JP2022068101A - Method and system for providing search result reflecting intention of retrieval query - Google Patents

Abstract

PROBLEM TO BE SOLVED: To provide a search result providing method, a computer program and a search result providing system reflecting the intention of a search query executed by at least one processor.
SOLUTION: This is a search result providing method that reflects the intent of a search query, and is one for a search query based on a step of receiving a search query from a user terminal and one or more query intents extracted from the search query. It includes a step of determining the above query pattern type and a step of determining the ranking of each of a plurality of contents related to the search query based on one or more query pattern types.
[Selection diagram] FIG. 6

Description

There is an application for exception of loss of novelty

The present disclosure relates to a method and system for providing search results that reflect the intent of a search query, specifically, a method for providing content and snippets corresponding to the intent of a query extracted from a search query. Regarding the system.

With the spread of mobile devices such as smartphones and the development of the Internet, users and others enter search terms in an application with a search function and search according to them in order to easily and quickly obtain desired search results in daily life. Depending on the result, you can come into contact with various contents. When the user inputs a search term, the search system extracts the content including the keyword extracted from the search term from the database and provides it as a search result. In such a search system, the ranking of the content is determined by the degree of keyword matching between the search term and the content, and the content can be arranged and provided to the user according to the determined ranking. In other words, by ranking the content having a high degree of keyword matching with respect to the search term, the content having a high degree of keyword matching can be preferentially provided to the user.

At this time, the user can input the search term with a clear intention to provide specific information and contents. In the case of the conventional search result providing method, the ranking of the content is determined by the degree of keyword matching with the search term, and the content is provided based on the determined ranking, so that the search result cannot accurately reflect the user's search intention. There is a problem. Therefore, in order to search for content that satisfies his or her search intent, the user must check the content output as a search result one by one, or search again using a combination of other keywords. There is inconvenience.

Korean Registered Patent No. 10-15037313

The present disclosure has been made to solve the above problems, and provides a search result providing method, a computer-readable computer program, and a device (system) that reflect the intention of the search query.

The present disclosure can be embodied in a variety of ways, including methods, devices (systems) or computer-readable computer programs.

A search result providing method that reflects the intent of a search query executed by at least one processor according to an embodiment of the present disclosure includes a step of receiving a search query from a user terminal, and one or more queries extracted from the search query. Intentionally, it comprises determining one or more query pattern types for a search query and, based on one or more query pattern types, determining the ranking of each of a plurality of contents associated with the search query.

A computer-readable computer program is provided for executing a search result providing method on a computer that reflects the query intent according to an embodiment of the present disclosure.

A search result providing system that reflects the intent of the search query according to an embodiment of the present disclosure is configured to be concatenated with a communication module, memory and memory to execute at least one computer-readable program contained in the memory. At least one program receives a search query from a user terminal and makes one or more query pattern types for the search query based on one or more query intents extracted from the search query. Includes directives to determine and determine the ranking of each of the plurality of contents associated with the search query based on one or more query pattern types.

According to various embodiments of the present disclosure, the query intent is grasped from the search query entered by the user, and the ranking factor that matches the query intent is dynamically applied to rank the content (rank). By doing so, it is possible to preferentially provide content that meets the needs of the user. That is, the user can preferentially obtain the content corresponding to the user's query intention as the search result, instead of the content simply matched with the keyword of the search query.

According to various embodiments of the present disclosure, snippets corresponding to each query intent are extracted in advance, and when a search query is input by a user, snippets that match the query intent of the search query are selected in real time to the user. Can be provided. Therefore, the user is not a snippet that simply includes a part in the body of the content that is uniformly keyword-matched to the search query, but a part that corresponds to the user's query intent, that is, an object that the user actually wants. You can get snippets that include parts that contain information and content.

Various embodiments of the present disclosure analyze / analyze not only the text of the content, but also the document content, text structure, attachments, images, etc., so that the content and snippets that match the query intent of the search query are more accurate. Can be extracted to.

According to the various embodiments of the present disclosure, the snippet emphasizes the area corresponding to the query intent so that the user can obtain a highly readable snippet.

The embodiments of the present disclosure will be described with reference to the following accompanying drawings. Here, similar reference numbers indicate similar elements, but are not limited thereto.
It is a figure which shows the example which the user obtains the search result for the search query through the screen of the user terminal which concerns on one Embodiment of this disclosure. It is a schematic diagram which shows the structure which the plurality of user terminals which concern on one Embodiment of this disclosure are connected so that they can communicate with an information processing system. It is a block diagram which shows the internal structure of the user terminal and the information processing system which concerns on one Embodiment of this disclosure. It is a detailed block diagram of the processor of the information processing system which concerns on one Embodiment of this disclosure. It is a detailed block diagram of the processor of the information processing system which concerns on other embodiment of this disclosure. It is a flow chat which shows the search result providing method which reflected the query intention which concerns on one Example of this disclosure. It is a figure which shows the example which provides the search result which reflected the query intention of the search query which concerns on one Example of this disclosure. It is a figure which shows the example which provides the search result which reflected the query intention of the search query which concerns on other embodiment of this disclosure. It is a figure which shows the example which provides the search result which reflected the query intention of the search query which concerns on another Example of this disclosure. It is a figure which shows the example which provides the snippet which differs depending on the query intention of the search query which concerns on one Example of this disclosure. It is a figure which shows the example which provides the snippet which emphasized the area related to the query intention of the search query which concerns on one Example of this disclosure.

Hereinafter, the specific contents for the implementation of the present disclosure will be described in detail based on the attached drawings. However, in the following description, if there is a risk of unnecessarily obscuring the gist of the present disclosure, specific description of known functions and configurations will be omitted.

In the accompanying drawings, the same or corresponding components are given the same reference numerals. Further, in the following description of the embodiment, duplicate description of the same or corresponding components may be omitted. However, even if the description of a component is omitted, it should not be intended that such a component is not included in the embodiment.

The advantages and features of the disclosed embodiments and the methods for achieving them will be clarified with reference to the embodiments described below based on the accompanying drawings. However, the present disclosure is not limited to the examples disclosed below, and can be embodied in various forms different from each other. However, the present embodiment is provided only to ensure that the present disclosure is complete and that the present disclosure allows ordinary technicians to accurately recognize the category of the invention.

The terms used herein will be briefly described and the embodiments of the disclosure will be specifically described. As the terms used herein, we have selected common terms that are as widely used today as possible, taking into account the functionality of this disclosure, but this is the intent or judicial precedent of engineers engaged in the relevant field. , Can change due to the emergence of new technologies. In addition, although there may be terms arbitrarily selected by the applicant in specific cases, their meanings will be described in detail in the description of the invention. Therefore, the terms used in this disclosure should be defined based on the meaning of the terms and the general content of the present disclosure, rather than the simple names of the terms.

In the present specification, a singular expression may include a plurality of expressions, and a plurality of expressions may include a singular expression, unless explicitly specified in the context. When a component is referred to as "contains" a component throughout the specification, this does not exclude other components unless otherwise stated, and may further include other components. It means that you can do it.

Also, the term "module" or "unit" used in the specification means software or hardware components, and the "module" or "department" performs a certain role. However, "module" or "part" is not limited to software or hardware. The "module" or "part" may be configured to be on an addressable storage medium or to regenerate one or more processors. Thus, as an example, a "module" or "part" is a component such as a software component, an object-oriented software component, a class component, a task component, as well as a process, function, attribute, procedure, subroutine, program. It can include at least one of a segment of code, driver, firmware, microcode, circuit, data, database, data structure, table, array or variable. A component and a "module" or "part" may be combined with a smaller number of components and "modules" or "parts" provided internally, or an additional component and a "module" or "part". Can be further separated into.

