Method and apparatus for controlling intelligent content output of digital signage by using big data related to visitor type, and computer-readable recording medium

Abstract

To provide an intelligent content output method, an intelligent content output device, and a recording medium that use attribute information of an object around a digital signage to select data to be output or control an output form and a pattern at the output of the data.SOLUTION: A method includes: a user information extraction step of analyzing a picture image in a photographed content output area direction and extracting attribute information of a user who checks a digital content as an object in the picture image; a data storage step of generating analysis target data obtained by matching user information and the digital content by using an output time point of the digital content on the basis of an acquisition time point of the user information and drive log data for a digital signage, and storing the analysis target data in a database; and an output control step of controlling an output content, an output form of the content, output brightness of the digital signage, and whether to drive the digital signage on the basis of the analysis target data or the user information.SELECTED DRAWING: Figure 1

Description

[Technical field]

[0001] The present invention relates to a technology for intelligently controlling output using a large amount of data related to visitor types when outputting content using digital signage, and more particularly, to a technology for selecting data to be output or controlling the output form and pattern when outputting data using attribute information of objects photographed around the digital signage. [Background technology]

[0002] Generally, people tend to think of digital signage as a large display installed for advertising purposes. However, digital signage has expanded beyond the scope of the advertising genre and has become functionally more flexible as a digital information medium, and all outdoor digital media can be defined as digital signage.

[0003] Recently, digital signage services have become capable of linking with technologies such as big data and artificial intelligence, and are now being used for a variety of purposes, including not only advertising but also public safety services, local information provision, and mobile-linked events. It is predicted that the use of digital signage in the 4th Industrial Revolution, smart cities, 5G convergence services, and other areas will become even more active.

[0004] For example, next-generation digital signage technology is expected to go beyond being a simple means of providing information; it is expected to function as a knowledge hub that provides content optimized for surrounding objects and acts as an information distribution channel between objects.

[0005] As a related technology, Patent Document 1 proposes a technology in which a user is photographed near a display unit (compatible with digital signage) and the level of interest is estimated from situational information including user information, the user's direction of movement, attention time, number of times of attention, and dwell time from the captured image, and content is recommended to be output from the display unit.

[0006] The above-mentioned conventional technology has some effective aspects in terms of selective content recommendation functions, such as recommending content to be output based on user information, but has some shortcomings in terms of controlling content output to effectively output content using user information.

[0007] Furthermore, when predicting user information that serves as a basis for content selection, etc., if only recently used facial recognition or the like is used, the recognition results will inevitably be affected by the installation environment of the digital signage, making it impossible to accurately predict user information, and there is a problem that no technology exists to correct or learn from this. [Prior art documents] [Patent documents]

[0008] [Patent Document 1] Korean Patent No. 10-1744940 Summary of the Invention [Problem to be solved by the invention]

[0009] The present invention has been made to solve the problems of the conventional technology as described above, and its purpose is, first, to provide a technology that increases the utilization rate of digital signage by controlling the output of content using user attribute information, automatically controlling not only the content selection but also the content output format to suit the user, and allowing the user to easily view content in a format preferred or customized according to gender and age.

[0010] Another object of the present invention is to provide a technology that, when predicting user attribute information, does not merely use image recognition, but learns an image recognition algorithm or a data analysis algorithm to improve prediction accuracy by using input data of the object at the time of image recognition, thereby further improving the prediction accuracy of user attribute information for the entire digital signage depending on the installation position of the digital signage, thereby enabling precisely customized content output control. [Means for solving the problem]

[0011] In order to achieve the above object, an intelligent content output method for digital signage using big data on visitor types according to one embodiment of the present invention includes a user information extraction step of analyzing a plurality of image images received from an image capturing device mounted on the digital signage and capturing images in the direction of a content output area, and extracting attribute information of a user who confirms digital content as an object within the image image; a data storage step of generating analysis target data by matching user information and digital content using the acquisition time of the user information and the output time of the digital content extracted based on the operation log data for the digital signage, and storing the data in a database; and an output control step of controlling the output content, the output form of the content, the output brightness of the digital signage, and whether or not to operate the digital signage based on the analysis target data or the user information.

[0012] The user information extraction step includes an object extraction step of extracting an object region constituting the user's body from an image received from a plurality of digital signages, and a first information extraction step of deriving the gender and age of the object using at least one of a first algorithm based on the static or dynamic connection relationship of the face region, shoulder region, arm region, and upper body region among the object region, and a second algorithm which is an artificial intelligence gender and age recognition algorithm for the face region, and extracts the gender and age of the object as attribute information of the user.

[0013] The user information extraction step further includes a second information extraction step of extracting the user's gender and age based on input information input from the digital signage at the time of acquiring the image used in the object extraction step, and an algorithm learning step of learning the algorithm used in the first information extraction step from among the first algorithm and the second algorithm, using the gender and age of the object derived in the first information extraction step and the gender and age of the user derived in the second information extraction step.

[0014] The second information extraction step, when receiving direct numerical information, which is numerical information for the user's gender and age, from the input information, extracts the user's gender and age directly into numerical information, or extracts the user's gender and age from the result value of a third algorithm that predicts the user's gender and age based on the user's input speed, input accuracy, and input pattern regarding the input information.

