices, internet of things (IoT) devices, virtual reality (VR) devices, and augmented reality (AR) devices. For example, although the shape of a smartphone is shown as an example of the electronic device 110 in FIG. 1, in the embodiments of the present invention, the electronic device 110 is substantially different from the network 170 using a wireless or wired communication method. It may mean one of various physical computer systems capable of communicating with the electronic devices 120, 130, 140 and/or the servers 150, 160.

The communication method is not limited, and a communication method using a communication network (eg, a mobile communication network, a wired Internet, a wireless Internet, a broadcasting network, a satellite network, etc.) that the network 170 may include, as well as short-range wireless communication between devices are included. Can. For example, the network 170 includes a personal area network (PAN), a local area network (LAN), a campus area network (CAN), a metropolitan area network (MAN), a wide area network (WAN), and a broadband network (BBN). , Any one or more of the networks such as the Internet. Further, the network 170 may include any one or more of a network topology including a bus network, a star network, a ring network, a mesh network, a star-bus network, a tree or a hierarchical network, etc. It is not limited.

Each of the servers 150 and 160 communicates with a plurality of electronic devices 110, 120, 130, and 140 through a network 170 to provide commands, codes, files, content, services, or the like, or a plurality of computers. It can be implemented with devices. For example, the server 150 may be a system that provides a first service to a plurality of electronic devices 110, 120, 130, 140 accessed through the network 170, and the server 160 is also a network ( It may be a system that provides a second service to a plurality of electronic devices (110, 120, 130, 140) accessed through (170). As a more specific example, the server 150 is a service that is intended for the application (eg, keyword management service, etc.) through an application as a computer program installed and driven on a plurality of electronic devices 110, 120, 130, and 140. As a first service, a plurality of electronic devices 110, 120, 130, and 140 may be provided. As another example, the server 160 may provide a service for distributing a file for installing and driving the above-described application to a plurality of electronic devices 110, 120, 130, 140 as a second service.

2 is a block diagram illustrating an internal configuration of an electronic device and a server according to an embodiment of the present invention. 2 illustrates an internal configuration of the electronic device 110 and the server 150 as an example of the electronic device. In addition, other electronic devices 120, 130, 140 or the server 160 may also have the same or similar internal configuration to the above-described electronic device 110 or the server 150.

The electronic device 110 and the server 150 may include memories 211 and 221, processors 212 and 222, communication modules 213 and 223, and input/output interfaces 214 and 224. The memory 211, 221 is a non-transitory computer-readable recording medium, such as random access memory (RAM), read only memory (ROM), disk drive, solid state drive (SSD), flash memory, etc. And a permanent mass storage device. Here, a non-volatile mass storage device such as a ROM, SSD, flash memory, disk drive, etc. may be included in the electronic device 110 or the server 150 as a separate permanent storage device separate from the memories 211 and 221. Also, the memory 211 and 221 may include an operating system and at least one program code (for example, a browser installed and driven in the electronic device 110 or a code for an application installed in the electronic device 110 to provide a specific service). Can be stored. These software components may be loaded from a computer-readable recording medium separate from the memories 211 and 221. Such a separate computer-readable recording medium may include a computer-readable recording medium such as a floppy drive, disk, tape, DVD/CD-ROM drive, and memory card. In other embodiments, software components may be loaded into memory 211 and 221 through communication modules 213 and 223 rather than a computer-readable recording medium. For example, at least one program is a computer program installed by files provided by a file distribution system (for example, the server 160 described above) that distributes installation files of developers or applications through the network 170. It may be loaded into the memories 211 and 221 based on (for example, the above-described application).

Processors 212 and 222 may be configured to process instructions of a computer program by performing basic arithmetic, logic, and input/output operations. Instructions may be provided to processors 212 and 222 by memory 211 and 221 or communication modules 213 and 223. For example, the processors 212 and 222 may be configured to execute instructions received according to program codes stored in a recording device such as the memories 211 and 221.

The communication modules 213 and 223 may provide a function for the electronic device 110 and the server 150 to communicate with each other through the network 170, and the electronic device 110 and/or the server 150 are different. An electronic device (eg, the electronic device 120) or another server (eg, the server 160) may provide a function for communication. For example, the request generated by the processor 212 of the electronic device 110 according to the program code stored in the recording device, such as the memory 211, the server 150 through the network 170 under the control of the communication module 213 ). Conversely, control signals or commands, contents, files, etc. provided under the control of the processor 222 of the server 150 are communicated through the communication module 223 and the network 170 and the communication module 213 of the electronic device 110. ) To the electronic device 110. For example, control signals, commands, contents, files, and the like of the server 150 received through the communication module 213 may be transmitted to the processor 212 or the memory 211, and contents or files may be transferred to the electronic device ( 110) may be further stored as a storage medium (permanent storage device described above).

