KR102458510B1 - Real-time complementary marketing system - Google Patents

Abstract

The present invention relates to a real-time complementary marketing system, which produces a customized advertising content, and shares information generated in a process of analyzing promotional efficiency using produced advertising content to a customer terminal in real time. The marketing system includes: a customer terminal possessed by a customer who intends to conduct online marketing; and a manager terminal which performs online marketing according to a marketing agency requested from the customer terminal, generates analysis data obtained by analyzing data generated in a process of the online marketing, and periodically transmits the analysis data to the customer terminal.

Description

Real-time complementary marketing system {Real-time complementary marketing system}

The present invention relates to a marketing system that can be supplemented in real time, and more particularly, information generated in the process of producing customized advertising content and analyzing the promotion efficiency using the produced advertising content can be shared in real time with a customer terminal in real time. It's about the marketing system.

Public relations and marketing are very important factors for a company's life or death, and the online market is just as important to a company as the offline market in the PR and marketing advertising market.

It goes without saying that the importance of publicity and marketing through the Internet is very important. However, there are many problems in how to make the public aware of its importance and induce the purchase of goods.

Specifically, in public relations and marketing, it is difficult to calculate the appropriate advertising cost through the analysis of advertising efficiency, the recognition is significantly lower than that of leading companies and large companies, the high cost that requires a large amount of money economically, and the appropriate target marketing for consumers. difficulties, and difficulties in meeting consumer needs.

In addition, in the public relations and marketing advertising market, the online market is as easy as the offline market for consumers to be exposed to advertisements. do.

However, due to various factors such as not meeting consumer needs due to the difficulty of information, not providing sufficient interest, excessive stimulation, or not beneficial to meeting and utilizing consumer needs, all advertisements are not available to consumers. It is not fulfilling its original role.

As such, if the company does not satisfy the needs of consumers, publicity and marketing will fail. In addition, there is a problem that economic support and recognition act as a big stumbling block for SMEs and small businesses.

On the other hand, the above-mentioned background art is technical information that the inventor possessed for the derivation of the present invention or acquired in the process of derivation of the present invention, and it cannot be said that it is necessarily a known technique disclosed to the general public before the filing of the present invention. .

Korean Patent Publication No. 10-2021-0017516

One aspect of the present invention provides a real-time complementary marketing system for producing customized advertising content and sharing information generated in the process of analyzing the promotional efficiency using the produced advertising content to a customer terminal in real time.

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

The real-time supplemental marketing system according to an embodiment of the present invention creates customized advertisement content and shares information generated in the process of analyzing the promotion efficiency using the produced advertisement content to the customer terminal in real time.

The real-time supplemental marketing system,

a customer terminal owned by a customer who wants to conduct online marketing; and

and a manager terminal that performs online marketing according to the marketing agency requested from the customer terminal, generates analysis data by analyzing data generated in the online marketing process, and periodically transmits the data to the customer terminal.

The manager terminal,

Promotional content generation unit for generating promotional content to be used for online marketing; and

and an analysis unit that generates analysis data by analyzing data generated in the online marketing process.

The analysis unit,

a data collection unit that collects marketing dictionary data according to the marketing request information received from the customer terminal in order to perform online marketing, and collects marketing progress data generated in an online marketing process performed by the manager terminal;

a marketing recommendation unit for determining an online marketing type based on the marketing dictionary data collected by the data collection unit;

a marketing analysis unit generating the analysis data based on the marketing progress data generated according to the online marketing execution determined by the marketing recommendation unit;

a risk management unit for generating risk management data for deriving problems occurring in the online marketing process based on the analysis data and proposing a solution for solving the problems derived using a pre-learned artificial neural network;

and a report management unit for transmitting the analysis data and the risk management data to the customer terminal.

The promotional content generation unit,

It collects news data, advertisement data, promotional material data, comment data and post data related to the target to be promoted through online media, classifies the collected text data according to preset classification criteria, and analyzes the classified text data. It is characterized by deriving a keyword, searching for image data related to a key keyword, and recommending a color to be applied to the promotional content for a sample received from the manager terminal or the customer terminal based on the searched image data.

The promotional content generation unit,

generate a histogram for the collected image data,

The generator counts the color used with the highest frequency by using the histogram generated from any one image, assigns a first weight, counts the color used as the next-order frequency, and adds a second weight lower than the first weight After counting the colors used with the 3rd priority frequency, when counting and weighting the image by giving a third weight lower than the second weight, the counting result for each color is added to calculate the summed counting result ,

Converting the received promotional content for sample into image data, labeling the promotional content for the sample with different object areas, calculating the ratio of each labeled object to the total area of the promotional content for the sample, and the promotional content for the sample The color with the highest counting result value is applied to the object occupying the highest weight in

The manager terminal,

Further comprising a big data analysis-based abnormal data derivation unit for determining whether abnormal data is included in the received marketing advance data and the marketing progress data,

The abnormal data derivation unit,

a collection management module for setting at least one of a collection target data source module, a collection target keyword, and a collection target period;

a data collection module for collecting big data from the corresponding data source module according to the data collection criteria set by the collection management module and storing it in the database module;

a morpheme analysis module that analyzes morphemes of big data stored in the database module, classifies them by morpheme, and generates morpheme analysis data; and

and a data analysis module that processes morpheme analysis data with a distributed parallel processing-based statistical analysis algorithm to calculate statistical values and outputs malicious codes according to statistical values.

In addition, in the computer-readable recording medium according to an embodiment of the present invention, a computer program for performing a real-time complementary marketing system according to the present invention is recorded.

