Method for Inserting PPL Based on Artificial Intelligence to Understand Context

Abstract

The present invention relates to a context-aware AI-based PPL insertion method. The context-aware AI-based PPL insertion method, which is executed through an operating server linked to a platform that can access video content or provides video content according to the present invention, comprises: a first step of receiving a context-aware PPL insertion instruction sentence from a user terminal that instructs the insertion of a designated PPL (Product Placement) item in a designated object area of ​​said n objects by recognizing a specific situation in which n (1 ≤ n ≤ N) objects among N (N ≥ 1) objects that can be included in the video content are exposed; a second step of generating PPL video data by inputting original video data corresponding to said video content and the context-aware PPL insertion instruction sentence into a designated AI module, recognizing M (M ≥ 1) playback sections among the playback sections of said original video data that correspond to said specific situation, and processing the insertion of said PPL item in the designated object area of ​​said n objects exposed in said M playback sections; and a third step of performing a procedure to play said PPL video data through said user terminal.

Description

Technology Field

[0001] The present invention enables a user to input or select a sentence that allows PPL related to a specific object within video content to be exposed according to a designated specific situation, and uses artificial intelligence to expose PPL related to the specific object within the video content in response to the input or selected sentence. Background Technology

[0003] As broadcast content increases and the platforms providing such content diversify, product placement (PPL) within broadcast content is on the rise.

[0005] Korean Patent Publication No. 10-2019-0078773 (July 5, 2019) relates to a video-linked PPL service provision system, and describes a system that provides an advertising product selected as an advertising target among props included in video content to a user terminal using a first content server and a second content server, and provides rewards such as points or mileage when a customer accesses a product sales site and makes a purchase.

[0007] In addition, Korean Published Patent Application No. 10-2013-0056532 (May 30, 2013) relates to a method for the selective insertion of PPL within a video and an advertising service. The method involves pre-specifying and editing the PPL area and the type of PPL object to be inserted into the video on an editing computer, selectively inserting an appropriate PPL object by referring to the information on the PPL area and the type of PPL object on a server computer, transmitting it to a user terminal, and enabling the user terminal to play the video containing the PPL.

[0009] However, in the case of Prior Patent 1, it merely enables the sale of PPL products, and in the case of Prior Patent 2, since the PPL area and object type are specified in advance, it was difficult to insert PPL at the exact point in the exact scene desired by the user. The problem to be solved

[0011] The objective of the present invention is to provide a context-aware AI-based PPL insertion method that recognizes a specific situation in which a designated object among one or more objects that can be included in video content received from a user terminal is exposed, and instructs the insertion of a designated PPL (Product Placement) item in a designated object area of ​​said object, inputs said video content into a designated AI module, and generates PPL video data in which the PPL item is inserted into a designated object area of ​​said object while recognizing a playback section of said original video data that corresponds to said specific situation, and plays the result through said user terminal. means of solving the problem

[0013] An AI-based PPL insertion method that understands the context executed through an operating server linked to a platform capable of accessing or providing video content according to the present invention comprises: a first step of receiving a context-aware PPL insertion instruction sentence from a user terminal that recognizes a specific situation in which n (1 ≤ n ≤ N) objects among N (N ≥ 1) objects that can be included in the video content are exposed, and instructs the insertion of a designated PPL (Product Placement) item in a designated object area of ​​said n objects; a second step of generating PPL video data by inputting original video data corresponding to said video content and the context-aware PPL insertion instruction sentence into a designated AI module, recognizing M (M ≥ 1) playback sections among the playback sections of said original video data that correspond to the specific situation, and processing the insertion of said PPL item in a designated object area of ​​said n objects exposed in said M playback sections; and a third step of performing a procedure to play said PPL video data through said user terminal.

[0015] According to the present invention, the first step may include receiving a situation-aware PPL insertion instruction sentence from a user terminal, the sentence comprising a situation description describing a situation in which a PPL item is inserted into n (1 ≤ n ≤ N) objects exposed within the video content using name strings of N (N ≥ 1) objects that can be included within the video content and strings of PPL (Product Placement) items that can be inserted within the video content, and a PPL insertion instruction instructing the insertion of a PPL item into a designated object area of ​​the n objects exposed in accordance with the described situation.

[0017] According to the present invention, the first step may further include the step of reading the received context-aware PPL insertion instruction sentence and verifying whether the context-aware PPL insertion instruction sentence contains a string of names of valid objects matching the N objects and a string of PPL items stored in a designated storage medium.

[0019] According to the present invention, the second step may include the step of generating PPL video data by inputting original video data corresponding to the video content and a situation recognition-based PPL insertion instruction sentence into a designated artificial intelligence module, recognizing M (M≥1) playback segments among the playback segments of the original video data that correspond to the context of the situation description content, and processing the insertion of PPL items corresponding to the PPL insertion content into designated object areas of n objects exposed in the M playback segments.