According to one embodiment of the present disclosure, a "module" or "part" may be embodied in a processor and memory. "Processor" should be broadly interpreted to include general purpose processors, central processing units (CPUs), microprocessors, digital signal processors (DSPs), controllers, microcontrols, state machines, and the like. In some environments, "processor" can also refer to application specific integrated circuits (ASICs), programmable logic devices (PLDs), field programmable gate arrays (FPGAs), and the like. A "processor" may be, for example, a combination of a DSP and a microprocessor, a combination of multiple microprocessors, a combination of one or more microprocessors coupled to a DSP core, or any other combination of such configurations. It can also refer to a combination of various processing devices. Also, "memory" should be broadly interpreted to include any electronic component capable of storing electronic information. "Memory" includes RAM (Random Access Memory), ROM (Read Only Memory), NVRAM (Non-Volatile Random Access Memory), PROM (Programmable Read-Only Memory), EPROM (Erasable Programmable Read-Only Memory), and EEPROM (Erasable Programmable Read-Only Memory). It can also refer to various types of processors-readable media such as Electrically Erasable Programmable Reda-Only Memory), flash memory, magnetic or optical data storage devices, registers, and the like. When a processor can read / read information from and record information in memory, the memory is said to be in electronic communication with the processor. The memory integrated in the processor is in electronic communication with the processor.

In the present disclosure, a "search query" may include, but is not limited to, text that can be entered and searched using a search engine (eg, keywords, words, phrases, sentences, etc.). not. For example, a search query may contain text that the user enters through the input UI of a search program such as a web browser or search application, or may be selected by clicking on any one of the search term lists provided by the user in the search program. Can contain text that can be done. In another example, the search term is not limited to text and may include text or information that can be extracted from multimedia content such as images, video, audio, voice and the like.

In the present disclosure, the "query intent" can indicate the purpose for which the user intends to search by the search query or the target information that the user seeks to obtain substantially by searching by the search query. For example, the query intent can be expressed or extracted through at least a portion of the keywords, words or phrases contained in the search query entered by the user. For example, the purpose of a user's attempt to search with the search query "recently popular songs" may include information about songs that have recently been heard or selected by the public (eg, within the last week or month). can. Such query intent can be expressed by one or more of the keywords included in the search query or other keywords, symbols, numbers, identifiers, etc. related to the keyword.

In the present disclosure, a "query pattern" can be a keyword or information indicating the query intent of a search query. For example, the query pattern of the search query "recently popular songs" can be expressed by the keyword "recently". Further, in the present disclosure, the "query pattern type" may be information or a symbol indicating the type of the query pattern of the search query. For example, "recent", which is the query pattern of the search query "recently popular song", is a unique information or identifier that can express or identify it (for example, a 4-digit number in which the first digit bit is represented by 1). It can have a query pattern type expressed in binary "0x0001").

In the present disclosure, the "ranking factor" can indicate one or more factors that determine the ranking or ranking of search results and the like based on a search query. Ranking factors include the number of search keywords contained in search results that include various forms of content (eg, web documents containing text, images or videos), the number of user visits or clicks to the search results, and the search keywords. It can include, but is not limited to, various factors that influence the ranking of search results. For example, in a search query "recently popular song", the ranking factor associated with "recent" of the keyword indicating the query intent may be "up-to-date". Therefore, the ranking or ranking of the search results and the like by the search query can be determined by the time and date when the search results are generated, or the up-to-dateness of the information contained in the search results.

In the present disclosure, "snippet" is the content or document extracted from the content or document searched by the search query (eg, web page, document, text or video content, etc.) and exposed as a search result. Can be shown as a part of. Snippets can be automatically generated based on the content or documents searched by the search query. Specifically, snippets may be generated to highlight parts of content or documents that are highly relevant to a search query or search keyword, or to provide a preview or summary thereof. For example, in the case of a document searched by a search query, the snippet extracts a part of the body of the document to which the search keyword included in the search query is matched, and displays the keyword in the emphasized and exposed form in the part. Or it is displayed in the form of a representative explanation or summary prepared in advance for the document.

FIG. 1 is a diagram showing an example in which a user 100 obtains a search result for a search query through a screen 120 of a user terminal 110 according to an embodiment of the present disclosure. The screen 120 shown in FIG. 1 shows an example in which a user 100 executes a search application on a user terminal (for example, a smartphone) 110 and uses a search service. For example, the user 100 can input a search query into the search term input unit 122 located at the upper part of the search application screen to execute the search. Here, the search query can include one or more query intents of the user or one or more keywords indicating the search intent.

The user terminal 110 can display the contents searched by the search query input by the user 100 on the screen 120 in order from the contents corresponding to the higher ranking. In one embodiment, the user terminal 110 can preferentially display the content ranked higher according to the query intention of the user 100. For this purpose, the information processing system (not shown) that provides the content can receive the search query from the user terminal 110 and determine the query pattern type of the search query based on the query intent extracted from the search query. The information system determines the ranking of each of the multiple contents associated with the search query based on the query pattern type of the search query, and arranges at least one or more contents of the multiple contents based on the determined ranking. The output can be made through the user terminal 110. Here, the plurality of contents related to the search query may be the contents matched with one or more keywords included in the search query. For example, a plurality of contents associated with a search query may be content containing one or more keywords contained in the search query. On the other hand, in order to determine the ranking of each of the plurality of contents based on the query pattern type of the search query, the information processing system determines each query pattern type of the plurality of contents in advance, and the query pattern corresponding to the content. You can label the type.

On the screen 120, as shown in the figure, extracted from the search query among the search results including the keywords (“dermatology”, “price”) included in the “dermatology price” of the search query entered by the user 100. Content that matches the "price" or "price information" of the query intention is ranked higher and can be displayed preferentially. For example, "[Dermatology water peeling at Gangnam station] Get skin management at the price of one meal!", "Dermatology acne extruding price, scars", which is the content that actually contains the price information of dermatology. "Real word-of-mouth of the treatment ointment" and "Price for removing dermatology from Suwon's A dermatology" are ranked high, and can be displayed on the user terminal 110 with priority over the content that does not include the price information of the dermatology.

The user terminal 110 can display one or more content links, titles, snippets, thumbnail images, hashtags, similar content links, and the like as search results on the screen. In one embodiment, the snippet displayed on the screen may be the part of the search result content that corresponds to the query intent. For this purpose, the information processing system can extract a plurality of snippets associated with each query pattern type for a plurality of contents in advance. After that, the information processing system can output the snippet related to the query pattern type of the search query from the plurality of snippets extracted in advance through the user terminal 110.

On the screen 120, as shown in the figure, when the user terminal 110 displays the content as a search result, the user terminal 110 can display the snippet corresponding to the query intention together among the plurality of snippets of the displayed content. For example, a snippet containing dermatological price information, that is, actual amount information, may be displayed in the entire text of the content displayed as a search result. In the whole text of each content displayed on the screen 120, the actual amount information "... but it does not reach 100,000 won ....", "... mid 200,000 won when proceeding in 4 times" The part including "..." and "... A dermatology 33,000 won for one year from within two months ..." can be displayed on the user terminal 110 as a snippet.

Therefore, the user 100 can preferentially obtain the content corresponding to the query intention of the user 100 as the search result, instead of the content simply matched with the keyword of the search query. Further, the user 100 can obtain a snippet including a part corresponding to the query intention of the user 100, instead of a snippet including a part that is simply keyword-matched to the search query in the entire text of the provided content. .. On the other hand, in FIG. 1, three contents are displayed through the screen 120 of the user terminal 110, but the present invention is not limited to this, and different numbers of contents may be displayed.

FIG. 2 is a schematic diagram showing a configuration in which a plurality of user terminals 210_1, 210_2, 210_3 according to an embodiment of the present disclosure are connected so as to be able to communicate with the information processing system 230. As shown in the figure, the plurality of user terminals 210_1, 210_2, 210_3 may be connected to the information processing system 230 to which the search service is provided via the network 220. In one embodiment, the information processing system 230 is a computer-executable program (eg, a downloadable application) associated with search service provision, etc., and one or more server devices capable of storing, providing, and executing data and / or. It can include a database and one or more distributed computer devices and / or distributed databases of a cloud computing service infrastructure.