The input/output interface 214 may be a means for interfacing with the input/output device 215. For example, the input device may include devices such as a keyboard, mouse, microphone, camera, and the like, and the output device may include devices such as a display, a speaker, a haptic feedback device, and the like. As another example, the input/output interface 214 may be a means for an interface with a device in which functions for input and output are integrated into one, such as a touch screen. The input/output device 215 may be configured with the electronic device 110 and one device. Further, the input/output interface 224 of the server 150 may be a means for interfacing with the server 150 or with an apparatus (not shown) for input or output that the server 150 may include. As a more specific example, the service configured by using the data provided by the server 150 or the electronic device 120 when the processor 212 of the electronic device 110 processes a command of a computer program loaded in the memory 211. The screen or content may be displayed on the display through the input/output interface 214.

Also, in other embodiments, the electronic device 110 and the server 150 may include more components than those in FIG. 2. However, there is no need to clearly show most prior art components. For example, the electronic device 110 may be implemented to include at least a part of the input/output device 215 described above, or other components such as a transceiver, a Global Positioning System (GPS) module, a camera, various sensors, and a database. It may also include more. As a more specific example, when the electronic device 110 is a smartphone, an acceleration sensor or a gyro sensor, a camera module, various physical buttons included in a smartphone, buttons using a touch panel, input/output ports, and a vibrator for vibration Various components, such as, may be implemented to be further included in the electronic device 110.

Hereinafter, a specific embodiment of a new keyword extraction method and system using a keyword relationship structure will be described.

3 is a block diagram showing an example of a component that a processor of a server may include according to an embodiment of the present invention, and FIG. 4 is an example of a method that the server can perform according to an embodiment of the present invention It is a flow chart showing.

The server 150 according to the present exemplary embodiment serves as a platform for providing a service for managing keywords used on the Internet. In particular, the server 150 may automatically extract new keywords based on the multi-graph structure after constructing a multi-graph structure representing relationships between related keywords for each product included in the product dictionary.

The processor 222 of the server 150 is a component for performing the keyword extraction method according to FIG. 4, as shown in FIG. 3, the graph generation unit 310, the product name and query analysis unit 320, and keywords An extraction unit 330 may be included. Depending on the embodiment, components of the processor 222 may be selectively included or excluded from the processor 222. Further, according to an embodiment, the components of the processor 222 may be separated or merged to express the function of the processor 222.

The processor 222 and the components of the processor 222 may control the server 150 to perform steps S410 to S430 included in the keyword extraction method of FIG. 4. For example, the processor 222 and components of the processor 222 may be implemented to execute instructions according to code of an operating system included in the memory 221 and code of at least one program.

Here, the components of the processor 222 may be expressions of different functions of the processor 222 performed by the processor 222 according to instructions provided by program code stored in the server 150. . For example, the graph generator 310 may be used as a functional expression of the processor 222 that controls the server 150 according to the above-described command so that the server 150 generates a multi-graph representing relationships between keywords. .

The processor 222 may read necessary commands from the memory 221 loaded with commands related to the control of the server 150. In this case, the read command may include an instruction for controlling the processor 222 to execute steps S410 to S430 to be described later.

In step S410, the graph generator 310 may generate a multi-graph representing relationships between keywords extracted from product information for each product included in the product dictionary. The product dictionary is a database system for managing keywords, and may be composed of keywords, dictionary types, and synonym sets. The product dictionary may include product information such as a retailer, a brand, a category, and an attribute matched to a corresponding product for each product.

The above product dictionary includes product management (automatic product brand matching, auto product category matching, product quality check, etc.), shopping, search, keyword autocomplete, tag dictionary, advertisement, store, NLU (natural language understanding), AI (Artificial Intelligence) ) And can be applied to various services.

For example, referring to FIG. 5, assuming that the product dictionary 500 is divided into a retailer 510, a brand 520, and a category 530, the vendor-brand, brand- from the product dictionary 500 Category, category-seller relationship data can be extracted.