[0015] The second information extraction step trains the third algorithm using a result value of the third algorithm at the time when the direct numerical information is received.

[0016] The output control step controls a size of text included in the content and an output brightness of the digital signage with priority when controlling the output of the content based on information related to age among the attribute information of the user.

[0017] When the user attribute information extracted at the same time is determined to be diverse, the output control step outputs a first content having metadata matching the user attribute information having the highest priority according to an attribute comparison algorithm that calculates the priority between the user attribute information, and outputs a content selection area in which one of the second contents having metadata matching the various user attribute information can be selected together with the output area of ​​the first content.

[0018] In the output control step, when there is no user attribute information extracted at a given point in time or extraction of user attribute information based on an image fails, content to be output to the digital signage is selected based on a first selection condition, and a user visit pattern in the space in which the digital signage is installed is selected as a second selection condition, so that content satisfying the first and second selection conditions is output to the digital signage.

[0019] In addition, an intelligent content output device for digital signage using big data on visitor types in one embodiment of the present invention is characterized in that it includes a user information extraction unit that is mounted on the digital signage and analyzes a plurality of image images received from an image capturing device that captures images in the direction of the content output area, and extracts attribute information of a user who confirms digital content as an object within the image image; a data storage unit that generates analysis target data by matching user information and digital content using the acquisition time of the user information and the output time of the digital content extracted based on the operation log data for the digital signage, and stores the data in a database; and an output control unit that controls the output content, the output form of the content, the output brightness of the digital signage, and whether or not to operate the digital signage based on the analysis target data or the user information. Effect of the Invention

[0020] According to the present invention, image data captured by an image capturing device of a digital signage is used to predict attribute information of an object, such as a user's gender and age, and the content being viewed by the user at the time of prediction is used to analyze the relevance of content based on the user's attribute information, and based on the results, content is selected, or the output format and brightness of the content are controlled based on the user's attribute information.

[0021] In this case, it is possible to output intelligent content by learning a prediction algorithm for content preferred by the user based on the user's attribute information using the user's usage content at the time of prediction with great precision, and it is also possible to control the output of content in a form and brightness that is easy for the user to recognize based on the user's attribute information, thereby allowing the user to easily view content in a customized form that is preferred based on gender and age, thereby increasing the utilization rate of digital signage.

[0022] Furthermore, when predicting user attribute information, simple image recognition is not used, but the input data of the object at the time of image recognition is used to improve prediction accuracy, and algorithms for predicting user attribute information through image recognition and predicting user attribute information through input data analysis are learned.This makes it possible to further improve the prediction accuracy of user attribute information for the entire digital signage, depending on the installation location of the digital signage, and precisely customize content output control. [Brief description of the drawings]

[0023] [Figure 1] FIG. 1 is a flowchart illustrating a method for intelligent content output of a digital signage using big data on visitor types according to an embodiment of the present invention. [Diagram 2] FIG. 2 is a flowchart illustrating a method for intelligent content output of a digital signage using big data on visitor types according to an embodiment of the present invention. [Diagram 3]FIG. 3 is a flowchart illustrating a method for outputting intelligent content of a digital signage using big data on a visitor type according to an embodiment of the present invention. [Figure 4] FIG. 4 is a block diagram of an intelligent content output device for digital signage using big data on visitor types according to an embodiment of the present invention. [Diagram 5] FIG. 5 is a diagram for explaining a first information extraction step according to an embodiment of the present invention. [Figure 6] FIG. 6 is a diagram for explaining an algorithm learning step according to an embodiment of the present invention. [Figure 7] FIG. 7 is a diagram for explaining a second information extraction step according to an embodiment of the present invention. [Figure 8] FIG. 8 is a diagram showing an example of a screen output to a digital kiosk according to an embodiment of the present invention. [Figure 9] FIG. 9 is a diagram showing an example of a screen output to a digital kiosk according to an embodiment of the present invention. [Figure 10] FIG. 10 is a diagram showing an example of the internal configuration of a computing device according to an embodiment of the present invention. DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS

[0024] Various embodiments and / or aspects are described below with reference to the drawings. In the following description, for purposes of explanation, numerous specific details are disclosed in order to facilitate a general understanding of one or more aspects. However, those skilled in the art will recognize that these aspects may be practiced without such specific details. The following description and the accompanying drawings set forth certain exemplary aspects of one or more aspects in detail. However, such aspects are illustrative, and some of the various methods of the principles of the various aspects may be utilized, and the description is intended to include all such aspects and their equivalents.

[0025] As used in this specification, "embodiment," "example," "mode," "exemplary," and the like may not be construed as construing any described mode or design as being better or advantageous over other modes or designs.

[0026] Additionally, the terms "comprise" and / or "comprising" are to be understood as meaning that the stated features and / or components are present, but not excluding the presence or addition of one or more other features, components and / or groups thereof.

[0027] Additionally, terms including ordinal numbers such as first, second, etc. are used to describe various components, but the components are not limited by the terms. The terms are used only to distinguish one component from another. For example, a first component can be referred to as a second component, and similarly, a second component can be referred to as a first component, without departing from the scope of the invention. The term "and / or" includes a combination of multiple related listed items or any of multiple related listed items.