The search service provided by the information processing system 230 may be provided to the user via a search application, a mobile browser application, a web browser, or the like installed in each of the plurality of user terminals 210_1, 210_2, 210_3. For example, the information processing system 230 can provide information corresponding to a search query received from user terminals 210_1, 210_2, 210_3 via a search application or the like, or execute a corresponding process.

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

In FIG. 2, a mobile phone terminal 210_1, a tablet terminal 210_2, and a PC terminal 210_3 are shown as examples of user terminals, but the user terminals 210_1, 210_2, and 210_3 are not limited to this, and wired and / or wireless communication is possible. It can be any computer device on which a search application, mobile browser application or web browser can be installed and run. For example, user terminals include smartphones, mobile phones, navigation systems, desktop computers, laptop computers, digital broadcasting terminals, PDAs (Personal Digital Assistants), PMPs (Portable Multimedia Players), tablet PCs, AI speakers (artificial intelligence speakers), etc. It can include a game console, a wearable device, an IoT (internet of things) device, a VR (virtual reality) device, an AR (augmented reality) device, a set top box, and the like. .. Further, in FIG. 2, it is shown that the three user terminals 210_1, 210_2, and 210_3 communicate with the information processing system 230 via the network 220, but the present invention is not limited to this, and different numbers of user terminals are transmitted via the network 220. It can also be configured to communicate with the information processing system 230.

According to one embodiment, the information processing system 230 can receive a search query or a request for a search query from a plurality of user terminals 210_1, 210_2, 210_3. In response to the search query or request received in this way, the information processing system 230 can provide at least one or more contents of the plurality of contents related to the search query to the plurality of user terminals 210_1, 210_2, 210_3. For example, the information processing system 230 can provide the plurality of user terminals 210_1, 210_2, 210_3 with ranking information and snippets of each of the plurality of contents determined based on the query intention of the search query.

FIG. 3 is a block diagram showing an internal configuration of a user terminal 210 and an information processing system 230 according to an embodiment of the present disclosure. The user terminal 210 can indicate an arbitrary computer device capable of executing a search application, a mobile browser application, a web browser, etc., and capable of having / wireless communication. For example, the mobile phone terminal 210_1 and the tablet terminal in FIG. 210_2, PC terminal 210_3, and the like can be included. As shown in the figure, the user terminal 210 can include a memory 312, a processor 314, a communication module 316 and an input / output interface 318. Similarly, the information processing system 230 may include a memory 332, a processor 334, a communication module 336 and an input / output interface 338. As shown in FIG. 3, the user terminal 210 and the information processing system 230 can be configured so that information and / or data can be communicated via the network 220 by using the respective communication modules 316 and 336. Further, the input / output device 320 is configured to input information and / or data to the user terminal 210 and output information and / or data generated from the user terminal 210 via the input / output interface 318. can.

The memory 312, 332 can include any non-temporary computer-readable recording medium. According to one embodiment, the memory 312, 332 is permanent such as RAM (random access memory), ROM (read only memory), disk drive, SSD (solid state drive) and flash memory (flash memory). It can include a permanent mass storage device. As another example, a permanent large capacity storage device such as a ROM, SSD, flash memory, disk drive, etc. is included in the user terminal 210 or the information processing system 230 as a separate permanent storage device separate from the memory. be able to. Further, the memory 312 and 332 may store an operating system and at least one program code (for example, a code for a search application installed and driven in the user terminal 210).

Such software components can be loaded from a computer-readable recording medium separate from the memory 312, 332. Such a separate computer-readable recording medium can include such a recording medium that can be directly connected to the user terminal 210 and the information processing system 230, and may include, for example, a floppy drive, a disk, a tape, or a DVD / CD. -Can include computer-readable recording media such as ROM drives and memory cards. As another example, software components and the like can be loaded into memory 312, 332 via a communication module instead of a computer-readable recording medium. For example, at least one program may be loaded into memory 312,332 based on a computer program installed by a file distribution system that distributes a developer or application installation file with a file provided via network 220. can.

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

The communication modules 316 and 336 can provide a configuration and a function for the user terminal 210 and the information system 230 to communicate with each other via the network 220, and the user terminal 210 and / or the information system 230 can be used by another user. It is possible to provide a configuration or a function for communicating with a terminal or another system (for example, a separate cloud system). As an example, a request or data (for example, a search query or a search request) generated by a program code stored in a recording device such as a memory 312 by the processor 314 of the user terminal 210 can be sent to a network under the control of the communication module 316. It may be transmitted to the information processing system 230 via 220. On the contrary, the control signal or instruction provided by the control of the processor 334 of the information processing system 230 may be received by the user terminal 210 via the communication module 336 and the network 220 and via the communication module 316 of the user terminal 210. For example, the user terminal 210 can receive information about a plurality of contents and snippets related to a search query from the information processing system 230 via the communication module 316.

The input / output interface 318 may be a means for an interface with the input / output device 320. As an example, input devices include devices such as cameras, keyboards, microphones, mice, etc., including audio and / or image sensors, and output devices, such as displays, speakers, haptic feedback devices, etc. Such devices can be included. As another example, the input / output interface 318 may be a means for an interface with a device such as a touch screen, which has a single integrated configuration and function for performing inputs and outputs. For example, a service screen configured using information and / or data provided by an information processing system 230 or another user terminal when the processor 314 of the user terminal 210 processes an instruction of a computer program loaded in the memory 312. Etc. may be displayed on the display via the input / output interface 318. In FIG. 3, it is shown that the input / output device 320 is not included in the user terminal 210, but the present invention is not limited to this, and the input / output device 320 can be integrally configured with the user terminal 210. Further, the input / output interface 338 of the information processing system 230 is for an interface with a device (not shown) for input or output that can be connected to the information processing system 230 or included in the information processing system 230. Can be a means of. In FIG. 3, the input / output interfaces 318 and 338 are shown as elements separately configured from the processors 314 and 334, but the input / output interfaces 318 and 338 are configured to be included in the processors 314 and 334. You can also do it.

The user terminal 210 and the information processing system 230 can include more components than those shown in FIG. However, it is not necessary to articulate most of the prior art components. According to one embodiment, the user terminal 210 can be embodied to include at least a part of the above-mentioned input / output device 320. Further, the user terminal 210 can further include other components such as a transceiver, a GPS (Global Positioning system) module, a camera, various sensors, a database, and the like. For example, when the user terminal 210 is a smartphone, it can include components generally possessed by the smartphone, for example, an accelerometer, a gyro sensor, a camera module, various physical buttons, a button using a touch panel, an input / output port, and the like. Various components such as accelerometers for vibration can be further embodied in the user terminal 210. According to one embodiment, the processor 314 of the user terminal 210 can be configured to operate an application or the like that provides a search service. At this time, the code related to the application and / or the program can be loaded into the memory 312 of the user terminal 210.

When a program for an application or the like that provides a search service is run, the processor 314 is such as a camera and microphone including a touch screen, keyboard, audio sensor and / or image sensor coupled with an input / output interface 318. The text, image, video, audio and / or operation input or selected by the input device can be received, and the received text, image, video, audio and / or operation, etc. can be saved in the memory 312, or the communication module. It can be provided to the information processing system 230 via the 316 and the network 220. For example, processor 314 can receive user input for a search query.

In one embodiment, the processor 314 receives user input including a search query or search request entered on an application or a web browser that provides a search service by an input device, and sends such a search query or search request to a network. It can be provided to the information processing system 230 via the 220 and the communication module 316. For example, the processor 314 can receive user input for a search query input to the search term input unit by an input device such as a touch screen or a keyboard, and the received search query is transmitted via the communication module 316 and the network 220. It can be provided to the information processing system 230. As another example, the processor 314 can receive user input including a search query by an input device such as a touch screen, mouse and keyboard, and forwards the search query to the information processing system 230 in response to such user input. can.