According to the above-described aspect of the present invention, information generated in the process of producing customized advertising content and analyzing the promotional efficiency using the produced advertising content can be shared with the customer terminal in real time.

1 is a diagram showing a schematic configuration of a real-time complementary marketing system according to an embodiment of the present invention.
FIG. 2 is a diagram illustrating a detailed configuration of the manager terminal shown in FIG. 1 .
3 is a diagram illustrating a detailed configuration of the analysis unit shown in FIG. 2 .
4 to 7 are diagrams illustrating a specific example of a chat room created by the communication management unit.
8 to 10 are diagrams illustrating a specific example of a document correction interface provided by a document management unit.

DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS [0012] DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS [0014] DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS [0016] Reference is made to the accompanying drawings, which show by way of illustration specific embodiments in which the present invention may be practiced. These embodiments are described in sufficient detail to enable those skilled in the art to practice the present invention. It should be understood that the various embodiments of the present invention are different but need not be mutually exclusive. For example, certain shapes, structures, and characteristics described herein with respect to one embodiment may be implemented in other embodiments without departing from the spirit and scope of the invention. In addition, it should be understood that the location or arrangement of individual components within each disclosed embodiment may be changed without departing from the spirit and scope of the present invention. Accordingly, the detailed description set forth below is not intended to be taken in a limiting sense, and the scope of the present invention, if properly described, is limited only by the appended claims, along with all scope equivalents to those claimed. Like reference numerals in the drawings refer to the same or similar functions throughout the various aspects.

Hereinafter, preferred embodiments of the present invention will be described in more detail with reference to the drawings.

1 is a diagram showing a schematic configuration of a real-time complementary marketing system according to an embodiment of the present invention.

The real-time complementary marketing system according to an embodiment of the present invention can share information generated in the process of producing customized advertising content and analyzing the promotional efficiency using the produced advertising content to the customer terminal in real time. By providing customized marketing methods to customers who wish to conduct online marketing and periodically transmitting data generated during the online marketing process to customers, customers can periodically check the promotional effect of the company or product they want to promote. And it is possible to derive a solution to the problem that occurred during the promotion process with an automated algorithm.

Specifically, the real-time supplemental marketing system 1000 according to an embodiment of the present invention includes a customer terminal 100 and a manager terminal 200 .

The customer terminal 100 is an electronic device owned by a customer who wants to conduct online marketing, and can communicate with an external device by wire or wirelessly, and can input/output and process information, such as a PC, notebook, tablet PC, smart phone, etc. It may be in the form of an electronic device.

The customer may transmit information about a product or company brand that he/she wants to promote to the manager terminal 200 by using the customer terminal 100 . For example, the customer using the customer terminal 100 to promote the target (product, brand, shop, etc.), detailed information about the target (features, functions, advantages, location of business, etc.), the period to promote, the desired Information on promotional agency costs, etc. may be transmitted to the manager terminal 200 .

To this end, the customer terminal 100 may be pre-installed with software (application) for receiving a marketing service using the real-time complementary marketing system 1000 according to the present invention, and the user (customer) is the customer terminal 100 . Various online marketing-related services provided from the manager terminal 200 may be provided by using software (application) installed in the .

The manager terminal 200 is a terminal possessed by a marketing agency or a marketing agent (hereinafter referred to as a manager) acting for online marketing according to a marketing agency requested from the customer terminal.

The manager receives an online marketing agency request from the customer terminal 100 using the manager terminal 200 , and performs marketing according to an online marketing method optimized according to the received request.

In this process, the manager terminal 200 generates analysis data by analyzing data generated during the online marketing process and periodically transmits it to the customer terminal, thereby providing information on whether the marketing requested by the customer is being properly performed. to be provided periodically. Hereinafter, a detailed configuration of the manager terminal 200 will be described, but the configuration implemented in the manager terminal, which will be described later, is preferably implemented in the customer terminal as well.

FIG. 2 is a diagram illustrating a detailed configuration of the manager terminal shown in FIG. 1 .

The manager terminal includes: a promotional content generation unit 210 for generating promotional content to be used for online marketing; an analysis unit 220 that generates analysis data by analyzing data generated in the online marketing process; and a communication management unit 230 that provides an online chat room and video call service between the user terminal and the manager terminal.

The promotional content generating unit collects text data related to an object that the customer wants to promote in order to generate customized promotional content. The promotional content generator automatically collects text data included in news, advertisements, promotional materials, comments, social media materials, etc. related to the target to be promoted.

The promotional content generation unit collects news data, advertisement data, publicity data, comment data, and posting data registered through online media such as portal sites, media homepages, broadcasting station homepages, and community sites, and collects news data, advertisement data, and promotional materials. Data, comment data, and text data included in post data are extracted.

The promotional content generating unit classifies the collected text data according to a predetermined criterion.

For example, the promotional content generator primarily classifies text data according to major classification criteria such as promotion target audience, competitive strength, third parties selling the same or similar product, and sales, and secondarily classifies the primary classified data according to detailed criteria. can do. For example, text data classified as a target audience is secondarily classified according to age/gender, and text data classified by competition intensity is secondarily classified according to keyword search volume and blog/cafe/SNS posts, and third-party products Text data classified as ' is secondarily classified according to average price, detailed category (type of product), etc. have.

The parsing of the text data performed by the promotional content generating unit classifies the data using any one of various known classification algorithms.