[0021] According to the present invention, the third step may include a step of performing a procedure to play PPL video data by selecting or concatenating M playback sections in which PPL items are inserted among the entire playback sections of the PPL video data through the user terminal.

[0023] According to the present invention, the third step may include a step of performing a procedure to play PPL video data by comparing and playing the original video data and PPL video data through the user terminal.

[0025] According to the present invention, the third step may include a step of performing a procedure to play PPL video data by selecting or concatenating M playback sections in which PPL items are inserted among the entire playback sections of the PPL video data through the user terminal and playing them in comparison with the original video data.

[0027] The context-aware AI-based PPL insertion method according to the present invention may further include the step of performing a procedure to register the inspected PPL video data on a designated platform or to replace video content already registered on the designated platform with the PPL video data and update the registration when the inspection of the PPL video data is completed through the user terminal. Effects of the invention

[0029] According to the present invention, there is an advantage in that AI is used to accurately recognize a situation corresponding to the context of a sentence input by a user, and to insert a PPL item into a designated object area of ​​a specific object exposed in a playback section corresponding to the recognized situation. Brief explanation of the drawing

[0031] FIG. 1 is a diagram illustrating the configuration of an AI-based PPL insertion system that understands context according to the method of implementing the present invention. FIG. 2 is a flowchart illustrating the process of receiving a context-aware PPL insertion instruction sentence from a user terminal according to the method of implementing the present invention. FIG. 3 is a diagram illustrating the process of generating and playing PPL video data according to the method of implementing the present invention. Specific details for implementing the invention

[0032] The operating principle of a preferred embodiment of the present invention will be described in detail below with reference to the attached drawings and description. However, the drawings and descriptions below relate to preferred embodiments among various methods for effectively explaining the features of the present invention, and the present invention is not limited to the drawings and descriptions below.

[0034] In other words, the following embodiments correspond to preferred union forms among the numerous embodiments of the present invention. It is explicitly stated that embodiments in which a specific configuration (or step) is omitted, embodiments in which a function implemented in a specific configuration (or step) is divided into specific configurations (or steps), embodiments in which a function implemented in two or more configurations (or steps) is integrated into a single configuration (or step), embodiments in which the order of operation of a specific configuration (or step) is changed, etc., fall within the scope of the present invention even if not separately mentioned in the following embodiments. Accordingly, it is clearly specified that various embodiments corresponding to subsets or complements based on the following embodiments may be divided retroactively to the filing date of the present invention.

[0036] Furthermore, in describing the present invention below, specific descriptions of related known functions or configurations will be omitted if it is determined that such detailed descriptions could unnecessarily obscure the essence of the invention. Additionally, the terms described below are defined considering their functions in the present invention, and these definitions may vary depending on the intentions or practices of the user or operator. Therefore, their definitions should be based on the overall content of the present invention.

[0038] Consequently, the technical concept of the present invention is determined by the claims, and the following embodiments are merely a means to efficiently explain the progressive technical concept of the present invention to those skilled in the art to which the present invention belongs.

[0040] Figure 1 is a diagram illustrating the configuration of an AI-based PPL insertion system that understands context according to the method of implementing the present invention.

[0042] More specifically, Figure 1 illustrates the configuration of a system that uses artificial intelligence to expose a PPL related to a specific object within video content in response to a sentence input or selected by a user, thereby enabling the exposure of said PPL related to the specific object within the video content according to a designated specific situation. A person skilled in the art to which the present invention pertains may infer various implementation methods for the configuration of said system (e.g., methods in which some components are omitted, subdivided, or combined) by referring to and / or modifying Figure 1; however, the present invention comprises all such inferred implementation methods and its technical features are not limited solely to the implementation method illustrated in Figure 1.

[0044] In the present invention, the video content may include at least one of video content provided through a broadcasting platform, video content provided through an OTT (Over The Top) platform, and video content provided through a streaming platform.

[0046] In the present invention, the system includes an operating server (100) that is linked to a platform capable of accessing or providing video content and provides an AI-based PPL insertion service that understands context, and a user terminal (125) that is linked to the operating server (100).

[0048] The above user terminal (125) may include a wired terminal, such as a desktop computer used by a user who wishes to insert a designated PPL (Product Placement) item into a designated object area of ​​an object in a specific situation where one or more objects that can be included in video content are exposed, or a wireless terminal such as a smartphone or tablet that the user possesses or owns. The above user terminal (125) may communicate with the operating server (100) via a communication network designated in a web manner, communicate with the operating server (100) via a communication network designated in an app manner using a designated application, or communicate with the operating server (100) via a communication network designated in a hybrid manner combining the web method and the app method.