The processor 314 of the user terminal 210 can be configured to manage, process and / or store information and / or data received from an input device, another user terminal, an information processing system 230 and / or a plurality of external systems. The information and / or data processed by the processor 314 can be provided to the information processing system 230 via the communication module 316 and the network 220. The processor 314 of the user terminal 210 can transfer and output information and / or data to the input / output device 320 via the input / output interface 318. For example, the processor 314 can display the received information and / or data on the screen of the user terminal. In one embodiment, the processor 314 can display at least one or more contents of the plurality of contents on the screen based on the ranking of each of the plurality of contents related to the search query reflecting the query intention. For example, the processor 314 can sequentially arrange a plurality of contents related to the search query received from the memory 312 and / or the information processing system 230 from the contents corresponding to the higher ranking and display them on the screen 120. In another embodiment, the processor 314 can display one or more content links, snippets, thumbnail images, hashtags, and the like on the screen. For example, the processor 314 can display on the screen a snippet corresponding to the query intent received from the memory 312 and / or the information processing system 230 for one or more contents. In one embodiment, the processor 314 can highlight and display some areas associated with one or more query pattern types in the snippet. For example, the processor 314 can display a snippet on the screen with some areas associated with one or more query pattern types highlighted by at least one of bold and background processing.

The processor 334 of the information processing system 230 can be configured to manage, process and / or store information and / or data received from the plurality of user terminals 210 and / or the plurality of external systems. The information and / or data processed by the processor 334 can be provided to the user terminal 210 via the communication module 336 and the network 220. In one embodiment, the processor 334 of the information processing system 230 has one or more query pattern types of search queries based on one or more query intents extracted from the search queries received from the user terminal 210. And can determine the ranking of each of the plurality of contents associated with the search query based on one or more query pattern types. For this purpose, the processor 334 can extract one or more keywords corresponding to one or more query intents from the search query and determine one or more query pattern types corresponding to the extracted one or more keywords. Alternatively, processor 334 can extract one or more query intents from a search query by Natural Language Processing (NLP) and determine one or more query pattern types for the extracted one or more query intents. ..

In one embodiment, one or more query pattern types are represented by one or more bits, where one or more bits are elements that give weights to determine the ranking of multiple contents. Can be pre-matched with the ranking factor of. In this case, the processor 334 calculates the ranking score of each of the plurality of contents related to the search query based on one or more ranking factors, and the plurality of related contents to the search query based on the ranking score of each of the plurality of contents. You can determine the ranking of each of the contents of.

In one embodiment, the processor 334 can pre-label the query pattern types of a plurality of contents contained in the content DB. For example, processor 334 can label a query pattern type determined based on at least one of text, text structure, attachments and images contained in a plurality of contents. At this time, the processor 334 can determine the ranking of each of the plurality of contents related to the search query based on the query pattern type of the plurality of contents and one or more ranking factors.

In one embodiment, the processor 334 can preliminarily extract at least one or more snippets from each of the plurality of contents included in the content DB. For example, processor 334 can analyze / analyze at least one of the text, text structure, attachments and images contained in each of the plurality of contents and extract at least one or more snippets from each of the plurality of contents. .. Also, the processor 334 is one or more associated with each query pattern type of the plurality of contents determined based on at least one of the text, text structure, attachments and images contained in each of the plurality of contents. Snippets can be extracted.

The processor 334 of the information processing system 230 outputs information and / or data processed by an output device such as a display output device (for example, a touch screen or a display) or a voice output device (for example, a speaker) of the user terminal 210. Can be configured to output. In one embodiment, the processor 334 can be configured to output at least one or more of the plurality of contents associated with the search query through the user terminal 210 based on the determined ranking. For example, the processor 334 can allow the user terminal 210 to sequentially arrange and output a plurality of contents related to the search query from the contents corresponding to the higher ranking.

In one embodiment, the processor 334 can be configured to output a snippet of at least one or more content of the plurality of content associated with the search query through the user terminal 210 based on the determined ranking. For example, if processor 334 extracts one or more snippets associated with each query pattern type of a plurality of contents, processor 334 extracts snippets associated with one or more query pattern types of one or more snippets. It can be output through the user terminal. Also, the processor 334 can output at least a portion of one or more snippets through the user terminal with a default priority for one or more query pattern types. In one embodiment, the processor 334 can highlight and output some areas associated with one or more query pattern types in the snippet. For example, the processor 334 can output a snippet with some areas associated with one or more query pattern types highlighted by at least one of bold and background processing.

FIG. 4 is a detailed block diagram of the processor 334 of the information processing system according to the embodiment of the present disclosure. As shown in the figure, the processor 334 includes a query pattern type determination unit 410, a ranking determination unit 420, and a content provision unit 430 by query intention classification, and can be connected to the content DB 440. Here, the content DB 440 can be included in the internal storage device of the information processing system, or can be included in the external storage device connected to the information processing system. Information about a plurality of contents can be stored in the content DB 440. For example, the content DB 440 can store a plurality of contents or links to the plurality of contents, one or more snippets extracted from each of the plurality of contents, thumbnail images, and the like.

The query pattern type determination unit 410 based on the query intent classification can receive a search query from the user terminal and extract one or more query intents from the received search query. In one embodiment, the query pattern type determination unit 410 based on the query intention classification can extract one or more keywords corresponding to one or more query intentions from the search query. For example, the query pattern type determination unit 410 based on the query intent classification can extract one or more of the keywords and / or similar keywords included in the following Table 1 from the search query, whereby one or more query intents from the search query. Can be extracted. That is, the query pattern type determination unit 410 based on the query intent classification extracts the keywords "recently" and the keywords "catalog" from the search query "recent Busan's popular gourmet restaurant inventory", thereby extracting from the search query. The query intent for "time point trend" and "item recommendation" can be extracted, respectively.

In another embodiment, the query pattern type determination unit 410 based on the query intent classification can extract one or more query intents from the search query by natural language processing. For example, if the search query contains the sentence "Search the list of popular gourmet restaurants in Busan recently", the query pattern type determination unit 410 based on the query intention classification will perform syntax analysis / analysis or semantic analysis for the sentence. / By executing analysis or the like, it can be derived that the query intent indicated by the above sentence includes "time point trend" and "item recommendation". In one embodiment, the query pattern type determination unit 410 by query intent classification is configured to derive the corresponding query intent for an input sentence or phrase, such as a natural language processing model, a probabilistic statistical model, and an artificial neural network. Any one of the models can be included.

The query pattern type determination unit 410 based on the query intent classification can determine one or more query pattern types of a search query based on one or more query intents extracted from the search query. Here, one or more query pattern types are represented by one or more bits, and one or more query pattern types can be pre-matched with one or more query intents. For example, as shown in Table 2 below, the query intent and query pattern type can be matched in advance.

For example, based on the "time trend" and "item recommendation" of the query intent extracted from the search query "List of popular gourmet restaurants in Busan recently", the query pattern type of the search query corresponds to each query intent "0". It can be determined as "x0001" and "0x0100". As an alternative, such multiple query pattern types can be merged and represented as "0x0101".

After that, the ranking determination unit 420 can determine the ranking of each of the plurality of contents related to the search query based on one or more query pattern types determined by the query pattern type determination unit 410 by the query intention classification. Here, information on a plurality of contents related to the search query can be received from the content DB 440. In one embodiment, the ranking determination unit 420 determines one or more ranking factors, calculates the ranking score of each of the plurality of contents related to the search query based on the one or more ranking factors, and performs the plurality of contents. Based on each ranking score of, the ranking of each of the plurality of contents related to the search query can be determined. Here, one or more bits of one or more query pattern types can be pre-matched with one or more ranking factors, as shown in Table 3 below, which determines the ranking of a plurality of contents. Can be an element that gives a weighted value to.