[0028] In addition, unless otherwise defined in the embodiments of the present invention, all terms used herein, including technical and scientific terms, have the same meaning as commonly understood by a person having ordinary skill in the art to which the present invention belongs. Terms defined in commonly used dictionaries should be interpreted as having a meaning consistent with the meaning they have in the context of the relevant art, and should not be interpreted as idealized or overly formal unless explicitly defined in the embodiments of the present invention.

[0029] Figures 1 to 3 are flowcharts of a method for outputting intelligent content for digital signage using big data on visitor types according to one embodiment of the present invention, Figure 4 is a block configuration diagram of a device for outputting intelligent content for digital signage using big data on visitor types according to one embodiment of the present invention, Figure 5 is a diagram for explaining a first information extraction step according to an embodiment of the present invention, Figure 6 is a diagram for explaining an algorithm learning step according to an embodiment of the present invention, Figure 7 is a diagram for explaining a second information extraction step according to an embodiment of the present invention, and Figures 8 and 9 are diagrams showing examples of screens output to a digital kiosk according to an embodiment of the present invention.

[0030] In the following description, it will be understood that a method for outputting intelligent content for digital signage using big data on visitor types according to an embodiment of the present invention (hereinafter referred to as the "method of the present invention") is performed by a computing device referred to in the description of Fig. 10 described below, or an intelligent content output device 10 for digital signage using big data on visitor types (hereinafter referred to as the "device of the present invention") and detailed components constituting the same referred to in the description of Fig. 4. Therefore, it will be understood that the device 10 of the present invention is included in the computing device of Fig. 10, is constituted as itself, or multiple computing devices are constituted as groupware to constitute the device 10 of the present invention.

[0031] In addition, in the description of the method and apparatus 10 of the present invention, descriptions of known processes for outputting general content, making payments, taking images, etc. using digital signage, and known hardware configurations for performing these processes will be omitted.

[0032] In the method of the present invention, the computing device first performs a user information extraction step (S10) of analyzing a number of image images received from an image capturing device mounted on the digital signage and capturing images in the direction of the content output area, and extracting attribute information of a user who identifies the digital content as an object within the image images.

[0033] In the present invention, digital signage refers to any device that has a touch screen or other input means and output means, is installed indoors or outdoors, and outputs content input by a user. Digital signage also includes devices such as a payment device, an image capture device such as a camera, a sound output device, and a printer for printing, for various functions.

[0034] In the present invention, the content may be composed of a plurality of types. In the case of a traffic information kiosk, the content may be for traffic conditions and related information, in the case of a public institution, the content may be for policy information, information on public services that can be performed through the kiosk, and content that constitutes a processing-related interface, in the case of a general store, the content may be for advertisements, and the content may be related to a product purchasing interface.

[0035] The user information extraction step is a process in which an image is taken in the direction of content output, i.e., in the direction toward the user looking at the digital signage display device, so that the user or an object (such as a vehicle) that can identify the content can be captured, and a computing device receives image images as a number of frame images contained in the image, analyzes them, and extracts attribute information of the user (object) that identifies the digital content as an object within the image image.

[0036] Here, the captured image is a video, and the data to be analyzed includes one or more image images selected to represent the object to be recognized from among many frame images included in the video. Here, representing the object means that the object is completely included within the image frame area, the photographed result of the object is the clearest, and other conditions are met. Among the image images as many frame images included in the image, the images that satisfy the above conditions are analyzed.

[0037] Object recognition means recognizing and identifying an object present in an image using a known artificial intelligence object recognition algorithm, etc. After the object is recognized, the type of the object can be identified using an algorithm such as CNN or RNN, or, as attribute information of the object, for example, the gender and age of the object can be predicted and the predicted gender and age can be extracted as attribute information of the user, as described below.

[0038] In particular, as a specific example of extracting a user's gender and age, an example for improving the extraction accuracy and performing more precise selection and output control of customized content is shown in Figures 2 and 3.

[0039] 2 and 3, the computing device first performs an object extraction step (S11) of extracting object regions constituting a user's body from image images received from a number of digital signages.

[0040] In step S11, the term "multiple digital signages" refers to multiple digital signages that are installed in a region or an area forming an indoor space, are in a relatively similar environment, and are determined to have similar effects on image analysis results, such as environmental information, i.e., temperature, humidity, external lighting, and the like. Alternatively, as described above, temperature, humidity, external lighting, population flow patterns, and the like may be used as metadata and collected for each digital signage for a certain period of time, and digital signages with similar metadata may be grouped into the multiple digital signages. Alternatively, all digital signages from which information can be collected, regardless of environmental information, are included in the concept of the multiple digital signages.

[0041] Thus, when the object region is extracted, the computing device performs a first information extraction step (S12) of deriving the gender and age of the object using at least one of a first algorithm based on the static or dynamic connection relationship of the face region, shoulder region, arm region, and upper body region of the object region, and a second algorithm which is an artificial intelligence gender and age recognition algorithm for the face region, thereby extracting the gender and age of the object as user attribute information, and predicting this as the gender and age of the user. In the following description, all algorithms are understood to be algorithms learned using artificial intelligence, machine learning, deep learning, and big data.