The promotional content generation unit provides data for producing promotional content by using data processing technologies such as Natural Language Processing (NLP), Regression Analysis, and Correlation Analysis.

For example, the promotion content generation unit uses natural language processing technology to process natural language processing for portals and community product mentions, and uses them in fields such as scoring and sales forecasting, and using regression analysis technology to determine the influence of independent variables on dependent variables. By estimating, direct causal relationships such as sales and advertisement exposure rankings are identified, and the indirect influence relationship on the dependent variable is analyzed by comparing the similarity (increase or decrease) of patterns between variables using correlation analysis technology.

In particular, the promotional content generating unit is characterized in that it derives key keywords included in the promotional content by analyzing the classified text data.

To this end, the promotional content generating unit compares the pre-stored or learned keyword list with text data, extracts words included in the keyword list from among the text data, and includes them in the core keyword candidate group list.

In order to analyze the meaning of the words included in the key keyword candidate group list, the promotional content generator vectorizes each word included in the core keyword candidate group list, and inputs each vectorized word to the input layer of the pre-trained artificial neural network. Thus, a key keyword is set based on an output value output from the output layer of the artificial neural network.

Here, the artificial neural network is a deep neural network composed of an input layer, a hidden layer, and an output layer. Since a technique for estimating the meaning of data using a deep neural network is a well-known technique, a detailed description thereof will be omitted.

The promotional content generating unit sets an image, text, font, size, and color to be included in the promotional content based on the portal site search result for the set key keyword.

Specifically, the promotional content generating unit collects image data and promotional data related to the key keyword by crawling image data and promotional data displayed as a result of a portal site search for the key keyword.

The promotional content generating unit generates a histogram, which is information indicating the distribution and frequency of color values constituting the image, from each of the collected image data and the images included in the promotional data. Since a specific method for generating a histogram is a known technique, a detailed description thereof will be omitted.

The promotional content generating unit counts the color used with the highest frequency by using the histogram generated from any one image, gives a first weight, counts the color used as the next-order frequency, and then counts the color used with the second priority A weight is given, and a third weight lower than the second weight is given after counting the colors used with the third priority frequency. For example, if it is confirmed that red is used the most by analyzing the histogram for any one image, the promotional content generator gives red = 1 (counting) * first weight (eg, 1.5) to give a red: 1.5 counting result When the value is calculated and it is confirmed that blue is used a lot in the next order, blue: 1 (counting) * second weight (eg, 1.3) is given to calculate a counting result value of blue: 1.3. The promotional content generating unit performs the same operation on all crawled images using this method.

When all images are counted and weighted, the promotional content generating unit calculates a summed counting result by summing the counting result values for each color. The promotional content generating unit compares the calculated sum counting result values for each color, and arranges the colors in order from the color having the highest counting result value to the color having the lowest counting result value.

Thereafter, the promotional content generating unit analyzes the promotional content for a sample received from the manager terminal or the customer terminal to classify the objects included in the promotional content, and labels the classified objects by type.

To this end, the promotional content generation unit converts the received sample promotional content into image data, pools the image data using a convolution filter, and inputs the feature vector generated through the pooling operation into the pre-trained artificial neural network. Thus, the object included in the promotional content for the sample is classified using the result value of the artificial neural network. Since such an object detection technology is already widely known, a detailed description thereof will be omitted.

The promotional content generating unit labels the promotional content for the sample into different object areas based on the object classification result, and calculates a ratio of each labeled object to the total area of the promotional content for the sample.

Thereafter, the promotional content generating unit may apply the color having the highest counting result value to the object occupying the highest proportion in the promotional content for the sample, and apply the color having the second-order counting result value to the object occupying the next priority.

For example, if it is determined that the text area occupies the highest ratio in the entire area of the promotional content for the sample, the promotional content generating unit may recommend a color having the highest counting result value. In addition, when it is confirmed that the first character object occupies the second-order ratio in the entire area of the promotional content for the sample, the promotional content generating unit may recommend a color having a second-order counting result value.

In this way, the promotional content generating unit may automatically apply different colors according to the proportion of objects constituting the sample promotional content to the sample promotional content.

The promotional content generating unit transmits the promotional content for the sample to which the color is applied to the manager terminal or the customer terminal, and when an approval message is received from the manager terminal or the customer terminal, the promotional content for the sample may be set as the final promotional content.

3 is a diagram illustrating a detailed configuration of an analysis unit.

As shown, the analysis unit includes a data collection unit 221 , a marketing recommendation unit 222 , a marketing analysis unit 223 , a risk management unit 224 , and a report management unit 225 .

The data collection unit collects marketing dictionary data according to the marketing request information received from the customer terminal 100 to perform online marketing, and marketing progress data generated in the online marketing process performed by the manager terminal 200 . to collect

Here, the marketing dictionary data is the same as or similar to the target to be promoted based on the marketing request information received from the above-described customer terminal 100 and the marketing request information received from the customer terminal 100 (product, brand, etc.) may include online data for

For example, when the data collection unit receives information related to lactic acid bacteria beverages from the customer terminal 100 to promote products related to the lactic acid bacteria beverages, the lactic acid bacteria beverages are mainly used in any route (portal sites, blogs, knowledge inquiries, social network services (SNS), etc.) ) can be collected as online data.

The marketing recommendation unit determines the type of online marketing based on the marketing dictionary data collected by the data collection unit 210 .

Specifically, the marketing recommendation unit considers information on the type of target to be promoted, the main target group interested in the target, the media method mainly used by the main target group, and the online promotion method in which similar product groups related to the target are mainly promoted. You can decide the type of publicity.