For example, when the query pattern type determined by the query pattern type determination unit 410 by the query intention classification is "0 × 0101", the ranking determination unit 420 performs the corresponding "up-to-dateness" and "inventory type information". It can be determined as a ranking factor. After that, the ranking determination unit 420 can give a weighted value to the ranking score of the content related to the "up-to-dateness" of the ranking factor among the plurality of contents. Further, the ranking determination unit 420 can give a weighted value to the ranking score of the content related to the "catalog type information" of the ranking factor among the plurality of contents. The ranking determination unit 420 can determine the ranking of each of the plurality of contents based on the finally calculated ranking score. Therefore, the score of the content having the ranking factor "up-to-date" and / or the "inventory information" can be higher than the score of the content without the "up-to-date" and "inventory information", and the search result. Can be ranked high among them. Here, the ranking determination unit 420 can give different weight values depending on the degree of association (degree) of each of the plurality of contents with respect to the ranking factor. For example, in the case of the "up-to-date" ranking factor, different weighted values can be given depending on the degree of up-to-dateness. That is, it was related to the "up-to-date" given to the ranking score of the content uploaded one hour ago, rather than the weighted value related to the "up-to-date" given to the ranking score of the content uploaded one day ago. The weighted value may be larger.

The content providing unit 430 provides the user terminal with at least one or more contents of the plurality of contents, and based on the ranking determined by the ranking determination unit 420, at least one or more of the plurality of contents related to the search query. You can make it output content. That is, the content providing unit 430 can be made to sequentially arrange and output the content having the highest ranking among the plurality of contents to the user terminal. Therefore, the user can preferentially obtain the content corresponding to the query intention among the plurality of contents related to the search query.

Tables 1 to 3 described above show an example of the correspondence between "query intent-keyword", "query intent-query pattern type", and "query pattern type-ranking factor", respectively, but are limited thereto. is not. Therefore, such correspondences can be newly added or extended by search queries or content analysis / analysis. For example, "query intent" and "keyword" can be extended by adding new query intent classifications and new keywords, respectively. Further, as described above, the query pattern type can be expressed by a 4-digit binary number, but is not limited to this. For example, it can be represented by a binary number with different digits depending on the total number of query pattern types.

FIG. 5 is a detailed block diagram of the processor 334 of the information processing system according to another embodiment of the present disclosure. As shown in the figure, the processor 334 can include a query pattern type determination unit 410, a ranking determination unit 420, a content provision unit 430, and a content DB 440 by query intention classification. Further, the processor 334 can further include a content labeling unit 510, a snippet extraction unit 520, and a snippet providing unit 530. Since the query pattern type determination unit 410, the ranking determination unit 420, the content provision unit 430, and the content DB 440 by the query intention classification of the processor 334 include the same or similar configurations and functions as the corresponding components of the processor 334 shown in FIG. In the following, duplicate explanations will be omitted.

The content labeling unit 510 can label the query pattern types of a plurality of contents stored in the content DB 440. In one embodiment, the content labeling unit 510 is based on at least one of a text, a text structure (eg, a table structure, a ranking structure, a list structure, etc.), an attachment, and an image contained in each of a plurality of contents. The determined query pattern type can be labeled for each of multiple contents. For example, the content labeling unit 510 analyzes / analyzes the text and list structure contained in the plurality of contents, and sets the query pattern type “0 × 0100” to the content having the catalog type information among the plurality of contents. Can be labeled.

In one embodiment, when labeling a query pattern type based on an attachment contained in a plurality of contents, the content labeling unit 510 uses the attachment extension name, the attachment title, and the attachment generation date. And the information contained in the attached file can be analyzed / analyzed to determine the query pattern type and label it. For example, in the case of content to which a file with the extension ".mp3" is attached, a query pattern type corresponding to "voice information" or "multimedia information" can be labeled. In another embodiment, when labeling a query pattern type based on an image contained in a plurality of contents, the content labeling unit 510 analyzes / analyzes text information, image information, etc. contained in the image. You can determine and label the query pattern type. For example, in the case of content to which an image of "score" is attached, a query pattern type corresponding to "score information", "music information", "multimedia information", or the like can be labeled.

The task of labeling the query pattern types of a plurality of contents is performed before the search result or the content is extracted for the search query. In addition, the task of labeling the query pattern types of multiple contents is based on an automatic labeling technique that utilizes a probabilistic statistical model or an artificial neural network model configured to determine the query pattern type for each of the plurality of contents. Will be done. As an alternative, the content labeling unit 510 can label the query pattern types of a plurality of contents by the information input to the information processing system by the human worker directly performing the labeling work. The content labeling unit 510 can store the labeled query pattern type in the content DB 440 in relation to a plurality of contents.

Then, for the search query entered by the user, the ranking determination unit 420 can determine the ranking of each of the plurality of contents related to the search query based on the query pattern types of the plurality of contents and one or more ranking factors. .. For example, the ranking determination unit 420 can determine the ranking of each of the plurality of contents so that the content labeled with the query pattern type corresponding to the ranking factor is ranked higher among the plurality of contents. That is, when the ranking factor is "catalog type information", the ranking determination unit 420 determines that the content having the catalog type information labeled with "0 × 0100" in advance is ranked higher in the content. Each ranking can be determined.

The snippet extraction unit 520 can extract at least one or more snippets from each of the plurality of contents. In one embodiment, the snippet extractor 520 analyzes / analyzes at least one of the text, text structure, attachments and images contained in each of the plurality of contents, and at least one or more from each of the plurality of contents. Snippets can be extracted. For example, the snippet extractor 520 is one associated with each query pattern type of the plurality of contents determined based on at least one of the text, text structure, attachments and images contained in each of the plurality of contents. The above snippets can be extracted. Here, the snippet extraction unit 520 can extract, in the text of each of the plurality of contents, a portion that is the basis for labeling the query pattern type as a snippet related to the query pattern type. The snippet extraction unit 520 can store the extracted snippets in the content DB 440 in relation to a plurality of contents.

The snippet providing unit 530 can output a snippet of at least one or more contents of a plurality of contents related to the search query through the user terminal based on the determined ranking. In one embodiment, the snippet provider 530 can output snippets associated with one or more query pattern types of one or more snippets (ie, query pattern types of search queries) through a user terminal. For example, when the query pattern type determination unit 410 based on the query intent classification determines the query pattern type of the search query as "0 × 0001" corresponding to the "time-time trend" of the query intent extracted from the search query, the snippet is provided. The unit 530 can output the snippet related to "0 × 0001" through the user terminal.

In one embodiment, the snippet provider 530 can output at least a part of one or more snippets for one or more query pattern types through a user terminal by a predetermined priority. For example, when the query pattern type determination unit 410 based on the query intention classification determines the query pattern type of the search query as "0 × 0101" which is a combination of "0 × 0001" and "0 × 0100", the snippet providing unit 530. Can output snippets related to "0x0100" prioritized by a default priority through the user terminal.

In one embodiment, the snippet provider 530 can highlight and output some areas associated with one or more query pattern types in the snippet. For example, the snippet provider 530 can output a partial area associated with one or more query pattern types in the snippet by emphasizing it with at least one of bold font processing and background processing.

FIG. 6 is a flow chat showing a search result providing method 600 that reflects the query intention according to the embodiment of the present disclosure. In one embodiment, the search result providing method 600 reflecting the query intention is performed by a processor (for example, at least one processor of a user terminal and / or an information processing system). As shown in the figure, the search result providing method 600 is started by the processor receiving a search query from the user terminal (S610).

The processor can then determine one or more query pattern types for the search query based on the one or more query intents extracted from the search query (S620). In one embodiment, the processor can extract one or more query intents from one or more keywords contained in a search query and determine one or more query pattern types for one or more query intents. In another embodiment, the processor extracts one or more query intents from a search query by natural language processing (eg, Natural Language Understanding, etc.) and one or more for one or more query intents. You can determine the query pattern type. Here, one or more query pattern types are represented by one or more bits, where one or more bits are one or more ranking factors that are factors that give weights to determine the ranking of multiple contents. Can be pre-matched with.

The processor can then determine the ranking of each of the plurality of contents associated with the search query based on one or more query pattern types (S630). In one embodiment, the processor calculates the ranking score of each of the plurality of contents associated with the search query based on one or more ranking factors, and associates with the search query based on the ranking score of each of the plurality of contents. The ranking of each of multiple contents can be determined. In another embodiment, the processor can determine the ranking of each of the plurality of contents for a search query based on the query pattern type of the plurality of contents and one or more ranking factors. To this end, the processor can pre-label multiple content query pattern types. For example, you can label a query pattern type that is determined based on at least one of the text, text structure, attachments, and images contained in the content. When new content is uploaded to the content DB, the processor can label the query pattern type of the content in real time. As an alternative, the processor can label the query pattern type of new content stored in the content DB at different intervals. In one embodiment, the processor can output at least one or more contents of a plurality of contents related to the search query through the user terminal based on the determined ranking.

