WO2015129987A1 - Appareil de service de fourniture de publicité à base de reconnaissance d'objet, équipement d'utilisateur de réception de publicité à base de reconnaissance d'objet, système de fourniture de publicité à base de reconnaissance d'objet, procédé associé et support d'enregistrement associé dans lequel est enregistré un programme d'ordinateur - Google Patents

Appareil de service de fourniture de publicité à base de reconnaissance d'objet, équipement d'utilisateur de réception de publicité à base de reconnaissance d'objet, système de fourniture de publicité à base de reconnaissance d'objet, procédé associé et support d'enregistrement associé dans lequel est enregistré un programme d'ordinateur Download PDF

Info

Publication number
WO2015129987A1
WO2015129987A1 PCT/KR2014/011175 KR2014011175W WO2015129987A1 WO 2015129987 A1 WO2015129987 A1 WO 2015129987A1 KR 2014011175 W KR2014011175 W KR 2014011175W WO 2015129987 A1 WO2015129987 A1 WO 2015129987A1
Authority
WO
WIPO (PCT)
Prior art keywords
advertisement
information
image
thing
user device
Prior art date
Application number
PCT/KR2014/011175
Other languages
English (en)
Korean (ko)
Inventor
한민호
Original Assignee
에스케이플래닛 주식회사
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by 에스케이플래닛 주식회사 filed Critical 에스케이플래닛 주식회사
Publication of WO2015129987A1 publication Critical patent/WO2015129987A1/fr

Links

Images

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q30/00—Commerce
    • G06Q30/02—Marketing; Price estimation or determination; Fundraising