[0050] Additionally, when the user terminal (125) communicates with the operating server (100) in a web manner, it is equipped with a browser for implementing the web manner; when it communicates with the operating server (100) in an app manner, it is equipped with an app for implementing the app manner; and when it communicates with the operating server (100) in a hybrid manner, it is equipped with an app that has a built-in browser function for implementing the hybrid manner.

[0052] Meanwhile, when an app for implementing the app method or hybrid method is installed on the user terminal (125), at least some of the functions of the function configuration unit shown in the operating server (100) of Figure 1 may be installed and implemented in the app of the user terminal (125), and / or may be installed in a form distributed between the app and the operating server (100), and the present invention may include such embodiments within the scope of rights.

[0054] The above operating server (100) is a general term for a server that performs a series of procedures using artificial intelligence to expose a PPL related to a specific object within the video content in response to the input or selected sentence when a user inputs or selects a sentence that allows the PPL related to a specific object within the video content to be exposed according to a designated specific situation, and the operating server (100) of Figure 1 is not limited to a specific (or any one) physical terminal device or server device.

[0056] In addition, each component of the operating server (100) illustrated in Figure 1 may be implemented through a device (or terminal) or server operated by a single entity (e.g., a business operator, company, institution, individual, etc.), or / or implemented in a distributed manner through two or more servers or devices operated by a single entity, or / or implemented in a distributed manner through two or more servers or devices operated by two or more affiliated entities, or / or implemented in the form of software added to or installed on a server or device already established by a single entity, or / or implemented in the form of software added to or installed on two or more servers or devices operated by two or more affiliated entities. It is clearly stated that the present invention is not limited by the method of implementing the operating server (100). Meanwhile, regarding the specific function executed by the component provided in the operating server (100) in the detailed description or claims of the present invention, the meaning of the description to the effect of "processing to..." or "performing a procedure to..." implies not only that a terminal or server (or software) of a specific entity directly executes the corresponding function, but also implies that a request is made to execute the corresponding function through a server or device of another entity affiliated with the terminal or server (or software) of the specific entity, or that a server or device of another entity performs preprocessing necessary to execute the corresponding function, or that a server or device of another entity receives the result of the execution of the corresponding function. It is hereby made clear that the subject of the act corresponding to such description can be interpreted as being attributed to the specific entity even if the specific entity does not perform the act directly (to avoid the scope of rights) but requests execution, performs preprocessing, or receives the result of execution through a server or device of another entity.

[0058] Referring to Drawing 1, the operating server (100) may be configured to include a situation awareness sentence receiving unit (105) that receives a situation awareness-based PPL insertion instruction sentence instructing the insertion of a specified PP item into a specified object area, a PPL video data generating unit (110) that generates PPL video data by processing the insertion of the PPL item into a specified object area of ​​an object exposed in a playback section, and a PPL video data playback unit (115) that plays the generated PPL video data through a user terminal (125).

[0060] The above-mentioned situation recognition sentence receiving unit (105) receives a situation recognition-based PPL insertion instruction sentence from a user terminal (125) that recognizes a specific situation in which n (1 ≤ n ≤ N) objects are exposed among N (N ≥ 1) objects that can be included in video content, and instructs the insertion of a specified PPL (Product Placement) item in the specified object area of ​​the n objects.

[0062] Here, the N objects may include at least one object among an object corresponding to a performer who can appear in the video content and an object corresponding to an object that can be exposed in the video content.

[0064] Additionally, the n objects may include at least one object among an object corresponding to a performer appearing in the video content who can insert a PPL item, and an object corresponding to an object exposed in the video content who can insert a PPL item.

[0066] In addition, the above PPL item may include at least one item data among a brand item, a logo item, and a product object item that can be inserted into video content.

[0068] According to the method of implementing the present invention, the situation recognition sentence receiving unit (105) can receive a situation recognition-based PPL insertion instruction sentence from a user terminal (125) that includes a situation description describing a situation in which a PPL item is inserted into n (1≤n≤N) objects exposed within the video content using a string of names of N (N≥1) objects that can be included within the video content and a string of a PPL (Product Placement) item that can be inserted within the video content, and a PPL insertion instruction instructing the insertion of a PPL item into a designated object area of ​​n objects exposed in accordance with the described situation.

[0070] Here, the above situation description may include a description of the situation in which the n objects are exposed while referring to the n objects into which the PPL item is to be inserted.

[0072] In addition, the above situation description may include at least one of the following: a description of the situation immediately before the n objects are exposed while referring to the n objects, and a description of the situation after the n objects are exposed while referring to the n objects.

[0074] In addition, the above description of the situation may further include at least one of the following: a description of n objects to be inserted, which refers to n' (1 ≤ n' < (Nn)) objects involved in the situation in which said n objects are exposed; or a description of the situation in which said n' objects are related to the situation in which said n objects are exposed, which refers to said n objects and said n' objects.

