WO2016137078A1

WO2016137078A1 - Matching device and method for spouse candidates

Info

Publication number: WO2016137078A1
Application number: PCT/KR2015/010771
Authority: WO
Inventors: 조재영; 이은강
Original assignee: (주)소울랩
Priority date: 2015-02-26
Filing date: 2015-10-13
Publication date: 2016-09-01
Also published as: KR101656024B1; KR20160104407A

Abstract

The present invention relates to a matching system and method for spouse candidates. To this end, the matching method according to the present invention comprises: a step of classifying categories by items of questionnaire information; a step of deriving a lower factor score of each item on the basis of the classified categories; a first calculation step of calculating lower factor values by calculating lower factor scores and a lower weight; a step of deriving upper factor scores by summing the lower factor values for each of the categories; a second calculation step of calculating upper factor values by calculating the upper factor scores and an upper weight; and deriving a mate value by summing the upper factor values.

Description

Matching Device and Method for Spouse Candidates

The present invention relates to a matching system and method for a spouse candidate, and more particularly, to a matching device and method for objectively analyzing a user and matching a spouse candidate to have a high success rate.

Furthermore, the present invention claims the benefit of Korean Patent Application No. 10-2015-0027404, filed February 26, 2015, the entire contents of which are incorporated herein.

Generally, a marriage information service collects a certain amount of membership fee from a member by a business entity, and provides introduction information between members by a matching technique for each operator based on a member DB. The operation of the existing providers of marriage information services is based on the provision of information on membership management by the consultant in charge of offline. Here, the marriage information company providing the marriage information service mainly uses a method of matching the ideal type of the corresponding customer through interviews with employees of the company, for example, consultants and couple managers. However, this type of marriage information company narrows the matching range because it only matches within members directly managed by the employee himself (eg, a couple manager). For example, even if hundreds or thousands of members are subscribed to a database of a marriage information company, only a few members are managed by a couple manager, so there is a low possibility of meeting a desired partner. Even the matching method through the marriage information company is made by the subjective judgment of the couple manager, and thus lacks objectivity.

In addition, with the development of current IT technology, a number of ideal matching applications for portable terminals such as smart phones have been developed. However, these applications mainly perform the matching method using the customer's ideal type. That is, these applications mainly use a method of matching the ideal type in the database based on factors set by the customer, for example, age, common interest, region, drinking status, religion, smoking status, etc. In reality, there is a problem that the ideal part is difficult to evaluate objectively. Accordingly, even if the customer meets according to the corresponding applications, since it is difficult to meet the partner of the desired level, there is a problem that the meeting rate is low.

In this regard, there is a Korean Patent Publication No. 2014-0108205 entitled "Marriage Information Providing System".

SUMMARY OF THE INVENTION An object of the present invention is to provide a matching device and method for a spouse candidate capable of objective evaluation and having a high rate of suicide.

The matching method of the present invention for solving the above problems, the step of classifying a category for each item of questionnaire information; Deriving a sub-factor score of each item based on the classified category; Calculating a lower factor values by calculating lower factor scores and lower weights; Deriving upper factor scores by adding lower factor values for each category; A second calculating step of calculating upper factor values by calculating upper factor scores and upper weights; And deriving a mate value by summing the upper factor values.

Also, the category may include a first information category, a second information category, and a third information category.

In addition, the upper weight extracts the lower representative group by performing leveling on the basis of attractiveness for each category, and generates question cards by combining each sub representative group so that one sub representative group belongs to each category, and then, question cards It can be derived by applying Y = aA + bB + cC + d to the answers of multiple users for, where Y is the respondent's preference for each question card and A, B and C are the attractiveness of each category. , a, b and c may represent a utility value for the attractiveness of each category, and d may represent a constant.

In addition, question cards may be generated such that there are two or less lower representative groups of the same level.

In addition, when the question cards are provided to a plurality of users, only some of the question cards may be extracted and provided.

In addition, the weight for each category (hereinafter, referred to as a higher weight) may be calculated based on a difference value between the maximum utility value and the minimum utility value of the attractiveness of each category.

In addition, the matching method of the present invention may further include matching candidate users whose difference between the mate value of the user and the mate value of the previously stored candidate users is less than or equal to a preset threshold to the spouse candidate of the user.

