KR20210121700A - Reading content management server performing book recommendation using persona model and reading content management method using the same - Google Patents

Abstract

A reading content management server according to one embodiment of the present invention comprises: a customer information collection part that collects customer information from a customer terminal; a customer information extraction part that extracts at least one among the behavior information, the tendency information, and the reading competency information from the collected customer information; a persona diagnosis part that diagnoses a customer persona corresponding to the behavior information and the tendency information based on a persona model pre-stored in a storage DB; a reading index calculation part that calculates a reading index based on the reading competency information; and a content generation part that generates a customized content based on the customer persona and the reading index. Therefore, the present invention is capable of having an effect of recommending a book that meets the needs of the customers.

Description

A reading content management server that recommends books using a persona model and a method of managing reading content using the same

The present invention relates to a reading content management server for recommending a book by using a persona model, and a reading content management method using the same.

Recently, online reading that is not limited by time and space is increasing.

However, due to the nature of such online reading, there is a limit to providing customized books that can satisfy the needs of all readers. In addition, in the case of the existing book recommendation system, even if personalized content is provided, it merely relies on personal profiling based on member registration information.

Accordingly, there is a demand for a system that can provide customized book contents online according to the individual tendency and needs of customers.

To this end, the need for research to classify customer types or patterns from a sociological or anthropological perspective and use them in marketing or sales activities has been raised.

The matters described in this background section are written to improve the understanding of the background of the application, and may include matters that are not already known to those of ordinary skill in the art to which this technology belongs.

An object of the present invention is to provide a reading content management server capable of recommending a book that meets a customer's needs by using a persona model based on a customer's personal information, and a reading content management method using the same.

Reading content management server according to an embodiment of the present invention, a customer information collection unit for collecting customer information from a customer terminal; a customer information extraction unit for extracting at least one of behavior information, tendency information, and reading ability information from the collected customer information; Based on the persona model pre-stored in the storage DB, the persona diagnosis unit for diagnosing the customer persona corresponding to the behavior information and tendency information; a reading index calculation unit for calculating a reading index based on the reading ability information; and a content generation unit for generating customized content based on the customer persona and the reading index, wherein the reading index calculation unit includes a concentration index, a comprehension index, a language ability index, and an intellectual curiosity index corresponding to the customer persona; It includes a competency score derivation unit for each domain that derives competency scores for each domain according to the set competency score calculation formula for each domain.

In an embodiment of the present invention, the persona diagnosis unit includes: a behavior model selection unit for selecting a customer behavior model by matching behavior information to a plurality of behavior models stored in a storage DB; a propensity model selector for selecting a customer propensity model by matching propensity information to a plurality of propensity models stored in a storage DB; and a customer persona determiner configured to combine the customer behavior model and the customer disposition model to generate a customer persona.

이고, 여기서 R은 영역별 역량 점수이며, t는 퍼소나 유형, n은 지표 영역이고,

은 영역별 고객 점수,

은 퍼소나에 따라 기 설정된 영역별 가중치,

은 퍼소나에 따라 기 설정된 영역별 지표 점수이다.In an embodiment of the present invention, the formula for calculating the competency score for each area is:

where R is the competency score for each domain, t is the persona type, n is the indicator domain,

is the customer score by area,

is the weight for each area preset according to the persona,

is an index score for each area preset according to persona.

In an embodiment of the present invention, the reading index calculation unit includes: a comprehensive competency score derivation unit for deriving a comprehensive competency score according to a preset comprehensive competency score calculation formula, based on the competency score for each domain; and a reading code generator generating reading codes indicating the highest and lowest regions from the competency scores for each region.

이고, 여기서 S는 종합 역량 점수, R은 영역별 역량 점수, N은 지표 영역의 개수이며, t는 퍼소나 유형, n은 지표 영역이고,

은 영역별 고객 점수,

은 퍼소나에 따라 기 설정된 영역별 가중치,

은 퍼소나에 따라 기 설정된 영역별 지표 점수이다.In an embodiment of the present invention, the overall competency score calculation formula is,

where S is the overall competency score, R is the competency score for each domain, N is the number of indicator domains, t is the persona type, n is the indicator domain,

is the customer score by area,

is the weight for each area preset according to the persona,

is an index score for each area preset according to persona.

In one embodiment of the present invention, the content generation unit, by setting the field and reading level of the content based on the customer persona and the reading index, the content selection unit for selecting the corresponding content; and an image analysis unit that analyzes an image of the selected content based on a color histogram preset according to the persona model. and an interface design unit for designing a content interface corresponding to a customer persona based on a preset interface according to the persona model.

The reading content management server according to an embodiment of the present invention stores the customer evaluation information received in real time from the customer terminal in a storage DB, and when calculating the reading index, reflects the customer evaluation information to recalculate the reading index.

In an embodiment of the present invention, the customized content includes learner-targeted content and instructor-targeted content.