Definitions

  • the present invention relates to a service device for providing advertisement based on object recognition, a user device for receiving advertisement based on object recognition, a system, method for providing advertisement based on object recognition, and a recording medium on which a computer program is recorded.
  • a service device, a user device, a method, and a computer program for transmitting and receiving an advertisement generated by recognizing a thing based on feature information of a thing included in the recording medium are recorded.
  • the mobile advertisement may be an advertisement based on multimedia information (eg, text, image, video, sound source, etc.) transmitted to a mobile communication terminal such as a smartphone.
  • multimedia information eg, text, image, video, sound source, etc.
  • Mobile advertising based on the wireless Internet has the advantages of personalization, location-based, and interaction. Based on customer information, it can maximize the efficiency of customer management.
  • Such a mobile advertisement may have the following characteristics.
  • mobile advertising has a feature of accurately delivering an advertising message to a personalized target.
  • Existing advertising media such as TV, radio, newspapers, magazines, pamphlets, etc. delivered only one-sided content for an unspecified majority.
  • the mobile advertisement means a user device such as each smart phone, an individual consumer, the advertisement company may establish a database of information about the individual consumer and perform differentiated personalized advertisements according to the characteristics of the individual consumer.
  • mobile advertising allows for two-way interaction.
  • mobile advertisements may also provide a phone number or uniform resource locator (URL), through which consumers can obtain additional product information.
  • URL uniform resource locator
  • mobile advertisements can be distinguished from existing advertisements in various ways, such as targeting advertisements based on location information of consumers and obtaining immediate response from consumers.
  • An object of the present invention is to determine a user's interests of the user device based on the image information stored in the user device, to provide an advertisement based on the object recognition for providing an advertisement suitable for the user's interests,
  • a user device for receiving an advertisement, a system, a method, and a computer program for providing an advertisement based on object recognition are provided.
  • Another object of the present invention is to provide an advertisement based on object recognition for selecting only an image including an advertisement target item of interest among the image information stored in the user device and performing analysis on the user's interest from only the image.
  • a service device, a user device for receiving an advertisement based on a thing recognition, a system, a method for providing an advertisement based on a thing recognition, a method, and a computer program are provided.
  • Another object of the present invention is to provide a service device for providing an advertisement based on object recognition for determining the priority of the user's item of interest based on the image stored in the user device to expose the advertisement for the item of high interest with the highest frequency.
  • the present invention provides a recording medium on which a user device for receiving advertisements based on object recognition, a system, method, and computer program for providing advertisements based on the object recognition are recorded.
  • a service device for providing advertisements based on object recognition may include an image collector configured to collect a user image from a user device, extract feature information of a first thing included in the user image, and generate the advertisement based on the feature information.
  • a thing recognizing unit that performs object recognition on a thing, first matching information matching device identifier information of a user device with thing identifier information of a first thing, and a second object recognized by a thing in the advertisement identifier information and the advertisement image of the advertisement
  • the search unit and the user device to generate second matching information matching the object identifier information of the search, and to search for advertising identifier information matching the identifier information of the user device based on the first matching information and the second matching information.
  • Request the searcher to search for advertisement identifier information matching the identifier information of the user device, and identify the retrieved advertisement It may include an advertisement information processing unit for transmitting an advertisement corresponding to the child to the user device.
  • the thing recognizing unit may extract feature information of the second thing included in the advertisement image, and perform object recognition on the second thing based on the extracted feature information.
  • a service apparatus for providing advertisements based on object recognition may include identifier information about a plurality of things and object information about a plurality of things for object recognition on the basis of feature information of the first thing.
  • the apparatus may further include a thing characteristic information database in which the feature information is stored and a search index database in which the first matching information and the second matching information are stored.
  • the advertisement information processor may transmit the registered new advertisement to the thing recognition unit and request to perform object recognition based on the advertisement image included in the new advertisement.
  • the image collector determines whether the first object included in the user image is an advertisement target object, and recognizes the object with respect to the first object with the object recognizer only when the first object is the advertisement target object. You can request
  • the advertisement information processor may determine the transmission frequency of the advertisement to be transmitted to the user device in consideration of the number of user images including the first object.
  • the advertisement information processor may determine the transmission frequency of the advertisement to be transmitted to the user device by further considering the shooting time at which the user image is captured.
  • the advertisement information processor may determine the transmission frequency of the advertisement to be transmitted to the user device by further considering the image information deleted from the user device.
  • a user device receiving an advertisement based on object recognition determines an storage path of an image captured by the user device, and receives an advertisement to be received from a service device performing an advertisement service based on object recognition among the photographed images.
  • a transmission image determination unit for determining a user image to be used for the determination, a communication unit for transmitting the user image to a service device that performs an advertisement service based on object recognition, and requesting an advertisement based on the user image to the service device, and receiving the advertisement from the service device. It may include an advertisement output unit for receiving and outputting.
  • the transmission image determiner may determine whether a thing included in the photographed image is an advertisement target object and determine the photographed image as a user image only when the thing is an advertisement target object.
  • a method of providing an advertisement based on object recognition receiving a user image from a user device, extracting feature information of a first thing included in the user image, and extracting the feature information from the first object based on the feature information.
  • thing recognition on the object first matching information matching the device identifier information of the user device with the thing identifier information of the first thing, advertisement identifier information of the advertisement, and thing identifier information of the second thing recognized in the advertisement image.
  • Generating matched second matching information retrieving advertisement identifier information matching the identifier information of the user device based on the first matching information and the second matching information; Request a search for advertisement identifier information matching the identifier information, and use an advertisement corresponding to the retrieved advertisement identifier. And transmitting to the child device.