As shown in FIG. 6, the graph generation unit 310, for a product A having a retailer ID of S1, a brand ID of B1, and a category ID of C1, the seller name'ABC' matching the corresponding product, the brand name 'DEF' and category name'GHI' can be converted into keywords. The graph generator 310 may convert product information matching product A to keywords'ABC','DEF', and'GHI' for product A, and then create a multi-graph representing the relationship between the converted keywords. The graph generator 310 may generate multi-graphs by extracting relationship data between information matching a product from a product dictionary as relationship data between keywords converted from the information.

Referring to FIG. 7, the graph generating unit 310 connects a seller-brand relationship between keywords'ABC' and'DEF', a brand-category connection relationship between keywords'DEF' and'GHI', and a keyword'ABC' Between the 'and'GHI' it is possible to build a multi-graph 700 made of a connection relationship between the seller and the category.

The multi-graph 700 may be constructed in a tree structure having a plurality of depths, as well as a tree structure having a single depth. For example, if there are multiple series within the same brand, that is, a sub-brand, a connection relationship called brand-series may be added.

As described above, the graph generator 310 may generate a database by accumulating relationship data between keywords, and may define this as a multi-graph 700 structure representing the relationship between keywords.

In FIG. 4 again, in step S420, the product name and query analysis unit 320 may analyze the click product name and the query or tag related to the click product by using the multi-graph generated in step S410 for the search query. In this specification, click may refer to all types of selection input by the user.

The present invention can process new keyword inflow trended based on a multi-graph structure. As a new keyword, a keyword that does not exist in the product dictionary, for example, a new category, a new brand, a new retailer, a new attribute, and a keyword (eg, a celebrity name, a movie name, a drama name, etc.) may be considered. . To this end, the product name and query analysis unit 320 may select an upper predetermined number of search queries as an analysis target based on the number of query inputs among recently input search queries.

The product name and query analysis unit 320 separates keywords in which the relationship is defined on the multi-graph from the search query and determines the rest of the keywords as candidate strings by talking to each of the search queries selected as analysis targets through talk aging. Can. In addition, the product name and query analysis unit 320 includes a list of product names clicked by users who have entered a search query, a list of tags associated with each clicked product, and a list of other queries associated with each clicked product (for example, when a user clicks the same product. An input pattern for a candidate string may be analyzed by analyzing at least one of a query input by users, another query input by the same user before clicking the same product, and the like.

In step S430, the keyword extraction unit 330 may extract new keywords from the search query according to the analysis result of step S420. For example, the keyword extracting unit 330 may extract the separated string as a new keyword by separating the string corresponding to the analyzed input pattern from the click product name list and the click product related tag/query list from the candidate string. The keyword extraction unit 330 may analyze the input pattern of the candidate string using the click product name and the click product related tag/query related to the search query, and have a probability of a certain level or higher among the input patterns of the candidate string or have the highest probability The string of the input pattern with the can be extracted as a new keyword.

The process of extracting new keywords will be described in detail as follows.

8 to 10 are exemplary views for explaining an example of a process of extracting a new keyword in an embodiment of the present invention.

Referring to FIG. 8, it is assumed that the search query 801 selected as an analysis target for extracting a new keyword is “DEFXYZGHI”.

The product name and query analysis unit 320 performs talk-naising using a multi-graph representing a keyword relationship, and separates'DEF' and'GHI' having a relationship of'brand-category' in the search query 801 You can see that'DEF' is the brand name and'GHI' is the category name.

The product name and query analysis unit 320 separates the brand name'DEF' and the category name'GHI' from the search query 801 based on the multigraph and extracts the remaining keyword'XYZ' as a candidate string (802) ).

Referring to FIG. 9, the product name and query analysis unit 320 includes a product name list 910 clicked by users who input a search query 801, another query list 920 related to a click product, and tags associated with a click product. The input pattern 903 for the candidate string 802 may be analyzed by analyzing at least one of the list 930.

In the process of extracting a new keyword, analyzing the clicked product name is to consider a string pattern written as a product name from the seller's point of view, and analyzing a click product related query/tag is a string pattern written by a query or tag from the user's point of view Is to consider.

The product name and query analysis unit 320 analyzes the click product name list 910, the click product related query list 920, and the click product related tag list 930, so that the candidate string 802'XYZ' is {'X', It is possible to determine which input pattern 903 is among'Y','Z'} or {'XY','Z'} or {'X','YZ'} or {'XYZ'}. At this time, the product name and query analysis unit 320 may provide a probability according to the appearance frequency for each input pattern 903 of the candidate string 802 as an analysis result.

The keyword extraction unit 330 has a probability of a predetermined level or higher among the input patterns 903 of the candidate string 802 based on the analysis results of the product name and the query analysis unit 320, or has the highest probability. String of can be extracted as a new keyword (904).