Reading content management method according to an embodiment of the present invention, a customer information collection step of collecting customer information from a customer terminal; a customer information extraction step of extracting at least one of behavior information, tendency information, and reading ability information from the collected customer information; A persona diagnosis step of diagnosing a customer persona corresponding to the behavior information and the tendency information based on the persona model pre-stored in the storage DB; a reading index calculation step of calculating a reading index based on the reading ability information; and a content generation step of generating customized content based on the customer persona and the reading index, wherein the reading index calculation step is based on the concentration index, the comprehension index, the language ability index, and the intellectual curiosity index corresponding to the customer persona. , including a step of deriving competency points for each area in which the competency points for each area are derived according to a preset competency score calculation formula for each area.

In a computer-readable recording medium including a program for executing a method for managing reading content according to an embodiment of the present invention, the method for managing reading content includes: a customer information collection step of collecting customer information from a customer terminal; a customer information extraction step of extracting at least one of behavior information, tendency information, and reading ability information from the collected customer information; A persona diagnosis step of diagnosing a customer persona corresponding to the behavior information and the tendency information based on the persona model pre-stored in the storage DB; a reading index calculation step of calculating a reading index based on the reading ability information; and a content generation step of generating customized content based on the customer persona and the reading index, wherein the reading index calculation step is based on the concentration index, the comprehension index, the language ability index, and the intellectual curiosity index corresponding to the customer persona. , including a step of deriving competency points for each area in which the competency points for each area are derived according to a preset competency score calculation formula for each area.

When applying the reading content management server and the reading content management method using the same according to an embodiment of the present invention, the effect of recommending a book that meets the customer's needs by using a persona model based on the customer's personal information there is

1 illustrates a reading content management system according to an embodiment of the present invention.
2 illustrates a persona diagnosis unit according to an embodiment of the present invention.
3 and 4 are examples showing a method for diagnosing a persona model according to an embodiment of the present invention.
5 is a diagram illustrating a reading index calculator according to an embodiment of the present invention.
6 illustrates a content generation unit according to an embodiment of the present invention.
7 illustrates a method for managing reading content according to an embodiment of the present invention.
8 is a diagram illustrating a method of calculating a reading index and selecting content according to an embodiment of the present invention.
9 and 10 are examples illustrating an image analysis method according to an embodiment of the present invention.
11 is an example illustrating an interface setting method according to an embodiment of the present invention.

Hereinafter, in adding reference numerals to the components of each drawing, it should be noted that the same components are given the same reference numerals as much as possible even though they are indicated on different drawings. In addition, in describing the present invention, if it is determined that a detailed description of a related known configuration or function may obscure the gist of the present invention, the detailed description thereof will be omitted.

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

1 illustrates a reading content management system according to an embodiment of the present invention.

Referring to FIG. 1 , a reading content management system 1000 according to an embodiment of the present invention includes a reading content management server 100 , a storage DB 200 , a customer terminal 300 , and a network 50 .

First, the reading content management server 100 may collect customer information, diagnose a customer persona based on the collected customer information, and provide customized content based on the diagnosed customer persona.

The reading content management server 100 may communicate with the customer terminal 300 through the network 50 in order to perform the above-described function. To this end, the reading content management server 100 is a central processing unit (CPU) to support WPAN, WiFi, 3G/4G/LTE, Bluetooth, Ethernet, BcN, satellite communication, Microware, serial communication, PLC local ad hoc network, Internet, etc. ), a microprocessor, an ASIC, or the like, or may include a communication module controlled by them.

The reading content management server 100 includes a customer information collection unit, a customer information extraction unit, a persona diagnosis unit, a reading index calculation unit, a content generation unit, and a content output unit.

Subsequently, the storage DB 200 stores persona model information based on customer information and demographic information, and functions to store reading content classified and stored according to a reading field and reading level preset for each persona model. .

In addition, the storage DB 200 stores behavioral keywords and propensity keywords necessary for diagnosing the persona model of the customer, and the behavioral model, the propensity model and the persona models classified by the manager based on each keyword in advance It functions to create, classify, store and manage.

In addition, the storage DB 200 , 200 may store reference scores for each index area, weight information for each area, and customer evaluation information (star points, comments, expert opinions) which are previously stored according to the persona model. Furthermore, all information necessary to provide customized content to customers may be stored.

Subsequently, the customer terminal 300 is a terminal possessed by each customer in order to receive a customized customer model, and is connected to a customized model management server through a network 50 to be described later so that data transmission/reception is possible. The customer terminal 300 may be provided as a computer, portable terminal, or television, and may include cell phones, smart phones, desktop computers, laptop computers, tablet computers, personal digital assistants (PDAs), wearable devices, and the like. may be

In addition, the customer terminal 300 brings a web page (Web Page) such as various HTML (Hyper Text Markup Language) documents provided from the customized model management server and displays it on the screen with a normal web browser (Web Browser). ) is provided, and may be any type of wired/wireless communication device capable of using various web services by accessing the customized model management server.

The customer terminal 300 accesses the customized model management server through the network 50 , and an application may be installed to use the service. In particular, it can be applied to an operating system where data inquiry between applications is not possible, and the operating system may include mobile operating systems such as IOS, Android, SYMBIAN, and BADA, and by combining these conditions, a mobile environment is formed. can be

In the drawings, for convenience of understanding, it is illustrated on the premise that there is only one customer terminal 300 , but the present invention is not limited thereto, and may be provided differently from the drawings in an environment in which an actual customized model management server is used. For example, the customer terminal 300 may be a child terminal used by children, and may be a parent terminal or an administrator terminal used by a parent. Such a plurality of terminals may be provided to share customer information with each other.