The processor can extract at least one or more snippets from each of the plurality of contents. For example, the processor can pre-extract at least one or more snippets from each of the plurality of contents and store them in the content DB. Alternatively, the processor can extract at least one or more snippets from each of the plurality of contents associated with the search query in real time when the search query is received. In one embodiment, the processor analyzes / analyzes at least one of the texts, text structures, attachments and images contained in each of the plurality of contents and produces at least one or more snippets from each of the plurality of contents. Can be extracted. For example, the processor may have one or more snippets associated with each query pattern type of the content determined based on at least one of the text, text structure, attachments and images contained in each of the content. Can be extracted.

Based on the determined ranking, the processor can output a snippet of at least one content of a plurality of contents related to the search query through the user terminal. In one embodiment, the processor can output snippets associated with one or more query pattern types of one or more snippets through a user terminal. In another embodiment, the processor can output at least a portion of one or more snippets through a user terminal for one or more query pattern types with a default priority.

In one embodiment, the processor can highlight and output some areas associated with one or more query pattern types in the snippet. For example, in a snippet, the processor can output some areas associated with one or more query pattern types with at least one of bold and background processing. Alternatively, the processor can output in the snippet some areas associated with one or more query pattern types, highlighted by a cataloged array. In another embodiment, the processor can output a snippet in which at least one of the attachments and images is highlighted among the plurality of contents associated with the search query.

FIG. 7 is a diagram showing an example of providing a search result reflecting the query intention of the search query according to the embodiment of the present disclosure. The processor can receive a search query from a user terminal and determine one or more query pattern types for the search query based on one or more query intents extracted from the search query. In one embodiment, the processor can extract one or more keywords corresponding to one or more query intents from a search query and determine one or more query pattern types corresponding to one or more keywords. The processor calculates the ranking score of each of the plurality of contents related to the search query based on the ranking factor corresponding to the determined query pattern type, and each of the plurality of contents based on the ranking score of each of the plurality of contents. Can determine the ranking of. Here, the ranking factor may be an element that gives a weighted value when determining the ranking of each of the plurality of contents. The processor can output one or more contents of a plurality of contents to the user terminal based on the ranking determined in this way. For example, a plurality of contents can be sequentially arranged from the contents of the higher ranking and output to the user terminal. That is, the content corresponding to the upper ranking can be output with priority over the content corresponding to the lower ranking.

As shown in the figure, the processor can receive the "today's fortune-telling" of the search query input to the search term input unit 702 of the screen of the user terminal. After that, the processor extracts the keyword "today" corresponding to the "time trend" of the query intention from the received "fortune-telling of today", and sets the query pattern type to the query pattern type "today" corresponding to the keyword "today". It can be determined as "0 x 0001". The processor calculates the ranking score of each of the multiple contents related to the "fortune-telling of today" of the search query based on the "up-to-dateness" of the ranking factor corresponding to the determined query pattern type "0x0001". , The ranking of each of the plurality of contents can be determined based on the ranking score of each of the plurality of contents. In one embodiment, the processor calculates the ranking score by giving a weighted value to each ranking score of the plurality of contents according to the "up-to-dateness" of the content, and based on the calculated ranking score, each of the plurality of contents. You can decide the ranking. In this case, the processor can give different weights to each of the plurality of contents depending on the degree of "up-to-date" of the contents. That is, the processor can give a larger weighted value to the content with high "up-to-date" than to the content with relatively low "up-to-date".

As shown in the figure, the first content "Today's fortune-telling (September 16th) constellation fortune-telling" 710 and the second content "Today" uploaded one hour ago with very high "up-to-dateness". Fortune-telling, 16th day of September (Wednesday) 720 and the third content uploaded 3 hours ago, "Fortune-telling at lunch, fortune-telling at Kyodai + Today's fortune-telling" 730 are relatively better. Content that is less up-to-date (eg, content uploaded a day or a month ago) (not shown) may be ranked higher and output preferentially. In addition, the first content 710 and the second content 720 uploaded one hour ago are ranked higher than the third content 730 uploaded three hours ago, and the first content 710 and the second content 720 are ranked higher. The second content 720 and the third content 730 may be arranged in this order and displayed on the screen 700.

FIG. 8 is a diagram showing an example of providing a search result reflecting the query intention of the search query according to another embodiment of the present disclosure. The processor can pre-label multiple content query pattern types. In one embodiment, a query pattern type determined based on at least one of text, text structure, attachments and images contained in a plurality of contents can be labeled. For example, the query pattern type can be labeled by analyzing / analyzing the text contained in a plurality of contents and the structure in which the text is arranged. That is, the processor can label the query pattern type "0 x 0100" corresponding to the "catalog type information" for the content in which the texts are arranged in the structure or structure (layout) of the catalog form. The first content "List of popular Busan gourmet restaurants 5 that everyone likes" 810 and the second content "List of popular Busan gourmet restaurants to go to in summer 14, Seomyeon, Lotus" output on the screen 800 of FIG. Since each of "Yeonsan-dong, Haeundae" 820 contains a list of popular gourmet restaurants, that is, "catalog type information", "0 x 0100" can be labeled in advance by a processor and stored in the content DB.

Based on the query pattern type of the plurality of pre-labeled contents and the ranking factor determined by the search query, the processor can determine the ranking of each of the plurality of contents associated with the search query. For example, the processor can determine the ranking of each of the plurality of contents so that the content labeled with the query pattern type corresponding to the ranking factor is ranked higher among the plurality of contents. As shown in the figure, the processor can receive the "List of popular gourmet restaurants in Busan" of the search query input to the search term input unit 802 of the screen 800 of the user terminal. After that, the processor can analyze / analyze the intent of "item recommendation" from the received "list of popular gourmet restaurants in Busan" and determine the intent of the search query as the query pattern type "0x0100". Here, the processor is related to the search query "Busan's popular gourmet store inventory" based on the "catalog type information" of the ranking factor corresponding to the query pattern type "0 x 0100" and the query pattern types of multiple contents. The ranking score of each of the plurality of contents is calculated, and the ranking of each of the plurality of contents can be determined based on the calculated ranking score. That is, the processor can give a weighted value to the ranking points of the first content 810 and the second content 820 including the "catalog type information" labeled "0 x 0100" in advance, whereby the first content The 810 and the second content 820 are ranked higher in the plurality of contents and can be output preferentially.

The processor can preliminarily extract at least one or more snippets from each of the plurality of contents. In one embodiment, the processor analyzes / analyzes at least one of the texts, text structures, attachments and images contained in each of the plurality of contents and produces at least one or more snippets from each of the plurality of contents. Can be extracted. For example, the processor may have one or more snippets associated with each query pattern type of the content determined based on at least one of the text, text structure, attachments and images contained in each of the content. Can be extracted. Here, one or more snippets associated with each query pattern type of the plurality of contents may be a part on which the query pattern type is labeled in the body of each of the plurality of contents.

The processor queries each of the plurality of contents determined based on at least one of the text, the text structure, the attachment and the image contained in each of the first content 810 and the second content 820 of FIG. One or more snippets associated with the type "0x0100" can be extracted. That is, when labeling the query pattern types of the first content 810 and the second content 820, the query pattern type "0 × 0100" is labeled in the body of each content. The part including "catalog type information" can be extracted as a snippet related to "0 × 0100". Similarly, if the first content 810 and / or the second content 820 are labeled together with a different query pattern type "0x0010" other than "0x0100", the query pattern type "0". The different parts on which "x0010" is labeled can be extracted as snippets associated with the query pattern type "0x0010". Therefore, the processor can extract multiple snippets that differ according to the query pattern type for one content.