[0076] Here, the n' objects may include at least one object among an object corresponding to a performer involved in a situation in which the n objects are exposed among performers appearing in the video content, and an object corresponding to an object involved in a situation in which the n objects are exposed among objects exposed in the video content.

[0078] Additionally, the n' objects may include at least one object among an object corresponding to a performer appearing in the video content who forms a designated relationship with the n objects, and an object corresponding to an object exposed in the video content who forms a designated relationship with the n objects.

[0080] In addition, the above relationship may include at least one of the positional relationship between objects within the video content, the movement relationship between objects, and the interaction relationship between objects.

[0082] In addition, the above situation description may include details explaining the limiting conditions for a specific situation in which a PPL item is to be inserted among situations in which n objects are exposed.

[0084] Here, the above limitation condition may include one or more conditions among a viewership condition associated with a situation in which n objects are exposed and verifiable through a video content platform, and an object-related comment condition associated with n objects among video content-related comments verifiable through a video content platform.

[0086] In addition, the above object-related comment condition may include at least one of the following conditions: a condition regarding the presence or absence of positive response comments related to n objects, a condition regarding the number of positive response comments related to n objects, and a condition regarding the number of recommendations for positive response comments related to n objects.

[0088] In addition, the above limitation condition may include a situation-related comment condition associated with a situation in which n objects are exposed among video content-related comments verifiable through the video content platform.

[0090] Here, the comment condition related to the above situation may include at least one of the following conditions: a condition regarding the presence or absence of positive response comments associated with a situation in which n objects are exposed, a condition regarding the number of positive response comments associated with a situation in which n objects are exposed, and a condition regarding the number of recommendations for positive response comments associated with a situation in which n objects are exposed.

[0092] Meanwhile, the above PPL insertion content may include at least one of the following: content naming the PPL item to be inserted, content specifying the object area among the n object areas to be inserted the PPL item, and content setting a PPL insertion method for inserting the PPL item into the specified object area of ​​the n objects.

[0094] Additionally, the above PPL insertion method may include at least one of the following methods: a method of inserting a PPL item into an empty designated object area of ​​the n objects, or a method of replacing and inserting a PPL item while deleting an item or pattern included in the designated object area of ​​the n objects.

[0096] Additionally, according to the method of implementing the present invention, the situation recognition sentence receiving unit (105) provides a webpage that includes a video playback interface for playing video content to insert a PPL item to the user terminal (125) and a character input interface for inputting a situation recognition-based PPL insertion instruction sentence including the situation description content and the PPL insertion content, and can receive the situation recognition-based PPL insertion instruction sentence input through the character input interface from the user terminal (125) during or after the playback of the video content through the video playback interface.

[0098] Additionally, according to the method of implementing the present invention, the situation recognition sentence receiving unit (105) can receive the situation recognition-based PPL insertion instruction sentence input through the text input interface from the user terminal (125) during or after the playback of the video content through the video playback interface when a video playback interface for playing video content to insert a PPL item is displayed through the app screen of the user terminal (125) and a text input interface for inputting a situation recognition-based PPL insertion instruction sentence including the situation description content and the PPL insertion content is displayed.

[0100] Here, the situation recognition sentence receiving unit (105) can provide the video content to the video playback interface of the user terminal (125) and play it when the video playback interface of the user terminal (125) is displayed.

[0102] In addition, according to the method of implementing the present invention, the situation recognition sentence receiving unit (105) can read the received situation recognition-based PPL insertion instruction sentence and authenticate whether the situation recognition-based PPL insertion instruction sentence contains a string of names of valid objects that match the N objects and a string of PPL items stored in a designated storage medium.

[0104] And, the above situation recognition sentence receiving unit (105) can back up and store original video data corresponding to the video content or maintain a backed-up state.

[0106] When the above PPL video data generation unit (110) receives a situation recognition-based PPL insertion instruction sentence through the situation recognition sentence receiving unit (105), it inputs the original video data corresponding to the video content and the situation recognition-based PPL insertion instruction sentence into a designated artificial intelligence module, recognizes M (M≥1) playback sections corresponding to the specific situation among the playback sections of the original video data, and generates PPL video data by inserting the PPL item into the designated object area of ​​n objects exposed in the M playback sections.

[0108] According to the method of implementing the present invention, the PPL video data generation unit (110) can generate PPL video data by inputting original video data corresponding to the video content and the situation recognition-based PPL insertion instruction sentence into a designated artificial intelligence module, recognizing M (M≥1) playback sections that correspond to the context of the situation description content among the playback sections of the original video data, and processing the insertion of PPL items corresponding to the PPL insertion content into designated object areas of n objects exposed in the M playback sections.