Next, the network 50 refers to a connection structure capable of exchanging information with each other, such as terminals and servers. The network 50 includes a TCP/IP protocol and various services existing in its upper layers, namely HTTP (Hyper Text Transfer Protocol), Telnet, FTP (File Transfer Protocol), DNS (Domain Name System), SMTP (Simple Mail Transfer Protocol). ), SNMP (Simple Network Management Protocol), NFS (Network File Service), NIS (Network Information Service), etc. are provided as a worldwide open computer network structure.

The network 50 includes all wired/wireless networks that can connect the customer terminal 300 and the reading content management server 100, for example, Wi-Fi, Bluetooth, Internet, LAN (Local Area Network), Wireless LAN (Wireless Local Area Network), WAN (Wide Area Network), PAN (Personal Area Network), WPAN, 3G, 4G, LTE, Ethernet, BcN, Satellite Communication, Microware, Serial Communication, It may be a PLC local ad hoc network, the Internet, etc. Here, the Internet includes a number of routing agents and processing agents. The Internet may be a global system using standard Internet protocols (eg, TCP/IP). TCP/IP is a communication protocol that specifies how data should be formatted, addressed, transmitted, routed and received at a destination.

If such a network 50 is utilized, the above-described customized model management server and the customer terminal 300 may be connected to each other to enable transmission and reception of information.

In the above, the configuration of the reading content management system according to an embodiment of the present invention has been described. Hereinafter, the detailed configuration of the above-described reading content management server will be described in detail.

Referring to FIG. 1 , first, the customer information collection unit 110 collects customer information from a customer terminal.

The customer information collection unit 110 collects customer information based on a result of a questionnaire, questionnaire, or pre-evaluation provided by the reading content management server to the customer terminal.

Customer information includes personal information (age, gender, personality), and may include living environment information such as occupation, living space (kindergarten, school, home), life pattern, and guardian information (parent, teacher).

Next, the customer information extraction unit 120 extracts at least one of behavior information, tendency information, and reading capability information from the collected customer information.

In addition, the customer information may include reading habit information, preference information, and non-preference information.

Behavioral information may include behavioral characteristics, core needs, and behavioral motives, and is used to diagnose a behavior model to be described later. It is used to diagnose the propensity model.

The reading capability information is information for determining the reading capability of the customer for each area of concentration, comprehension, language, and intellectual curiosity, and may be extracted based on a result of a pre-evaluation provided by the reading content management server to the customer terminal. In this case, the pre-evaluation may be provided as a test item in the form of problem solving, and the result of the pre-evaluation may be scored and extracted as reading competency information. This reading ability information is used as an index for evaluating the customer's concentration, comprehension, language, and intellectual curiosity in the reading index calculation unit 140 , which will be described later.

Reading habit information may include average daily reading amount, average daily reading time, one reading time, reading frequency, reading purpose (main field additional learning, unknown field indirect learning, various field indirect experience, self-development, hobbies, etc.) have. Such reading habit information may be used as a material for setting an interface when providing customized content.

Preference information may include interest information such as interest learning fields (language, mathematics, science, music, art, physical education, etc.), hobbies, specialties, future hopes, hope books, and non-preference information, indifferent fields, unfamiliar areas Fields, non-preferred books, and avoidable areas may be included. The preference information and the non-preference information may be used to set a reading field of the customized content.

2 illustrates a persona diagnosis unit according to an embodiment of the present invention.

3 and 4 are examples showing a method for diagnosing a persona model according to an embodiment of the present invention.

2 to 4 , the persona diagnosis unit 130 diagnoses a customer persona corresponding to behavior information and disposition information based on a persona model pre-stored in the storage DB. The persona diagnosis unit 130 may include the above-described behavior model selection unit 131 , a disposition model selection unit 132 , and a customer persona determination unit 133 .

The behavior model selection unit 131 selects a customer behavior model by matching behavior information to a plurality of behavior models stored in the storage DB. The propensity model selection unit 132 selects a customer propensity model by matching propensity information to a plurality of propensity models stored in the storage DB.

Behavior models and disposition models are classified according to the type of customer's personal temperament, and are the basis for diagnosing customer persona, which will be described later.

Referring to FIG. 4 , for example, the behavior model may be classified into four models according to behavioral characteristics and core desires, and the propensity model may be classified into four models according to preference and avoidance factors and acceptance attitudes.

A customer behavior model and a customer disposition model are selected based on customer information, and any one of the four models is provided to be selected.

3 and 4 , the customer persona determining unit 133 generates a customer persona by combining the customer behavior model and the customer tendency model selected above.

As for the persona model, a total of 16 persona models as shown may be preset. The customer persona determining unit 133 determines any one of 16 persona models as the customer persona by combining the customer disposition model and the customer behavior model.

