KR20200081565A - Apparatus and method for providing a searching service - Google Patents

Abstract

The present invention relates to a search service providing device for providing search results which improved search ranking based on a user log and to a method thereof. According to one embodiment of the present invention, the search service providing device comprises: a setting unit which sets weights for incoming keywords and stores the weights in a database by using a search frequency and an occurrence frequency of incoming keywords included in each document based on the user log; a processing unit which extracts a plurality of documents matching the search keyword input by the user from the database, and calculates a sum of weights in accordance with the number of incoming keywords which are the same as the search keyword in the document; and a providing unit which provides a search result obtained by arranging documents in an order in which the sum of weights is high.

Description

Search service providing device and method {APPARATUS AND METHOD FOR PROVIDING A SEARCHING SERVICE}

The present invention relates to a search service providing apparatus and method for providing search results with improved search ranking based on user logs.

Tuning search rankings through search modeling requires a lot of work. It is very difficult to respond to the entire intention through a single ranking model, and for this purpose, it is necessary to design a ranking model that fits each intention, and even this tends to change little by little over time, so it requires a lot of maintenance effort. Is done. In addition, in the case of a short name such as a map search or a short name, the weight of words has a large influence on the search ranking.

The above-mentioned background technology is technical information acquired by the inventor for the derivation of the present invention or acquired in the derivation process of the present invention, and is not necessarily a known technology disclosed to the general public prior to the filing of the present invention.

Domestic Patent Publication No. 2018-0027278

The present invention has been devised to solve the problems and/or limitations described above, and an object of the present invention according to an aspect is to provide a search result with improved search ranking based on a user log.

The apparatus for providing a search service according to an embodiment of the present invention sets a weight in the keyword by using the search frequency of each document based on the user log and the frequency of occurrence of the incoming keyword included in each of the documents, and sets the weight in the keyword. A setting unit for storing; A processing unit for extracting a plurality of documents matching the search keyword input by the user from the database, and calculating a sum of weights according to the number of the incoming keywords equal to the search keyword in the document; And a providing unit that provides a search result in which the documents are sorted in the order in which the sum of the weights is high.

The setting unit may calculate an inflow probability value using a softmax function to the frequency of occurrence of the inflow keyword, multiply the search frequency of the document and the inflow probability value to calculate the weight for each inflow keyword, and set the weight to the inflow keyword have.

The processing unit may extract one or more meaningful words after morpheme analysis of the search keyword input by the user.

The method for providing a search service according to an embodiment of the present invention, by a setting unit, uses a search frequency of each document based on a user log and a frequency of appearance of an incoming keyword included in each of the documents, to weight the incoming keyword Setting and storing in a database; Extracting, by the processing unit, a plurality of documents matching the search keyword input by the user from the database, and calculating a sum of weights according to the number of the inflow keywords equal to the search keyword in the document; And providing a search result obtained by arranging the documents in the order in which the sum of the weights is high by the providing unit.

The method includes: calculating, by the setting unit, an inflow probability value using a softmax function to the frequency of occurrence of the inflow keyword, and multiplying the search frequency of the document and the inflow probability value to calculate the weight for each inflow keyword; It may further include.

The method may further include, by the processing unit, extracting one or more meaningful words after morpheme analysis of the search keyword input by the user.

In addition to this, other methods for implementing the present invention, other systems, and computer programs for executing the methods may be further provided.

Other aspects, features and advantages other than those described above will become apparent from the following drawings, claims and detailed description of the invention.

According to embodiments, a user can check a more accurate search result by providing a search result with improved search ranking based on a user log.

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

1 is a view schematically illustrating a search service providing system according to an embodiment of the present invention.
FIG. 2 is a diagram schematically illustrating a detailed configuration of a search service providing device among the search service providing systems of FIG. 1.
3 and 4 are flowcharts illustrating a method for providing a search service according to an embodiment of the present invention.

Advantages and features of the present invention, and methods for achieving them will be clarified with reference to embodiments described in detail with reference to the accompanying drawings. However, the present invention is not limited to the embodiments presented below, but may be implemented in various different forms, and should be understood to include all transformations, equivalents, and substitutes included in the spirit and scope of the present invention. . The embodiments presented below are provided to complete the disclosure of the present invention and to fully inform the scope of the invention to those skilled in the art to which the present invention pertains. In the description of the present invention, when it is determined that a detailed description of related known technologies may obscure the subject matter of the present invention, the detailed description will be omitted.