The matching device of the present invention for solving the above problems is to classify the categories for each item of questionnaire information, to derive the sub-factor scores of each item based on the classified category, and to calculate the sub-factor scores and sub-weights Derive lower factor values, sum lower factor values for each category to derive upper factor scores, calculate upper factor scores with upper factor scores, derive upper factor values, and sum the upper factor values It characterized in that it comprises a control unit for deriving.

In addition, the upper weight may be calculated based on a difference between the maximum utility value and the minimum utility value of the attractiveness of each category.

In addition, the controller may match candidate users whose difference between the user's mate value and pre-stored mate values of the candidate users are less than or equal to a preset threshold as the spouse candidates of the user.

According to the matching device and method for a spouse candidate of the present invention, not only by using the ideal type of the customer or user, but also by statistically analyzing and matching the matching partner with the customer or user, not only more objective matching is possible, There is a rising effect.

In addition, according to the matching apparatus and method of the present invention, since the data is collected and matched based on the data of people belonging to the marriage high involvement group, more reliable data can be obtained, and thus the matching rate of matching is also increased. There is an effect that can be raised together.

1 is a conceptual diagram of a matching system according to an embodiment of the present invention.

2 is a block diagram of a matching system according to an embodiment of the present invention.

3 is a block diagram of a matching device according to an embodiment of the present invention.

4 is a diagram showing an example of deriving a mate value through the matching device of the present invention.

5 is a flowchart illustrating a matching method according to an embodiment of the present invention.

6 is a flowchart illustrating a method of deriving a higher weight according to an embodiment of the present invention.

7 is a diagram illustrating an example of a question card of the present invention.

Hereinafter, the present invention will be described in detail with reference to the accompanying drawings. Here, the repeated description, well-known functions and configurations that may unnecessarily obscure the subject matter of the present invention, and detailed description of the configuration will be omitted. Embodiments of the present invention are provided to more completely describe the present invention to those skilled in the art. Accordingly, the shape and size of elements in the drawings may be exaggerated for clarity.

Matching system 1000 according to an embodiment of the present invention stores the mating values of marriage-aged customers in the storage unit, and when the request of a specific customer, the difference between the mate value of the customer and the mate values of other customers is a predetermined threshold It extracts the information of customers below the value and selects them as candidates for spouses. Here, the term mate value is a value that quantifies the attractiveness of the customer as long as it is objectively recognized by the opposite sex, and the mate value is calculated by considering three categories (external attractiveness, internal attractiveness, and social attractiveness).

That is, matching of spouse candidates according to the present invention is a method of matching spouse candidates having a similar level of attractiveness. Accordingly, rather than matching a spouse candidate through the ideal-type matching referred to in the prior art, a method of matching a person having a level similar to that of a customer as a spouse candidate. Accordingly, the process of deriving mate values is important, and derivation of these mate values should be made objectively, not subjectively. Hereinafter, a description will be given of the matching system 1000 according to an embodiment of the present invention.

1 is a conceptual diagram of a matching system 1000 according to an embodiment of the present invention. 2 is a block diagram of a matching system 1000 according to an embodiment of the present invention. As shown in FIGS. 1 and 2, the matching system 1000 according to an embodiment of the present invention may include a user terminal 10 and a matching device 100. Hereinafter, each configuration included in the matching system 1000 of the present invention will be described.

The user terminal 10 receives a user's information from the user or receives data such as an answer to a questionnaire or the like described below. In addition, the user terminal 10 may perform a function of providing the user with information about the matched spouse candidates through the matching device 100 of the present invention. Here, although the user terminal 10 shown in FIG. 1 is illustrated in the form of a computer such as a desktop, this is only an example, and may be a portable computer such as a laptop computer or a portable terminal such as a smartphone or a tablet PC. Can have.

The matching device 100 may include a communication unit 110 and a control unit 120. Herein, the communication unit 110 functions to perform communication with the user terminal 10 through the network 30, and the control unit 120 controls a user who operates the user terminal 10 and a spouse candidate suitable for the user. Function to perform matching.

To this end, first, the controller 120 classifies categories for each item of questionnaire information, and transmits each item of the questionnaire information to the user terminal 10 through the communication unit 110. Here, each question of the questionnaire information represents problems for deriving a lower factor score that is the most basic for calculating a user's mate value, as mentioned below. That is, the questionnaire information described above may include questions for determining whether a user who responds to the question through the user terminal 10 is a person, and what appearance and social attractiveness.