The determined customer persona is provided to the content generating unit 150, which is a basis for generating customized content corresponding to the customer persona.

5 is a diagram illustrating a reading index calculator according to an embodiment of the present invention.

Referring to FIG. 5 , the reading index calculation unit 140 functions to calculate a reading index based on reading competency information, and includes a competency score deriving unit 141 for each area, a comprehensive competency score deriving unit 142 , and reading. and a code generation unit 143 . In this case, the reading index may include a comprehensive competency score and a reading code.

First, the competency score derivation unit 141 for each area calculates the competency score for each area according to a preset competency score calculation formula for each area based on the concentration index, comprehension index, language ability index, and intellectual curiosity index corresponding to the customer persona. derive

In this case, the formula for calculating the competency score for each area is as follows.

[Equation 1]

은 영역별 고객 점수,

은 퍼소나에 따라 기 설정된 영역별 가중치,

은 퍼소나에 따라 기 설정된 영역별 지표 점수이다.where R is the competency score for each domain, t is the persona type, n is the indicator domain,

is the customer score by area,

is the weight for each area preset according to the persona,

is an index score for each area preset according to persona.

The index score for each area may be set differently for each area according to a persona model.

Referring to FIG. 4 , for example, when the persona model is set to types 1 to 16 as shown, index scores may be set as follows.

The index score for each area of Persona Model No. 3 “Little Edison type” will be set to 17 points, 18 points, 15 points, and 22 points out of 25 points in the order of concentration, comprehension, language ability, and intellectual curiosity. can

In the case of persona model number 9 “Happy Virus Type”, the index score for each area was 18, 19, 18, and 16 out of 25, in the order of concentration, comprehension, language, and intellectual curiosity. can be set.

In addition, when the index score for each persona model is greater or less than, weights for each area may be provided to increase discrimination from the average score, and the weights may also be differentially set for each area according to the persona model. have.

The reason for setting the index score and weight for each area according to the persona model as described above is that a very high score or a low score is calculated according to the persona model in a specific area, which may reduce the reliability of the prior evaluation. .

For example, in the case of persona model 3, which has a more curious temperament than other persona models, it has a very high tendency compared to the average persona model in the area of intellectual curiosity, so the score for each area is inevitably calculated relatively high. . Accordingly, there is a problem in that discrimination power is lowered, and it is difficult to accurately analyze the test result.

However, when the index score and weight for each domain are set differently according to each persona model, it is possible to calculate a more accurate competency score for each domain in consideration of the characteristics of each persona model.

Looking at an example, it is assumed that the index score of the 2nd comprehension domain of the 7th persona model “Know-It-All type” is 20 out of 25 and the weight of the comprehension domain is set to 0.5 , the competency score in the comprehension domain can be calculated as follows.

In other words, if the customer score of the 7th persona model in the comprehension area is 19, even if the average score is higher than other persona models, the index score is set to 20. The competency score of the domain may be subtracted.

As described above, by applying the index score and weight for each area, it is possible to effectively consider the characteristics of the persona model and at the same time provide discrimination from the average score, so that it is possible to calculate a score that more accurately reflects the propensity and capability of the customer. .

Next, the comprehensive competency score derivation unit 142 derives a comprehensive competency score according to a preset comprehensive competency score calculation formula, based on the area-specific competency scores derived above.

At this time, the formula for calculating the overall competency score is as follows.

[Equation 2]

은 영역별 고객 점수,

은 퍼소나에 따라 기 설정된 영역별 가중치,

은 퍼소나에 따라 기 설정된 영역별 지표 점수이다.where S is the overall competency score, R is the competency score for each domain, N is the number of indicator domains, t is the persona type, n is the indicator domain,

is the customer score by area,

is the weight for each area preset according to the persona,

is an index score for each area preset according to persona.

Below, it will be explained by way of an example.

First, the index score for each area of Persona Model No. 3 “Little Edison type” is 17 points, 18 points, 16 points, and 22 points out of 25, in the order of concentration, comprehension, language ability, and intellectual curiosity. It is assumed that the weights for each area are set to 0.5, 0.8, 0.5, and 1.

Assuming that the customer scores are 19 points, 18 points, 20 points, and 20 points in the order of the domains, the competency scores for each domain can be calculated as follows.

Calculating the customer's overall competency score with respect to the competency score for each area is as follows.

The total competency score calculated in this way is used to set the reading level in the content generation unit 150, which will be described later.

Then, referring back to FIG. 5 , the reading code generator 143 generates reading codes indicating the highest and lowest regions from the competency scores for each region.

The reading code may be generated in the order of the area obtaining the lowest score from the area obtaining the highest score from the competency scores for each area, or may be generated by extracting the highest and lowest two areas.

For example, the competency score for each domain of the persona model No. 3 “Little Edison type” was 20 points, 16 points, 22 points, and 18 points in the order of concentration, comprehension, language ability, and intellectual curiosity. Assume At this time, if each area is arranged in the order of the area that obtained the highest score, it becomes the language ability (L), concentration (C), intellectual curiosity (I), and comprehension area (U). Based on this, the reading code is “LCIU” ” or “LU”.