Terms used in the present application are only used to describe specific embodiments, and are not intended to limit the present invention. Singular expressions include plural expressions unless the context clearly indicates otherwise. In this application, the terms "include" or "have" are intended to indicate the presence of features, numbers, steps, actions, components, parts or combinations thereof described herein, one or more other features. It should be understood that the existence or addition possibilities of fields or numbers, steps, operations, components, parts or combinations thereof are not excluded in advance. Terms such as first and second may be used to describe various components, but the components should not be limited by the terms. The terms are used only for the purpose of distinguishing one component from other components.

Hereinafter, embodiments according to the present invention will be described in detail with reference to the accompanying drawings, and in describing with reference to the accompanying drawings, identical or corresponding components are assigned the same reference numbers, and redundant description thereof is omitted. I will do it.

1 is a view schematically illustrating a search service providing system according to an embodiment of the present invention. Referring to FIG. 1, the search service providing system 1 may include a user terminal 100, a search service providing device 200, and a communication network 300.

The user terminal 100 may generate a user log as a series of information processed by accessing the search service providing apparatus 200. Here, the user log may include a search log such as entering a search term, and an internet user log such as viewing documents, web pages, content (images, videos, texts, etc.). Hereinafter, documents, web pages, and contents will be referred to as documents. The user log includes search term input history information (for example, the type of search terms entered in the past, the number of search terms entered repeatedly over a period of time, the time at which the search terms were entered, etc.), and Internet document information viewed by the user (for example, , The time the user viewed the document, the keywords included in the document read, the search frequency of the document, the preferred document set by the search frequency of the document, non-preferred document, etc.). In this embodiment, the user terminal 100 may mount and execute a search service application or program provided by the search service providing apparatus 200 in order to receive search results.

The user terminal (100 in FIG. 1) is a desktop computer (101 in FIG. 1) operated by a user, a smartphone (102 in FIG. 1), a laptop (103 in FIG. 1), a tablet PC, a smart TV, a mobile phone, a PDA (personal digital assistant), laptops, media players, micro servers, global positioning system (GPS) devices, e-book terminals, digital broadcasting terminals, navigation, kiosks, MP3 players, digital cameras, consumer electronics and other mobile or non-mobile computing devices It may be, but is not limited thereto. Further, the user terminal 100 may be a wearable terminal such as a watch, glasses, hair band, and ring equipped with a communication function and a data processing function. In addition, the user terminal 100 may be a navigation terminal that generates and provides a driving route to a destination. In this embodiment, when the user terminal 100 is a navigation terminal, a GPS receiver (not shown) for determining the location of the vehicle, a map DB (not shown), and a display unit for displaying the driving route to the destination (not shown) City) and a voice guidance unit (not shown) for guiding the driving route by voice, a search word may be a destination, and a document may include location information of a destination provided as a search result when entering a destination. . The user terminal 100 is not limited to the above, and a terminal capable of web browsing can be borrowed without limitation.

The search service providing apparatus 200 collects user logs from the user terminal 100 and uses the search frequency of each document collected based on the user log and the frequency of appearance of the incoming keywords included in each of the documents, and weights the incoming keywords You can set it and save it inside.

In addition, the search service providing apparatus 200 uses the user terminal 100 to extract a plurality of documents matching the search keyword input by the user, and sums the weights according to the number of incoming keywords equal to the search keyword in the document Calculation, and the search results obtained by arranging the documents in the order of the highest sum of weights may be provided to the user terminal 100.

The communication network 300 serves to connect the user terminal 100 and the search service providing device 200. That is, the communication network 300 may mean a communication network that provides a connection path so that the user terminal 100 can transmit and receive predetermined information after accessing the search service providing device 200. The communication network 300 includes, for example, wired networks such as Local Area Networks (LANs), Wide Area Networks (WANs), Metropolitan Area Networks (MANs), and Integrated Service Digital Networks (ISDNs), wireless LANs, CDMA, Bluetooth, satellite communication, etc. It may cover a wireless network, but the scope of the present invention is not limited thereto. Also, the communication network 300 may transmit and receive information using short-range communication and/or long-distance communication. Here, the short-range communication may include Bluetooth, radio frequency identification (RFID), infrared data association (IrDA), ultra-wideband (UWB), ZigBee, Wi-Fi (wireless fidelity) technology, and remote Communication includes code division multiple access (CDMA), frequency division multiple access (FDMA), time division multiple access (TDMA), orthogonal frequency division multiple access (OFDMA), and single carrier frequency division multiple access (SC-FDMA) technology. Can be.

