KR20200081569A - Apparatus and method for recommending a searching result - Google Patents

Abstract

The present invention relates to a search result recommendation apparatus and method. According to one embodiment of the present invention, the search result recommendation apparatus includes: an alignment unit that assigns different alignment weights satisfying a predetermined condition to a point of interest (POI) and aligns the different alignment weights; a generation unit that creates a plurality of user groups with similar attributes based on a user′s search log and destination log collected through a navigation terminal and user information; an inquiry unit for inquiring a non-preferred POI from each of the plurality of user groups, and comparing the non-preferred POI with a preferred POI of another user group to inquire a POI having a high sorting weight; a recommendation unit that recommends POI having the high sorting weight to the navigation terminal.

Description

Search result recommendation device and method {APPARATUS AND METHOD FOR RECOMMENDING A SEARCHING RESULT}

The present invention relates to a search result recommendation device and method.

Of the location-based services provided by a navigation terminal equipped with a global positioning system (GPS) function, the current service recommending a specific location is a one-dimensional service that shows all registered locations within a certain range based on the current location of the current user. It stops.

Therefore, the existing technology does not take into account the preferences of the individual who visited a specific place or the preferences of others, and the current user must select a place suitable for himself from the list of multiple places displayed. To compensate for this, create a user's own preference map using a database that bookmarks the places they have visited, or share these local bookmarks with other users through the transmission of short messages. The way it appeared.

However, even in such a case, the degree of preference of the preference is not known for a place where the user has not been to, and even if the bookmark is shared with other users, there is no guarantee that the taste of the other person matches their own taste, and thus the reliability for the place not visited. There is a low problem.

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 Published Patent Publication No. 2018-0089846

The present invention has been devised to solve the above-mentioned problems and/or limitations, and an object of the present invention according to one aspect is to solve a cold start problem based on similarity of contents and regional similarity, and clustering based on user preferences. The solution is to solve the filter bubble problem by extracting non-preferred content.

The search result recommendation apparatus according to an embodiment of the present invention includes: an alignment unit that assigns and sorts different alignment weights satisfying a predetermined condition to a point of interest (POI); A generation unit generating a plurality of user groups having similar attributes based on user information and search logs and destination logs of users collected through a navigation terminal; A query unit for querying a non-preferred POI from each of the plurality of user groups, and comparing the non-preferred POI with a preferred POI of another user group to inquire the POI having the high sorting weight; And a recommendation unit that recommends the POI having the high sorting weight to the navigation terminal.

When the attribute information of the newly generated new POI satisfies the reference information, the alignment unit determines the new POI as a landmark POI, assigns a first weight to the new POI, and applies the first weight New POIs can be added to the landmark POI list.

The sorting unit compares the name and industry of the new POI with the landmark POI list to check whether there is one or more landmark POIs that match, and if there is a matching landmark POI, the new POI is regarded as a landmark POI. In addition, an average value of alignment weights assigned to the matching one or more landmark POIs may be assigned as the first weights.

When the attribute information of the newly generated new POI does not satisfy the reference information, the alignment unit determines the new POI as a general POI, assigns a second weight to the new POI, and adds the second weight to the new You can add a POI to the general POI list.

The sorting unit compares the name and industry of the new POI with the general POI list to check whether there is at least one general POI that matches, and if there is a matching general POI, the new POI is regarded as a general POI, and the match The average value of the alignment weights assigned to one or more general POIs may be assigned as the second weight.

A search result recommendation method according to an embodiment of the present invention includes: assigning, by the sorting unit, different sorting weights satisfying a predetermined condition to the POI and sorting them; Generating, by the generation unit, a plurality of user groups having similar attributes based on user information and search logs and destination logs of users collected through the navigation terminal; Querying a non-preferred POI from each of the plurality of user groups, and comparing the non-preferred POI with a preferred POI of another user group to inquire the POI having the high sorting weight; And recommending, by the recommendation unit, the POI having the high alignment weight to the navigation terminal.

The sorting may include, when the attribute information of the newly generated new POI satisfies the reference information, determining the new POI as a landmark POI and assigning a first weight to the new POI; And adding the new POI to which the first weight is assigned to a landmark POI list.

The granting step includes: comparing the name and industry of the new POI with the landmark POI list to check whether there is one or more landmark POIs that match; And if there is a matching landmark POI, the new POI is regarded as a landmark POI, and an average value of alignment weights assigned to the matching one or more landmark POIs may be assigned as the first weight.

The sorting step may include determining, when the attribute information of the newly generated new POI does not satisfy the reference information, determining the new POI as a general POI and assigning a second weight to the new POI; And adding the new POI to which the second weight is assigned to a general POI list.