The generated reading code may be used to set a reading area in the content generating unit 150, which will be described later.

As described above, the reading index calculation unit 140 may be provided to store the customer evaluation information received in real time from the customer terminal in a storage DB, and to recalculate the reading index by reflecting the customer evaluation information when calculating the reading index. .

6 illustrates a content generation unit according to an embodiment of the present invention.

Referring to FIG. 6 , the content generation unit 150 functions to generate customized content based on a customer persona and a reading index, and a content selection unit 151 , an image analysis unit 152 , and an interface design unit ( 153) can be configured.

The content selection unit 151 sets the field of content and the reading level based on the customer persona received from the persona diagnosis unit 130 and the reading index received from the reading index calculation unit 140, and the corresponding content to select

First, the content selection unit 151 sets the reading level based on the overall competency score among the reading index calculated above. The reading level may be set based on the overall competency score and a reading level setting table preset according to the age of the customer.

For example, even if the overall competency score of 8-year-old customer A and 12-year-old customer B is both 90 points, considering the age of the customer, the reading level of the 12-year-old may be set higher than that of customer A. have.

Next, the content selection unit 151 sets a reading area based on the reading code received from the reading code generation unit 143 .

The reading area may be set in consideration of a reading recommendation area preset for each customer persona together with the reading code. Accordingly, there is an advantage in that the reading ability can be reflected from the reading code and the reading propensity can be reflected from the customer persona to set a reading area that is more suitable for the needs of the customer.

In addition, preference information and non-preference information extracted from the customer information extraction unit 120 may be used, and a reading area may be set by reflecting the content ratio set by the customer.

The content selection unit 151 selects reading content based on the reading level and reading area set as described above, so that reading content that meets the customer's needs can be derived in consideration of both the reading capability and the preferred field of the customer.

The derived reading content is created as customized content provided to the end customer terminal by setting the color, design, interface, and delivery method of the content through the image analysis unit 152 and the interface design unit 153 to be described later.

The image analyzer 152 analyzes an image of the selected content based on a color histogram preset according to the persona model.

Image analysis is performed to arouse customer interest and maintain concentration by applying a color histogram preset according to the persona model to the content.

In order to derive an image suitable for the customer, it is necessary to classify the color class by databaseizing the personal information, propensity information, behavior information, preference information, and non-preference information extracted from the customer persona and customer information, and the following algorithm is required. technology can be applied.

According to an embodiment, the image analysis may be performed using an image color analysis algorithm using a color histogram, a dominant color, and a color layout.

In addition, the color information analyzed by the above method may be analyzed through machine learning including a learning algorithm (Neural network/Boosting/SVM/etc.) and K-Nearest Neighbor (KNN).

According to another embodiment, the information of the image may be analyzed using a direct learning algorithm such as deep learning. Alternatively, by extracting features of an image using deep learning, a learning algorithm (Neural network/Boosting/SVM/etc.) or KNN (K-Nearest Neighbor) may be used to classify the class.

Next, the interface design unit 153 designs a content interface corresponding to the customer persona based on a preset interface according to the persona model provided from the persona diagnosis unit 130 .

In an embodiment, the interface design unit 153 may design an interface based on the reading habit information extracted from the customer information extraction unit 120 in addition to the customer persona, and the interface is a user interface (UX) in addition to a user interface (UI). Experience) design may be provided to include.

As a result, it is possible to design an interface that matches the customer persona and the reading habit and reading tendency of the customer, so that the layout, text design, and delivery method constituting the content can be provided to the customer.

As described above, in the case of including the image analysis unit 152 and the interface design unit 153 of the present invention, by setting the color, design, interface, and delivery method of the selected content to meet customer needs, the customer It has the advantage of being able to create customized content.

Also, in an embodiment, the customized content may be provided to include learner-targeted content and instructor-targeted content.

For example, when the customer is a teenager, a child, or an infant, learner-targeted content is generated in consideration of the customer's persona model, and at the same time, leader-targeted content corresponding to the learner-targeted content may be generated together.

The leader content may be content for a learner's reading instruction, and may be generated based on the learner content, the learner's persona model, and an age.

In this case, for the content for learners, a large proportion of books centered on preference and desire factors may be set, and for the content for leaders, a large proportion of books centered on avoidance and improvement factors may be set. Accordingly, there is an advantage that not only content in the preferred field is provided, but content in various fields can be provided, and in particular, in the case of content in a non-preferred field, effective reading can be made under the guidance of a leader.

The content output unit 160 may be provided to output customized content including learner-targeted content and leader-targeted content received from the content generating unit 150 to the customer terminal.

The content output unit 160, the customer terminal may be provided to both the learner terminal and the leader terminal, and may transmit the learner-targeted content and the instructor-targeted content to the learner's terminal and the leader's terminal, respectively.

If the reading target corresponds to an infant or child, the content output unit 160 may transmit both the learner target content and the leader guidance content to the leader terminal, and such an output method may be preset by the customer terminal. have.

As described above, by providing content for not only learners but also leaders, there is an advantage that correct reading instruction can be made by the leader even when the target of reading is infants or children.

