KR102424346B1 - Data analysis server, method of calculating an estimated delivery volume by region for commerce content and computer program - Google Patents

Abstract

According to embodiments of the present disclosure, the data analysis server may include: searching for one or more second commerce contents in consideration of at least one of a programming time zone of a first commerce content scheduled to be broadcast and a product code for sale; retrieving, by the data analysis server, order data related to the one or more second commerce contents; The data analysis server classifies the order data by region and generates expected order information for each region for the first commerce content based on the classified order data; and generating, by the data analysis server, advance quantity information based on expected order information for each region for the first commerce content, and transmitting the advance quantity information to a logistics data server; A method of calculating an expected shipment volume is disclosed.

Description

DATA ANALYSIS SERVER, METHOD OF CALCULATING AN ESTIMATED DELIVERY VOLUME BY REGION FOR COMMERCE CONTENT AND COMPUTER PROGRAM}

Embodiments of the present disclosure relate to a data analysis server, a method and a computer program for calculating an expected delivery volume by region for commerce content.

Today, with the development of digital technology, television is gradually becoming digitized, and on the other hand, the convergence of broadcasting and communication, which provides content with different characteristics through a separate network, is accelerating. That is, the initiative is shifting from one-way analog broadcasting to interactive digital broadcasting in which a viewer interacts. In addition, methods through which users can use content such as broadcast content and commerce content are provided through mobile multimedia broadcasting (DMB, Digital Multimedia Broadcasting), the Internet, and the like are diversifying.

The conventional viewer rating calculation method has used a method of calculating the audience rating by selecting a limited number of panels, installing dedicated equipment necessary for calculating the audience rating in the household of the selected panel, and collecting data of the channels watched by the household by date. In particular, since such viewing panel-related data is uniformly transmitted to a server that calculates an audience rating during a specific time period (eg, 4-5 am), it was impossible to calculate the audience rating in real time.

In addition, since it is impossible to determine who is currently watching a channel among members of the household, the apparatus for calculating the audience rating installed in the home cannot calculate the audience rating data with high reliability. In addition, there is a problem in that the data provided by the viewer rating calculating device includes only information on which channel is being viewed among the channels currently being broadcast in real time, so that it is impossible to collect information on various events related to transmitted content.

In order to solve the above-described problem, embodiments of the present disclosure are to provide a data analysis server, method, and computer program for calculating the expected delivery volume by region for commerce content.

According to the present embodiments, the data analysis server may include: searching for one or more second commerce contents in consideration of at least one of a programming time zone and a sales product code of the first commerce contents scheduled to be broadcast; retrieving, by the data analysis server, order data related to the one or more second commerce contents; and classifying, by the data analysis server, the order data by region and generating expected order information for each region for the first commerce content based on the classified order data; and generating, by the data analysis server, advance quantity information based on expected order information for each region for the first commerce content, and transmitting the advance quantity information to a logistics data server; A method of calculating an expected shipment volume is disclosed.

According to the present embodiments, the logistics data server further comprises the step of generating an expected logistics amount for each region based on the pre-volume information, and generating dispatch schedule information for delivery based on the expected logistics amount for each region, Disclosed is a method of calculating an expected delivery volume for each region for commerce content.

According to the present embodiments, the data analysis server selects an excess quantity expected area exceeding a preset reference order value from the expected order information for each region, and inventory status of distribution warehouses located within the selected excess quantity expected area. Disclosed is a method of calculating an expected delivery volume by region for commerce content, further comprising acquiring information.

The data analysis server may further include determining, by the data analysis server, a first logistics warehouse in which the quantity of the first commerce content is loaded, based on each inventory status information, from among the warehouses in the excess quantity expected area.

The computer program according to the embodiment of the present disclosure may be stored in a medium to execute any one of the methods according to the embodiment of the present disclosure using a computer.

In addition to this, another method for implementing the present invention, another system, and a computer-readable recording medium for recording a computer program for executing the method are further provided.

Other aspects, features and advantages other than those described above will become apparent from the following drawings, claims, and detailed description of the invention.

The data analysis server, the method and computer program for calculating the expected delivery volume by region for commerce content according to embodiments of the present disclosure, before the commerce content is transmitted, by using the expected sales level and region-specific order data related to the commerce content, It is possible to calculate expected delivery volume information by region for commerce content.

1 is a block diagram of a data processing system for generating processed data by analyzing user viewing data according to embodiments of the present disclosure.
2 is a diagram of a data analysis server in communication with one or more media provision servers.
3 is a block diagram of a data analysis server 100 according to embodiments of the present disclosure.
4 is a block diagram of the data processing unit 130 .
5 and 6 are flowcharts of a method of calculating a real-time expected sales level during transmission according to embodiments of the present disclosure.
7 to 13 are exemplary diagrams of a user interface generated by the data analysis server 100 .

Hereinafter, the configuration and operation of the present invention will be described in detail with reference to the embodiments of the present invention shown in the accompanying drawings.

Since the present invention can apply various transformations and can have various embodiments, specific embodiments are illustrated in the drawings and described in detail in the detailed description. Effects and features of the present invention, and a method of achieving them, will become apparent with reference to the embodiments described below in detail in conjunction with the drawings. However, the present invention is not limited to the embodiments disclosed below and may be implemented in various forms.