[0042] In the present invention, the first algorithm estimates the user's gender and age by setting points (P) representing joints or facial areas, eyes, nose, mouth, etc. in an image 100 capturing all or part of the body, as shown in Fig. 5, and grasping the user's body shape using the lengths of connecting lines between each point (P) and the vector values ​​between each connecting line. For example, gender can be predicted using the shape of the chest area and the curvature of the body, and age can be predicted by determining aging from the angle between the shoulder and waist line and the head line.

[0043] On the other hand, the second algorithm is a well-known algorithm that uses an image 101 of the facial area to analyze facial curvature, skin roughness, skin color, and shapes of the eyes, lips, nose, etc. using the artificial intelligence, machine learning, deep learning, big data, etc., to predict the gender and age of a user.

[0044] Using such a first algorithm (f1(P)) and a second algorithm (f2(P)), the user's gender and age 110 are derived as described above, and the results are used in steps S20 and S30 described below to select content and control the output of content.

[0045] On the other hand, the first and second algorithms as mentioned above predict the gender and age of a user based on images taken of the user, and have relatively high accuracy through artificial intelligence learning, but as mentioned above, they are affected by the environment in which the digital signage is installed and the mobile population.

[0046] In order to accurately reflect such influences and enable a precise process for content selection and control as described below, in one embodiment of the present invention, step S10 can provide feedback control for further algorithms in addition to steps S11 and S12 described above.

[0047] That is, as shown in FIG. 3, in step S12, the computing device in the present invention performs a second information extraction step (S13) of extracting the user's gender and age based on the input information input from the digital signage at the time of acquiring the image used in the object extraction step (S11).

[0048] The image capturing device inputs information about the user when the user checks the content using the digital signage or interacts with the digital signage. The computing device, which is located in front of the digital signage while the image is being captured by executing step S13, infers or extracts the actual user's gender and age based on the input data, since the object of capturing the image and the subject of input data are the same object.

[0049] Thereafter, an algorithm learning step (S14) is performed in which the algorithm used in the first information extraction step (S12) is learned from the first algorithm (f1(P)) and the second algorithm (f2(P)) using the gender and age of the object derived in the first information extraction step (S12) and the gender and age of the user derived in the second information extraction step (S13).

[0050] 6, in the actual input data 200, the user's gender and age 210 are extracted by precise analysis of the input data. At this time, the gender and age 210 of the user are extracted together with the gender and age 110 of the object derived in step S12, and the result of the user's gender and age 210 is learned through feedback control of the algorithm used in the first information extraction step (S12) out of the first algorithm (f1(P)) and the second algorithm (f2(P)).

[0051] In this case, if input data exists, feedback control is performed, and the accuracy of recognizing and predicting attribute information such as the user's gender and age is higher than when only image analysis is performed. In particular, precise learning is possible by comparing the surrounding environment, such as local demographic characteristics (by race, nationality, culture), temperature, humidity, external lighting, and population mobility patterns, with actual data from the input data, making it possible to make precise judgments about the user's gender and age, which has the effect of making it possible to select and control the output of customized content for the user.

[0052] Meanwhile, the input data is formatted or unformatted data such as characters or images input by a user when using content, and includes data that directly reflects the gender and age of the user or data that varies depending on the gender and age of the user. Also, input characteristics for the input data change depending on the gender and age of the user.

[0053] By reflecting these characteristics more precisely, an embodiment for collecting and reflecting rich big data for predicting a user's gender and age is embodied. For example, in step S13, when the computing device receives direct numerical information 201, which is numerical information related to the user's gender and age, from the input information as shown in Fig. 7, the computing device may extract the user's gender and age 211 as the direct numerical information 201, or may extract the user's gender and age from the result value of a third algorithm (f3(In)) that predicts the user's gender and age 212 based on input data input characteristic information 202 such as the user's input speed, input accuracy, and input pattern for the input information.

[0054] The direct numerical information 201 is data received when a user directly inputs his / her gender and age, and is the most accurate information for predicting or extracting user attribute information. Meanwhile, the probability of accurate input in a specific area is determined depending on the user's gender and age, whether the input speed for input data is fast or slow, and whether the user has advanced presbyopia and has a decline in motor skills. In addition, the possibility of making mistakes in input data and the movement pattern are also configured differently depending on the gender and age, as described above.

[0055] The third algorithm (f3(In)) is an algorithm that predicts the gender and age of a user based on the characteristics of the input data, not on the content of the input data itself. In this case, the input data used for learning the algorithm in step S14 is only used when the direct numerical information 201 is generated, and in this case, the third algorithm is also used for learning.

[0056] That is, in executing step S13, the third algorithm (f3(In)) can be trained using the result value of the third algorithm (f3(In)) at the time when the direct numerical information 201 is received.

[0057] After completing step S10, the computing device performs a data storage step (S20) in which the computing device generates analysis target data by matching the user information and the digital content using the time of acquisition of the user information and the time of output of the digital content extracted based on the driving log data for the digital signage, and stores the data in a database.

[0058] Digital content customized by a user can be stored by matching data on attribute information of an object targeted by the author's intention at the time of generating the digital content as metadata to each digital content.