For example, as a result of analyzing the input pattern for the candidate string 802'XYZ', patterns of {'XY','Z'} and {'XYZ'} exist, and of {'XY','Z'} If the pattern is 9% and the pattern of {'XYZ'} is 91%, the keyword'XYZ' may be extracted as a new keyword 904 in the search query 801 "DEFXYZGHI".

In other words, by analyzing the string of the click product name and the click product related query/tag for the search query 801 "DEFXYZGHI", the candidate string 802 {'X','Y','Z'} in case of'XYZ'} Or it can be understood that it should be separated as {'XYZ'}, not {'XY','Z'} or {'X','YZ'}.

Referring to FIG. 10, the keyword extracting unit 330 may additionally register a new keyword 904 on the multigraph 700, and at this time, establish a relationship with an existing keyword on the multigraph 700. For example, the keyword extracting unit 330 has at least one frequency that appears with the new keyword 904 in the string of the clicked product name and the clicked product related query/tag for the search query 801 "DEFXYZGHI" is higher than a certain level. You can add a relationship as related to the keyword.

If a new keyword (904)'XYZ' appears in a search query, a click product name, or a query/tag related to a click product mainly with the brand name'DEF' and the category name'GHI', create a relationship with the relevant keyword Can.

In extracting a new keyword, by considering the product name string inputted by the seller and the query or tag string inputted by the user together, information between the seller and the user can be well matched between the keywords.

Through the above-described method, by extracting a new keyword from a frequently input query and registering it on the multi-graph 700, the multi-graph 700 can be automatically expanded while solving the trend of new keyword inflow.

By constructing a multi-graph showing the relationship between keywords in the product dictionary and using this to automatically process new keyword inflow, it is possible to dramatically reduce the related work resources by realizing the automation of keyword management tasks.

As described above, according to embodiments of the present invention, a new graph may be automatically extracted based on a multi-graph structure after constructing a multi-graph structure indicating a relationship between keywords for keywords extracted from product information. In particular, according to embodiments of the present invention, a new keyword trended may be automatically extracted by analyzing a product name corresponding to a recent popular query and other queries/tags related to a product based on a multi-graph structure.

The device described above may be implemented with hardware components, software components, and/or combinations of hardware components and software components. For example, the devices and components described in the embodiments include a processor, controller, arithmetic logic unit (ALU), digital signal processor (micro signal processor), microcomputer, field programmable gate array (FPGA), programmable It may be implemented using one or more general purpose computers or special purpose computers, such as a logic unit, microprocessor, or any other device capable of executing and responding to instructions. The processing device may perform an operating system (OS) and one or more software applications running on the operating system. In addition, the processing device may access, store, manipulate, process, and generate data in response to the execution of the software. For convenience of understanding, a processing device may be described as one being used, but a person having ordinary skill in the art, the processing device may include a plurality of processing elements and/or a plurality of types of processing elements. It can be seen that may include. For example, the processing device may include a plurality of processors or a processor and a controller. In addition, other processing configurations, such as parallel processors, are possible.

The software may include a computer program, code, instruction, or a combination of one or more of these, and configure the processing device to operate as desired, or process independently or collectively You can command the device. Software and/or data may be embodied in any type of machine, component, physical device, computer storage medium, or device in order to be interpreted by the processing device or to provide instructions or data to the processing device. have. The software may be distributed on networked computer systems, and stored or executed in a distributed manner. Software and data may be stored in one or more computer-readable recording media.

The method according to the embodiment may be implemented in the form of program instructions that can be executed through various computer means and recorded on a computer-readable medium. In this case, the medium may continuously store a program executable on a computer or may be temporarily stored for execution or download. In addition, the medium may be various recording means or storage means in the form of a single or several hardware combinations, and is not limited to a medium directly connected to a computer system, but may be distributed on a network. Examples of the medium include magnetic media such as hard disks, floppy disks, and magnetic tapes, optical recording media such as CD-ROMs and DVDs, and magneto-optical media such as floptical disks, And program instructions including ROM, RAM, flash memory, and the like. Also, examples of other media include an application store for distributing applications, a site for distributing or distributing various software, and a recording medium or storage medium managed by a server.

As described above, although the embodiments have been described by a limited embodiment and drawings, those skilled in the art can make various modifications and variations from the above description. For example, the described techniques are performed in a different order than the described method, and/or the components of the described system, structure, device, circuit, etc. are combined or combined in a different form from the described method, or other components Alternatively, even if replaced or substituted by equivalents, appropriate results can be achieved.