The marketing analysis unit generates analysis data based on data (marketing progress data) generated according to an online marketing process performed according to the online marketing method determined by the marketing recommendation unit.

For example, the marketing analysis unit may generate the first analysis data including information on the marketing progress according to the online marketing for each customer (by customer). In the first analysis data, detailed information related to the key keyword related to the target to be promoted, the number of daily exposures for each key keyword, the number of non-exposures per day for each key keyword, and the number of guaranteed exposures (days) negotiated during the online marketing agency contract are displayed.

In addition, the marketing analysis unit may generate the second analysis data including information on the overall marketing progress for each company. When transmitting the second analysis data for each customer terminal, the marketing analysis unit may filter and transmit only data related to the customer terminal.

Here, when the customer selects an object to be promoted from among the second analysis data displayed on the customer terminal, information on a detailed exposure rate related to the selected object may be provided.

To this end, the marketing analysis unit may generate the third analysis data including data on the target exposure rate by day of the week, weekly cumulative exposure rate, the number of exposures per day, and the like.

Accordingly, the report data generated by the marketing analysis unit includes the first analysis data, the second analysis data, and the third analysis data.

The risk management unit 224 derives a problem occurring in the online marketing process based on the analysis data generated by the marketing analysis unit 223, and a solution for solving the derived problem using a pre-learned artificial neural network suggest

For example, the risk management unit 224 may compare the previously agreed target exposure rate with the cumulative exposure rate, and if the cumulative exposure rate is lower than the target exposure rate, it may be determined that a risk has occurred in the online marketing process.

In this case, the risk management unit 224 controls the data collection unit 221 to collect data on other objects of the same or similar type as the promotion object, and compares the data collected by the data collection unit 221 and the publicity. A difference value of the target data can be calculated. For example, if the risk management department agreed to expose Shampoo A, the target of promotion, more than 10 times a week, but was exposed to the portal site 3 times a week, the data on Shampoo B, which recorded the highest number of exposures among other shampoo products exposed more than 10 times a week The difference value between the number of times of collection and exposure can be calculated as 7.

In this way, the risk management unit calculates a difference value by comparing data on the promotional target with the low advertisement effect and the competitive target with the best advertisement effect. Here, the difference values are the difference in the number of weekly exposures, the difference in exposure rate for all competitive products (comparative value), the difference in the number of exposures by media (portal site, knowledge inquiry article, SNS, blog, etc.), and the promotion concept. It includes the difference value of the number of exposures according to the exposure number, the difference value of the number of exposures according to the promotional model, and the like.

The risk management unit inputs the plurality of difference values calculated in this way as input values of the artificial neural network learned in advance, and derives a solution to improve the publicity effect based on the output value of the artificial neural network.

For example, if the risk management unit compares the target to be promoted with the competitive target with high advertising efficiency using an artificial neural network, and it is found that the number of exposures is the most different according to the difference in the promotional medium, the risk of suggesting to change the promotional medium Create management data.

The communication management unit provides an online chat room and video call service between user terminals accessing the collaboration service providing server.

The communication management unit opens a chat room in which at least two user terminals participate or provides a video call service in which at least two user terminals participate, as shown in FIGS. 4 to 7 .

The communication management department opens chat rooms by topic according to the organizational structure and work culture, and chat rooms can be set publicly or privately according to the situation.

The communication management department can designate whether or not chat rooms are open for each work topic, and if a private chat room is created, only invited user terminals can participate and it does not appear in the chat room list, so information in the chat room can be shared limitedly.

Companies with limited work space must designate an internal network access IP to block external access. The communication management unit may provide a setting function that allows access or download of files only from an internally authorized IP.

In addition, the communication management unit converts the document data into image data so that another user terminal can check the document data uploaded from any one user terminal through the chat room in a preview format, and transfers the converted image data to the chat room Upload automatically.

Accordingly, documents such as Hangul, Word, Excel, PowerPoint, and images can be easily previewed regardless of PC/mobile, and the speed of collaboration can be improved by previewing files shared with members and leaving feedback immediately. have.

In addition, based on the text message input through the chat room, the communication management unit transmits a leave request message to the user terminal set as the personnel manager, and transmits the payment request message to the user terminal set as the approval authority.

The report management unit collects information generated during real-time communication of document data uploaded through chat rooms and automatically creates revised document data that reflects the revisions.

Specifically, the report management unit, with respect to the original document data uploaded from the first user terminal through the chat room, based on the text message input from the second user terminal in the chat room in which the first user terminal and the second user terminal participated. Automatically create modified document data for original document data, and additionally upload the created modified document data to the chat room.

For example, if the second user inputs the message 'Please change the date on the second line of page 3 of the document to the date' with respect to the original document data uploaded through the chat room, the report management unit It is possible to automatically generate correction document data by correcting the word date in the second line of page 3 of the document data with the date.

To this end, the report management unit 300 may understand the meaning of the text message by natural language processing of the text message input through the chat room. Since such a natural language processing technology has already been disclosed and is widely used, a detailed description thereof will be omitted.

Accordingly, the correction and management of the document may be facilitated.

Alternatively, the report management unit automatically generates correction document data for the original document data based on a voice signal detected in a video call process performed between the first user terminal and the second user terminal, and the generated correction document Data is transmitted to the first user terminal.

In some other embodiments, when it is confirmed that the content to be added is discussed in the chat room or video call process, the report management unit provides information on the content to be added.