In addition, the category may be divided into a first information category, a second information category, and a third information category. Here, the first information category may be an external attractiveness, the second information category may be a social attractiveness, and the third information category may be a category for internal attractiveness. Here, the category does not include age, since age serves as a leading indicator of other categories, and thus no statistical significance exists. In addition, when age is applied as a variable, subjective factors such as prejudice due to age may play a role. Therefore, age is not included in the category for more objective evaluation.

Thereafter, the control unit 120 functions to derive the lower factor scores of each item based on the data transmitted from the user terminal 10. Here, the derivation of the lower factor score for each item may be made according to a preset algorithm, and an example thereof is further described below with reference to FIG. 4, and thus, further description thereof will be omitted.

Thereafter, the controller 120 performs a function based on the lower factor scores and the lower weight, thereby deriving the lower factor values. Here, as mentioned above, the lower factor scores and the lower factor values may be divided into categories and calculated.

Sub-factor values, for example, in the case of the appearance attractiveness category, are values for detailed subfactors such as appearance or body shape, and in the case of the internal attractiveness category, such as personality, stability, reliability, consideration, etc. Values for detailed subfactors, and in the case of social attractiveness categories, may indicate scores for subfactors such as education, income and occupation. These subfactor scores may be calculated with a predetermined subweight to be used to derive subfactor values. Here, for each category, although examples of detailed subfactors have been mentioned, the subfactors are not limited to the above-described ones, and various subfactors may be applied.

Here, the lower weight is a numerical value that is set according to how important the customer having the opposite sex as the user evaluates the factor. In other words, the higher the importance, the higher the weight. In addition, the present invention discloses a matching technique based on an objective evaluation, not an ideal matching method, as mentioned above. That is, the weights mentioned throughout the specification may be calculated based on the general value of the plurality of users, not calculated based on the importance of matching between the user and the specific user. In other words, the sub-factor values are calculated by considering the importance and the sub-factor scores of the sub-factors, which are considered important by customers with opposite sex to the user. This can be done.

Thereafter, the controller 120 performs a process of deriving upper factor scores by adding the lower factor values for each category. As mentioned above, there are a plurality of lower factor values for each category, and accordingly, a process of deriving one upper factor score for each category is performed by collecting the above-described lower factor values for each category for conversion of a final mate value. .

Thereafter, the controller 120 calculates upper factor scores and upper weights derived through the process to derive upper factor values. Here, as mentioned above, the upper factor value represents a derived value for each of the external attractiveness, the social attractiveness, and the internal attractiveness, which may be derived through calculation with the upper weight like the lower factor value. Here, the upper weight is calculated based on the importance considered by a plurality of users, that is, customers having opposite sexes. Here, the method of deriving the upper weight is as follows.

First, the sub-group is extracted by leveling based on the attractiveness level for each category, and question cards are generated by combining the sub-groups such that one sub-group is included in each category. Here, the lower representative group represents, for example, a group divided into upper, middle, and lower levels for the category for each category. That is, when leveling is performed at three levels for each category, since three sub-representative groups belong to each of the first information category, the second information category, and the third information category, a total of nine sub-representative groups are generated. . Here, three grades classified through leveling have been described, but it should be understood that this is only an example and may be divided into various numbers of grades.

In addition, since the question card may be generated to belong to one sub-representative group per category, information about a virtual person including one sub-representative group for each category may be described in each question card. For example, appearances, normal appearances, and below-average appearances that conformed to the sub-representative group for the first category of information; Assume that the sub-representative group for the category is 50 million won, 30 million won, and 15 million won. In this case, the generated question card includes one sub-representative group for each category, so the question card can be used in various combinations such as (Appearance Appearance, Normal Personality, Salary 15 million won), (Compliance Appearance, Coarse Personality, Salary 30 million won) Can be generated. Here, the question cards are preferably generated such that there are two or less lower representative groups of the same level. This means that if all of the sub-groups that are all good or belong to the sub-groups are all poor, the evaluation results by respondents will be similar, but only the number of question cards will increase, making it difficult to achieve effective statistical analysis. Because. An example of the question card described above is shown in FIG. 7.