FIG. 2 is a diagram schematically illustrating a detailed configuration of a search service providing device among the search service providing systems of FIG. 1. Referring to FIG. 2, the search service providing apparatus 200 includes a communication unit 210, a database 220, a collection unit 230, a setting unit 240, a processing unit 250, a provision unit 260, and a control unit 270 ).

The communication unit 210 may provide a communication interface necessary to provide a transmission/reception signal between the user terminal 100 and the search service providing device 200 in packet data form in conjunction with the communication network 300. Furthermore, the communication unit 210 may serve to receive a user log and/or search word from the user terminal 100, and transmit the search results processed by the search service providing apparatus 200 to the user terminal 100 You can do Here, the communication network is a medium that plays a role of connecting the user terminal 100 and the search service providing device 200, and transmits and receives information after the user terminal 100 accesses the search service providing device 200. It may include a path to provide a connection path. Also, the communication unit 210 may be a device including hardware and software necessary for transmitting and receiving a signal such as a control signal or a data signal through a wired or wireless connection with another network device.

The database 220 may include a user database that stores user information. Here, the user information includes basic information about the user such as first, second user's name, affiliation, personal information, gender, age, contact information, email, address, and ID (or email) and password (password). It may include information on authentication (login), access country, access location, information on a device used for access, information related to access such as a connected network environment, and the like.

In addition, the user database includes user-specific information, information and/or category history provided by a user accessing a search service application or a search service site, environment setting information set by the user, resource usage information used by the user, and resource usage of the user. Corresponding billing and payment information may be stored. In addition, a user log including a search log and an internet user log may be stored in the user database.

In addition, the database 220 includes an inflow keyword database in which weights are set and stored in the inflow keywords for each document based on the user log, a document database for calculating and storing the search frequency for each document based on the user log, and a search service. The search service database may store a series of information provided.

The collection unit 230 may collect user information and user log information from the user terminal 100 and store it in the database 220. As described above, the user log may include a search log such as inputting a search term and an internet user log such as viewing a document. The user log includes search term input history information (for example, the type of search terms entered in the past, the number of search terms entered repeatedly over a period of time, the time at which the search terms were entered, etc.), and Internet document information viewed by the user (for example, , The time the user viewed the document, the keywords included in the document read, the search frequency of the document, the preferred document set by the search frequency of the document, non-preferred document, etc.).

The setting unit 240 may set the weight of the incoming keyword and store it in the database 220 by using the search frequency of each document collected based on the user log and the appearance frequency of the incoming keyword included in each of the documents. Here, the incoming keyword may include meaningful words through morphological analysis of the document and one or more of search keywords that have been searched in the user log.

The setting unit 240 may calculate an inflow probability value using a softmax function for the frequency of occurrence of the inflow keyword. The softmax function is a function that normalizes the output value for class classification. The output has a positive value and has a total sum of 1. The setting unit 240 may calculate a weight for each inflow keyword by multiplying a search frequency of the document and an inflow probability value, and assign the weight to the inflow keyword and store it in the database 220. Here, the search frequency of the document can be calculated by normalizing the search frequency of each document to the total search frequency.

The processing unit 250 receives the search keyword from the user terminal 100, extracts a plurality of documents matching the search keyword from the database 220, and weights the weight assigned to the same inflow keyword as the search keyword in the plurality of documents. It can extract and calculate the sum of weights according to the number of inflow keywords.

In the present embodiment, the processing unit 250 analyzes a meaningful word through morpheme analysis of a search keyword, extracts a plurality of documents matching the meaningful word from the database 220, and inflows the same as a meaningful word in the plurality of documents It is possible to extract weights assigned to keywords and calculate sums of weights according to the number of keywords.

The providing unit 260 may provide the user terminal 100 with search results in which the documents are sorted in the order of the highest sum of the weights.