Specifically, the report management unit analyzes the message input through the chat room or voice data generated during the video call process and when it is confirmed that the content to be added is a specific image, searches for the image and enters the link address into the chat room for video call video can be displayed together with

In addition, the report management unit analyzes the message input through the chat room or voice data generated during the video call process, and when it is confirmed that the content to be added is statistical data, the report management unit automatically creates a form for statistical data generation to the user terminal can be sent to

In some other embodiments, the report management unit may provide an interface call screen for editing the original document data uploaded through the chat room as shown in FIGS. 8 to 10 .

First, as shown in FIG. 8 , when the report management unit receives a request to modify the original document data uploaded through the chat room from the manager terminal, the uploaded document is displayed in the central part of the user terminal, and the document display area The editing start area and editing stop area are displayed in the form of icons at the bottom. In this state, when the manager touches the edit start icon, the report management unit may guide to display a specific point of the original document data displayed in the center of the terminal.

Thereafter, when the user (administrator) touches a part to be corrected on the screen, the report management unit may determine which part of the original document data is to be corrected based on the touch signal. To this end, the report management unit converts the original document data into the original image data, and detects which area is displayed on the manager terminal among the entire area of the image. In this state, the report management unit may coordinate the location of the touch signal input through the manager terminal to detect information on which part of the document the user is pointing to.

The report management unit estimates the point pointed by the user in the original document data by the above-described method, and classifies an object corresponding to the estimated location. Specifically, the report management unit may estimate information on whether the user points to text, image, diagram, and the like, and since the technology for extracting an object from an image is a well-known technology, a detailed description thereof will be omitted.

In this case, as shown in FIG. 9 , the report management unit displays the content that needs correction selected by the user in the area before the change, and displays the text, image or text to be corrected in the area after the change based on information input from the user terminal. Let the diagram be displayed. For example, when an administrator inputs text to be corrected through a text input window displayed on the administrator terminal, the report management unit generates a corrected image that is an image of the input text, and displays the corrected image in the area after the change. . The report management unit queries the manager terminal as to whether to change the document from the content before the change to the content after the change, and if the manager terminal approves the document, the modified image is placed in a specific area of the original image data. Here, the specific region may be defined as a location selected by the manager terminal through the above-described process, and the report management unit arranges the corrected image in the original image data so that the center of the corrected image is mapped to the location selected by the manager terminal. can As described above, the report management unit may provide a function (interface screen) for easily modifying and changing documents with simple manipulation.

On the other hand, the report management unit inquires to the manager terminal whether the text corresponding to the desired point of correction input by the manager terminal is the text to be corrected, and the answer from the manager terminal is that the text corresponding to the point is not the text to be corrected. , can provide additional functionality to change the point to be modified.

In this case, as shown in FIG. 10 , the report management unit displays an interface screen for receiving an input of a correction region including the content to be corrected on the manager terminal, and the correction region moves up, down, left, and right based on the manipulation signal of the manager terminal. It can be moved or resized.

In this case, the report management unit searches where the finally determined correction region is formed in the original image data, and detects which data (text, image, etc.) included in the correction region is in the above-described object detection method, as shown in FIG. 9 . can be displayed in the area before the change of Therefore, even if the manager selects an unintended point due to a mistake, etc., it accurately determines the area that needs to be corrected so that effective real-time communication can be achieved.

In this way, the report management unit provides various functions to facilitate the modification of documents uploaded to the non-face-to-face collaboration service providing system, thereby improving the work convenience of users using the non-face-to-face collaboration service providing system according to the present invention. have.

In some other embodiments, the report management unit may provide an interface call screen for editing the original document data uploaded through the chat room as shown in FIGS. 8 to 10 .

First, as shown in FIG. 8 , when the report management unit receives a request to modify the original document data uploaded through the chat room from the manager terminal, the uploaded document is displayed in the central part of the user terminal, and the document display area The editing start area and editing stop area are displayed in the form of icons at the bottom. In this state, when the manager touches the edit start icon, the report management unit may guide to display a specific point of the original document data displayed in the center of the terminal.

Thereafter, when the user (administrator) touches a part to be corrected on the screen, the report management unit may determine which part of the original document data is to be corrected based on the touch signal. To this end, the report management unit converts the original document data into the original image data, and detects which area is displayed on the manager terminal among the entire area of the image. In this state, the report management unit may coordinate the location of the touch signal input through the manager terminal to detect information on which part of the document the user is pointing to.

The report management unit estimates the point pointed by the user in the original document data by the above-described method, and classifies an object corresponding to the estimated location. Specifically, the report management unit may estimate information on whether the user points to text, image, diagram, and the like, and since the technology for extracting an object from an image is a well-known technology, a detailed description thereof will be omitted.

In this case, as shown in FIG. 9 , the report management unit displays the content that needs correction selected by the user in the area before the change, and displays the text, image or text to be corrected in the area after the change based on information input from the user terminal. Let the diagram be displayed. For example, when an administrator inputs text to be corrected through a text input window displayed on the administrator terminal, the report management unit generates a corrected image that is an image of the input text, and displays the corrected image in the area after the change. . The report management unit inquires to the manager terminal whether to change the document from the content before the change to the content after the change, and if the manager terminal approves it, the modified image is placed in a specific area of the original image data. Here, the specific region may be defined as a location selected by the manager terminal through the above-described process, and the report management unit arranges the corrected image in the original image data so that the center of the corrected image is mapped to the location selected by the manager terminal. can As described above, the report management unit may provide a function (interface screen) for easily modifying and changing documents with simple manipulation.