In the above, we looked at the detailed configuration of the reading content management server. Hereinafter, a method for managing reading content using the above-described reading content management server will be described.

7 illustrates a reading content management method according to an embodiment of the present invention, and FIG. 8 illustrates a reading index calculation and content selection method according to an embodiment of the present invention.

In the process of explaining each step of FIGS. 7 and 8 , the content overlapping with those described with reference to FIGS. 1 to 6 will be omitted or simply described, and FIGS. 1 to 6 will be referred to together for better understanding of the description. In addition, unless otherwise specified, it is assumed that the subject performing each step shown in FIGS. 7 and 8 is the reading content management server shown in FIGS. 1 to 6 .

7 and 8 , the method for managing reading content may include the following steps.

First, the customer information collection step (S110) of collecting customer information from the customer terminal is performed.

Thereafter, a customer information extraction step (S120) of extracting at least one of behavior information, tendency information, and reading capability information from the collected customer information is performed. In the customer information extraction step (S120), the behavior information extraction step (S121) of extracting behavior information from the customer information and the tendency information step (S122) of extracting the tendency information are performed.

Then, based on the persona model pre-stored in the storage DB, the persona diagnosis step (S130) of diagnosing the customer persona corresponding to the behavior information and the disposition information is performed. The persona diagnosis step S130 is performed in the order of the behavior model selection step S131 , the propensity model selection step S132 , and the customer persona determination step S133 .

Thereafter, a reading index calculation step ( S140 ) of calculating a reading index based on the reading ability information is performed.

Referring to FIG. 8 , the reading index calculation step ( S140 ) proceeds in the order of the area-specific competency score deriving step ( S141 ), the comprehensive competency score deriving step ( S142 ), and the reading code generation step ( S143 ).

In the step of deriving competency scores for each domain ( S141 ), based on the concentration index, comprehension index, language ability index, and intellectual curiosity index corresponding to the customer persona, the competency score for each area is derived according to a preset competency score calculation formula for each area do. In this case, the weight of each area of the indicators is differentially assigned based on the customer persona, so that a competency score reflecting the characteristics of the customer persona can be derived.

In the step of deriving the comprehensive competency score ( S142 ), a comprehensive competency score is derived according to a preset comprehensive competency score calculation formula, based on the above-derived competency score for each area.

Thereafter, in the reading code generation step ( S143 ), reading codes indicating the highest and lowest regions are generated from the competency scores for each region. When this reading code is applied in the content selection step S151, which will be described later, there is an advantage in that a reading field that satisfies both the customer persona and the pre-evaluation result performed by the customer can be derived.

Thereafter, a content creation step ( S150 ) of generating customized content based on the customer persona and the reading index is performed.

The content creation step S150 may include the following detailed steps.

First, the content selection step (S151) of setting the field and reading level of the content based on the customer persona and the reading index, and selecting the corresponding content is performed.

In this step, the reading level is set through the following steps based on the reading level setting table set in advance based on the overall competency score and the age of the customer.

First, the step of setting the reading level corresponding to the overall competency score (S1511) is performed. Thereafter, a step ( S1512 ) of comparing a preset reading level range and a comprehensive competency score according to the customer's age is performed. If the reading level is higher than the customer's age, the reading level is lowered by one level, and when the reading level is lower than the customer's age, the level readjustment step ( S1513 ) is performed to increase the reading level by one level. The grade readjustment step ( S1513 ) may be performed until the reading level set within the range of the reading level set according to the age of the customer is located.

Thereafter, a reading recommendation region selection step ( S1514 ) of selecting a reading recommendation region most corresponding to the generated reading code is performed. Thereafter, a step ( S1515 ) of determining whether the selected reading area corresponds to the customer persona is performed. This step may continue until the selected reading area and customer persona correspond. Thereafter, a step ( S1516 ) of setting a final reading area by selecting a reading area corresponding to the customer persona is performed. Thereafter, a content selection step ( S1517 ) of selecting content according to the set reading area is performed. In this step, it may be provided so that the ratio of the content selected according to the customer information received from the customer terminal is controlled.

For example, when the customer sets the ratio of the preferred area, the essential supplementary area, and the indifferent area to 0.6, 0.3, or 0.1, the content candidate group is selected based on the corresponding ratio in the content selection step (S1517), and finally generated The content to be used may be provided so as to be similar to the set ratio.

Thereafter, an image analysis step of analyzing an image of the selected content is performed based on a color histogram preset according to the persona model.

9 and 10 are examples illustrating an image analysis method according to an embodiment of the present invention.

Referring to FIGS. 9 and 10 , the image analysis step is performed to derive customized content that meets the customer's tendency by filtering the book image for the book candidates selected in the content selection step.

Here, the book image may include color, brightness, layout information, and the like.

For example, a color histogram with high saturation may be applied to a persona model having an extroverted tendency, and a color histogram having a low saturation may be applied to a persona model having an introverted tendency. In addition, a color histogram having a high brightness when having an emotional tendency and a low brightness when having a rational tendency may be applied.

In addition, a color histogram of a warm series, a cold series, a clear series, and a cloudy series may be applied according to the propensity and character of each persona model.