In addition, the reason why the question card is used is to prevent this because when people question the importance of each category in a sequence, people may be conscious of moral values, and may misunderstand their desired condition or respond falsely. That is, by generating a question card and using the scores of the plurality of users on the question card, it is possible to grasp the potential, that is, the actual condition and the like of the plurality of users. In other words, it is possible to derive an objective higher weight. Here, it is preferable that the plurality of users are people belonging to a marriage high involvement group. Here, the marriage high involvement group refers to a group of people who have married thoughts within a predetermined period regardless of age. In other words, the weights according to the invention are based on the thinking of those who are directly or indirectly related to marriage, and thus can have higher accuracy.

And, when presenting a question card to a plurality of users, not all of the question cards are provided to the users, but only some of them are extracted and provided. That is, if too many question cards are provided to users, it may be difficult for users to answer this question, so the number of question cards is limited to a certain number to receive a score. The collected data may be applied to Equation 1 below.

In the above equation, Y is the preference of respondents for each question card, A, B, and C are the attractiveness of each category, a, b, and c are the utility values for the attractiveness of each category, and d is the constant. Indicates. In the above formula, variables are marked with uppercase and lowercase letters, and they should be interpreted as different variables. In addition, A, B, and C values representing the attractiveness of each category correspond to independent variables, and thus the number of independent variables corresponds to multiple regression analysis. In addition, since each of the independent variables has three sub-groups divided into upper, middle, and lower, and the shape of the sub-representative group is a nominal scale, Equation 1 shows that the independent variable is the nominal scale among multiple regression analysis. Apply dummy multiple regression analysis, which should be used when implemented in the form of. When the dummy multiple regression analysis is applied, Equation 1 may be expressed as Equation 2 below.

Where Y is the respondent's preference for each question card, A, B, and C are the attractiveness of each category, A ₁ , A ₂ , and A ₃ are the three dummy variables in the sub-group of category A, and B ₁ , B ₂ , B ₃ represent the three dummy variables of sub-group of category B, C ₁ , C ₂ , C ₃ represent the three dummy variables of sub-group of category C, and a ₁ , a ₂ , a ₃ Is the utility value of each sub-representative group of category A, b ₁ , b ₂ , and b ₃ are the utility values of each of the sub-representative group of category B, and c ₁ , c ₂ , and c ₃ are each of the sub-representative group of category C The utility value of d is a constant. Here, the upper weight is a value obtained by quantifying the difference between the maximum utility value and the minimum utility value for each category, and the maximum utility value of category A is the largest value among a ₁ , a ₂ , and a ₃ , and the minimum utility value is the smallest value. Means. Since all view cards are a combination of one sub-representative group for each category, two of the three dummy variables in each category are labeled with 0 and the other is labeled with 1. Presenting different combinations of viewcards to all respondents, and aggregating preference results, a dummy multiple regression equation is derived:

Y = 2.414+ (0.24) A ₁ + (-0.18) A ₂ + (-0.06) A ₃ + (0.12) B ₁ + (-0.02) B ₂ + (-0.10) B ₃ + (0.18) C ₁ + When derived as (-0.03) C ₂ + (-0.15) C ₃ , the minimum utility value for A can be -0.18, the intermediate utility value is -0.06, and the maximum utility value can be 0.24. The upper weight value for each category is a value obtained by standardizing the difference between the maximum and minimum utility values of A, B, and C, respectively. That is, the difference between the maximum utility value of A and the minimum utility value of 0.42 (0.24-(-0.18), and the maximum utility value of 0.22, C, which is the difference between the maximum utility value and the minimum utility value of B (0.12-(-0.10)). If we normalize 0.33, which is the difference between and the minimum utility value (0.18-(-0.15)) to 100%, we get 43%, 23%, and 34%, which are the upper weights.

Again, the control unit 120 will be described. The controller 120 performs a process of deriving a mate value by summing the upper factor values after the derivation process of the upper factor values described above. In addition, the controller 120 performs a function of matching candidate users whose difference between the user's mate value and the pre-stored candidate users' mate values are equal to or less than a predetermined threshold value as the spouse candidates of the user. That is, the controller 120 functions to match the spouse candidates based on a comparison of the Euclidean distance between the user's mate value and the candidate users' mate values and the threshold value. Accordingly, matching between people having similar attractiveness is possible, so that a matching capable of a higher closing rate can be achieved.