[0059] However, regardless of the intention of the copyright holder, preferences for content may change depending on the location where the digital signage is installed and the characteristics of the moving population. In order to reflect such characteristics, when the content that is output at the time of generation of the image or input data on which the extracted user attribute information is based is determined, that is, the content that the user is viewing is determined, and big data on the content is constructed. When this is analyzed for a number of digital signages grouped according to the same criteria as the concept of a number of digital signages in step S11, it becomes possible to grasp the content that the user prefers, which reflects the accurate user characteristics and environmental information.

[0060] Thereafter, the computing device performs an output control step (S30) of controlling the output content, the output form of the content, the output brightness of the digital signage, and whether or not the digital signage is operated based on the analysis target data or the user information.

[0061] Here, controlling the content to be output means that when a specific user recognizes in step S10 based on the analysis results of the user's preferred content as described above, content corresponding to the user's preferred content is selected as content matching the metadata of the user and provided to the user.

[0062] Here, using the data to be analyzed means that the storage results mentioned in step S20 and the correlation between the accumulated multiple data to be analyzed are used to analyze the correlation between the content attribute information such as the length, content, and color pattern of the content and the user attribute information using a known correlation analysis algorithm, etc., and thereby select the content that has the highest correlation with the user attribute information from among the contents that can currently be output on the digital signage.

[0063] On the other hand, when many users use one digital signage, there are many contents that match the above-mentioned user attribute information. In this case, when the user attribute information extracted at the same time is determined to be diverse in the execution of step S30, the computing device in Fig. 9 can output the first contents (C1, C2) that are contents having metadata that match the attribute information of the user having the highest priority according to an attribute comparison algorithm that calculates the priority between the user attribute information, and can output a content selection area 311 in which any one of the second contents (C3, C4, C5) that are contents having metadata that match the various user attribute information, in the output area of ​​the first content.

[0064] The priority between user attribute information can be set in advance depending on the installation environment of the digital signage, such as the users who are most likely to use the services provided at the installation location (e.g., the elderly in a nursing home) in the case of a digital signage for public purposes, or the users who are perceived to have the highest purchasing power at the installation location in the case of a digital signage in a general sales area.

[0065] Meanwhile, when reflecting the user's attribute information, especially age, the content output format must be set differently when using digital signage. That is, it is possible to increase the concentration of users by changing the output format depending on whether the user is a child or adolescent, an adult, or an elderly user, or to differentiate the content output method to increase the concentration of users depending on the gender.

[0066] In this case, the content output form refers to all forms of the content output method, such as the content of the image constituting the content, color, interface structure, character size, font, etc.

[0067] In particular, in performing step S30, for example, the computing device may control the size of text included in the content and the output brightness of the digital signage with priority when controlling the output of the content according to information on age among the user attribute information as shown in Fig. 8. That is, for an older user, the size of the text is expanded and a simplified form 301 of the content is output in comparison with the basic output form 300, thereby improving the recognition according to the user attribute information.

[0068] On the other hand, in the execution of step S30, a case may occur where the user attribute information extracted at a certain point in time does not exist, or extraction of the user attribute information based on the image has failed.

[0069] In this case, if no object is identified at all, the output of the content itself, i.e., the driving of the digital signage, is stopped to save power, or the brightness is reduced to save power.

[0070] However, in the case of digital signage that is constantly driven, for example, when selecting content to be output to the digital signage, content that corresponds to the purpose of installing the digital signage can be set as the first selection criterion, and the user visit pattern of the space in which the digital signage is installed can be set as the second selection criterion, and content that satisfies the first and second selection conditions can be output to the digital signage.

[0071] Specifically, in selecting content corresponding to the first selection condition, if the digital signage is installed for commercial purposes, marketing content based on a provider of commercial services is output on the digital signage so as to be utilized as a marketing tool, and if the digital signage is installed for public purposes, public media content received at preset intervals by a server linked to a public institution terminal is output so as to be utilized as an information transmission medium.

[0072] On the other hand, when the database has completed the selection of multiple contents corresponding to the first selection condition described above, the computing device, in executing step S30, selects content from the multiple contents corresponding to the first selection condition, with the user visitation pattern of the space in which the digital signage is installed as the second selection condition.

[0073] In this case, the aforementioned user visitation pattern is understood as deriving the main user gender and main user age group by time period from the user visitation pattern by time period already stored in the space where the digital signage is installed, or as object information based on the aforementioned big data processing results, and applying the first selection condition to select content corresponding to the main user gender and main user age group from among the multiple contents extracted from the database, and outputting it to the digital signage.

[0074] In other words, in the present invention, even if gender and age group are not identified as object information around the digital signage, content preferred by the gender and age group likely to be currently around the digital signage is output to the digital signage based on user visitation patterns in the area where the digital signage is installed, thereby increasing the viewing efficiency of the digital signage and preventing a decline in marketing effectiveness and information transmission effectiveness.

[0075] On the other hand, when the digital signage is installed for public purposes, in executing step S30, the computing device receives public media content at preset intervals from a server linked to the public institution terminal, rather than from a database, and can output the public media content on the digital signage.