For example, suppose that among 10000 documents, there is a restaurant named <Haeundae> and a document named <Haeundae Beach>. It is assumed that each document extracts the words <Haeundae> and <Haeundae/Beach/Haeundae Beach> by morpheme analysis, respectively. In addition, the words <Haeundae> appeared in both the Haeundae restaurant and the Haeundae beach once, and the IDF (inverse document frequency), the frequency of occurrence of reverse documents in <Haeundae> in the entire document, shared the same value, so each was set to 1. Suppose you set Simplified BM25 weight model as a known technology, and the weight is calculated using the (TF(term frequency)*IDF)/Length value.In the case of <Haeundae> restaurant, the word <Haeundae> by (1*1)/1 formula Has a weight of 1. In the case of <Haeundae Beach>, the word <Haeundae> has a weight of 0.333 by the (1*1)/3 formula. In this situation, the restaurant <Haeundae> has a more favorable ranking than <Haeundae Beach> by the user entering the search keyword <Haeundae>.

However, in order to apply the user inflow keyword analysis model, which is the method presented in this embodiment, users performed 10 searches for the restaurant <Haeundae> with the search keyword <Haeundae>, and performed 15 searches for <Haeundae Beach>. Suppose that you have performed 5 searches for the full name keyword <Haeundae Beach>. When the Softmax function was applied, the keyword <Haeundae> in the restaurant <Haeundae> was searched with the keyword <Haeundae> in all 10 times out of 10 searches, so it has an inflow probability value of 10/10. However, in the case of <Haeundae Beach>, since 15 of the 20 searches were through the <Haeundae> keyword, the probability of inflow was 0.75 by 15/20. In addition, since the search frequency of the document is calculated by normalizing the search frequency of each document to the total search frequency, the <Haeundae> restaurant has a weight of 0.333 as 10/30, and the <Haeundae Beach> has a weight of 0.666. For the search term <Haeundae>, finally, <Haeundae> Restaurant has a weight of 0.333*1.0=0.333, <Haeundae Beach> has a weight of 0.666*0.75=0.4995, so <Haeundae Beach> has a more favorable ranking value. Can.

Since the above-described model utilizes both the search frequency and the weight of the inflow keyword in each document, in the opposite situation, the <Haeundae Beach> described above is the <Haeundae Beach>, which has a high search frequency, in the search query by entering the search keyword <Sea Beach> in the opposite situation. It is possible to prevent a situation having a ranking value (0.666*0.25=0.1665) that is more favorable than a restaurant named <beach> with the same conditions as the restaurant.

The control unit 270 is a kind of central processing unit, which drives the control software installed therein, sets and stores the weight of the incoming keyword using the user log, and stores the search result in response to the search keyword input by the user terminal 100 It can provide a variety of functions, such as providing. Here, the control unit 270 may include all types of devices capable of processing data, such as a processor. Here, the'processor (processor)', for example, may mean a data processing device embedded in hardware having physically structured circuits to perform functions represented by codes or instructions included in a program. As an example of such a data processing device embedded in hardware, a microprocessor, a central processing unit (CPU), a processor core, a multiprocessor, and an application-specific integrated ASIC circuit, a field programmable gate array (FPGA), and the like, but the scope of the present invention is not limited thereto.

3 is a flowchart illustrating a search service providing method according to an embodiment of the present invention. In the following description, portions overlapping with the descriptions of FIGS. 1 and 2 will be omitted.

Referring to FIG. 3, in step S100, the search service providing apparatus 200 sets a weight for the inflow keyword included in the document and stores it in a database based on the user log collected from the user terminal 100.

FIG. 4 is a flowchart for explaining a method of setting a weight for an inflow keyword in the search service providing method of FIG. 3 and storing it in a database. In step S110, the search service providing apparatus 200 is collected from the user terminal 100 Calculate the frequency of searching documents based on user logs. Here, the search frequency of the document can be calculated by normalizing the search frequency of each document to the total search frequency.

In step S120, the search service providing apparatus 200 extracts the incoming keywords included in each of the documents, and calculates the frequency of appearance of the incoming keywords in the document.

In step S130, the search service providing apparatus 200 calculates an inflow probability value using a softmax function for the frequency of occurrence of the inflow keyword. Here, the softmax function is a known technique, and detailed description will be omitted.

In step S140, the search service providing apparatus 200 calculates a weight for each inflow keyword by multiplying the search frequency of the document and the inflow probability value.