  • the feature information of the first object may be extracted from the user image by separating the background from the object and based on the edge information of the object.
  • a computer program for performing the method according to the above-described embodiments may be stored in a recording medium on which a computer program according to an embodiment of the present invention is recorded.
  • a system for providing advertisements based on object recognition may generate multimedia information, determine and transmit a user image to be transmitted to a service device, and request advertisement information from a service device.
  • a user device for outputting advertisement information received from the service device; And storing the user image received from the user device, extracting feature information of the object included in the user image, performing object recognition based on the extracted feature information of the object, and advertising information based on the recognized thing information.
  • a service device for searching and transmitting the retrieved advertisement information to the user device in response to an advertisement request of the user device.
  • the user may receive advertisement information about necessary item information by determining an interest of the user of the user device based on the image information stored in the user device and providing an advertisement suitable for the interest of the user.
  • advertisement information about necessary item information by determining an interest of the user of the user device based on the image information stored in the user device and providing an advertisement suitable for the interest of the user.
  • marketing can be effectively conducted by limiting the targeting of advertisements.
  • unnecessary analysis loading may be reduced by selecting and analyzing only an image including an advertisement target object among the user's images.
  • FIG. 1 is a conceptual diagram illustrating an advertisement recommendation system through object recognition in a picture according to an embodiment of the present invention.
  • FIG. 2 is a conceptual diagram illustrating an advertisement recommendation system through object recognition in a photo according to an exemplary embodiment of the present invention.
  • FIG. 3 is a conceptual diagram illustrating a method for finding advertisement information matching device information according to an embodiment of the present invention.
  • FIG. 4 is a flowchart illustrating a method of configuring a search index DB unit based on image information transmitted from a user device according to an embodiment of the present invention.
  • FIG. 5 is a flowchart illustrating a method of configuring a search index DB unit based on image information of an advertisement according to an embodiment of the present invention.
  • FIG. 6 is a flowchart illustrating a method for requesting an advertisement and receiving an advertisement in a user device according to an embodiment of the present invention.
  • FIG. 7 is a conceptual diagram illustrating a method for providing an advertisement to a user device according to an embodiment of the present invention.
  • FIG. 8 is a conceptual diagram illustrating a method for providing an advertisement to a user device according to an embodiment of the present invention.
  • first and second used in the present invention may be used to describe components, but the components should not be limited by the terms. The terms are used only to distinguish one component from another.
  • first component may be referred to as the second component, and similarly, the second component may also be referred to as the first component.
  • a user of a user equipment may frequently photograph objects (or objects) of which he is interested. That is, the more objects that appear in the image photographed by the user, the higher the interest of the user may be. For example, a user may photograph a nearby object of interest, such as a book, pet, person, clothes, using a user device such as a smartphone.
  • An embodiment of the present invention discloses a method of targeting and transmitting specific advertisement information to a user of a user device based on image information photographed based on the user device.
  • the click through rate (CTR) and the effective cost per mille (eCPM) of the advertisement may be increased.
  • CTR is the clickthrough rate
  • eCPM is the effective clickthrough rate.
  • the description is based on image information photographed based on a user device, but various information such as video information and multimedia content information stored in the user device targets an advertisement adaptively specific to an individual user. It can be used as information for
  • FIG. 1 is a conceptual diagram illustrating a system for providing an advertisement based on object recognition in a photo according to an embodiment of the present invention.
  • FIG. 1 schematically illustrates a method of targeting and transmitting specific advertisement information to a user device based on image information captured by the user device.
  • a system for providing an advertisement based on object recognition in a photo may include a user device and a service device.
  • the user device may include a multimedia information generation unit 100, a transmission image determination unit 110, an advertisement output unit 120, a communication unit 130, and a processor 140.
  • the service device may include an image collection unit 150, a object recognition unit 160, a search unit 170, an advertisement information processor 180, a communication unit 190, and a processor 190.
  • Components of the user device and the service device are functionally classified to describe the functions of each device, and a plurality of components may be implemented as one component or one component may be implemented as a plurality of components.
  • the multimedia information generating unit 100 may be implemented to generate multimedia information.
  • the multimedia information may include various information such as image information, video information, and sound information.
  • the multimedia information generation unit 100 may be a camera application installed in the user device.
  • the embodiment of the present invention discloses image information among multimedia information for convenience of description.
  • the transmission image determiner 110 may be implemented to determine information to be transmitted to the service device among the image information generated by the multimedia information generator 100.
  • the service device may determine an advertisement to be transmitted to the user device based on the image information determined by the transmission image determiner 110.
  • the transmission image determiner 110 may be implemented based on a software development kit (SDK), and may determine an image to be transmitted to the service device by identifying an image storage path of an application for generating image information in the user device.
  • SDK software development kit
  • the image transmitted from the user device is called a user image.
  • the advertisement output unit 120 may be implemented to request advertisement information from the service device and output advertisement information received from the service device.
  • the advertisement output unit 120 may also be implemented based on the SDK.
  • the communication unit 130 may be implemented to transmit and receive data with the service device.
  • the processor 140 may be implemented to control the multimedia information generation unit 100, the transmission image determination unit 110, the advertisement output unit 120, and the communication unit 130.
  • the service device may include an image collector 150, a object recognizer 160, a searcher 170, an advertisement information processor 180, a communicator 190, and a processor 195.
  • the image collector 150 may be implemented to store a user image received from the user device.
  • the image collector 150 may store the user image determined by the transmission image determiner 110 of the user device and transmitted from the user device, as a file.
  • the object recognizer 160 may be implemented to recognize an object of a user image stored in the image collector 150.
  • the object recognition unit 160 may extract feature information of an object included in a user image.
  • the object recognition unit 160 may recognize which object the object corresponds to based on the extracted feature information of the object. For example, when the feature information of the object matches the feature information of the car, the object recognition unit 160 may recognize the object as a car.
  • the thing recognition unit 160 may allocate an identifier (identifier, id) (hereinafter referred to as a thing identifier) of the thing to the object included in the user image. By mapping the thing identifier of the object included in the user image and the identifier of the user device photographing the object, a table in which the identifier of the user device and the thing identifier are mapped may be generated.