[0076] However, if the playback time of the first public media content received by the server linked to the public institution terminal described above is shorter than the time corresponding to the period in which the second public media content is received, and a blank time occurs in which no content is output through the digital signage, in executing step S30 of the present invention, the computing device outputs a section corresponding to a highlight point of the first public media content to the digital signage during the blank time, and then switches the playback to the second public media content received in the next period.

[0077] For example, if the reception cycle of public media content is 10 minutes and the playback time of the first public media content is 8 minutes, a 2-minute blank time will occur. However, in the present invention, during such blank time, the highlight points of the first public media content are repeatedly played back without interrupting the content output on the digital signage, thereby improving the efficiency of information transmission using digital signage.

[0078] In this case, the above-mentioned highlight point can be understood as a concept of a section having a playback time including a part having more objects than the average objects by calculating the average number of objects for each scene constituting the content, or a section having a playback time including a part in which the most color changes occur in the content. By outputting such highlight points in blank time, the information transmission effect of public media content can be further maximized.

[0079] In the process of content conversion, the computing device receives public media content from the public institution server at a preset period, and causes the first public media content previously received to be output on the digital signage.

[0080] At this time, the computing device checks whether the playback time of the first public media content being output to the digital signage is shorter than the period for receiving the next public media content. If the playback time of the first public media content is shorter than the period for receiving the next public media content, step S4 is performed in which highlight points of the first public media content are repeatedly output to the digital signage, thereby eliminating blank time on the digital signage. Thereafter, after checking whether the second public media content has been received, the received second public media content is output to the digital signage.

[0081] Of course, it is understood that when the playback time of the first public media content is the same as the period for receiving the next public media content, the received second public media content is immediately played when the playback of the first public media content ends; when the playback time of the first public media content is longer than the period for receiving the next public media content, the playback of the received second public media content is delayed, and then the playback of the second public media content is performed after the playback of the first public media content is completed.

[0082] In addition, the digital signage of the present invention may be installed in multiple units in one unit space, as shown in Figure 4, and grouping may be performed based on at least one of the installation direction and installation position of the digital signage.

[0083] Specifically, the grouping criteria for the digital signage may be such that digital signages having the same installation direction are grouped into one group, or digital signages installed within a critical area according to the installation position are grouped into one group, etc. Of course, the grouping criteria for the digital signages may be directly set by a management entity that manages the unit space, but the present invention is not limited thereto.

[0084] On the other hand, once grouping of the digital signage dollars is performed, in performing step S30, the computing device can transmit the same content output signal to the digital signage dollars belonging to the same group.

[0085] Furthermore, the digital signage can receive weather information for the area in which it is installed from an external meteorological control center server, obtain information including at least one of the sunrise time and the sunset time from the received weather information, and control the level values ​​of elements including at least one of the screen brightness and luminance of the digital signage based on the amount of sunlight corresponding to the obtained time information.

[0086] Specifically, in the present invention, when there is a lot of sunlight or when the sun is up (from sunrise to sunset), the visibility of the content output through the digital signage tends to decrease slightly due to sunlight, so the brightness and luminance level values ​​of the digital signage are set to values ​​higher than a predetermined level value to prevent the decrease in visibility of the content output through the digital signage. Conversely, when there is little sunlight due to rainy or cloudy weather or when the sun is setting (after sunset), the brightness and luminance of the digital signage are set to values ​​lower than a predetermined level value to minimize light pollution caused by the digital signage and significantly improve energy consumption efficiency.

[0087] Fig. 4 is a configuration block diagram of the above-mentioned device 10 of the present invention, and as shown in Fig. 4, the device 10 of the present invention is linked to or installed inside a digital signage 20, and includes a user information extraction unit 11, a data storage unit 12, and an output control unit 13. At this time, a database 14 is included in the device 10 of the present invention or configured to be linked to the device 10 of the present invention in order to integrally associate the data to be analyzed and various data related to the use of the digital signage.

[0088] The user information extraction unit 11 is mounted on the digital signage 20 and performs a function of analyzing a number of images received from an image capturing device 21 that captures images in the direction of the content output area, and extracting attribute information of a user who recognizes digital content as an object in the image. That is, it can be understood as a configuration that performs all the functions of the computing device mentioned in the description of steps S10 to S14 in the above description.

[0089] The data storage unit 12 performs a function of generating analysis target data that matches user information and digital content using the time point of acquiring user information and the time point of outputting digital content extracted based on the driving log data for the digital signage 20, and storing the data in the database 14. That is, it is understood that the data storage unit 12 is configured to perform all the functions mentioned in the description of step S20 in the above description.

[0090] The output control unit 13 performs a function of controlling the content to be output, the output form of the content, the output brightness of the output means 22 of the digital signage 20, and whether or not the digital signage is driven, based on the analysis target data or user information. That is, it is understood as a configuration that performs all the functions mentioned in the description of step S30 in the above description.

[0091] FIG. 10 shows an example of the internal configuration of a computing device according to an embodiment of the present invention. In the following description, any description that overlaps with the description of FIGS. 1 to 9 will be omitted.

[0092] 10, the computing device 10000 includes at least one processor 11100, a memory 11200, a peripheral device interface 11300, an input / output subsystem 11400 (I / O subsystem), a power circuit 11500, and a communication circuit 11600. In this case, the computing device 10000 corresponds to a user terminal (A) connected to a haptic interface device, or the above-mentioned computing device (B).