Based on the determined ranking, the processor can output a snippet of at least one content of a plurality of contents related to the search query through the user terminal. In one embodiment, the processor can output snippets associated with one or more query pattern types of one or more snippets (ie, query pattern types of search queries) through a user terminal. For example, in the snippets of the first content 810 and the second content 820, it was related to the query pattern type "0 x 0100" of the search query "List of popular gourmet restaurants in Busan" input to the search term input unit 802. The part including the "catalog type information" of the snippet can be output through the user terminal.

When the snippet is uniformly extracted and output by keyword matching with the search query as in the past, the keywords "Busan", "Popular gourmet restaurant", and "Catalog" are simply included in the body of the content. The part (for example, the introductory part of the text) is output as a snippet, but according to the embodiment of the present disclosure, the part actually including the "popular gourmet store catalog" (that is, the catalog type information) is output as a snippet. Therefore, the user can obtain a part corresponding to the query intention such as the content as a snippet.

FIG. 9 is a diagram showing an example of providing a search result reflecting the query intention of the search query according to the other embodiment of the present disclosure. The processor can label the query pattern type determined based on at least one of the text, text structure, attachments and images contained in the content. In one embodiment, if the processor labels an attachment based on an attachment contained in multiple contents, the processor may include the attachment extension name, attachment title, attachment generation date, and attachment. The query pattern type can be determined by analyzing / analyzing the content contained in the attached file, and the determined query pattern type can be labeled in the content including the attached file. In another embodiment, when labeling a query pattern type based on an image contained in a plurality of contents, the processor analyzes / analyzes the text information, the image information, etc. contained in the image to obtain the query pattern type. It can be determined and the content containing the image can be labeled with the determined query pattern type.

The first content "I U-Let's play a love poem on a guitar (easy-to-play version including a guitar chord score)" 910 output on the screen 900 can include an attachment. In this case, the processor sets the query pattern type of the first content 910 to "score" based on the extension ".pdf" of the attachment of the first content 910, the title "guitar chord score of love poem", and the like. It can be labeled as "0x1000" of the query pattern type corresponding to "information" or "multimedia information". On the other hand, the second content "[melody] i U-love poetry score" 920 output to the screen 900 can include an image. In this case, the processor analyzes / analyzes the image of the second content 920 and recognizes texts such as "love poem", "lyrics", "writer", and "musical notes", "five-line paper". , "Sheet music image", etc., the query pattern type of the second content 920 is labeled as "0x1000", which is the query pattern type corresponding to "Sheet music information" or "Multimedia information". Can be attached.

As shown in the figure, the processor can receive the "score of the love poem of I U" of the search query input to the search term input unit 902 of the screen 900 of the user terminal. After that, the processor extracts the keyword "score" from the received "score of love poem of IU" and sets the query pattern type to "0x1000" of the query pattern type corresponding to the keyword "score". I can decide. Here, the processor is based on each of the plurality of contents based on the "score information" or "multimedia information" of the ranking factor corresponding to the query pattern type of the plurality of contents and the query pattern type of the search query "0 x 1000". The ranking score of is calculated, and the ranking of each of a plurality of contents can be determined. That is, the processor can give a weighted value to the ranking scores of the first content 910 and the second content 920 labeled "0x1000", whereby the first content 910 and the second content 920 can be assigned a weighted value. It can be ranked high among a plurality of contents and can be output preferentially.

FIG. 10 is a diagram showing an example of providing snippets that differ depending on the query intent of the search query according to the embodiment of the present disclosure. In one embodiment, the processor analyzes / analyzes at least one of the texts, text structures, attachments and images contained in each of the plurality of contents and produces at least one or more snippets from each of the plurality of contents. Can be extracted. For example, the processor may have one or more snippets associated with each query pattern type of the content determined based on at least one of the text, text structure, attachments and images contained in each of the content. Can be extracted. Here, one or more snippets associated with each query pattern type of the plurality of contents may be a part on which the query pattern type is labeled in the body of each of the plurality of contents.

For example, the processor analyzes / analyzes at least one of the text, text structure, attached file, and image contained in the content "A car release information (release date, price)" 1014, 1034, and the content 1014. 1034 can be labeled with the query pattern type "0x10000" corresponding to "time information" and the query pattern type "0x000010" corresponding to "price information". At this time, the processor can extract the snippet associated with the query pattern type "0x10000" and the snippet associated with the query pattern type "0x000010" from the content. That is, in the text of the contents 1014 and 1034, "... the release date of the A car is September 15 after the 2020 motor show (May 29), and ..." including "time information". Is extracted as a snippet 1016 related to the query pattern type "0 x 10000", and includes "price information" "... from the middle of the minimum price of 40 million won to the maximum of 60 million won ..." Can be extracted as a snippet 1036 associated with the query pattern type "0x000010".

The processor can output snippets associated with one or more query pattern types of one or more snippets (ie, query pattern types of search queries) through the user terminal. For example, when the processor receives the "release date of car A" of the search query input to the search term input unit 1012 of the first screen 1010, among the snippets of the content 1014, the search query "release of car A". The snippet 1016 related to the query pattern type "0 x 10000" of "day" can be output through the user terminal. On the other hand, when the processor receives the "price of car A" of the search query input to the search term input unit 1032 of the second screen 1030, among the snippets of the content 1034, the search query "of car A" The snippet 1036 associated with "0x00010" of the "price" query pattern type'can be output through the user terminal. Therefore, as shown in the first screen 1010 and the second screen 1030, the same content 1014 as the search result for the "release date of the A car" in the search query and the search result for the "price of the A car" in the search query, Even if 1034 is output, different snippets 1016 and 1036 can be output.

FIG. 11 is a diagram illustrating an example of providing snippets 1110, 1120, 1130 in which areas related to the query intent of the search query according to an embodiment of the present disclosure are highlighted. The processor can highlight and output some areas associated with one or more query pattern types in the snippet. That is, for the user's readability, a part of the snippet that matches the user's query intention (for example, an area containing the target information desired by the user) can be emphasized and output to the user terminal. For example, the processor can output some areas associated with one or more query pattern types in the snippet with at least one of bold and background processing.

As shown in the figure, the first content snippet 1110 is "100,000 won" associated with the "dermatology price" query pattern type (ie, the query pattern type corresponding to the keyword "price") in the search query. The areas "" and "price" are highlighted by bold processing and displayed on the screen 1100. In addition, in the second content snippet 1120, the area of "mid 200,000 won when proceeding in 4 times" related to the query pattern type of "dermatology price" in the search query is emphasized by background processing. , Is displayed on the screen 1100. In addition, in the snippet 1130 of the third content, the area of "33,000 won in A dermatology for 1 year from 2 months" related to the query pattern type of "Dermatology price" in the search query is processed in the background. The area "33,000 won" is highlighted by the bold font processing and displayed on the screen 1100. Therefore, the user can get a readable snippet that emphasizes the area corresponding to the query intent.

FIG. 11 shows a bold font processing method or a background processing method as the snippet emphasis processing method, but the present invention is not limited to this, and various emphasis processing methods for improving user readability are used. For example, an emphasis processing method in which the text contained in the content is arranged in a catalog type and output can also be used. Further, FIG. 11 shows an example in which a snippet in which the text of the content is emphasized is output, but the present invention is not limited to this, and a snippet in which the attachment file or the image included in the content is emphasized is output. You can also do it.

The search result providing method that reflects the above-mentioned query intent may be provided as a computer-readable computer program for execution on a computer. The medium may be one that continuously stores a program that can be run on a computer, or that it is temporarily stored for execution or download. Also, the medium can be a variety of recording or storage means in the form of a single piece or a combination of multiple pieces of hardware, but is not limited to a medium directly connected to a computer system and is distributed over a network. It can exist. Examples of media include magnetic media such as hard disks, floppy disks and magnetic tapes, optical recording media such as CD-ROMs and DVDs, and magnetic-optical media such as floptical disks. Medium), and includes ROM, RAM, flash memory, etc., and includes those configured to store program command words. Further, examples of other media include a recording medium or a storage medium managed by an app store that distributes applications, a site that supplies or distributes various other software, a server, or the like.