  • the object recognition unit 160 may perform object recognition based on the advertisement image information included in the advertisement and allocate the thing identifier to the object included in the advertisement image.
  • the thing recognition unit 160 may map the thing identifier of the object included in the advertisement image and the identifier information of the advertisement. A table that maps thing identifiers to advertisement identifiers can be created.
  • the search unit 170 may search for advertisement information on the user device based on the information about the thing that has been recognized by the thing recognition unit 160.
  • the searcher 170 may use the user device based on a table that maps identifier information (for example, device_id or mdn (mobile directory number)) and thing identifier information of the user device, and a table that maps thing identifier information and advertisement identifier information. Search for an advertisement to be sent to.
  • the advertisement information processing unit 180 may be implemented to transmit the retrieved advertisement information to the user terminal based on identifier information of the user terminal.
  • the communication unit 190 may be implemented to transmit and receive data between the user device and the service device.
  • the processor 195 may be implemented to control operations of the image collector 150, the object recognizer 160, the searcher 170, the advertisement information processor 180, and the communicator 190.
  • FIG. 2 is a conceptual diagram illustrating an advertisement providing system based on object recognition in a photo according to an exemplary embodiment of the present invention.
  • 2 specifically discloses a method in which a user device receives advertisement information based on image information captured by the user device. 2 may correspond to operations of the components included in the user apparatus and the service apparatus illustrated in FIG. 1. Although the specific connection relationship between each component is not shown, the following may have a specific connection relationship between each component according to an embodiment of the present invention.
  • each component is included in the service device, but each component may be implemented as a separate device.
  • each component is functionally separated, and a single component may be implemented by a plurality of components, or a plurality of components may be implemented by a single component.
  • the image information processor 200 of the user device may transmit the captured user image to the image collector 205.
  • the image information processor 200 may generate a user image through an image capturing application provided in the user device.
  • the image information processor 200 may determine an image storage path of the image capturing application and transmit the user image to the image collector 205.
  • the image collector 205 may store the user image received from the image information processor 200 of the user device in the form of a file.
  • the input information feature extractor 210 may read a user image and extract feature information.
  • the input information feature extractor 210 may read a user image stored in the image collector 205 and extract feature information.
  • the input information feature extractor 210 may extract features (eg, detailed information such as color and shape) of an object (eg, a car) of the user image.
  • the input information feature extraction unit 210 may be implemented to analyze the location of the registered advertisement later, and to establish a relationship between the thing identifier and the advertisement by analyzing the feature information.
  • feature points may be extracted using edge information of an image as a feature, and feature information for each object may be extracted by setting relationship information between feature points.
  • the feature information of the object may be determined by separating the background and the object in consideration of color information and extracting feature points for each separated object.
  • the object recognition unit 215 may perform object recognition by comparing the feature information stored in the object feature information DB unit 220 for object recognition based on the feature information of the object extracted by the input information feature extractor 210. Can be.
  • the feature information DB unit 220 may include feature information of various objects.
  • the thing recognizing unit 215 may determine the similarity between the feature information of the objects included in the thing feature information DB unit 220 and the feature information of the object extracted from the user image. As a result of the similarity determination, the object having the highest similarity with the object of the user image among the objects included in the object feature information DB unit 220 may be determined as the final recognized object.
  • the thing recognizing unit 215 may match the identifier of the thing determined as the last recognized thing with the object of the user image.
  • the thing recognizing unit 215 may return the information about the thing identifier corresponding to the object of the user image to the search index construction unit 225.
  • the object recognition unit 215 may obtain object identifier information corresponding to the object included in the advertisement image based on the object feature information included in the registered advertisement image.
  • the information on the thing identifier corresponding to the object of the user image and the information on the thing identifier corresponding to the object included in the advertisement image may be used to generate the device-object relationship table and the thing-advertisement relationship table.
  • the search index construction unit 225 and the search index DB unit 230 may be implemented to form relationship information about the thing recognized by the thing recognition unit.
  • FIG. 3 is a conceptual diagram illustrating a method for finding advertisement information matching device information according to an embodiment of the present invention.
  • mapping relationship between information is disclosed based on a table for convenience of description, but the mapping relationship may be expressed in other various ways.
  • the search index construction unit 225 may configure, for example, a device-object relationship table.
  • the device-object relationship table defines device identifier information (device id or mdn (mobile device number)) as a first field and thing identifier information as a second field, thereby providing information on a relationship between device identifier information and thing identifier information. Can be defined.
  • the search index configuration unit 225 may configure, for example, an object-advertisement relationship table.
  • the thing-advertisement relation table may define advertisement identifier information as a first field, and the second field may define thing identifier information to define information about a relationship between the thing identifier information and the advertisement identifier information.
  • the thing identifier information for the device identifier information of the specific user device may be found based on the device-object relationship table, and the advertisement identifier for the specific thing identifier may be found based on the thing-advertisement relationship table.
  • a device thing relationship table in which an object called a car is mapped to the user device may be formed by the user device photographing an image of the car.
  • an object-advertisement relationship table may be formed in which an identifier of a car and a vehicle advertisement is mapped in the vehicle advertisement. In this case, the vehicle advertisement may be provided to the user device.
  • advertisement information corresponding to the user device may be found based on the two tables.
  • the relationship between the device-object relationship table and the object-advertisement relationship table may be matched by a 0 ... n relationship.
  • data may be managed separately from each other, and the correlation between the two tables (the device-object relationship table and the object-advertisement relationship table) may be checked in actual search.
  • the device-object relationship table may be updated based on the image sent from the user device.
  • the thing-ad relation table may be updated through material analysis when registering a creative mapped to a thing identifier.
  • the search index DB unit 230 may store information about the device-object relationship table and the object-advertisement relationship table.