Hereinafter, embodiments of the present disclosure will be described in detail with reference to the accompanying drawings, and when described with reference to the drawings, the same or corresponding components are given the same reference numerals, and the overlapping description thereof will be omitted. .

In this specification, terms such as “learning” and “learning” are not intended to refer to mental actions such as human educational activities, but are terms referring to performing machine learning through computing according to procedures. interpret

In the following embodiments, terms such as first, second, etc. are used for the purpose of distinguishing one component from another, not in a limiting sense.

In the following examples, the singular expression includes the plural expression unless the context clearly dictates otherwise.

In the following embodiments, terms such as include or have means that the features or components described in the specification are present, and the possibility that one or more other features or components may be added is not excluded in advance.

In the drawings, the size of the components may be exaggerated or reduced for convenience of description. For example, since the size and thickness of each component shown in the drawings are arbitrarily indicated for convenience of description, the present invention is not necessarily limited to the illustrated bar.

In cases where certain embodiments are otherwise practicable, a specific process sequence may be performed different from the described sequence. For example, two processes described in succession may be performed substantially simultaneously, or may be performed in an order opposite to the order described.

A set-top box is a hardware device necessary for viewing satellite broadcasting or cable broadcasting at home. Data such as satellite broadcasting, cable broadcasting, or Internet broadcasting is transmitted to the set-top box as data processed through compression and modulation, etc., which performs demodulation and decompression processing on the received data It plays a role that enables it to be implemented in a terminal such as a TV.

1 is a configuration diagram of a data processing system for generating processed data by analyzing user viewing data according to embodiments of the present disclosure.

As shown in FIG. 1 , the data processing system includes a data analysis server 100 , a media providing server 200 , a content transmission server 300 , a first set-top box 401 , a second set-top box 402 , and the second 3 set-top box 403, . , an n-th set-top box 40n, and one or more user terminals T1, T2, T3, ..., Tn, hereinafter, T).

The data analysis server 100 receives viewing data, call-in data, and/or order data for content and/or content-related output data through the media providing server 200 , and receives viewing data, call-in data and/or Alternatively, by analyzing the order data, it is possible to generate data processing data such as the order amount related to the content, the expected handling amount, the order amount compared to the viewer, the number of revisits, the average viewing duration, the number of inflows, the number of departures, the number of views compared to the previous. The data analysis server 100 generates analysis data analyzed by linking viewing data, order data, call-in data, etc. for previously transmitted commerce contents with each other, and using the analysis data to predict sales of commerce contents scheduled to be transmitted in advance degree can be calculated. The data analysis server 100 calculates the pre-estimated sales level, and then transmits the real-time forecast transmitted using the real-time viewing data, real-time order data, real-time call-in data, etc. acquired while the commerce content is transmitted in real time in real time. sales can be calculated.

The data analysis server 100 may generate expected order information for each region from the expected sales level for commerce content scheduled to be broadcast. The pre-expected degree of sales may be calculated by determining the expected viewers and applying the degree of average ordering by the viewers. Expected order information for each region may be generated based on the delivery destination information of the expected viewer (buyer).

The data analysis server 100 may calculate the expected order quantity for each region and generate advance quantity information in consideration of the expected order quantity for each region. The data analysis server 100 may transmit the pre-volume information to the logistics data server, and in the logistics data server, schedule information for a logistics warehouse and a delivery means for each region may be generated.

The data analysis server 100 may transmit the expected order information for each region and the amount information in advance to the logistics data server 600 . The logistics data server 600 may generate an expected logistics amount for each region based on the pre-volume information, and may generate dispatch schedule information for delivery based on the predicted logistics amount for each region.

The media providing server 200 may generate output data for broadcasting of content and transmit the output data for broadcasting to one or more set-top boxes 400 . In this case, the media providing server 200 may transmit the output data for broadcasting to one or more set-top boxes 400 using a cloud service. The set-top box 400 may run an application provided by the media providing server 200 to execute various user interfaces. The set-top box 400 may output content by each connected output device. The set-top box 400 may be implemented to connect to the content transmission server 300 and output the content included in the output data for broadcasting. The user terminal (T) refers to an electronic device that each user has separately from the set-top box 400, and various types of devices with display functions such as smartphones, mobile phones, wearable devices, PMPs, tablets, desktops, and laptops. can

The media providing server 200 may transmit to one or more set-top boxes 400 , commerce content that guides sales products and provides a telephone ordering function, a remote control ordering function, a homepage ordering function, and the like for the sales products.

Meanwhile, the media providing server 200 may control the set-top box 400 through a program installed in the set-top box 400 . The media providing server 200 may perform a function of reading information of the set-top box 400 . The media providing server 200 may receive a platform code, an STP ID, and access information of the set-top box 400 . The media providing server 200 may generate output data of the set-top box 400 based on the information on the set-top box 400 . The media providing server 200 may regenerate output data for broadcasting in response to a user input obtained through the set-top box 400 and transmit it to the set-top box 400 .

Media providing server 200 through the cloud solution, instead of the information itself including various contents such as operation, capture information of these contents through the set-top box 400 to the output device (411, 412, 413, ... 41n) on the screen can be displayed. The media providing server 200 may be implemented using a cloud server, and may control conversion of one or more first and second cloud servers. The media providing server 200 implements the screens of the output devices 411, 412, 413, ... 41n by driving an application corresponding to the selected channel through the first cloud server, and can accommodate a plurality of users through this.