On the other hand, the report management unit inquires to the manager terminal whether the text corresponding to the desired point of correction input by the manager terminal is the text to be corrected, and the answer from the manager terminal is that the text corresponding to the point is not the text to be corrected. , can provide additional functionality to change the point to be modified.

In this case, as shown in FIG. 10 , the report management unit displays an interface screen for receiving an input of a correction region including the content to be corrected on the manager terminal, and the correction region moves up, down, left, and right based on the manipulation signal of the manager terminal. It can be moved or resized.

In this case, the report management unit searches where the finally determined correction region is formed in the original image data, and detects which data (text, image, etc.) included in the correction region is in the above-described object detection method, as shown in FIG. 9 . can be displayed in the area before the change of Therefore, even if the manager selects an unintended point due to a mistake, etc., it accurately determines the area that needs to be corrected so that effective real-time communication can be achieved.

In this way, the report management unit provides various functions to facilitate the modification of documents uploaded to the non-face-to-face collaboration service providing system, thereby improving the work convenience of users using the non-face-to-face collaboration service providing system according to the present invention. have.

In some other embodiments, the report management unit may provide an interface call screen for editing the original document data uploaded through the chat room as shown in FIGS. 8 to 10 .

First, as shown in FIG. 8 , when the report management unit receives a request to modify the original document data uploaded through the chat room from the manager terminal, the uploaded document is displayed in the central part of the user terminal, and the document display area The editing start area and editing stop area are displayed in the form of icons at the bottom. In this state, when the manager touches the edit start icon, the report management unit may guide to display a specific point of the original document data displayed in the center of the terminal.

Thereafter, when the user (administrator) touches a part to be corrected on the screen, the report management unit may determine which part of the original document data is to be corrected based on the touch signal. To this end, the report management unit converts the original document data into the original image data, and detects which area is displayed on the manager terminal among the entire area of the image. In this state, the report management unit may coordinate the location of the touch signal input through the manager terminal to detect information on which part of the document the user is pointing to.

The report management unit estimates the point pointed by the user in the original document data by the above-described method, and classifies an object corresponding to the estimated location. Specifically, the report management unit may estimate information on whether the user points to text, image, diagram, and the like, and since the technology for extracting an object from an image is a well-known technology, a detailed description thereof will be omitted.

In this case, as shown in FIG. 9 , the report management unit displays the content that needs correction selected by the user in the area before the change, and displays the text, image or text to be corrected in the area after the change based on information input from the user terminal. Let the diagram be displayed. For example, when an administrator inputs text to be corrected through a text input window displayed on the administrator terminal, the report management unit generates a corrected image that is an image of the input text, and displays the corrected image in the area after the change. . The report management unit queries the manager terminal as to whether to change the document from the content before the change to the content after the change, and if the manager terminal approves the document, the modified image is placed in a specific area of the original image data. Here, the specific region may be defined as a location selected by the manager terminal through the above-described process, and the report management unit arranges the corrected image in the original image data so that the center of the corrected image is mapped to the location selected by the manager terminal. can As described above, the report management unit may provide a function (interface screen) for easily modifying and changing documents with simple manipulation.

On the other hand, the report management unit inquires to the manager terminal whether the text corresponding to the desired point of correction input by the manager terminal is the text to be corrected, and the answer from the manager terminal is that the text corresponding to the point is not the text to be corrected. , can provide additional functionality to change the point to be modified.

In this case, as shown in FIG. 10 , the report management unit displays an interface screen for receiving an input of a correction region including the content to be corrected on the manager terminal, and the correction region moves up, down, left, and right based on the manipulation signal of the manager terminal. It can be moved or resized.

In this case, the report management unit searches where the finally determined correction region is formed in the original image data, and detects which data (text, image, etc.) included in the correction region is in the above-described object detection method, as shown in FIG. 9 . can be displayed in the area before the change of Therefore, even if the manager selects an unintended point due to a mistake, etc., it accurately determines the area that needs to be corrected so that effective real-time communication can be achieved.

In this way, the report management unit provides various functions to facilitate the modification of documents uploaded to the non-face-to-face collaboration service providing system, thereby improving the work convenience of users using the non-face-to-face collaboration service providing system according to the present invention. have.

In some other embodiments, the report management unit may provide an interface call screen for editing the original document data uploaded through the chat room as shown in FIGS. 8 to 10 .

First, as shown in FIG. 8 , when the report management unit receives a request to modify the original document data uploaded through the chat room from the manager terminal, the uploaded document is displayed in the central part of the user terminal, and the document display area The editing start area and editing stop area are displayed in the form of icons at the bottom. In this state, when the manager touches the edit start icon, the report management unit may guide to display a specific point of the original document data displayed in the center of the terminal.

Thereafter, when the user (administrator) touches a part to be corrected on the screen, the report management unit may determine which part of the original document data is to be corrected based on the touch signal. To this end, the report management unit converts the original document data into the original image data, and detects which area is displayed on the manager terminal among the entire area of the image. In this state, the report management unit may coordinate the location of the touch signal input through the manager terminal to detect information on which part of the document the user is pointing to.

The report management unit estimates the point pointed by the user in the original document data by the above-described method, and classifies an object corresponding to the estimated location. Specifically, the report management unit may estimate information on whether the user points to text, image, diagram, and the like, and since the technology for extracting an object from an image is a well-known technology, a detailed description thereof will be omitted.