The granting step includes: comparing the name and industry of the new POI with the general POI list to check whether there is at least one general POI that matches; And if there is a matching general POI, the new POI is regarded as a general POI, and an average value of alignment weights assigned to the matching one or more general POIs may be assigned as the second weight.

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 cold start problem may be solved based on similarity of contents and regional similarity.

In addition, when sorting the newly constructed POI, it is possible to solve the filter bubble problem by preventing exposure to only the lower part and recommending POIs that are not exposed by the sorting weight by group.

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 diagram schematically illustrating a search result recommendation system according to an embodiment of the present invention.
2 is a flowchart illustrating a search result recommendation method according to an embodiment of the present invention.
FIG. 3 is a flowchart illustrating a method of assigning weights to new POIs among search method recommendation methods of FIG. 2.

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 for schematically explaining a search result recommendation system according to an embodiment of the present invention. Referring to FIG. 1, the search result recommendation system 1 may include a navigation terminal 100, a search result recommendation device 200, and a communication network 300.

The navigation terminal 100 may provide a driving route from a current location to a destination in response to a destination log input by a user in connection with the search result recommendation device 200. The navigation terminal 100 may receive a search log and/or a destination log from a user. In this embodiment, the navigation terminal 100 includes a GPS receiver (not shown) for determining the location of the vehicle, a map DB (not shown), and a display unit (not shown) for displaying the driving route to the destination, and the driving route It may include a voice guide (not shown) for guiding the voice.

The search result recommendation apparatus 200 may provide the POI processed with the driving route in response to the search log and/or the destination log input by the user from the navigation terminal 100. Here, the point of interest (POI) may include the destination itself, and may include a point of interest that can be recommended to the user according to situation information such as time, location, speed, and weather in which the user is driving. That is, the information provided by the search result recommendation device 200 to the navigation terminal 100 may include a driving route to a destination, recommendation information of a user's interest point on the driving route, but the user is not interested (non-preferred) ) It can provide recommendation information of other users' points of interest.

The search result recommendation apparatus 200 may give POIs different sorting weights that satisfy the conditions. The search result recommendation device 200 generates a plurality of user groups having similar attributes based on the search log and destination log of the user collected through the navigation terminal 100 and the user information stored therein, and the plurality of user groups A non-preferred POI is inquired from each other, and a non-preferred POI is compared with a preferred POI of another user group to search for a POI having a high sorting weight, and the POI having a high sorting weight can be provided to the navigation terminal 100 as recommendation information.

The communication network 300 serves to connect the navigation terminal 100 and the search result recommendation device 200. That is, the communication network 300 may refer to a communication network that provides a connection path so that the navigation terminal 100 can transmit and receive predetermined information after accessing the search result recommendation 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.

In this embodiment, the search result recommendation device 200 includes a communication unit 210, a storage unit 220, an alignment unit 230, a generation unit 240, a query unit 250, a recommendation 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 navigation terminal 100 and the search result recommendation device 200 in the form of packet data in cooperation with the communication network 300. Further, the communication unit 210 may serve to receive a search log and/or a destination log from the navigation terminal 100, and transmit the POI recommendation result processed by the search result recommendation device 200 to the navigation terminal 100 Can play a role. Here, the communication network is a medium that plays a role of connecting the navigation terminal 100 and the search result recommendation device 200, and after the navigation terminal 100 accesses the search result recommendation device 200, information is transmitted and received. 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 storage unit 220 temporarily or permanently stores data processed by the control unit 270. Specifically, the storage unit 220 may store the search log and/or the destination log collected from the navigation terminal 100, and search statistics and destination statistics may be stored in individual POIs based on the collected logs. In addition, the storage unit 220 may store user information, for example, basic information about the user, such as the user's name, affiliation, personal information, gender, age, contact information, email, address, and ID (or Email) and passwords (password), authentication (login) information, access country, access location, information about a device used for access, and connected network environment. The user information may include a POI preferred by the user and a POI not preferred by the user. Also, the storage unit 220 may store information about one or more user groups in which users having similar attribute information (eg, age, gender, frequently used destinations, etc.) are grouped. Also, the storage unit 220 may store the weighted POIs for each list (eg, landmark POI list and/or general POI list).

The storage unit 220 may include a magnetic storage media or a flash storage media, but the scope of the present invention is not limited thereto. The storage unit 220 may include internal memory and/or external memory, volatile memory such as DRAM, SRAM, or SDRAM, one time programmable ROM (OTPROM), PROM, EPROM, EEPROM, mask ROM, flash ROM SSD, non-volatile memory, such as NAND flash memory, or NOR flash memory. It may include a compact flash (CF) card, an SD card, a Micro-SD card, a Mini-SD card, an Xd card, a flash drive such as a memory stick, or a storage device such as an HDD.