[0110] Here, the artificial intelligence module may include an artificial intelligence module that is trained to recognize and edit objects within video data, and is linked to a storage medium storing PPL items while learning object features to recognize N objects, and interprets the context of a designated instruction sentence, recognizes objects within the designated video data based on the interpreted context, and simultaneously recognizes a playback section corresponding to a situation that aligns with the interpreted context, and is trained to edit specific recognized objects within the playback section in accordance with the interpreted context.

[0112] Additionally, the artificial intelligence module may include a combination of: a video editing artificial intelligence module linked to an artificial intelligence module trained to recognize and edit objects within video data, and capable of accessing a storage medium storing PPL items while learning object features to recognize N objects; and an editing control artificial intelligence module that interprets the context of a designated instruction sentence, links with the video editing artificial intelligence module based on the interpreted context to recognize objects within the designated video data, and simultaneously recognizes a playback section corresponding to a situation that aligns with the interpreted context, thereby controlling the editing of a specific recognized object within the playback section to align with the interpreted context.

[0114] In addition, according to the method of implementing the present invention, the PPL video data generation unit (110) can learn object features for recognizing N objects in an artificial intelligence module that is trained to recognize and edit objects within the video data, and can link to a storage medium that stores PPL items so as to be accessible.

[0116] In addition, the PPL video data generation unit (110) can interpret the context of a command sentence specified in the artificial intelligence module and, based on the interpreted context, recognize an object within the specified video data and, at the same time, recognize a playback section corresponding to a situation that matches the interpreted context, thereby enabling the recognition of a specific object within the playback section to be editable in accordance with the interpreted context.

[0118] The above PPL video data playback unit (115) performs a procedure to play the PPL video data through the user terminal (125) when PPL video data is generated through the above PPL video data generation unit (110).

[0120] Here, the PPL video data playback unit (115) can perform a procedure to inspect the PPL video data by playing it through the user terminal (125).

[0122] According to the method of implementing the present invention, the PPL video data playback unit (115) can perform a procedure to play the PPL video data in a manner that allows for playback by designating an arbitrary playback section among the entire playback section of the PPL video data through the user terminal (125).

[0124] Here, the PPL video data playback unit (115) provides a webpage including a PPL video playback interface that allows playback of any playback section of the PPL video data by designating it to the user terminal (125), and can provide the PPL video data to the PPL video playback interface of the user terminal (125) to play it.

[0126] Additionally, the PPL video data playback unit (115) can provide the PPL video data to the PPL video playback interface of the user terminal (125) and play it when a PPL video playback interface that can play a PPL video data is displayed by specifying an arbitrary playback section of the PPL video data through the app screen of the user terminal (125).

[0128] Here, the PPL video playback interface may include an area where PPL video data is played and an area including a control panel for specifying an arbitrary playback section of the PPL video data.

[0130] In addition, according to the method of implementing the present invention, the PPL video data playback unit (115) can perform a procedure for playing PPL video data by selecting or connecting M playback sections in which PPL items are inserted among the entire playback sections of the PPL video data through the user terminal (125).

[0132] Here, the PPL video data playback unit (115) provides a webpage including a PPL video playback interface that allows playback of any playback section of the PPL video data by designating it to the user terminal (125), and can play M playback sections in which PPL items are inserted among the entire playback section of the PPL video data by selecting or connecting them through the PPL video playback interface of the user terminal (125).

[0134] Additionally, the PPL video data playback unit (115) can play M playback segments in which PPL items are inserted among the entire playback segments of the PPL video data by selecting or connecting them through the PPL video playback interface of the user terminal (125) when a PPL video playback interface is displayed that allows playback by specifying an arbitrary playback segment of the PPL video data through the app screen of the user terminal (125).

[0136] Here, the PPL video playback interface may include an area where PPL video data is played and an area including a control panel for specifying an arbitrary playback section of the PPL video data.

[0138] In addition, according to the method of implementing the present invention, the PPL video data playback unit (115) can perform a procedure to play PPL video data by comparing and playing the original video data and PPL video data through the user terminal (125).

[0140] Here, the PPL video data playback unit (115) provides a webpage including an original video playback interface that can be played by designating an arbitrary playback section of original video data to the user terminal (125) and a PPL video playback interface that can be played by designating an arbitrary playback section of PPL video data. When the original video playback interface of the user terminal (125) provides a designated playback section of the original video data to be played, the PPL video playback interface provides a playback section of the PPL video data that is synchronized with the playback section of the original video data to be played in synchronization. When the PPL video playback interface provides a designated playback section of the PPL video data to be played, the original video playback interface provides a playback section of the original video data that is synchronized with the playback section of the PPL video data to be played in synchronization.

[0142] Additionally, the PPL video data playback unit (115) can, after displaying an original video playback interface capable of playing an arbitrary playback section of original video data and a PPL video playback interface capable of playing an arbitrary playback section of PPL video data through the app screen of the user terminal (125), provide the designated playback section of the original video data to the original video playback interface of the user terminal (125) to play the original video data, thereby providing the PPL video playback interface with the playback section of the PPL video data synchronized with the original video data to play the original video data, and, when providing the designated playback section of the PPL video data to the PPL video playback interface to play the original video data, provide the original video playback interface with the playback section of the PPL video data synchronized with the PPL video data to play the original video data.