The set-top box 400 communicates with the media providing server 200 to receive output data, interprets and reads (encodes, etc.) the received output data to output devices 411, 412, 413, ... 41n, such as a TV. can be output through The set-top box 400 may output broadcast output data received from the media providing server 200 through the output devices 411 , 412 , 413 , ... 41n. The set-top box 400 may obtain a user input through a provided input device and transmit a request signal corresponding to the user input to the media providing server 200 .

The content transmission server 300 performs a function of transmitting broadcast images of one or more broadcasters or broadcast channels to the set-top boxes 400 . The content transmission server 300 may be implemented to broadcast and transmit the content received from the content providing server. The content transmission server 300 may convert and store it according to a platform or format of one or more broadcasters, portal companies, content producers, and the like. This is the same in the embodiments and modifications thereof to be described later.

The data processing system includes a first set-top box 401, a second set-top box 402, a third set-top box 403, ... , a first output device 411 , a second output device 412 , a third output device 413 , respectively connected to the n-th set-top box 40n, . An n-th output device 41n may be further included. The first set-top box 401, the second set-top box 402, the third set-top box 403, ... , at least one of the n-th set-top box 40n may be referred to as a set-top box 400 . The first terminal T1, the second terminal T2, the third terminal T3, ... , at least one of the n-th terminal (Tn) may be referred to as a terminal (T).

In the data processing system, the data analysis server 100, the media providing server 200, the content transmission server 300, the first set-top box 401, the second set-top box 402, the third set-top box 403, ... , n-th set-top box 40n, one or more user terminals (T1, T2, T3, ..., Tn, hereinafter, T) may communicate with each other through a network. The communication method of the network of the present disclosure includes, but is not limited to, wired or wireless communication, but the network according to some embodiments may use short-range wireless communication. In the data processing system, the set-top box 400 and the output devices 411 , 412 , ... 41n may be connected by a network or an electric line. Also, the set-top box 400 and the output devices 411 , 412 , 413 , ... 41n may be implemented as one piece of hardware. The media providing system 10 may further include a remote control device (eg, remote control) for communicating with the set-top box 400 and/or the output devices 411 , 412 , 413 , ... 41n. The set-top box 400 and/or the output devices 411 , 412 , 413 , ... 41n may communicate with the remote controller through a local area network.

2 is a diagram of a data analysis server in communication with one or more media provision servers.

As shown in FIG. 2 , the data analysis server 100 includes a first media providing server 201 , a second media providing server 202 , . . . , may receive viewing data, call-in data, and/or order data from the n-th media providing server 20n.

The data processing system also provides content through one media providing server 200 as shown in FIG. 1 , but as shown in FIG. 2 , the first media providing server 201 and the second media providing server 202 ), … , the content may be provided through the n-th media providing server 20n.

A first media providing server 201, a second media providing server 202, ... , at least one of the n-th media providing servers 20n may perform a function of obtaining information input to the set-top box 400 while providing commerce content of one or more broadcast channels to the set-top box 400 .

3 is a block diagram of a data analysis server 100 according to embodiments of the present disclosure.

The processor 110 is a configuration for controlling the data analysis server 100 as a whole. Specifically, the processor 110 controls the overall operation of the data analysis server 100 by using various programs stored in the data processing unit 130 of the data analysis server 100 . For example, the processor 110 may include a CPU, a RAM, a ROM, and a system bus. Here, the ROM is a configuration in which an instruction set for booting the system is stored, and the CPU copies the stored operating system of the media providing server 200 to the RAM according to the instructions stored in the ROM, and executes the O/S to boot the system. When booting is complete, the CPU can perform various operations by copying various stored applications to RAM and executing them. Although it has been described above that the data analysis server 100 includes only one CPU, it may be implemented with a plurality of CPUs (or DSPs, SoCs, etc.).

According to an embodiment of the present disclosure, the processor 110 may be implemented as a digital signal processor (DSP), a microprocessor, or a time controller (TCON) for processing a digital signal. However, the present invention is not limited thereto, and a central processing unit (CPU), a micro controller unit (MCU), a micro processing unit (MPU), a controller, an application processor (AP), or It may include one or more of a communication processor (CP) and an ARM processor, or may be defined by a corresponding term. In addition, the processor 110 may be implemented as a system on chip (SoC), large scale integration (LSI), or a field programmable gate array (FPGA) type having a built-in processing algorithm.

The communication unit 120 is a configuration for transmitting and receiving data with devices such as the media providing server 200, the content transmission server 300, one or more set-top boxes 401, 402, 403, ... 40n, and the user terminal T. . The communication unit 120 includes a Bluetooth communication unit, a BLE (Bluetooth Low Energy) communication unit, a near field communication unit, a WLAN (Wi-Fi) communication unit, a Zigbee communication unit, an infrared (IrDA, infrared Data Association) communication unit, a WFD ( It may include a Wi-Fi Direct) communication unit, an ultra wideband (UWB) communication unit, a short-distance communication unit such as an Ant+ communication unit, a mobile communication network, or a wired Ethernet network.

4 is a block diagram of the data processing unit 130 .