The sorting unit 230 assigns and sorts different sorting weights satisfying a predetermined condition to the POI, and may store the sorting results in the storage unit 220. When a new POI is generated, the new POI may be divided into a landmark POI or a general POI. The landmark POI and the general POI can be divided into two because the user's cognitive level and preference are significantly different when creating a new one.

When the attribute information of the newly generated new POI satisfies the reference information, the sorting unit 230 determines the new POI as a landmark POI, assigns a first weight to the new POI, and a new POI to which the first weight is assigned Can be added to the list of landmark POIs. The storage unit 220 and the alignment unit 230 compares the name and industry of the new POI with the landmark POI list to check whether there is one or more landmark POIs that match, and if there is a matching landmark POI, lands the new POI It is regarded as a mark POI, and an average value of alignment weights assigned to one or more matching landmark POIs may be assigned as a first weight.

The sorting unit 230 extracts the name, industry, and scale (width of the POI area) from the attribute information of the new POI, and when the size of the new POI is greater than or equal to a certain size, the name and industry of the new POI are stored in the landmark POI list Compared with the landmark POIs, it is possible to check whether there is one or more POIs that match. If there is a matching POI, the new POI is regarded as a landmark POI, and an approximation of the alignment weight of the matching POI (for example, 80% of the weight, or the average value of the matching POI's alignment weight) is given as the first weight. It can be added to the list of landmark POIs. However, if there is no matching POI, it is regarded as a new landmark property POI having a size of a certain size or more, and after assigning the median sorting weight of POIs of the same industry in the landmark POI list as the first weight, it is added to the landmark POI list. Can.

When the attribute information of the newly generated new POI does not satisfy the reference information, the sorter 230 determines the new POI as a general POI, assigns a second weight to the new POI, and assigns a new POI to which the second weight is assigned. It can be added to the general POI list. Compare the name and industry of the new POI with the general POI list to check if there is at least one general POI that matches, and if there is a matching general POI, the new POI is regarded as a general POI and is assigned to the matching one or more general POIs. The average value of the sorted weights may be assigned as a second weight.

The sorting unit 230 selects POIs whose scale does not satisfy a certain size criterion among the new POI attribute information. It extracts the address information and industry type of the selected POI from the general POI list. From the general POI list, POIs of the same industry as the new POI are extracted while belonging to the same statutory minimum unit (the number of POIs is too small for copper, cotton, and lee). You can obtain the median (or average) of the sorting weights of the extracted POIs and multiply the value by a certain magnification (for example, 120% of the median) as the second sorting weight of the new POI and add it to the general POI list. .

The generation unit 240 may generate a plurality of user groups having similar attributes based on the user's search log and destination log collected through the navigation terminal 100 and user information stored in the storage unit 220.

The querying unit 250 queries the non-preferred POI (which can be defined as an industry that has never been selected as a destination) from each of a plurality of user groups, and compares the non-preferred POI with the preferred POI of other user groups to query the POI having a high sorting weight can do.

The recommender 260 may recommend the POI having a high alignment weight to the navigation terminal 100. For example, when a user belonging to the first user group searches for cosmetics by designating a search log, a search result of a cosmetics store in a department store or mart, which is a major shopping place of the first user group, is provided. If it is XX cosmetics, and the second user group different from the first user group (women in their 20s, exercise, major destination sports facilities, restaurants, and road shops) has a preferred POI of XX cosmetics, the first user group's unfavorable POI and second Since the user group's preferred POI is consistent, when providing a cosmetic search result to the user, the XX cosmetic product in the first user group may provide an unfavorable POI image or recommendation information.

The control unit 270 may control the overall operation state of the search result recommendation device 200. The control unit 270 may include a processor (not shown) provided with at least one or more, may be implemented as an array of multiple logic gates, a general-purpose microprocessor and a memory in which programs that can be executed in the microprocessor are stored. It may be implemented in combination. In addition, those of ordinary skill in the art to which this embodiment pertains may understand that it may be implemented in other types of hardware.

2 is a flowchart illustrating a search result recommendation method according to an embodiment of the present invention. In the following description, parts that overlap with the description of FIG. 1 will be omitted.

Referring to FIG. 2, in step S100, the search result recommendation apparatus 200 assigns and sorts different sorting weights satisfying the condition to the POI.

In step S200, the search result recommendation device 200 generates a plurality of user groups having similar attributes based on the user's search log and destination log collected from the navigation terminal 100 and user information stored therein.

In step S300, the search result recommendation device 200 searches for a non-preferred POI from each of a plurality of user groups, and compares the non-preferred POI with a preferred POI of another user group to query a POI having a high sorting weight.

In step S400, the search result recommendation apparatus 200 provides the POI having the high sorting weight as the recommendation information to the navigation terminal 100.

3 is a flowchart illustrating a method of sorting by assigning a weight to a new POI among search method recommendation methods of FIG. 2. In the following description, portions overlapping with the descriptions of FIGS. 1 and 2 will be omitted.