[0144] Here, the original video playback interface may include an area in which original video data is played and an area including a control panel for specifying an arbitrary playback section of the original video data.

[0146] Additionally, the PPL video playback interface may include an area where PPL video data is played and an area including a control panel for specifying an arbitrary playback section of the PPL video data.

[0148] In addition, according to the method of implementing the present invention, the PPL video data playback unit (115) can perform a procedure to play PPL video data by selecting or connecting M playback sections in which PPL items are inserted among the entire playback sections of the PPL video data through the user terminal (125) and comparing them with the original video data.

[0150] Here, the PPL video data playback unit (115) provides a webpage including an original video playback interface that can be played by designating an arbitrary playback section of the original video data to the user terminal and a PPL video playback interface that can be played by designating an arbitrary playback section of the PPL video data, and can play M playback sections in which PPL items are inserted among the entire playback sections of the PPL video data by selecting or connecting them to the PPL video playback interface of the user terminal (125), and can play synchronized playback by providing a playback section of the original video data synchronized with the playback section of the PPL video data to the original video playback interface.

[0152] Additionally, when the original video playback interface, which can be played by specifying an arbitrary playback section of the original video data, and the PPL video playback interface, which can be played by specifying an arbitrary playback section of the PPL video data, are displayed through the app screen of the user terminal (125), the PPL video playback interface of the user terminal (125) can select or connect M playback sections in which PPL items are inserted among the entire playback sections of the PPL video data to be played, and the original video playback interface can provide a playback section of the original video data synchronized with the playback section of the PPL video data to be played in synchronization.

[0154] Here, the original video playback interface may include an area in which original video data is played and an area including a control panel for specifying an arbitrary playback section of the original video data.

[0156] Additionally, the PPL video playback interface may include an area where PPL video data is played and an area including a control panel for specifying an arbitrary playback section of the PPL video data.

[0158] Additionally, if the PPL video data playback unit (115) is not inspected, it may receive a situation-aware PPL insertion instruction sentence through the user terminal (125) that modifies at least one of the situation description content and the PPL insertion content of the situation-aware PPL insertion instruction sentence.

[0160] Meanwhile, referring to Drawing 1, the operating server (100) may further include a PPL video data registration unit (120) that performs a procedure to register the inspected PPL video data to a designated platform when the inspection of the PPL video data is completed through the user terminal (125).

[0162] Here, the PPL video data registration unit (120) can perform a procedure to update and register video content that has been registered on a designated platform by replacing it with the PPL video data that has been verified through the user terminal (125) when the PPL video data has been verified.

[0164] In addition, the above PPL video data registration unit (120) can check the details of providing PPL video data registered on a designated platform to at least one viewer terminal during a designated period, calculate the advertising cost using the PPL item based on the details of providing the PPL video, and then settle the advertising cost through the advertiser of the PPL item.

[0166] And, the above PPL video data registration unit (120) can deduct an amount corresponding to the advertising cost from the advertising deposit deposited by the advertiser of the above PPL item during the advertising cost settlement process.

[0168] Figure 2 is a flowchart illustrating the process of receiving a context-aware PPL insertion instruction sentence from a user terminal according to the method of implementing the present invention.

[0170] More specifically, Figure 2 illustrates a process of receiving a situation-aware PPL insertion instruction sentence from a user terminal (125) in an operating server (100) connected to a platform that can access or provides video content, instructing the insertion of a designated PPL (Product Placement) item in the designated object area of ​​said n objects by recognizing a specific situation in which n (1 ≤ n ≤ N) objects among N (N ≥ 1) objects that can be included in the video content are exposed. A person skilled in the art to which the present invention belongs may infer various implementation methods for said process (e.g., methods in which some steps are omitted or the order is changed) by referring to and / or modifying Figure 2, but the present invention is made up of all such inferred implementation methods and its technical features are not limited only to the implementation method illustrated in Figure 2.

[0172] Referring to Figure 2, first, the operating server (100) receives from the user terminal (125) a situation recognition-based PPL insertion instruction sentence (200) that includes a situation description describing a situation in which a PPL item is inserted into n (1 ≤ n ≤ N) objects exposed within the video content using a string of names of N (N ≥ 1) objects that can be included within the video content and a string of a PPL (Product Placement) item that can be inserted within the video content, and a PPL insertion instruction instructing the insertion of a PPL item into a designated object area of ​​n objects exposed in accordance with the described situation.

[0174] Here, the above situation description may include a description of the situation in which the n objects are exposed while referring to the n objects into which the PPL item is to be inserted.