  • the advertisement identifier information corresponding to the device identifier information input by the searcher 235 may be transmitted to the searcher 235.
  • the search index DB unit 230 may manage a separate index by mapping the thing identifier to the thing for ease of searching. In addition, the index may be mapped to the device identifier information. In addition, the search index DB unit 230 may delete the mapping information for the advertisement identifier information of the terminated advertisement.
  • the search unit 235 may be implemented to search for advertisement identifier information corresponding to the device identifier based on the search index DB unit 230.
  • the search unit 235 may search for advertisement identifier information matching the device identifier information and transmit the advertisement identifier information to the advertisement transmitting unit 240.
  • the advertisement register 250 may be implemented to register an advertisement.
  • the feature information extractor 210 may extract feature information about the material of the advertisement to be registered.
  • the input information feature extractor 210 may extract feature information from an object included in an image of an input advertisement.
  • the feature information of the extracted advertisement image may be mapped to object identifier information of the corresponding object through the object recognition unit 215.
  • the thing-ad table may be generated based on the relationship between the recognized thing identifier and the advertisement identifier, which may be stored in the search index DB unit.
  • the advertisement sending unit 240 may be responsible for sending an advertisement and may transmit the searched advertisement based on the search unit 235.
  • the user device may perform an advertisement request based on the SDK.
  • the search unit 235 may be used to search for an advertisement identifier corresponding to the device identifier of the user device based on the device identifier received from the user device. For example, the searcher 235 may obtain a thing identifier mapped to the device identifier based on the device-object relationship table information. In addition, the searcher 235 may obtain an advertisement identifier mapped to the thing identifier based on the thing-advertisement relationship table. The searcher 235 may transmit the searched result to the advertisement transmitter 240.
  • the advertisement transmitter 240 may transmit the advertisement to the user device. On the contrary, if there is no advertisement searched based on the searcher 235, the advertisement transmitting unit 240 may search for another scheduling advertisement, search for an advertisement to be transmitted to the user device, and transmit the scheduled advertisement to the user device.
  • the advertisement scheduling unit 245 may be implemented to determine advertisement information scheduled for transmission to the user device.
  • the advertisement content unit 255 may be implemented to register the advertisement content with the advertisement registration unit 250 or determine the advertisement content to be transmitted to the user device.
  • the advertisement DB unit 260 may be connected to the advertisement scheduling unit 245 to perform advertisement scheduling, and may be connected to the advertisement registration unit 250 to perform advertisement registration.
  • an embodiment of the present invention posts a method of transmitting advertisement information corresponding to a user device based on a flowchart.
  • FIG. 4 is a flowchart illustrating a method of configuring a search index DB unit based on image information transmitted from a user device according to an embodiment of the present invention.
  • FIG. 4 illustrates a method of generating and storing a device-object relationship table in a search index DB by performing feature information extraction and object recognition based on image information transmitted from a user device.
  • the user device may transmit an image captured based on the SDK to the image collector (step S400).
  • the user device may be equipped with an image capturing application. Images can be captured via an image capture application.
  • the SDK may determine the image storage path of the image capturing application and transmit the user image to the image collecting unit.
  • the image collecting unit transmits the image information to the input information feature extracting unit (step S410).
  • the image collector may store an image received from the user device in the form of a file based on the SDK of the user device.
  • the image collector may transmit image information to the input information feature extractor according to a request of the input information feature extractor.
  • the input information feature extractor may read an image and extract feature information of an object included in the image.
  • the input information feature extractor may transmit the feature information of the object to the object recognizer (step S420).
  • the object recognizer may perform object recognition by comparing the feature information stored in the object feature information DB unit for object recognition based on the feature information of the object extracted by the input information feature extractor (step S430).
  • the thing recognizing unit may recognize a thing matching the feature information of the object.
  • the thing that matches the feature information of the object may be specified based on the thing identifier information.
  • the search index construction unit may configure index information for the recognized thing (step S440).
  • the search index configuration unit may generate a device-object relationship table that maps identifier information and thing identifier information of the user device that has transmitted the image including the object.
  • the search index configuration unit may assign and manage an index to a thing identifier and a device identifier for ease of searching.
  • the device-object relationship table may be stored in the search index DB unit (step S450).
  • a device-object relationship table based on index information may be stored. If advertisement information is requested from the user device later, the device-object relationship table may be used to search for a thing identifier corresponding to the device identifier information of the user device.
  • FIG. 5 is a flowchart illustrating a method of configuring a search index DB unit based on image information of an advertisement according to an embodiment of the present invention.
  • FIG. 5 a method of receiving and recognizing advertisement information from an advertisement registration DB unit and an advertisement content unit, extracting feature information and recognition of objects for advertisement image information, and generating and storing a thing-advertisement relationship table in a search index DB unit is posted. do.
  • the advertisement registration DB unit and the advertisement content unit may receive and store an advertisement registered from the advertisement registration unit and store a material file of the advertisement (step S500).
  • the advertisement register may transmit an advertisement image to the input information feature extractor (step S510).
  • the advertisement register may transmit image information included in the advertisement to be transmitted to the input information feature extractor.
  • Image information constituting the advertisement may include objects that constitute the subject of the advertisement.
  • the input information feature extractor may read an image and extract feature information of an object included in the image.
  • the input information feature extractor may transmit the feature information of the object to the object recognizer (step S520).
  • the input information feature extractor may extract feature information of an object included in the image based on the image included in the advertisement related information.
  • the feature information of the extracted object may be transmitted to the object recognition unit.
  • the object recognizer may perform object recognition by comparing the feature information stored in the object feature information DB unit for object recognition based on the feature information of the object extracted by the input information feature extractor (step S530).
  • the thing recognizing unit may recognize a thing matching the feature information of the object included in the advertisement image.
  • the thing that matches the feature information of the object included in the advertisement image may be specified based on the thing identifier information.
  • the search index construction unit may configure index information for the recognized thing (step S540).
  • the search index configuration unit may generate a thing-advertisement relationship table that maps identifier information and thing identifier information of the advertisement that transmits the image including the object.