In step S150, the search service providing apparatus 200 sets a weight for the incoming keyword and stores it in the database.

Returning to FIG. 3, in step S200, the search service providing apparatus 200 receives a search keyword input from the user terminal 100, and extracts a plurality of documents matching the search keyword input by the user from the database. The search service providing apparatus 200 may analyze a meaningful word through morpheme analysis of a search keyword, and extract a plurality of documents matching the meaningful word.

In step S300, the search service providing apparatus 200 calculates a sum of weights according to the number of search keywords (or meaningful words) equal to the number of incoming keywords in the extracted document.

In step S400, the search service providing apparatus 200 provides the search result in which the documents are arranged in the order of the highest sum of weights, to the user terminal 100.

The embodiment according to the present invention described above may be implemented in the form of a computer program that can be executed through various components on a computer, and such a computer program can be recorded on a computer-readable medium. At this time, the medium includes a hard disk, a magnetic medium such as a floppy disk and magnetic tape, an optical recording medium such as CD-ROM and DVD, a magneto-optical medium such as a floptical disk, and a ROM. , Hardware devices specially configured to store and execute program instructions, such as RAM, flash memory, and the like.

Meanwhile, the computer program may be specially designed and configured for the present invention, or may be known and available to those skilled in the computer software field. Examples of computer programs may include not only machine language codes produced by a compiler, but also high-level language codes executable by a computer using an interpreter or the like.

The use of the term "above" in the specification (particularly in the claims) of the present invention and similar indication terms may be in both singular and plural. In addition, in the case of describing a range in the present invention, as including the invention to which the individual values belonging to the range are applied (if there is no contrary description), each individual value constituting the range is described in the detailed description of the invention. Same as

Unless explicitly stated or contrary to the steps constituting the method according to the invention, the steps can be done in a suitable order. The present invention is not necessarily limited to the description order of the above steps. The use of all examples or exemplary terms (eg, etc.) in the present invention is merely for describing the present invention in detail, and the scope of the present invention is limited due to the examples or exemplary terms, unless it is defined by the claims. It does not work. In addition, those skilled in the art can recognize that various modifications, combinations, and changes can be configured according to design conditions and factors within the scope of the appended claims or equivalents thereof.

Accordingly, the spirit of the present invention is not limited to the above-described embodiment, and should not be determined, and the scope of the spirit of the present invention, as well as the claims to be described later, as well as all ranges that are equivalent to or equivalently changed from the claims Would belong to

100: user terminal
200: search service providing device
300: communication network

Claims (7)

A setting unit configured to set a weight for the incoming keyword and store it in a database using a search frequency of each document based on a user log and an appearance frequency of the incoming keyword included in each of the documents;
A processing unit for extracting a plurality of documents matching the search keyword input by the user from the database, and calculating a sum of weights according to the number of the incoming keywords equal to the search keyword in the document; And
And a search unit providing search results in which the documents are sorted in the order in which the sum of the weights is high. The method of claim 1, wherein the setting unit,
Providing a search service by calculating the incidence probability value using a softmax function to the frequency of occurrence of the inflow keyword, multiplying the search frequency of the document by the inflow probability value, and calculating the weight for each inflow keyword and setting the weight to the inflow keyword Device. The method of claim 1, wherein the processing unit,
A search service providing device that extracts one or more meaningful words after morpheme analysis of the search keyword input by the user. Setting, by the setting unit, a weight based on the incoming keyword using the search frequency of each document and the frequency of appearance of the incoming keyword included in each of the documents based on a user log and storing the weight in the database;
Extracting, by the processing unit, a plurality of documents matching the search keyword input by the user from the database, and calculating a sum of weights according to the number of the inflow keywords equal to the search keyword in the document; And
And providing a search result obtained by arranging the documents in the order in which the sum of the weights is high by the providing unit. The method of claim 4,
Further comprising; by the setting unit, calculating the incidence probability value using a softmax function to the frequency of occurrence of the inflow keyword, and multiplying the search frequency of the document and the inflow probability value to calculate the weight for each inflow keyword; , Search service provision method. The method of claim 4,
And extracting one or more meaningful words after morpheme analysis of the search keyword input by the user by the processing unit. A computer program stored in a recording medium readable by the computer to execute the method of any one of claims 4 to 6 using a computer.

Images