For example, in the case of the persona model of the 13th persona model “Idol Wannabe type”, the preferred color can be set as a primary color (high saturation) and a colorful color (high brightness) spectrum, and the classification type is Irregular grids and three-dimensional shapes can be applied, and the core material can be set as a person or an imaginary object. In addition, as the avoidance factor, cold and achromatic (low saturation, low brightness) spectrums can be applied, the classification form is set to a formal and regular style, and the core material can be nature or imaginary objects.

The image analysis as described above may be performed using an image analysis algorithm, and may be subdivided into the following steps.

First, a book image filtering step based on a customer persona is performed. In this step, the primary book image identification including color group, design form, and core material using personal temperament, preference factor, and avoidance factor based on customer persona is made.

Thereafter, a book image filtering step based on a reading index including a reading code and a competency score for each area of the customer is performed. In this step, the customer's reading habit information, reading tendency information, preference information, and non-preference information may be considered together.

When custom content is derived based on the book image filtered in the above steps, a color histogram set according to the persona model is applied to the content to arouse the interest of the customer and maintain the concentration. . In addition, it has the advantage of creating a friendly and comfortable reading environment by providing a feeling close to the customer's tendency.

Furthermore, the interface design can be set differently for each persona model in a way that not only colors and images but also reading content are delivered.

11 is an example illustrating an interface setting method according to an embodiment of the present invention.

Referring to FIG. 11 , in the interface design step, a content interface corresponding to a customer persona is designed based on an interface preset according to a persona model.

As the type of interface, layout design such as basic type, wide type, pop-up type, array type, image type, etc. may be applied.

In the case of the basic type, it is suitable for children who show a lot of time and a large amount of reading pattern once they start reading. It can be used to maintain interest.

In the case of the wide type and the image type, the interface is suitable for infants and young children who are in the growth stage of language ability, attention, and comprehension. there is an advantage

The list type is a method suitable for children who have difficulty reading a lot of reading for a long time, and the purpose of information search is for reading, and it is a method for the type that prefers to organize a simple summary. It is a design that can be done.

In the case of the pop-up type, it is a delivery method that is provided to the type of customer who lacks attention and concentration and is distracted. Since these types of children lose interest quickly, by applying a pop-up type interface to induce new interest, attention can be regained. It is mainly used to provide

The interface types may be provided mixed with each other as needed, based on customer information such as customer persona or age and reading habits, and basic settings are provided to be changed according to customer evaluation information fed back from the customer terminal after the content is provided it might be

Referring back to FIG. 7 , a content output step of outputting at least one of the customer content and the content for guardians generated in the content creation step to the customer terminal is performed.

Thereafter, after the content is used in the customer terminal, a reading evaluation step of providing feedback to the reading content management server with customer evaluation information may be further performed.

In this case, the customer evaluation information may include reading level evaluation information, output field ratio reset information, comments, and star point information, and may be provided in the form of a response to a questionnaire provided from the reading content management server to the customer terminal. have.

By applying the customer evaluation information received in this way, for each reading content, the image, reading ability, preference, deficiency index, and satisfaction information for each persona are accumulated and stored and converted into a database, which is utilized for the advancement of context analysis and is more suitable for customer needs. It has the effect of recommending a book. In addition, there is an advantage in that customer satisfaction can be gradually improved by providing that the reading level and reading field desired by the customer can be readjusted.

By using the reading content management server and the reading content management method according to the embodiment of the present invention as described above, it is possible to perform a book recommendation that meets the needs of the customer by using the persona model based on the customer's personal information. .

Furthermore, by utilizing the above-described reading content management method, a program for executing the reading content management method and a computer-readable recording medium including the same may be implemented.

In a computer-readable recording medium including a program for executing a method for managing reading content according to an embodiment of the present invention, the method for managing reading content includes: a customer information collection step of collecting customer information from a customer terminal; a customer information extraction step of extracting at least one of behavior information, tendency information, and reading ability information from the collected customer information; A persona diagnosis step of diagnosing a customer persona corresponding to the behavior information and the tendency information based on the persona model pre-stored in the storage DB; a reading index calculation step of calculating a reading index based on the reading ability information; and a content generation step of generating customized content based on the customer persona and the reading index, wherein the reading index calculation step is based on the concentration index, the comprehension index, the language ability index, and the intellectual curiosity index corresponding to the customer persona. , it may be provided to include a step of deriving competency scores for each domain according to a preset competency score calculation formula for each domain.

In the above, even though it has been described that all components constituting the embodiment of the present invention are combined or operated in combination, the present invention is not necessarily limited to this embodiment. That is, within the scope of the object of the present invention, all the components may operate by selectively combining one or more.

In addition, terms such as "comprises", "comprises" or "have" described above mean that the corresponding component may be embedded, unless otherwise stated, so that other components are excluded. Rather, it should be construed as being able to further include other components. All terms, including technical and scientific terms, have the same meaning as commonly understood by one of ordinary skill in the art to which the present invention belongs, unless otherwise defined. Terms commonly used, such as those defined in the dictionary, should be interpreted as being consistent with the meaning in the context of the related art, and are not interpreted in an ideal or excessively formal meaning unless explicitly defined in the present invention.