[0093] The memory 11200 may include, for example, a high-speed random access memory, a magnetic disk, an SRAM, a DRAM, a ROM, a flash memory, or a non-volatile memory. The memory 11200 may include software modules, a set of commands, or other various data required for the operation of the computing device 10000.

[0094] At this time, access to the memory 11200 from other components such as the processor 11100 and the peripheral device interface 11300 is controlled by the processor 11100.

[0095] The peripheral device interface 11300 couples input and / or output peripheral devices of the computing device 10000 to the processor 11100 and the memory 11200. The processor 11100 executes software modules or sets of commands stored in the memory 11200 to perform various functions and process data for the computing device 10000.

[0096] The I / O subsystem 11400 couples various I / O peripherals to the peripheral interface 11300. For example, the I / O subsystem 11400 may include controllers for coupling peripherals such as a monitor, keyboard, mouse, printer, and, optionally, a touch screen or sensor to the peripheral interface 11300. In other aspects, I / O peripherals may also be coupled to the peripheral interface 11300 without going through the I / O subsystem 11400.

[0097] The power circuit 11500 can supply power to all or some of the components of the terminal device. For example, the power circuit 11500 can include a power management system, one or more power sources such as a battery or alternating current (AC), a charging system, a power failure detection circuit, a power converter or inverter, a power status indicator, or any other components for power generation, management, and distribution.

[0098] The communications circuitry 11600 provides for communication with other computing devices using at least one external port.

[0099] Alternatively, as previously mentioned, if desired, the communications circuitry 11600 may include RF circuitry to enable communication with other computing devices by sending and receiving RF signals, also known as electromagnetic signals.

[0100] The embodiment of Fig. 10 is merely one example of the computing device 10000, and the computing device 11000 may have a configuration or arrangement in which some components in Fig. 10 are omitted, additional components in Fig. 10 are included, or two or more components are combined. For example, a computing device for a communication terminal in a mobile environment may further include a touch screen, a sensor, etc. in addition to the components shown in Fig. 10, and the communication circuit 1160 includes circuits for RF communication of various communication methods (WiFi, 3G, LTE, Bluetooth (registered trademark), NFC, Zigbee (registered trademark), etc.). The components included in the computing device 10000 are embodied in hardware, software, or a combination of both hardware and software, including one or more signal processing or application-specific integrated circuits.

[0101] The method according to the embodiment of the present invention is embodied in the form of program instructions executed through various computing devices and recorded on a computer-readable medium. In particular, the program according to the embodiment of the present invention is configured as a PC-based program or an application dedicated to a mobile terminal. The application to which the present invention is applied is installed in a user terminal through a file provided by a file distribution system. As an example, the file distribution system includes a file transmission unit (not shown) that transmits the file at the request of the user terminal.

[0102] The devices described above may be implemented with hardware components, software components, and / or a combination of hardware and software components. For example, the devices and components described in the embodiments may be implemented using one or more general-purpose or special-purpose computers, such as a processor, a controller, an arithmetic logic unit (ALU), a digital signal processor, a microcomputer, a field programmable gate array (FPGA), a programmable logic unit (PLU), a microprocessor, or any other device that executes and responds to instructions. The processing device may execute an operating system (OS) and one or more software applications that run on the operating system. The processing device may also access, store, manipulate, process, and generate data in response to the execution of software. For ease of understanding, the processing device may be described as being one, but those skilled in the art will appreciate that the processing device may include multiple processing elements and / or multiple types of processing elements. For example, the processing device may include multiple processors or one processor and one controller. Other processing configurations are also possible, such as parallel processors.

[0103] Software includes computer programs, codes, instructions, or a combination of one or more of these, which can configure or instruct a processing device, either independently or collectively, to operate as desired. The software and / or data can be permanently or temporarily embodied in any type of machine, component, physical device, virtual device, computer storage medium, or device to be analyzed by the processing device or to provide instructions or data to the processing device. The software can also be distributed across computing devices coupled in a network, and stored or executed in a distributed manner. The software and data can be stored on one or more computer-readable recording media.

[0104] The method according to the embodiment may be embodied in the form of program instructions executed by various computer means and recorded on a computer readable medium. The computer readable medium may include, alone or in combination, program instructions, data files, data structures, and the like. The program instructions recorded on the medium may be those specifically designed and constructed for the embodiment, or those known and available to those skilled in the art of computer software. Computer readable recording media include magnetic media such as hard disks, floppy disks, and magnetic tapes, optical media such as CD-ROMs and DVDs, magneto-optical media such as floptical disks, and hardware devices specifically configured to store and execute program instructions, such as ROMs, RAMs, flash memories, and the like. Program instructions include not only machine language code, such as produced by a compiler, but also high-level language code executable by a computer using an interpreter, and the like. The hardware devices may be configured to operate as one or more software modules to perform the operations of the embodiment, and vice versa.