In this case, as shown in FIG. 9 , the report management unit displays the content that needs correction selected by the user in the area before the change, and displays the text, image or text to be corrected in the area after the change based on information input from the user terminal. Let the diagram be displayed. For example, when an administrator inputs text to be corrected through a text input window displayed on the administrator terminal, the report management unit generates a corrected image that is an image of the input text, and displays the corrected image in the area after the change. . The report management unit queries the manager terminal as to whether to change the document from the content before the change to the content after the change, and if the manager terminal approves the document, the modified image is placed in a specific area of the original image data. Here, the specific region may be defined as a location selected by the manager terminal through the above-described process, and the report management unit arranges the corrected image in the original image data so that the center of the corrected image is mapped to the location selected by the manager terminal. can As described above, the report management unit may provide a function (interface screen) for easily modifying and changing documents with simple manipulation.

On the other hand, the report management unit inquires to the manager terminal whether the text corresponding to the desired point of correction input by the manager terminal is the text to be corrected, and the answer from the manager terminal is that the text corresponding to the point is not the text to be corrected. , can provide additional functionality to change the point to be modified.

In this case, as shown in FIG. 10 , the report management unit displays an interface screen for receiving an input of a correction region including the content to be corrected on the manager terminal, and the correction region moves up, down, left, and right based on the manipulation signal of the manager terminal. It can be moved or resized.

In this case, the report management unit searches where the finally determined correction region is formed in the original image data, and detects which data (text, image, etc.) included in the correction region is in the above-described object detection method, as shown in FIG. 9 . can be displayed in the area before the change of Therefore, even if the manager selects an unintended point due to a mistake, etc., it accurately determines the area that needs to be corrected so that effective real-time communication can be achieved.

In this way, the report management unit provides various functions to facilitate the modification of documents uploaded to the non-face-to-face collaboration service providing system, thereby improving the work convenience of users using the non-face-to-face collaboration service providing system according to the present invention. have.

In some other embodiments, the risk management unit may quantify and derive the risk by item (promotion means, price, target audience selection, etc.) based on the evaluation data for the promotion target.

For example, the risk management unit 240 collects user review data for shampoo A, which is a promotion target, vectorizes the meaning of the review data (evaluation data), and inputs the vectorized input value to the artificial neural network based on the output value. In this way, it is possible to determine where the publicity target has problems in public relations.

Thereafter, the risk management unit may generate risk management data including a method for solving the derived problems.

To this end, the risk management unit trains an artificial neural network.

The risk management unit is characterized by grouping all the words constituting the learning data input for learning of the artificial neural network in units of predetermined words.

For example, as shown, the risk management unit classifies three consecutive words into one group, classifies the first to third words of the training data into the first group, and the second word of the training data to the fourth word are classified into the second group, and the third to fifth words of the training data are classified into the third group. In this way, the risk management unit 240 may divide the training data into a plurality of groups in which a predetermined number of words are sequentially listed, and thus, one word including the training data may be classified into at least two or more groups.

Thereafter, the risk management unit may classify a plurality of words included in each group into a reference word and an adjacent word.

For example, the risk management unit may set the middlemost word among the words included in the first, second, and third groups as the reference word, and set the words on both sides as the surrounding words.

After that, the risk management unit vectorizes each reference word and surrounding words, sets a vector value or a vector matrix for the surrounding words as a dataset to be input to the input layer of the artificial neural network, and sets the reference word to be predicted in the output layer as the reference value , and the weights between nodes constituting the artificial neural network are reset according to the result of comparing the output vector for the input data with the set reference value.

That is, in order for the artificial neural network to infer words having frequent combinations with each other, the risk management unit learns and adjusts the weights between nodes of the artificial neural network when the neighboring words of the reference word are given as input values and the reference word is given as an output value. characterized in that

The report management unit transmits the analysis data generated by the marketing analysis unit and the risk management data generated by the risk management unit to the customer terminal. The report management department periodically transmits the generated analysis data and risk management data so that customers can periodically check the promotional effect of the company or product they want to promote.

In some other embodiments, the data collection unit may include: a collection management module that sets a collection criterion of at least one of a collection target data source module, a collection target keyword, and a collection target period; a data collection module for collecting big data from the corresponding data source module according to the data collection criteria set by the collection management module and storing it in the database module; a morpheme analysis module that analyzes morphemes of big data stored in the database module, classifies them by morpheme, and generates morpheme analysis data; and a data analysis module that processes morpheme analysis data with a distributed parallel processing-based statistical analysis algorithm to calculate statistical values and outputs malicious codes according to statistical values; a big data analysis-based abnormal data derivation system (for convenience of explanation) It can be automatically determined whether text data maliciously slandering a company is included in the received data by using (not shown in the drawing).

Here, the data collection unit generates morpheme analysis data by dividing the received text data by morphemes having a meaning, and includes: a distributed file system for storing the morpheme analysis data; a data processing unit providing a virtualized database interface to process morpheme analysis data existing in the distributed file system based on SQL (structured query language); And by executing a statistical analysis algorithm through the virtualized database interface provided by the data processing unit, from the morpheme analysis data, the number of occurrences per year (instance frequencies) by year, the number of simultaneous appearances between words by year, the number of appearances by year and by year The word-to-words may include a statistical analysis unit that calculates at least one of the processed values from the number of simultaneous appearances.

In addition, the statistical analysis unit, the statistical analysis unit may calculate an increase rate of the number of occurrences per word based on the number of occurrences per year (instance frequencies) and the number of word-word simultaneous occurrences.