The data processing unit 130 includes the viewing data acquisition unit 131 , the external environment data acquisition unit 132 , the call-in data acquisition unit 133 , the order data acquisition unit 134 , the commerce content analysis unit 135 , the real-time It may include a data analysis unit 136 , a statistical data analysis unit 137 , and a prediction data generation unit 138 .

The viewing data acquisition unit 131 may receive viewing data for content displayed in the set-top box acquired through the media providing server 200 .

The viewing data is related to behavior patterns of one or more users who view content transmitted through the media providing server 200 , and may be collected by the media providing server 200 through the set-top box 400 . The viewing data acquisition unit 131 receives the inflow and exit times of the commerce content to be transmitted recorded in the media providing server 200, and records the inflow and exit times for each user, such as for each time of the commerce content. Viewing data such as the number of inflows, the number of departures, the number of viewers, the number of revisits, and the average viewing duration can be generated. In addition, the viewing data may include identification information of the set-top box, and may be classified for each viewer who views the commerce content using the identification information of the set-top box. In the case of a set-top box used by a plurality of users, a viewer of the commerce content may be identified based on an order signal made during viewing. Through this, the viewing data acquisition unit 131 may calculate an inflow time, a departure time, and the like for the commerce content for each identified viewer.

The viewing data may include information about the viewer, and may include information on the viewing area of the viewer, identification information of a user, identification information of a set-top box, and the like. Here, the number of inflows and/or the number of departures may be counted through a connection signal to the set-top box while the commerce content is being transmitted. The number of viewers compared to before refers to the number of viewers compared to the commerce content that sells the same product as the product of the corresponding commerce content. The number of revisits may be a value counting the number of times that an access signal is received again from a set-top box that has been introduced and departed. The average viewing duration may be calculated as a difference value between an inflow time and an exit time. The order amount relative to the viewers may be calculated by dividing the order amount generated while the commerce content is being transmitted by the total number of viewers. The number of viewers may be determined by the number of connected set-top boxes. The viewing data may be classified into location information of a viewer or location information of a set-top box.

The external environment data acquisition unit 132 may acquire external environment data for a time when the commerce content is transmitted. The external environment data acquisition unit 132 externally provides weather information (temperature, precipitation, rainfall, wind information, etc.), real-time news information, real-time event information (sports games, parades, festivals, etc.) for the time period in which the commerce content is transmitted. It can be obtained by requesting it from the server of The external environment data acquisition unit 132 may acquire the corresponding information by searching for weather information, real-time news information, real-time event information, and the like, and reading the searched result pages. The external environment data acquisition unit 132 may store weather information, real-time news information, real-time event information, and the like in correspondence with each time the commerce content is transmitted.

The call-in data acquisition unit 133 may acquire call-in data for commerce content from the media providing server 200 and/or the data server 500 . The call-in data may be data obtained by analyzing the number of call-ins for each time while the commerce content is being transmitted. The call-in data may include a call-in time change pattern of one or more transmitted commerce contents. The call-in data is information managed by a separately provided ARS server, and may be stored in the media providing server 200 or the data server 500 . The call-in data may be classified based on the location information of the caller.

The order data obtaining unit 134 may obtain order data for commerce content from the media providing server 200 and/or the data server 500 . The order signal may be introduced through a set-top box (400 in FIG. 1 ) through which commerce content is transmitted, or may be introduced through a user terminal (T in FIG. 1 ) carried by the user. The media providing server 200 may generate and store order data corresponding to the order signal. The order data acquisition unit 134 transmits a signal for requesting order data for commerce content to the media providing server 200 and/or the data server 500 and receives a response signal therefor, thereby placing an order for commerce content. data can be obtained. Order data refers to order-related information for goods or services sold by commerce content, and may include an order amount for each hour for commerce content, an order amount for each order medium provided from commerce content, the number of orders, order option information, etc. .

The order data may be data such as the number of orders ordered by an order method such as remote control order, phone order, on-demand order, mobile simple order, etc., order amount, order amount per viewer, option information per viewer, etc. while the commerce content is being transmitted. The order data may be classified by region based on the delivery address information of the orderer.

The commerce content analysis unit 135 may generate directing data for each time of the transmitted commerce content. The directing data for the commerce content may be information related to the content of the commerce content. For example, the direction information of the first section of the commerce content is content information where the show host describes the product, the direction information of the second section is content information that enlarges the product, and the direction information of the third section is the model Content information using the product may be included.

The directing information of commerce content may be generated by a PD or a planner who planned the content. In this case, directing information corresponding to the corresponding section for each section of the commerce content may be tagged by a PD, a planner, or the like.

The commerce content analysis unit 134 may obtain by analyzing object information and situation information obtained from the image when the directing information of the commerce content includes image information included for each section. The object information may include a main model in commerce content, a product used, color information, arrangement information, and the like. The situation information may be set as one of a situation in which a product is described, a situation in which the product is used, and a situation in which a video prepared in advance is displayed.