  • the search index configuration unit may assign and manage indexes to thing identifiers and advertisement identifiers for ease of searching.
  • the thing-advertisement relationship table may be stored in the search index DB unit (step S550).
  • the thing-ad relation table based on the index information may be stored. If advertisement information is requested from the user device later, the device-object relationship table is used to search for the thing identifier corresponding to the device identifier information of the user device, and then the advertisement identifier corresponding to the thing identifier is identified through the thing-advertisement relationship table. You can navigate.
  • the advertisement registration procedure is completed (step S560).
  • FIG. 6 is a flowchart illustrating a method for requesting an advertisement and receiving an advertisement in a user device according to an embodiment of the present invention.
  • FIG. 6 a method of transmitting advertisement information corresponding to a user device is posted according to a request of the user device.
  • the advertisement registration DB unit may transmit advertisement scheduling information to the advertisement scheduling unit (step S600).
  • the advertisement scheduling unit may transmit scheduling data to the advertisement transmitting unit (step S610).
  • the advertisement sending unit may receive a request for advertisement information from the user device (step S620).
  • the advertisement sending unit may request a search for advertisement information targeted to the user device based on identifier information of the user device (step S630).
  • the advertisement sending unit may request a search unit to search whether a targeting advertisement matching the user device exists based on the identifier information (device_id, mdn) of the user device which has performed the request for the advertisement information.
  • the search unit may search whether the targeting advertisement corresponding to the user identifier information exists through the search index DB unit (step S640).
  • the search index DB unit transmits the search result to the advertisement sending unit (step S650).
  • the search unit may transmit the search result to the advertisement sending unit.
  • the advertisement transmitting unit may transmit the retrieved advertisement to the terminal based on the search result of the search unit (step S660).
  • the user device may receive the creative from the advertising content unit (step S670).
  • the advertisement is exposed to the user device (step S680).
  • FIG. 7 is a conceptual diagram illustrating a method for providing an advertisement to a user device according to an embodiment of the present invention.
  • FIG. 7 a method of searching for an advertisement target image in an image captured by the user device in providing an advertisement to the user device is described.
  • the feature information extraction procedure and the object recognition procedure may not be performed except for the image for generating the advertisement information.
  • the feature information extraction procedure (step S720) and the object recognition procedure (step S740) may be performed through the advertisement information generation image determination procedure (step S700).
  • the image for generating advertisement information may be determined in various ways.
  • the user device may determine the center object among the objects included in the captured image and determine that the image as the advertisement information generation image only when the center object corresponds to the advertisement target object.
  • the central object may mean an object located at the center of the image or an object focused on the image.
  • the image when the central object of the image captured by the user device is an advertisement target object such as shoes, books, or food, the image may be determined as an advertisement information generation image.
  • the central object of the image photographed by the user device is not an object that is an advertisement target such as a building or a person, it may be determined that the image is not an advertisement information generation image.
  • the advertisement target object may be determined by pre-stored advertisement target object exclusion information.
  • the advertisement target object exclusion information may be preset as information other than the advertisement target object such as a person, a building, and a landscape.
  • the procedure of determining the advertisement information generation image may be performed by the user device or the image collector.
  • the procedure for determining the advertisement information generation image is performed by the user device, only the advertisement information generation image may be transmitted to the image collector.
  • the image collector may transmit only the advertisement information generation image to the input information feature extraction unit.
  • This procedure may be used to determine the advertisement information generating image from the advertisement image information upon advertisement registration. That is, only the advertisement information generation image is extracted from the registered advertisements, and thus the input information feature extraction and object recognition may be performed.
  • FIG. 8 is a conceptual diagram illustrating a method for providing an advertisement to a user device according to an embodiment of the present invention.
  • FIG. 8 a method of considering a frequency of an image captured by a user device and / or a timing of capturing an image in providing an advertisement to the user device is described.
  • the priority of an advertisement to be transmitted to the user device may be determined by recording the frequency of the image photographed by the user device.
  • the advertisement exposure frequency may be adjusted differently according to the frequency of the image.
  • the advertisement for the shoes may be exposed to the user most frequently, and the advertisement for the smartphone and the pants may be exposed to the user in the following order.
  • the exposure frequency of the advertisement may be further adjusted in consideration of the time taken by the user. For example, an image exposure frequency may be adjusted by assigning a higher weight to an image recently stored in a user device. Even if there are two images of the pants, it may be assumed that the image of the pants is the most recently stored image. In this case, weights may be assigned to the pants advertisement to increase the frequency of exposure of the advertisement to the pants.
  • the deleted image in the case of an advertisement related to the deleted image, may be controlled by analyzing the deleted image in the user device.
  • a service device for providing an advertisement based on object recognition may be written as a computer program.
  • the constructing codes and code segments can be easily inferred by a computer programmer in the art.
  • the computer program may be stored in a computer readable media, and the product program may be implemented by being read and executed by a computer or a service device or a user device according to an embodiment of the present invention. .
  • the information storage medium includes a magnetic recording medium, an optical recording medium and a carrier wave medium.
  • a service device for providing an advertisement based on object recognition a user device receiving an advertisement based on the object recognition, and a computer program for implementing a method for providing an advertisement based on the object recognition may include a user device. It can be stored and installed in memory. Or, storing and installing a service device for providing an advertisement based on object recognition according to an embodiment of the present invention, a user device for receiving an advertisement based on the object recognition, and a computer program for implementing a method for providing an advertisement based on the object recognition An external memory such as a smart card may be mounted on a user device or the like through an interface.
  • the present invention can provide an advertisement suitable for the user's interest by determining the user's interest of the user device based on the image information stored in the user device.
  • the image information stored in the user device only the image including the advertisement target item that the user is interested in is selected, and the priority of the user's item of interest is determined based on the image stored in the user device.
  • advertisements can be effectively targeted to the user of the user device.
  • it is possible to minimize unnecessary advertisements to the user and increase the click through rate (CTR) and the effective cost per mille (eCPM) of the advertisement.
  • CTR click through rate
  • eCPM effective cost per mille