In addition, the statistical analysis unit divides the number of occurrences per year (instance frequencies) by the number of documents per year to standardize the number of appearances per year of the words per document to calculate a standardized increase rate of the frequency of appearance per word for the words. can

In addition, the statistical analysis unit calculates the increase rate of the degree of connection degree centrality for each word by using the word-word co-occurrence matrix, and the standardized word-by-word appearance frequency increase rate and the connection degree centrality increase rate are above a certain portion or higher Words that are less than a certain lower part can be deduced as malicious code.

Meanwhile, the data collection module may collect big data including unstructured data of at least any one of image, video, voice, sensor, GPS, GIS, and M2M data.

Accordingly, the computer device may improve the reliability of analysis by filtering text data written for malicious purposes in advance through big data analysis through the abnormal data derivation system including the configuration as described above.

Such technology may be implemented as an application or implemented in the form of program instructions that may be executed through various computer components and recorded in a computer-readable recording medium. The computer-readable recording medium may include program instructions, data files, data structures, etc. alone or in combination.

The program instructions recorded on the computer-readable recording medium are specially designed and configured for the present invention, and may be known and available to those skilled in the art of computer software.

Examples of the computer-readable recording medium include a hard disk, a magnetic medium such as a floppy disk and a magnetic tape, an optical recording medium such as a CD-ROM and DVD, and a magneto-optical medium such as a floppy disk. media), and hardware devices specially configured to store and execute program instructions such as ROM, RAM, flash memory, and the like.

Examples of program instructions include not only machine language codes such as those generated by a compiler, but also high-level language codes that can be executed by a computer using an interpreter or the like. The hardware device may be configured to operate as one or more software modules to perform processing according to the present invention, and vice versa.

Although the above has been described with reference to the embodiments, those skilled in the art will understand that various modifications and changes can be made to the present invention without departing from the spirit and scope of the present invention as set forth in the following claims. will be able

210: Promotional content generation unit
220: analysis unit
230: communication management department

Claims (8)

In a real-time complementary marketing system that produces customized advertising content and shares information generated in the process of analyzing the promotional efficiency using the produced advertising content to a customer terminal in real time,
a customer terminal owned by a customer who wants to conduct online marketing; and
and a manager terminal that performs online marketing according to the marketing agency requested from the customer terminal, generates analysis data by analyzing data generated in the online marketing process, and periodically transmits it to the customer terminal,
The manager terminal,
Promotional content generation unit for generating promotional content to be used for online marketing;
an analysis unit that generates analysis data by analyzing data generated during the online marketing process; and
and a communication management unit that provides an online chat room and video call service between the user terminal and the manager terminal.
The analysis unit,
a data collection unit that collects marketing dictionary data according to the marketing request information received from the customer terminal in order to perform online marketing, and collects marketing progress data generated in an online marketing process performed by the manager terminal;
a marketing recommendation unit for determining an online marketing type based on the marketing dictionary data collected by the data collection unit;
a marketing analysis unit generating the analysis data based on the marketing progress data generated according to the online marketing execution determined by the marketing recommendation unit;
a risk management unit for generating risk management data for deriving problems occurring in the online marketing process based on the analysis data and proposing a solution for solving the problems derived using a pre-learned artificial neural network;
A real-time supplemental marketing system comprising a; a report management unit for transmitting the analysis data and the risk management data to the customer terminal.
According to claim 1,
The customer terminal is a smart phone, characterized in that the real-time complementary marketing system.
3. The method of claim 2,
The customer terminal is a personal computer (PC), characterized in that the real-time supplemental marketing system.
According to claim 1,
The promotional content generation unit,
It collects news data, advertisement data, promotional material data, comment data and post data related to the target to be promoted through online media, classifies the collected text data according to preset classification criteria, and analyzes the classified text data. A real-time complementary marketing system, characterized in that a keyword is derived, image data related to a key keyword is retrieved, and a color to be applied to the promotional content for a sample received from an administrator terminal or a customer terminal is recommended based on the retrieved image data.
5. The method of claim 4,
The promotional content generation unit,
generate a histogram for the collected image data,
The generator counts the color used with the highest frequency by using the histogram generated from any one image, assigns a first weight, counts the color used as the next-order frequency, and adds a second weight lower than the first weight After counting the colors used with the 3rd priority frequency, when counting and weighting the image by giving a third weight lower than the second weight, the counting result for each color is added to calculate the summed counting result ,
Converting the received promotional content for sample into image data, labeling the promotional content for the sample with different object areas, calculating the ratio of each labeled object to the total area of the promotional content for the sample, and the promotional content for the sample A real-time complementary marketing system that applies the color with the highest counting result value to the object that occupies the highest weight in
According to claim 1,
The manager terminal,
A real-time complementary marketing system, further comprising a big data analysis-based abnormal data derivation unit for determining whether abnormal data is included in the received marketing advance data and the marketing progress data.
7. The method of claim 6,
The abnormal data derivation unit,
a collection management module for setting at least one of a collection target data source module, a collection target keyword, and a collection target period;
a data collection module for collecting big data from the corresponding data source module according to the data collection criteria set by the collection management module and storing it in the database module;
a morpheme analysis module that analyzes morphemes of big data stored in the database module, classifies them by morpheme, and generates morpheme analysis data; and
A data analysis module that processes morpheme analysis data with a distributed parallel processing-based statistical analysis algorithm to calculate statistical values and outputs malicious codes according to the statistical values; a real-time complementary marketing system that includes.
A computer-readable recording medium on which a computer program is recorded, for performing the real-time complementary marketing system according to any one of claims 1 to 7.

Images