The statistical data analysis unit 136 uses the viewing data, order data, external environment data, and directing data for one or more commerce contents that have been transmitted, viewing data corresponding to the programming time, order data corresponding to the programming time, and directing. It is possible to generate viewing data corresponding to the information, order data corresponding to the direction information, and the like. Statistical data analysis unit 136 statistically analyzes one or more commerce contents that have been transmitted to generate past analysis data including viewing data or order data corresponding to at least one of programming time, direction information, and external environment data. have. The statistical data analysis unit 136 may generate regional preference direction information by combining the viewing data and directing data of the commerce content. The statistical data analysis unit 136 may generate regional order pattern information based on purchase data of commerce content.

The real-time data analysis unit 137 may analyze data acquired while the commerce content is transmitted in real time. The real-time data analysis unit 136 receives the viewing data and/or order data from the viewing data acquisition unit 131 and/or the order data acquisition unit 134 while the commerce content is transmitted, and the call-in data acquisition unit ( It is possible to receive call-in data from 133 , external environment data from the external environment data acquisition unit 132 , and directing data for commerce content from the commerce content analysis unit 135 . The real-time data analysis unit 137 may match the received data for each time of the commerce content.

For example, the real-time data analysis unit 137 combines the viewing data of the first time section included in the viewing data for the currently transmitted commerce content, the order data, the external environment data, and the directing data for the commerce content to create a first Real-time analysis data such as the number of viewers in a time section, order amount, purchase conversion rate compared to the number of viewers, order amount compared to viewers, order amount according to weather, purchase conversion rate according to weather, viewing time according to weather, etc. can be generated.

Real-time analytics data or historical analytics data includes views, viewers, churn, repeat visits, average duration, orders, conversion rate, transaction price, order amount versus views, order amount versus viewers, highest transaction target timeframe, minimum transaction amount Target Time Zone, Highest Viewer Time Zone, Lowest Viewer Time Zone, Highest Conversion Time Zone, Lowest Purchase Conversion Time Zone, Highest Unit Price Time Zone, Lowest Transaction Value Time Zone, Highest Estimated Transaction Time Zone, Lowest Expected Transaction Time Zone, Highest Viewer Directing Information , the lowest number of viewers directing information, the highest purchase conversion rate directing information, the lowest purchase conversion rate directing information, the highest handling amount per customer price directing information, the lowest handling amount per customer price directing information, the highest expected handling amount directing information, the lowest expected handling amount directing information, etc. . Real-time analysis data or historical analysis data may be generated in a predetermined period unit, for example, one day, one week, one month, or the like. Real-time analysis data or historical analysis data may be generated for each commerce content unit.

The pre-sale information prediction unit 138 may generate an expected sales level for commerce content scheduled to be broadcast. The pre-sale information prediction unit 138 is generated through the statistical data analysis unit 136, past analysis data including viewing data or order data corresponding to at least one of programming time, direction information, and external environment data, and / Alternatively, in consideration of real-time analysis data, a pre-estimated sales level for commerce content may be generated. The pre-estimated sales level may include an estimated order quantity obtained by combining an hourly order quantity, an order amount, an order quantity processed by a call-in, and the like, and expected purchaser information.

The pre-sale information prediction unit 138 generates expected external environment data based on the organizing time of the commerce content, and analyzes the commerce content to generate directing data, and the commerce content arrangement time, directing data, and expected external environment. In consideration of at least one of the data, it is possible to generate a pre-expected sales level for the commerce content.

The pre-sale information prediction unit 138 determines the number of viewers, order amount, and/or purchase conversion rate for each time section of the commerce content based on at least one of programming time, direction data, and expected external environment data, The pre-estimated sales level for the commerce content may be generated in consideration of at least one of the number of viewers, the order amount, and the purchase conversion rate.

The pre-sale information prediction unit 138 calculates the expected sales level for the commerce content in consideration of the past analysis data and/or real-time analysis data for the commerce content that sold the same or similar product as the product sold in the commerce content. can The expected sales degree may calculate the pre-expected sales degree for the entire time of the commerce content in consideration of the number of views per unit time, the number of viewers, the order amount, the purchase conversion rate, and the like.

The pre-sale information prediction unit 138 may receive a signal requesting the expected sales level of the commerce content scheduled to be transmitted through the communication unit 120 . The prediction data generation unit 137 may extract a code of a product sold from commerce content and a time period for organizing commerce content in response to a request signal, and may determine direction data obtained by analyzing the commerce content.

The pre-sale information prediction unit 138 may generate first historical analysis data related to the product code of the commerce content. The pre-sale information prediction unit 138 searches for one or more similar commerce contents that sold the same product or similar product based on the product code of the commerce contents, and includes viewing data, order data, and external environment for one or more similar commerce contents. Based on the data, first historical analysis data including at least one of a past number of viewers, a past order amount, and a past purchase conversion rate may be generated. The pre-sale information prediction unit 138 searches for one or more similar commerce contents that sold the same product or similar product based on the product code of the commerce contents, detects call-in data for one or more similar commerce contents, and calls Based on the incoming data, it is possible to generate call-in prediction information for the corresponding commerce content.

The pre-sale information prediction unit 138 may determine expected external environment data related to the expected programming time period in which the commerce content is organized. The pre-sale information prediction unit 138 may receive one or more external environment data corresponding to the programming time period of the commerce content from one or more external servers, and determine the expected external environment data by combining the one or more external environment data.