[0105] Although the embodiments have been described above by way of limited examples and drawings, those skilled in the art will appreciate that various modifications and variations may be made from the above description. For example, the techniques described may be performed in a different order than described, and / or the components of the described systems, structures, devices, circuits, etc. may be combined or combined in a different manner than described, or may be counterbalanced or replaced by other components or equivalents, while still achieving suitable results. Therefore, other implementations, other embodiments, and equivalents to the claims are also within the scope of the following claims.

Claims

1. A method for outputting intelligent content for digital signage using big data on visitor types, the method being implemented in a computing device including one or more processors and one or more memories storing instructions executable by the processors, A user information extraction step of analyzing a plurality of images received from an image capturing device mounted on the digital signage and capturing an image in a direction of a content output area, and extracting attribute information of a user who recognizes the digital content as an object in the image; a data storage step of generating analysis target data by matching the user information with the digital content using the acquisition time of the user information and the output time of the digital content extracted based on the driving log data for the digital signage, and storing the analysis target data in a database; An intelligent content output method for digital signage using big data on visitor types, characterized in that it includes an output control step of controlling the output content, the output format of the content, the output brightness of the digital signage, and whether or not the digital signage is operated based on the data to be analyzed or user information.

2. The user information extraction step includes: An object extraction step of extracting an object region constituting a user's body from the image images received from the plurality of digital signages; a first information extraction step of deriving the gender and age of the object using at least one of a first algorithm based on a static or dynamic connection relationship of a face region, a shoulder region, an arm region, and an upper body region among the object regions, and a second algorithm which is an artificial intelligence gender and age recognition algorithm for the face region; The method for outputting intelligent content for digital signage using big data on visitor types according to claim 1, further comprising extracting gender and age of the object as the user attribute information.

3. The user information extraction step further includes: A second information extraction step of extracting the gender and age of a user based on input information input from a digital signage at the time of acquiring the image used in the object extraction step; The method for outputting intelligent content for digital signage using big data on visitor types as described in claim 2, further comprising an algorithm learning step of learning the algorithm used in the first information extraction step, of the first algorithm and the second algorithm, using the gender and age of the object derived in the first information extraction step and the gender and age of the user derived in the second information extraction step.

4. The second information extraction step includes: When receiving direct numerical information, which is numerical information on the gender and age of the user, from the input information, extracting the gender and age of the user as direct numerical information; The intelligent content output method for digital signage using big data on visitor types as described in claim 3, characterized in that the user's gender and age are extracted from the result value of a third algorithm that predicts the user's gender and age based on the user's input speed, input accuracy, and input pattern regarding the input information.

5. The method for outputting intelligent content for digital signage using big data on visitor types as described in claim 4, characterized in that the second information extraction step learns the third algorithm using the result value of the third algorithm at the time the direct numerical information is received.

6. The intelligent content output method for digital signage using big data on visitor types as described in claim 1, characterized in that the output control step controls the size of text included in the content and the output brightness of the digital signage with priority when controlling the output of content based on information regarding age among user attribute information.

7. The output control step includes: When it is determined that the user attribute information extracted at the same time is of multiple types, a first content is output, which is a content having metadata that matches the user attribute information having the highest priority according to an attribute comparison algorithm that calculates the priority between the user attribute information; The intelligent content output method for digital signage using big data on visitor types as described in claim 1, characterized in that a content selection area in which one of second contents, which is content having metadata matching multiple types of user attribute information, can be selected is output together with the output area of ​​the first content.

8. The output control step is performed when there is no user attribute information extracted at a time point or when extraction of user attribute information based on an image has failed. The intelligent content output method for digital signage using big data on visitor types as described in claim 1, characterized in that when selecting content to be output to the digital signage, content corresponding to the purpose of installing the digital signage is set as a first selection condition, and user visit patterns in the space in which the digital signage is installed are set as a second selection condition, and content that satisfies the first selection condition and the second selection condition is output to the digital signage.

9. An intelligent content output device for digital signage using big data on visitor types, the intelligent content output device being implemented by a computing device including one or more processors and one or more memories storing instructions executable by the processors, a user information extraction unit that is mounted on the digital signage and analyzes a plurality of images received from an image capturing device that captures an image in a content output area direction, and extracts attribute information of a user who recognizes digital content as an object in the image; a data storage unit that generates analysis target data by matching the user information with the digital content using the acquisition time of the user information and the output time of the digital content extracted based on the driving log data for the digital signage, and stores the analysis target data in a database; An intelligent content output device for digital signage using big data on visitor types, characterized in that it includes an output control unit that controls the output content, the output format of the content, the output brightness of the digital signage, and whether or not the digital signage is operated based on the data to be analyzed or user information.

10. A computer-readable recording medium, comprising: The computer-readable medium stores instructions that cause a computing device to perform the following steps, the steps comprising: A user information extraction step of analyzing a plurality of images received from an image capturing device mounted on the digital signage and capturing an image in a direction of a content output area, and extracting attribute information of a user who recognizes the digital content as an object in the image; a data storage step of generating analysis target data by matching the user information with the digital content using the acquisition time of the user information and the output time of the digital content extracted based on the driving log data for the digital signage, and storing the analysis target data in a database; A computer-readable recording medium characterized by including an output control step of controlling the output content, the output format of the content, the output brightness of the digital signage, and whether or not the digital signage is operated based on the analysis target data or user information.

Images