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

Claims (20)

A method for extracting keywords executed in a computer system,
The computer system includes at least one processor configured to execute computer readable instructions contained in memory,
The keyword extraction method,
Generating, by the at least one processor, a multigraph representing a relationship between keywords on a product dictionary;
Analyzing, by the at least one processor, at least one of product names related to the search query and other queries using the multi-graph for the search query; And
Extracting, by the at least one processor, a new keyword that does not exist in the product dictionary from the search query based on the analyzed result.
Keyword extraction method comprising a. According to claim 1,
The generating step,
Converting product information matching a corresponding product into keywords for each product included in the product dictionary; And
Extracting relationship data between information matching the product from the product dictionary as relationship data between keywords;
Keyword extraction method comprising a. According to claim 1,
The analyzing step,
Selecting a query to be analyzed based on the number of query inputs among recently entered search queries
Keyword extraction method comprising a. According to claim 1,
The analyzing step,
Separating keywords included in the multi-graph from the search query and determining the remaining keywords as candidate strings for extracting the new keywords
Keyword extraction method comprising a. According to claim 1,
The analyzing step,
Separating keywords included in the multi-graph from the search query and determining the remaining keywords as candidate strings; And
After inputting the search query, analyzing an input pattern for the candidate string using at least one of a clicked product name list, a different query list associated with each clicked product, and a tag list associated with each clicked product.
Keyword extraction method comprising a. According to claim 4,
The extraction step,
Extracting at least some of the candidate strings as the new keyword
Keyword extraction method characterized in that. The method of claim 5,
The extraction step,
Separating the character string corresponding to the input pattern from the candidate character string and extracting the separated character string as the new keyword
Keyword extraction method characterized in that. The method of claim 5,
The extraction step,
Extracting a character string of an input pattern having a probability above a certain level or the highest probability among the input patterns for the candidate character string as the new keyword
Keyword extraction method characterized in that. The method of claim 5,
The extraction step,
Extracting at least some of the candidate strings as the new keyword based on the input pattern for the candidate strings; And
Adding the new keyword to the multi-graph
Keyword extraction method comprising a. The method of claim 9,
The additional registration step,
Adding a relationship between keywords appearing with the new keyword to at least one of the product name list, the query list, and the tag list among keywords on the multigraph
Keyword extraction method characterized in that. A non-transitory computer readable recording medium in which a program for executing a keyword extraction method of any one of claims 1 to 10 is recorded on a computer. In the computer system,
At least one processor configured to execute computer readable instructions contained in memory
Including,
The at least one processor,
A graph generator that generates a multi-graph representing relationships between keywords in the product dictionary;
An analysis unit that analyzes at least one of product names related to the search query and other queries using the multi-graph for the search query; And
A keyword extraction unit that extracts new keywords that do not exist in the product dictionary from the search query based on the analyzed results
Computer system comprising a. The method of claim 12,
The graph generator,
For each product included in the product dictionary, product information matching the product is converted into keywords,
Extracting relationship data between information matching the product from the product dictionary as relationship data between keywords
Computer system characterized in that. The method of claim 12,
The analysis unit,
Separating keywords included in the multi-graph from the search query and determining the remaining keywords as candidate strings for extracting the new keywords
Computer system characterized in that. The method of claim 12,
The analysis unit,
Separate keywords included in the multi-graph from the search query and determine the remaining keywords as candidate strings,
After inputting the search query, the input pattern for the candidate string is analyzed by using at least one of a clicked product name list, a different query list associated with each clicked product, and a tag list associated with each clicked product.
Computer system characterized in that. The method of claim 14,
The keyword extraction unit,
Extracting at least some of the candidate strings as the new keyword
Computer system characterized in that. The method of claim 15,
The keyword extraction unit,
Separating the character string corresponding to the input pattern from the candidate character string and extracting the separated character string as the new keyword
Computer system characterized in that. The method of claim 15,
The keyword extraction unit,
Extracting a character string of an input pattern having a probability above a certain level or the highest probability among the input patterns for the candidate character string as the new keyword
Computer system characterized in that. The method of claim 15,
The keyword extraction unit,
Based on the input pattern for the candidate string, at least a part of the candidate string is extracted as the new keyword,
Adding the new keyword to the multi-graph
Computer system characterized in that. The method of claim 19,
The keyword extraction unit,
Adding a relationship between keywords appearing with the new keyword to at least one of the product name list, the query list, and the tag list among keywords on the multigraph
Computer system characterized in that.

Images