The pre-sale information prediction unit 138 may generate second past analysis data including viewing data or purchase data related to directing data included in commerce content. The pre-sale information prediction unit 138 searches for viewing data or order data for each direction information included in the direction data included in the commerce content, and for commerce content based on the viewing data or order data for each direction information. The second historical analysis data including at least one of a past number of viewers, a past order amount, and a past purchase conversion rate may be generated.

The pre-sale information prediction unit 138 may calculate the pre-sales level of the commerce content in consideration of the first past analysis data, the second past analysis data, and the expected external environment data.

The pre-sale information prediction unit 138 calculates the number of inflows, the number of departures, the number of views compared to the previous, the number of revisits while the commerce content is being transmitted, the expected handling amount, the order amount compared to the viewers, the ordered option composition ratio, the highest handling amount target time period, the lowest handling amount By calculating information such as target time zone, highest viewer count time zone, lowest viewer count time zone, highest purchase conversion rate time zone, lowest purchase conversion rate time zone, highest transaction price time zone, minimum customer unit price time zone, highest expected transaction amount time zone, and lowest estimated transaction amount time zone, can provide

The post-sales information prediction unit 139 may receive real-time data from the real-time data analysis unit 137 and calculate a real-time expected sales degree using the received real-time viewing data, real-time order data, and real-time call-in data.

The post-sales information prediction unit 139 may generate sales comparison data corresponding to the real-time expected sales level to the pre-expected sales level. The sales comparison data may include an environmental hit degree by comparing the expected external environment data related to the scheduling time of the commerce content with the real-time external environment data of the commerce content.

The post-sales information prediction unit 139 may compare the real-time viewing data of the commerce content with the expected viewing data corresponding to the product code, the programming time zone, and the directing data to calculate the viewing hit degree. Audience hit level

The post-sales information prediction unit 139 may calculate an order hit degree by comparing real-time order data of commerce content with expected order data corresponding to at least one of a product code, a programming time zone, and directing data.

The delivery allocation information generating unit 140 may extract information about the buyer expected from the pre-expected sales level, and obtain delivery address information on the expected purchaser information from the data server 500 . The delivery allocation information generating unit 140 may generate expected order information for each region by collecting the delivery locations of the expected purchasers by region.

The delivery allocation information generating unit 140 searches for the second commerce content related to the commerce content in consideration of at least one of a programming time zone of the first commerce content scheduled to be broadcast, a sales product code, directing data, and external environment data, The order data of the second commerce content is extracted. The delivery allocation information generating unit 140 may classify the extracted order data by region. Based on the classified order data, expected order information for each region may be generated. The delivery allocation information generating unit 140 may generate advance quantity information based on expected order information for each region for the first commerce content, and transmit the advance quantity information to the logistics data server. The advance quantity information is divided by the whole or each region, and may be a value proportional to the order quantity for each region in the expected order information.

The delivery allocation information generating unit 140 may select an excess quantity expected area exceeding a preset reference order value from the expected order information for each region, and transmit data on the excess quantity expected area to the logistics data server.

The delivery allocation information generating unit 140 may obtain information on the loading status of the distribution warehouses located in the excess amount expected area from the distribution data server. The delivery allocation information generating unit 140 may determine a distribution warehouse in which the quantity of the first commerce content is to be loaded based on the loading status information.

Through this, the data analysis server 100 can prevent a phenomenon in which delivery is delayed due to a large number of orders before the commerce content is transmitted. The data analysis server 100 may select a region having a large number of orders through the commerce content before transmitting the commerce content, and load the corresponding products in the region with a large order quantity in advance. In addition to pre-determining the warehouse where the products are to be loaded, it is possible to preempt the delivery means for delivering the products.

5 and 6 are flowcharts of a method of calculating a real-time expected sales level for commerce content during transmission according to embodiments of the present disclosure.

In S110 , the data analysis server 100 may search for one or more second commerce contents in consideration of at least one of a programming time zone of the first commerce contents scheduled to be broadcast, a sales product code, directing data, and external environment data.

In S120, order data related to one or more second commerce contents may be searched.

In S130, the data analysis server 100 may classify the order data by region and generate expected order information for each region for the first commerce content based on the classified order data.

In S140 , the data analysis server 100 may generate purchase quantity information based on expected order information for each region for the first commerce content, and transmit the prior quantity information to the logistics data server.

As shown in FIG. 6 , in S210, the data analysis server 100 selects an excess quantity expected area that exceeds a preset reference order value in the expected order information for each region, and loads the warehouses located within the selected excess quantity expected area. Status information can be obtained.

In S220, the data analysis server 100 may determine a logistics warehouse in which the quantity of the first commerce content is to be loaded, based on each loading status information, from among the logistics warehouses in the area where the excess quantity is expected.

The determined information on the distribution warehouse is transmitted to the distribution data server, and sales products of the first commerce content are allocated to be loaded through the distribution warehouse. It is possible to solve the problem of delay in delivery due to the large number of orders by starting the allocation before broadcasting the first commerce content.

7 to 13 are exemplary diagrams of a user interface generated by the data analysis server 100 .

As shown in FIG. 7 , the expected order information for each region may be generated as level information corresponding to the quantity. Based on the expected order information for each region, it is possible to check in advance the regions with a high order quantity, and to increase the allocation of delivery to the regions with a high order quantity.