Landscapes

  • Business, Economics & Management (AREA)
  • Strategic Management (AREA)
  • Engineering & Computer Science (AREA)
  • Accounting & Taxation (AREA)
  • Development Economics (AREA)
  • Finance (AREA)
  • Economics (AREA)
  • Game Theory and Decision Science (AREA)
  • Entrepreneurship & Innovation (AREA)
  • Marketing (AREA)
  • Physics & Mathematics (AREA)
  • General Business, Economics & Management (AREA)
  • General Physics & Mathematics (AREA)
  • Theoretical Computer Science (AREA)
  • Management, Administration, Business Operations System, And Electronic Commerce (AREA)
  • Information Transfer Between Computers (AREA)

Abstract

La présente invention concerne un appareil de service de fourniture de publicité à base de reconnaissance d'objet, un équipement d'utilisateur de réception de publicité à base de reconnaissance d'objet, un système de fourniture de publicité à base de reconnaissance d'objet, un procédé associé et un support d'enregistrement associé dans lequel est enregistré un programme d'ordinateur. C'est-à-dire, en analysant une image publicitaire comprise dans une image d'utilisateur et une publicité transmise par l'équipement d'utilisateur, la présente invention permet de déterminer la présence éventuelle d'informations à mettre en concordance les unes avec les autres. Selon le procédé ci-dessus, il est possible de transmettre une publicité répondant à l'intérêt d'un utilisateur à l'équipement d'utilisateur, ce qui permet d'assurer une annonce publicitaire efficace.
PCT/KR2014/011175 2014-02-26 2014-11-20 Appareil de service de fourniture de publicité à base de reconnaissance d'objet, équipement d'utilisateur de réception de publicité à base de reconnaissance d'objet, système de fourniture de publicité à base de reconnaissance d'objet, procédé associé et support d'enregistrement associé dans lequel est enregistré un programme d'ordinateur WO2015129987A1 (fr)

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
KR10-2014-0022319 2014-02-26
KR1020140022319A KR20150101488A (ko) 2014-02-26 2014-02-26 사물 인식에 기반한 광고를 제공하는 서비스 장치, 사물 인식에 기반한 광고를 수신하는 사용자 장치, 사물 인식에 기반한 광고를 제공하는 시스템, 방법 및 컴퓨터 프로그램이 기록된 기록매체

Publications (1)

Publication Number Publication Date
WO2015129987A1 true WO2015129987A1 (fr) 2015-09-03

Family

ID=54009272

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/KR2014/011175 WO2015129987A1 (fr) 2014-02-26 2014-11-20 Appareil de service de fourniture de publicité à base de reconnaissance d'objet, équipement d'utilisateur de réception de publicité à base de reconnaissance d'objet, système de fourniture de publicité à base de reconnaissance d'objet, procédé associé et support d'enregistrement associé dans lequel est enregistré un programme d'ordinateur

Country Status (2)

Country Link
KR (1) KR20150101488A (fr)
WO (1) WO2015129987A1 (fr)

Cited By (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
WO2017171231A1 (fr) * 2016-04-01 2017-10-05 Samsung Electronics Co., Ltd. Procédé de synthèse d'image et dispositif électronique utilisant celui-ci
CN110049094A (zh) * 2019-02-28 2019-07-23 阿里巴巴集团控股有限公司 信息推送的方法和线下展示终端

Families Citing this family (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN112954410A (zh) * 2018-01-19 2021-06-11 西安万像电子科技有限公司 多媒体信息的推送方法、装置和系统

Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20080306749A1 (en) * 2007-06-05 2008-12-11 Fredlund John R System and method for presenting image bearing products for sale
KR20090014655A (ko) * 2007-08-06 2009-02-11 주식회사 인스프리트 맞춤형 광고 서비스 제공 장치 및 방법
US20100228558A1 (en) * 2009-03-03 2010-09-09 International Business Machines Corporation Aggregate Content-Based Advertising
US20110295693A1 (en) * 2010-06-01 2011-12-01 Microsoft Corporation Generating Tailored Content Based On Scene Image Detection
KR20120003587A (ko) * 2010-07-05 2012-01-11 에스케이플래닛 주식회사 객체 인식 기반 쇼핑 정보 서비스 제공 방법, 서버 및 시스템