[0176] In addition, the above description of the situation may further include at least one of the following: a description of n objects to be inserted, which refers to n' (1 ≤ n' < (Nn)) objects involved in the situation in which said n objects are exposed; or a description of the situation in which said n' objects are related to the situation in which said n objects are exposed, which refers to said n objects and said n' objects.

[0178] In addition, the above situation description may include details explaining the limiting conditions for a specific situation in which a PPL item is to be inserted among situations in which n objects are exposed.

[0180] Meanwhile, the above PPL insertion content may include at least one of the following: content naming the PPL item to be inserted; content specifying the object area among the n object areas to which the PPL item is to be inserted; and content setting a PPL insertion method for inserting the PPL item into the specified object area of ​​the n objects. Here, the PPL insertion method may include at least one of the following: a method of inserting the PPL item into an empty specified object area of ​​the n objects; and a method of replacing and inserting the PPL item while deleting an item or pattern included in the specified object area of ​​the n objects.

[0182] When the above situation-aware PPL insertion instruction sentence is received, the operating server (100) reads the received situation-aware PPL insertion instruction sentence and authenticates whether the situation-aware PPL insertion instruction sentence contains a string of names of valid objects that match the N objects and a string of PPL items stored in a designated storage medium (205).

[0184] And, the operating server (100) backs up and stores original video data corresponding to the video content or maintains the backed-up state (210).

[0186] Figure 3 is a drawing illustrating the process of generating and playing PPL video data according to the method of implementing the present invention.

[0188] More specifically, Figure 3 illustrates a process in which, after the process of Figure 2, the operating server (100) inputs the original video data corresponding to the video content and the situation recognition-based PPL insertion instruction sentence into a designated artificial intelligence module to recognize M (M≥1) playback sections corresponding to the specific situation among the playback sections of the original video data, generates PPL video data in which the PPL item is inserted into the designated object area of ​​n objects exposed in the M playback sections, and performs a procedure to play the PPL video data through the user terminal (125). A person skilled in the art to which the present invention belongs may infer various implementation methods for the process (e.g., methods in which some steps are omitted or the order is changed) by referring to and / or modifying Figure 3; however, the present invention is formed by including all such inferred implementation methods, and its technical features are not limited to the implementation method illustrated in Figure 3.

[0190] Referring to Figure 3, during or before the process of Figure 2, the operating server (100) interprets the context of the instruction sentence specified in the artificial intelligence module and, based on the interpreted context, recognizes an object within the specified image data and, at the same time, recognizes a playback section corresponding to a situation that matches the interpreted context, thereby training the recognized specific object within the playback section to be editable in accordance with the interpreted context (300).

[0192] Afterwards, the operating server (100) inputs the original video data corresponding to the video content and the situation recognition-based PPL insertion instruction sentence into the designated artificial intelligence module (305).

[0194] Here, the artificial intelligence module may include an artificial intelligence module that is trained to recognize and edit objects within video data, and is linked to a storage medium storing PPL items while learning object features to recognize N objects, and interprets the context of a designated instruction sentence, recognizes objects within the designated video data based on the interpreted context, and simultaneously recognizes a playback section corresponding to a situation that aligns with the interpreted context, and is trained to edit specific recognized objects within the playback section in accordance with the interpreted context.

[0196] And, the operating server (100) recognizes M (M≥1) playback sections among the playback sections of the original video data that correspond to the context of the situation description content, and generates PPL video data by inserting PPL items corresponding to the PPL insertion content into designated object areas of n objects exposed in the M playback sections (310).

[0198] Afterward, when the above PPL video data is generated, the operating server (100) performs a procedure to verify the above PPL video data by playing it through the user terminal (125) (315).

[0200] When the inspection procedure is performed, the operating server (100) performs a procedure to play the PPL video data by selecting or connecting M playback sections in which PPL items are inserted among the entire playback sections of the PPL video data through the user terminal (125) (320).

[0202] And, when the operating server (100) has completed the inspection of the PPL video data through the user terminal (125), it performs a procedure to register the inspected PPL video data on a designated platform or to replace video content already registered on a designated platform with the PPL video data and update the registration (325). Explanation of the symbols

[0204] 100 : Production server 105 : Context-aware sentence receiver 110 : PPL Video Data Generation Unit 115 : PPL Video Data Playback Section 120 : PPL Video Data Register 125 : User terminal