As shown in FIG. 8 , while the commerce content (VOD) is displayed through the user's set-top box 400, the data analysis server 100 converts the number of views and the order amount by time of the commerce content to time series data as FD1. can create

The data analysis server 100 considers the number of viewers who have selected commerce content (VOD) from the set-top box 400 , the number of inflows, the number of exits, the number of views compared to the previous, the number of revisits, expected handling amount, order amount compared to viewers, and ordered options Analysis data such as composition ratio can be generated like FD2.

As shown in FIG. 9 , the data analysis server 100 divides the commerce content by time section, the number of section inflows, the number of section departures, the number of section revisits, the section average viewing duration, section order amount, expected handling amount per minute, section viewers Analysis data FD3 such as per order amount can be generated.

As shown in FIG. 10 , in relation to viewing, the data analysis server 100 may calculate analysis data WD including the number of views, the number of viewers, the number of exits, the number of revisits, and the average viewing duration. . The number of views is a value obtained by counting the connection signal, and may be counted twice even if the viewer is the same. As for the number of viewers, the number of viewers who are introduced and then departed may be counted as one.

The data analysis server 100 may calculate the analysis data DD including the number of orders, the conversion rate of purchases, the unit price of the handling amount, the order amount compared to the number of views, and the order amount compared to the viewers by linking the viewing and the order.

The data analysis server 100 may visually generate the intensity of the viewing rate for each week and time period (DR). The intensity with respect to the viewing ratio is set to a constant between 0 and 5, and it can be seen that the greater the intensity value, the greater the number of viewers.

As shown in Figure 11, the data analysis server 100 can generate visual data (VTD) a time series change pattern of the handling amount target, expected handling amount, number of viewers, purchase conversion rate, and handling amount per time period in units of 1 day. have.

The data analysis server 100 is based on the time series change pattern generated by linking the viewing data and the order data, the highest handling amount target time zone, the lowest handling amount target time zone (TD1), the highest number of viewers time zone, the lowest number of viewers time zone (TD2), It can be calculated for the highest purchase conversion rate time period, the lowest purchase conversion rate time period (TD3), the highest transaction amount per customer time period, the lowest transaction amount per customer price time period (TD4), the highest expected transaction amount time period, and the lowest expected transaction amount time period (TD5). TD1, TD2, TD3, TD4, TD5 can be provided including time value and amount.

As shown in FIG. 12 , for commerce content (VOD) provided to each set-top box through the media providing server 200, real-time analysis data may be generated to generate RTD1, RTD2, RTD3, and RTD4.

The data analysis server 100 compares the number of viewers, the number of views, the purchase conversion rate, the handling amount per unit price, the total order amount, the expected handling amount, the expected handling amount per minute, the expected handling amount compared to the number of views, and the expected handling amount compared to the number of viewers for the transmitted commerce content, the same product The number of viewers, number of views, purchase conversion rate, handling amount per customer, total order amount, expected handling amount, expected handling amount per minute, expected handling amount compared to the number of views, and expected handling amount compared to the number of viewers of the first and second commerce contents that were previously broadcast can be provided in preparation for

As shown in FIG. 13 , the data analysis server 100 may generate comparison data for comparing between commerce contents.

The data analysis server 100 may generate average data for one or more commerce contents based on an organization or a product for sale. For example, an average value (views per minute, number of departures per minute, number of revisits per minute, average viewing duration, etc.) of commerce content analysis data for a predetermined number of times, such as 4 times or 12 times, may be generated.

The data analysis server 100 may generate average analysis data of commerce contents selling the same or similar product, such as 4 times average trend, 12 times average trend, and the like. As for the commerce contents that sell the same or similar product, the data analysis server 100 generates average analysis data of the commerce contents transmitted in the same time period, such as the number of views per minute, the number of departures per minute, the number of revisits per minute, the average viewing duration, etc. can do. The data analysis server 100 may generate analysis data of commerce content immediately before the same product is sold. The data analysis server 100 uses average analysis data of commerce contents selling the same or similar product, average analysis data of commerce contents transmitted in the same time period, and analysis data of commerce contents immediately before selling the same product, Future order data for commerce content scheduled to be broadcast can be generated.

The device described above may be implemented as a hardware component, a software component, and/or a combination of the hardware component and the software component. For example, devices and components described in the embodiments may include, for example, a processor, a controller, an arithmetic logic unit (ALU), a digital signal processor, a microcomputer, a field programmable gate array (FPGA). , a programmable logic unit (PLU), microprocessor, or any other device capable of executing and responding to instructions, may be implemented using one or more general purpose or special purpose computers. The processing device may execute an operating system (OS) and one or more software applications running on the operating system. The processing device may also access, store, manipulate, process, and generate data in response to execution of the software. For convenience of understanding, although one processing device is sometimes described as being used, one of ordinary skill in the art will recognize that the processing device includes a plurality of processing elements and/or a plurality of types of processing elements. It can be seen that may include For example, the processing device may include a plurality of processors or one processor and one controller. Other processing configurations are also possible, such as parallel processors.

The software may comprise a computer program, code, instructions, or a combination of one or more thereof, which configures a processing device to operate as desired or is independently or collectively processed You can command the device. The software and/or data may be any kind of machine, component, physical device, virtual equipment, computer storage medium or device, to be interpreted by or to provide instructions or data to the processing device. , or may be permanently or temporarily embody in a transmitted signal wave. The software may be distributed over networked computer systems and stored or executed in a distributed manner. Software and data may be stored in one or more computer-readable recording media.