Patent Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20080306749A1 (en) * 2007-06-05 2008-12-11 Fredlund John R System and method for presenting image bearing products for sale
KR20090014655A (ko) * 2007-08-06 2009-02-11 주식회사 인스프리트 맞춤형 광고 서비스 제공 장치 및 방법
US20100228558A1 (en) * 2009-03-03 2010-09-09 International Business Machines Corporation Aggregate Content-Based Advertising
US20110295693A1 (en) * 2010-06-01 2011-12-01 Microsoft Corporation Generating Tailored Content Based On Scene Image Detection
KR20120003587A (ko) * 2010-07-05 2012-01-11 에스케이플래닛 주식회사 객체 인식 기반 쇼핑 정보 서비스 제공 방법, 서버 및 시스템

Cited By (7)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
WO2017171231A1 (fr) * 2016-04-01 2017-10-05 Samsung Electronics Co., Ltd. Procédé de synthèse d'image et dispositif électronique utilisant celui-ci
US10043260B2 (en) 2016-04-01 2018-08-07 Samsung Electronics Co., Ltd. Method for synthesizing image and an electronic device using the same
CN108781262A (zh) * 2016-04-01 2018-11-09 三星电子株式会社 用于合成图像的方法和使用该方法的电子装置
US11145047B2 (en) 2016-04-01 2021-10-12 Samsung Electronics Co., Ltd. Method for synthesizing image and an electronic device using the same
CN108781262B (zh) * 2016-04-01 2022-03-08 三星电子株式会社 用于合成图像的方法和使用该方法的电子装置
CN110049094A (zh) * 2019-02-28 2019-07-23 阿里巴巴集团控股有限公司 信息推送的方法和线下展示终端
CN110049094B (zh) * 2019-02-28 2022-03-04 创新先进技术有限公司 信息推送的方法和线下展示终端

Also Published As

Publication number Publication date
KR20150101488A (ko) 2015-09-04

Similar Documents

Publication Publication Date Title
US11659220B2 (en) System and method for surveying broadcasting ratings
WO2012020927A1 (fr) Système de recherche d'image intégré et procédé de service associé
WO2013141630A1 (fr) Terminal de communication mobile et procédé de recommandation d'une application ou d'un contenu
WO2012060537A2 (fr) Système de recommandation basé sur la reconnaissance d'un visage et d'un style, et procédé associé
WO2014069891A1 (fr) Procédé et dispositif pour fournir des informations concernant un objet
WO2012128538A2 (fr) Système de traitement de code d'identification, son procédé et appareil permettant de les prendre en charge
WO2015147437A1 (fr) Système de service mobile, et méthode et dispositif de production d'album basé sur l'emplacement dans le même système
WO2020032487A1 (fr) Procédé de fourniture d'informations relatives à des marchandises sur la base d'une priorité et dispositif électronique associé
WO2016035970A1 (fr) Systeme publicitaire utilisant une recherche de publicite
WO2016013767A1 (fr) Procédé pour assurer un service de communications entre terminaux mobiles en utilisant un dispositif sans fil en champ proche
WO2019164288A1 (fr) Procédé de fourniture de données de gestion de traduction de texte associées à une application, et dispositif électronique associé
US10628955B2 (en) Information processing device, information processing method, and program for identifying objects in an image
WO2020032383A1 (fr) Dispositif électronique permettant de fournir un résultat de reconnaissance d'un objet externe à l'aide des informations de reconnaissance concernant une image, des informations de reconnaissance similaires associées à des informations de reconnaissance, et des informations de hiérarchie, et son procédé d'utilisation
WO2013165083A1 (fr) Système et procédé de fourniture de service de vidéo fondée sur une image
WO2015129987A1 (fr) Appareil de service de fourniture de publicité à base de reconnaissance d'objet, équipement d'utilisateur de réception de publicité à base de reconnaissance d'objet, système de fourniture de publicité à base de reconnaissance d'objet, procédé associé et support d'enregistrement associé dans lequel est enregistré un programme d'ordinateur
WO2015080347A1 (fr) Procédé, support de stockage et appareil pour réaliser un service entre pairs en utilisant des renseignements de contacts
WO2016114475A1 (fr) Procédé pour fournir un service préétabli par courbure d'un dispositif mobile selon une entrée d'utilisateur de courbure de dispositif mobile et dispositif mobile réalisant ce dernier
WO2020085558A1 (fr) Appareil de traitement d'image d'analyse à grande vitesse et procédé de commande associé
WO2018066938A1 (fr) Dispositif d'affichage, procédé de commande associé, et système de fourniture d'informations
WO2020171558A1 (fr) Procédé de fourniture de contenus de réalité augmentée et dispositif électronique associé
WO2014148691A1 (fr) Dispositif mobile et son procédé de commande
WO2019164196A1 (fr) Dispositif électronique et procédé de reconnaissance de caractères
WO2023027389A1 (fr) Dispositif de fourniture de contenus et procédé associé
KR20120076570A (ko) 광고 시스템 및 광고 제공 방법
CN111223220A (zh) 一种影像关联方法、装置及服务器

Legal Events

Date Code Title Description
121 Ep: the epo has been informed by wipo that ep was designated in this application

Ref document number: 14884118

Country of ref document: EP

Kind code of ref document: A1

NENP Non-entry into the national phase

Ref country code: DE

122 Ep: pct application non-entry in european phase

Ref document number: 14884118

Country of ref document: EP

Kind code of ref document: A1