The methods, actions or techniques of the present disclosure can be embodied by a variety of means. For example, such techniques can be embodied in hardware, firmware, software, or a combination thereof. It is understood by ordinary engineers that the various exemplary logical blocks, modules, circuits and algorithm steps described by the disclosures of the present application can be embodied in electronic hardware, computer software, or a combination of both. Should be. To articulate such mutual substitution of hardware and software, a variety of exemplary components, blocks, modules, circuits and steps have been generally described above in terms of their functionality. Whether such a function is embodied as hardware or software depends on the design requirements added to the specific application and the entire system. The usual technician may also embody the functionality described in various ways for each particular application, but such embodying shall not be construed as departing from the scope of the present disclosure. ..

In the realization of hardware, the processing units used to perform the technique are one or more ASICs, DSPs, digital signal processing devices (DSPDs), programmable logic devices (PLDs). ), Field programmable gate arrays (FPGAs), processors, controllers, microprocessors, microprocessors, electronic devices, and other electronic devices designed to perform the functions described in this disclosure. It can also be embodied within a unit, computer, or combination thereof.

Accordingly, the various exemplary logic blocks, modules and circuits described herein are general purpose processors, DSPs, ASICs, FPGAs and other programmable logic devices, discrete gates and transistor logic, discrete hardware components, or. , Can also be embodied or performed in any combination, such as those designed to perform the functions described herein. The general purpose processor can be a microprocessor, but as an alternative, the processor can be any conventional processor, controller, microprocessor, or state machine. The processor may also be embodied in a combination of computing devices, such as a DSP and microprocessor, multiple microprocessors, one or more microprocessors associated with a DSP core, or any other configuration combination. can.

In the realization of firmware and / or software, the techniques are RAM (random access memory), ROM (read-only memory), NVRAM (non-volatile random access memory), PROM (programmable read-only memory), EPROM (erasable). It can be embodied by instructions stored on a computer-readable medium such as programmable read-only memory), EEPROM (electrically erasable PROM), flash memory, CD (compact disc), magnetic or optical data storage devices, and the like. Instructions can be executed by one or more processors, which can be made to perform the particular mode of function described in the present disclosure.

Although the aforementioned embodiments are described as taking advantage of the aspects of the subject currently disclosed in one or more stand-alone computer systems, the present disclosure is not limited to this, such as networks and distributed computing environments. It can be embodied by any computing environment. Furthermore, the aspects of the subject matter in this disclosure can be embodied in multiple processing chips and devices, and storage can be similarly affected across multiple devices. Such devices may also include PCs, network servers and portable devices.

Although the present disclosure has been described by some embodiments herein, various modifications and modifications are made to the extent that they do not deviate from the present disclosure as understood by ordinary technicians in the technical field to which the invention of the present disclosure belongs. It is possible. It should also be understood that such modifications or alterations fall within the scope of the claims attached herein.

100 users 110 user terminals 120 screens

Claims (20)

In a method of providing search results that reflects the intent of a search query executed by at least one processor.
Steps to receive search queries from user terminals;
A step of determining one or more query pattern types for the search query based on one or more query intents extracted from the search query; and
A method of providing search results that reflects a query intent, comprising a step of determining the ranking of each of a plurality of contents associated with the search query based on the one or more query pattern types. The step of determining one or more query pattern types for the search query based on the one or more query intents extracted from the search query
A step of extracting the one or more query intents from the search query by one or more keywords included in the search query;
The method for providing search results that reflects the query intent according to claim 1, comprising the step of determining one or more query pattern types for the one or more query intent. The step of determining one or more query pattern types for the search query based on the one or more query intents extracted from the search query
A step of extracting one or more query intents from the search query by natural language processing;
The method for providing search results that reflects the query intent according to claim 1, comprising the step of determining one or more query pattern types for the one or more query intent. The one or more query pattern types are represented by one or more bits.
In any one of claims 1 to 3, the one or more bits are pre-matched with one or more ranking factors that are elements that give weights to determine the ranking of the plurality of contents. How to provide search results that reflect the stated query intent. The step of determining the ranking of each of the plurality of contents associated with the search query based on the one or more query pattern types is
A step of calculating the ranking score of each of the plurality of contents related to the search query based on the one or more ranking factors;
The search result providing method according to claim 4, further comprising a step of determining the ranking of each of the plurality of contents related to the search query based on the ranking score of each of the plurality of contents. It further includes a step of labeling the query pattern types of the plurality of contents.
The step of calculating the ranking score of each of the plurality of contents for the search query based on the one or more ranking factors is
A search result that reflects the query intent of claim 5, comprising a step of determining the ranking of each of the plurality of contents for the search query based on the plurality of content query pattern types and the one or more ranking factors. How to provide. The step of labeling the query pattern types for multiple contents is
A search that reflects the query intent of claim 6, comprising labeling a query pattern type determined based on at least one of the text, text structure, attachments, and images contained in the plurality of contents. How to provide results. The invention according to any one of claims 1 to 7, further comprising a step of outputting at least one or more contents of a plurality of contents related to the search query based on the determined ranking through the user terminal. How to provide search results that reflect the query intent. A method for providing search results that reflects the query intent according to any one of claims 1 to 8, further comprising a step of extracting at least one or more snippets from each of the plurality of contents. The step of extracting at least one or more snippets from each of the plurality of contents is
9. Claim 9 comprising parsing at least one of the text, text structure, attachments and images contained in each of the plurality of contents and extracting at least one or more snippets from each of the plurality of contents. How to provide search results that reflect the query intent described in. The step of parsing at least one of the text, text structure, attachments and images contained in each of the plurality of contents and extracting at least one or more snippets from each of the plurality of contents is a step.
A step of extracting one or more snippets associated with each query pattern type of a plurality of content determined based on at least one of the text, text structure, attachments and images contained in each of the plurality of contents. A search result providing method that reflects the query intention according to claim 10. One of claims 1-8, further comprising a step of outputting at least one or more content snippets of the plurality of contents related to the search query through the user terminal based on the determined ranking. How to provide search results that reflect the stated query intent. Further including the step of extracting one or more snippets associated with each query pattern type of the plurality of contents.
Based on the determined ranking, the step of outputting a snippet of at least one content of a plurality of contents related to the search query through the user terminal is
The search result providing method according to claim 12, which comprises a step of outputting a snippet related to the one or more query pattern types among the one or more snippets through the user terminal. The step of outputting the snippet related to the one or more query pattern types among the one or more snippets through the user terminal is
13. A search that reflects the query intent of claim 13, including the step of outputting at least a portion of the one or more snippets to the one or more query pattern types through the user terminal by a predetermined priority. How to provide results. Based on the determined ranking, the step of outputting at least one content snippet of the plurality of contents related to the search query through the user terminal is
The search result providing method according to claim 12, which comprises a step of emphasizing and outputting a part of the area related to the one or more query pattern types in the snippet. In the snippet, the step of emphasizing and outputting a part of the area related to the one or more query pattern types is
The query intent according to claim 15, wherein in the snippet, a step of emphasizing and outputting a partial area associated with the one or more query pattern types by at least one of bold processing and background processing. How to provide the reflected search results. A computer-readable computer program for executing a search result providing method reflecting the query intention according to any one of claims 1 to 16 on a computer. In a search result providing system that reflects the intent of a search query
Communication module;
Memory; and
Containing at least one processor concatenated with said memory and configured to execute at least one computer-readable program contained in said memory.
The at least one program receives a search query from a user terminal, determines one or more query pattern types for the search query, and determines one or more query pattern types based on the one or more query intents extracted from the search query. A search result providing system that reflects the intent of a query, including a command term for determining the ranking of each of a plurality of contents related to the search query based on the above query pattern types. The search result providing system according to claim 18, wherein the at least one program includes an instruction word for labeling a query pattern type of the plurality of contents. The search result providing system according to claim 18 or 19, wherein the at least one program includes an instruction word for extracting at least one snippet for each of the plurality of contents.

Images