The method according to the embodiment may be implemented in the form of program instructions that can be executed through various computer means and recorded in a computer-readable medium. The computer-readable medium may include program instructions, data files, data structures, etc. alone or in combination. The program instructions recorded on the medium may be specially designed and configured for the embodiment, or may be known and available to those skilled in the art of computer software. Examples of the computer-readable recording medium include magnetic media such as hard disks, floppy disks and magnetic tapes, optical media such as CD-ROMs and DVDs, and magnetic such as floppy disks. - includes magneto-optical 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 devices described above may be configured to operate as one or more software modules to perform the operations of the embodiments, and vice versa.

As described above, although the embodiments have been described with reference to the limited embodiments and drawings, various modifications and variations are possible by those skilled in the art from the above description. For example, the described techniques are performed in a different order than the described method, and/or the described components of the system, structure, apparatus, circuit, etc. are combined or combined in a different form than the described method, or other components Or substituted or substituted by equivalents may achieve an appropriate result.

Therefore, other implementations, other embodiments, and equivalents to the claims are also within the scope of the following claims.

100: data analysis server 110: processor
120: communication unit 130: data processing unit
131: viewing data acquisition unit 132: external environment data acquisition unit
133: call-in data acquisition unit 134: order data acquisition unit 135: commerce content analysis unit 137: statistical data analysis unit 136: real-time data analysis unit 138: pre-sale information prediction unit
139: post-sales information prediction unit 140: shipping allocation information generation unit
200: media providing server
300: content transmission server 400: set-top box
411, 412, 413, ... 41n: output device 500: data server

Claims (9)

retrieving, by the data analysis server, one or more similar commerce contents that sold the same product or similar product based on the product code of the first commerce contents scheduled to be broadcast;
The data analysis server generates first historical analysis data including at least one of the number of past viewers, the past order amount, and the past purchase conversion rate based on the viewing data, order data, and external environment data related to the one or more similar commerce contents, , detecting call-in data for the similar commerce content;
determining, by the data analysis server, expected external environment data related to an expected programming time period in which the first commerce content is organized;
generating, by the data analysis server, second past analysis data including viewing data or purchase data related to directing data included in the first commerce content;
generating, by the data analysis server, a pre-expected sales degree for the first commerce content in consideration of the first past analysis data, the second past analysis data, and the expected external environment data; and
The data analysis server extracts buyer information expected from the pre-expected sales level, obtains delivery address information for the buyer information from the data server, collects delivery locations of the expected buyer by region, and generates expected order information for each region, A method of calculating the expected delivery volume by region for commerce content, including generating advance quantity information based on expected order information for each region for the first commerce content, and transmitting the advance quantity information to a logistics data server . According to claim 1,
Regional prediction for commerce contents, further comprising, by the logistics data server, generating an expected logistics amount for each region based on the pre-quantity information, and generating dispatch schedule information for delivery based on the predicted logistics amount for each region How to calculate shipment volume. According to claim 1,
The data analysis server selects, from the expected order information for each region, an excess quantity expected area exceeding a preset reference order value,
The method of calculating the estimated delivery volume for each region for commerce content, further comprising the step of acquiring inventory status information of distribution warehouses located within the selected excess volume expected area. 4. The method of claim 3,
The data analysis server,
From among the distribution warehouses in the excess amount expected area, based on each inventory status information, determining a first distribution warehouse in which the amount of the first commerce content is loaded, How to calculate. In the data analysis server comprising a communication unit and a processor,
the processor
Searching for one or more similar commerce contents that sold the same product or similar product based on the product code of the first commerce contents scheduled to be broadcast;
generating first historical analysis data including at least one of a number of past viewers, a past order amount, and a past purchase conversion rate based on the viewing data, order data, and external environment data related to the one or more similar commerce contents; Detects call-in data for
Determining expected external environment data related to an expected programming time period in which the first commerce content is organized,
generating second past analysis data including viewing data or purchase data related to directing data included in the first commerce content;
generating a pre-expected sales degree for the first commerce content in consideration of the first past analysis data, the second past analysis data, and the expected external environment data;
Extracting the buyer information expected from the pre-estimated sales level, obtaining the delivery address information for the buyer information from the data server, and collecting the delivery locations of the expected buyer by region to generate expected order information for each region,
A data analysis server for generating advance quantity information based on expected order information for each region for the first commerce content, and transmitting the advance quantity information to a logistics data server. 6. The method of claim 5,
The logistics data server is
A data analysis server for generating an estimated amount of logistics for each region based on the pre-volume information, and generating dispatch schedule information for delivery based on the expected amount of logistics for each region. 6. The method of claim 5,
the processor
In the expected order information for each region, an excess quantity expected area exceeding a preset reference order value is selected,
A data analysis server for acquiring inventory status information of distribution warehouses located within the selected excess quantity expected area. 8. The method of claim 7,
the processor
A data analysis server for determining a first distribution warehouse in which the quantity of the first commerce content is loaded, based on each inventory status information, among the distribution warehouses in the excess amount expected area. A computer program stored in a computer-readable storage medium for executing the method of any one of claims 1 to 4 using a computer.

Images