The above description is merely illustrative of the technical spirit of the present invention, and various modifications and variations will be possible without departing from the essential characteristics of the present invention by those skilled in the art to which the present invention pertains. Accordingly, the embodiments disclosed in the present invention are not intended to limit the technical spirit of the present invention, but to explain, and the scope of the technical spirit of the present invention is not limited by these embodiments. The protection scope of the present invention should be construed by the following claims, and all technical ideas within the equivalent range should be construed as being included in the scope of the present invention.

1000: Reading Content Management System
100: reading content management server
110: customer information collection unit
120: customer information extraction unit
130: persona diagnosis unit
131: behavior model selection unit
132: propensity model selection unit
133: customer persona decision unit
140: reading index calculation unit
141: Competency score derivation unit for each area
142: Comprehensive competency score derivation unit
143: reading code generation unit
150: content creation unit
151: content selection unit
152: image analysis unit
153: interface design unit
160: content output unit
200: storage DB
300: customer terminal
50: network

Claims (10)

Customer information collection unit for collecting customer information from the customer terminal;
a customer information extraction unit for extracting at least one of behavior information, tendency information, and reading capability information from the collected customer information;
a persona diagnosis unit for diagnosing a customer persona corresponding to the behavior information and the tendency information based on the persona model pre-stored in the storage DB;
a reading index calculation unit for calculating a reading index based on the reading ability information; and
A content generator for generating customized content based on the customer persona and the reading index,
The reading index calculation unit is, based on the concentration index, comprehension index, language ability index, and intellectual curiosity index corresponding to the customer persona, competency for each area to derive competency scores for each area according to a preset competency score calculation formula for each area Reading content management server including a score derivation unit. According to claim 1,
The persona diagnosis unit,
a behavior model selection unit for selecting a customer behavior model by matching the behavior information to a plurality of behavior models stored in the storage DB;
a propensity model selection unit for selecting a customer propensity model by matching the propensity information to a plurality of propensity models stored in the storage DB; and
Reading content management server including a customer persona determining unit for determining a customer persona by combining the customer behavior model and the customer tendency model. According to claim 1,
The formula for calculating the competency score for each area is,

ego,
where R is the competency score for each area, t is the persona type, n is the index area,

is the customer score by area,

is the weight for each area preset according to the persona,

is a reading content management server that is a preset index score for each area according to persona. 4. The method of claim 3,
The reading index calculation unit,
a comprehensive competency score derivation unit for deriving a comprehensive competency score according to a preset comprehensive competency score calculation formula, based on the competency score for each area; and
The reading content management server further comprising a reading code generation unit for generating reading codes indicating the highest and lowest regions from the competency scores for each region. 5. The method of claim 4,
The overall competency score calculation formula is,

ego,
where S is the overall competency score, R is the competency score for each domain, N is the number of index areas, t is the persona type, n is the index area,

is the customer score by area,

is the weight for each area preset according to the persona,

is a reading content management server that is a preset index score for each area according to persona. According to claim 1,
The content generation unit,
a content selection unit configured to select a corresponding content by setting a field and a reading level of the content based on the customer persona and the reading index; and
an image analysis unit that analyzes the image of the selected content based on a color histogram preset according to the persona model; and
Reading content management server including an interface design unit for designing a content interface corresponding to the customer persona based on a preset interface according to the persona model. According to claim 1,
A reading content management server that stores customer evaluation information received from the customer terminal in real time in the storage DB, and recalculates the reading index by reflecting the customer evaluation information when calculating the reading index. According to claim 1,
The customized content is a reading content management server including learner-targeted content and leader-targeted content. Customer information collection step of collecting customer information from the customer terminal;
a customer information extraction step of extracting at least one of behavior information, tendency information, and reading capability information from the collected customer information;
a persona diagnosis step of diagnosing a customer persona corresponding to the behavior information and the tendency information based on the persona model pre-stored in the storage DB;
a reading index calculation step of calculating a reading index based on the reading ability information; and
A content creation step of generating customized content based on the customer persona and the reading index,
In the reading index calculation step, based on the concentration index, comprehension index, language ability index, and intellectual curiosity index corresponding to the customer persona, the competency score for each area is derived according to a preset competency score calculation formula for each area. A method for managing reading content, including the step of deriving competency scores. A computer-readable recording medium comprising a program for executing the reading content management method of claim 9,
The reading content management method includes:
Customer information collection step of collecting customer information from the customer terminal;
a customer information extraction step of extracting at least one of behavior information, tendency information, and reading capability information from the collected customer information;
a persona diagnosis step of diagnosing a customer persona corresponding to the behavior information and the tendency information based on the persona model pre-stored in the storage DB;
a reading index calculation step of calculating a reading index based on the reading ability information; and
A content creation step of generating customized content based on the customer persona and the reading index,
In the reading index calculation step, based on the concentration index, comprehension index, language ability index, and intellectual curiosity index corresponding to the customer persona, the competency score for each area is derived according to a preset competency score calculation formula for each area. A computer-readable medium comprising the step of deriving a competency score.

Images