Claims

Claim 1 A method for executing through an operating server linked to a platform that can access or provides video content, comprising: a first step of receiving a context-aware PPL insertion instruction sentence from a user terminal that recognizes a specific situation in which n (1 ≤ n ≤ N) objects among N (N ≥ 1) objects that can be included in the video content are exposed, and instructs the insertion of a specified PPL (Product Placement) item into a specified object area of ​​said n objects; a second step of generating PPL video data by inputting original video data corresponding to said video content and the context-aware PPL insertion instruction sentence into a specified artificial intelligence module, recognizing M (M ≥ 1) playback sections among the playback sections of said original video data that correspond to the specific situation, and processing the insertion of said PPL item into a specified object area of ​​said n objects exposed in said M playback sections; and a third step of performing a procedure to play said PPL video data through said user terminal. Claim 2 A context-aware AI-based PPL insertion method according to claim 1, wherein the first step comprises receiving a context-aware PPL insertion instruction sentence from a user terminal, the sentence including a situation description describing a situation in which a PPL item is to be inserted into n (1≤n≤N) objects exposed within the video content using a string of names of N (N≥1) objects that can be included within the video content and a string of a PPL (Product Placement) item that can be inserted within the video content, and a PPL insertion instruction instructing the insertion of a PPL item into a designated object area of ​​the n objects exposed in accordance with the described situation. Claim 3 A context-aware AI-based PPL insertion method according to claim 2, characterized in that the above-mentioned situation description includes a description of the situation in which the n objects are exposed while referring to n objects to be inserted as PPL items. Claim 4 A context-aware AI-based PPL insertion method according to claim 2, characterized in that the above-mentioned situation description further includes at least one of the following: a description of n objects to be inserted into which n objects are called, and n' (1 ≤ n' < (Nn)) objects involved in the situation in which said n objects are exposed, and a description of the situation in which said n' objects are related to the situation in which said n objects are exposed, while calling said n objects and n' objects. Claim 5 A context-aware AI-based PPL insertion method characterized in that, in claim 2, the above-mentioned situation description includes a description of the limiting conditions of a specific situation in which a PPL item is to be inserted among situations in which n objects are exposed. Claim 6 A context-aware AI-based PPL insertion method according to claim 5, characterized in that the above limitation condition includes at least one condition among a viewership rating condition linked to a situation in which n objects are exposed and verifiable through a video content platform, and a situation-related comment condition linked to a situation in which n objects are exposed among video content-related comments verifiable through a video content platform. Claim 7 A context-aware AI-based PPL insertion method according to claim 2, characterized in that the PPL insertion content includes at least one of the following: content naming the PPL item to be inserted, content specifying the object area among the n object areas to which the PPL item is to be inserted, and content setting a PPL insertion method for inserting the PPL item into the specified object area of ​​the n objects. Claim 8 A context-aware AI-based PPL insertion method according to claim 7, wherein the PPL insertion method comprises at least one of the following: a method of inserting a PPL item into an empty designated object area of ​​n objects, and a method of replacing and inserting a PPL item while deleting an item or pattern included in the designated object area of ​​n objects. Claim 9 A context-aware AI-based PPL insertion method according to claim 1 or 2, wherein the first step further comprises the step of reading the received context-aware PPL insertion instruction sentence and certifying whether the context-aware PPL insertion instruction sentence contains a string of names of valid objects matching the N objects and a string of PPL items stored in a designated storage medium. Claim 10 A context-aware AI-based PPL insertion method according to claim 2, wherein the second step comprises the step of generating PPL video data by inputting original video data corresponding to the video content and a situation-aware PPL insertion instruction sentence into a designated AI module, recognizing M (M≥1) playback segments that correspond to the context of the situation description content among the playback segments of the original video data, and processing the insertion of PPL items corresponding to the PPL insertion content into designated object areas of n objects exposed in the M playback segments. Claim 11 A context-understanding AI-based PPL insertion method, characterized in that, in claim 10, the AI ​​module is linked to a storage medium storing PPL items while learning object features for recognizing N objects to an AI module trained to recognize and edit objects within video data, and simultaneously recognizes a playback section corresponding to a situation matching the interpreted context, and includes an AI module trained to edit specific recognized objects within the playback section in accordance with the interpreted context. Claim 12 A context-aware AI-based PPL insertion method according to claim 1, wherein the third step comprises a step of performing a procedure to play PPL video data by selecting or connecting M playback segments in which PPL items are inserted among the entire playback segments of the PPL video data through the user terminal. Claim 13 A context-aware AI-based PPL insertion method according to claim 1, wherein the third step comprises a step of performing a procedure to play PPL video data by comparing and playing the original video data and PPL video data through the user terminal. Claim 14 A context-aware AI-based PPL insertion method according to claim 1, wherein the third step comprises a step of performing a procedure to play PPL video data by selecting or concatenating M playback segments in which PPL items are inserted among the entire playback segments of the PPL video data through the user terminal and playing them in comparison with the original video data. Claim 15 A context-aware AI-based PPL insertion method characterized by further including the step of, in claim 1, performing a procedure to register the inspected PPL video data on a designated platform or to replace video content already registered on a designated platform with the PPL video data and update the registration when the inspection of the PPL video data is completed through the user terminal.

Images