In step S101, the search result recommendation device 200 determines whether the attribute information of the new POI satisfies the reference information. Here, the attribute information of the new POI may include a name, an industry, and a scale (the width of the POI area), and the reference information may include a scale.

In step S103, the search result recommendation apparatus 200 determines the new POI as a landmark POI when the size of the new POI is greater than or equal to a reference scale.

In step S105, the search result recommendation device 200 compares the name and industry of the new POI with the landmark POI list to check whether there is one or more landmark POIs that match.

In step S107, if there is a matching landmark POI, the search result recommendation device 200 regards the new POI as the landmark POI, and the average value of the alignment weights assigned to the matching one or more landmark POIs is the first weight. Grant.

In step S109, the search result recommendation device 200 adds the new POI to which the first weight is assigned to the landmark POI list.

In step S111, if the size of the new POI is greater than or equal to a reference scale, the search result recommendation device 200 determines the new POI as a general POI.

In step S113, the search result recommendation device 200 compares the name and industry of the new POI with the general POI list to check whether there is one or more general POIs that match.

In step S115, if there is a matching general POI, the search result recommendation device 200 considers the new POI as a general POI, and the search result recommendation device 200 averages the sorting weights assigned to one or more matching general POIs. Is assigned as a second weight.

In step S117, the search result recommendation apparatus 200 adds the new POI to which the second weight is assigned to the general POI list.

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: navigation terminal
200: search result recommendation device
300: communication network

Claims (11)

A sorting unit for assigning and sorting different sorting weights satisfying a predetermined condition to a point of interest (POI);
A generation unit generating a plurality of user groups having similar attributes based on user information and search logs and destination logs of users collected through a navigation terminal;
A query unit for querying a non-preferred POI from each of the plurality of user groups, and comparing the non-preferred POI with a preferred POI of another user group to inquire the POI having the high sorting weight; And
And a recommendation unit for recommending the POI having the high sorting weight to the navigation terminal. According to claim 1, The alignment unit,
When the attribute information of the newly generated new POI satisfies the reference information, the new POI is determined as a landmark POI, a first weight is assigned to the new POI, and the new POI to which the first weight is assigned is landed. Mark POI to add to the list, search results recommendation device. According to claim 2, The alignment unit,
Compare the name and industry of the new POI with the landmark POI list to check whether there is one or more landmark POIs that match, and if there is a matching landmark POI, the new POI is regarded as a landmark POI, and the match The search result recommendation device assigns an average value of alignment weights to one or more landmark POIs as the first weight. According to claim 1, The alignment unit,
When the attribute information of the newly generated new POI does not satisfy the reference information, the new POI is determined as a general POI, a second weight is assigned to the new POI, and the new POI to which the second weight is assigned is a general POI. Add to list, search results recommendation device. According to claim 4, The alignment unit,
Compare the name and industry of the new POI with the general POI list to check whether there is at least one general POI that matches, and if there is a matching general POI, the new POI is regarded as a general POI, and the matched one or more general A search result recommendation device that assigns an average value of alignment weights assigned to a POI as the second weights. Assigning, by the sorting unit, different sorting weights satisfying a predetermined condition to the POI and sorting;
Generating, by the generating unit, a plurality of user groups having similar attributes based on user information and search logs and destination logs of users collected through the navigation terminal;
Querying a non-preferred POI from each of the plurality of user groups, and comparing the non-preferred POI with a preferred POI of another user group to inquire the POI having the high sorting weight; And
And recommending, by the recommendation unit, the POI having the high sorting weight to the navigation terminal. The method of claim 6, wherein the step of aligning,
If the attribute information of the newly generated new POI satisfies the reference information, determining the new POI as a landmark POI and assigning a first weight to the new POI; And
And adding the new weighted POI to the landmark POI list. The method of claim 7, wherein the step of giving,
Comparing the name and industry of the new POI with the landmark POI list to check whether there is at least one matching landmark POI; And
If there is a matching landmark POI, considering the new POI as a landmark POI, and assigning the average value of the alignment weights assigned to the one or more matching landmark POIs as the first weight. How to recommend results. The method of claim 6, wherein the step of aligning,
If the attribute information of the newly generated new POI does not satisfy the reference information, determining the new POI as a general POI and assigning a second weight to the new POI; And
And adding the new weighted POI to the general POI list. The method of claim 9, wherein the step of giving,
Comparing the name and industry of the new POI with the general POI list to check whether there is at least one general POI that matches; And
And if there is a matching general POI, considering the new POI as a general POI and assigning an average value of the sorting weights assigned to the matching one or more general POIs as the second weight. . A computer program stored in a computer-readable recording medium to execute the method of any one of claims 6 to 10 using a computer.

Images