Hereinafter, the controller 120 included in the matching device 100 of the present invention will be further described with reference to FIG. 3. 3 is a block diagram of a matching device according to an embodiment of the present invention. The control unit 120 according to an embodiment of the present invention may include a weight derivation module 121, a calculation module 122, and a matching module 123. Hereinafter, each configuration included in the control unit 120 of the present invention will be described.

The weight derivation module 121 functions to derive the lower and upper weights used to derive the lower and upper factor values of the user. Here, the upper weight may be derived based on the answers of the plurality of users to the extracted question cards, as mentioned above. Since the description of the higher weight has been described in detail with reference to FIGS. 1 and 2 above, further description thereof will be omitted.

In addition, similarly to the method of deriving the upper weight, the lower weight may be derived based on answers to a plurality of questions to a plurality of users. However, the upper weight may be derived through multiple regression analysis, while the lower weight may be derived through the sequence DEA (Data Envelopment Analysis) method. For example, the lower weight can be derived through the flow below.

First, subfactors are presented to a plurality of users through a questionnaire. Here, the lower factors are categorized by the upper factors, that is, the categories, and presented, and answers are obtained. For example, for appearance, the first category of information: 1) healthy (born health), 2) good skin, 3) good style (clothes, hair, etc.), 4) attractive face shape, 5) attractive body shape and proportions. 6) moderate weight, 1) educational level 2) annual income level 3) occupational type 3) job type, and 3) category of internal attractiveness 1) hardworking integrity, 2) emotional Stability (dependent or sensitive), 3) a good personality (easily forgiving or caring for the wrongs of others), 4) confident, 5) a degree of commitment (how devoted to the relationship between the two), 6) smiling well , Etc. may be included. And the above-described sub-factors are merely examples and are not limited to the number and type described above.

After presenting the lower factors to the plurality of users in this way, the preferred rank is input from the plurality of users. After receiving the ranking like this, the score is given by inverting the ranking, and the score of each factor is calculated based on the ranking. The lower weight may be calculated based on this score.

The higher weight and lower weight derived as described above may be stored in the storage unit 20. That is, the upper weight and the lower weight may not be calculated every time a user's mate value is calculated, but may be utilized by storing these weights after the above-described statistical analysis technique and calling and writing them whenever necessary. This method is possible because, as mentioned above, the matching method of the present invention is not an ideal matching method, but a method of determining a user from a general point of view and matching based on the matching method.

The operation module 122 functions to derive a lower factor score, a lower factor value, an upper factor score, an upper factor value, and a mate value. As mentioned above, the lower factor score may be classified based on the category of each item of questionnaire information, and may be derived based on the user's answer to each item based on the classified category. Here, the lower factor score may be derived according to a predetermined algorithm. The lower factor value may be derived by calculating a lower factor score and a lower weight stored in the storage unit 20. The upper factor score may be derived based on the sum of the lower factor values for each category, and the upper factor value may be derived by calculating the upper factor score and the upper weight, and the mate value may be derived based on the sum of the upper factor values. . Since the method of calculating the values derived through the calculation module 122 has been described in detail with reference to FIGS. 1 and 2, further description thereof will be omitted.

The matching module 123 functions to match the spouse candidates based on a comparison of the Euclidean distance and the threshold value between the user's mate values and the candidate users' mate values.

As described above, the matching device 100 according to the present invention is characterized in that the weights are set based on questionnaires and question data for the marriage high involvement group, and the mate value of the user is derived based on the weights. Accordingly, the user's mate value has the advantage that it can be objectively quantified. In addition, the matching method also has a merit of increasing the success rate after matching, since matching between people having a similar level of mate values other than the ideal matching method is performed. That is, the matching method used in a conventional marriage information company, an online website or an application is a method in which a matching is performed without calculating a mate value that quantifies the attractiveness to customers, and thus lacks reliability in matching and difficulty in objective matching. Have On the other hand, the present invention is a method of performing matching between people with similar attractiveness based on the mate value, there is an advantage that can achieve a more objective and high rate of success.

Hereinafter, with reference to FIG. 4, the derivation method of a mate value is further demonstrated. 4 is a diagram showing an example of deriving a mate value through the matching device of the present invention.

First, a lower factor score (LFS) is derived based on an answer to questionnaire information input from a user, that is, data. Here, the method of deriving the lower factor score (LFS) may be performed according to a preset algorithm, as shown in FIG. 4. In this example, the subfactor scores for internal attractiveness are 70, 40, 80, 20, 60, 50, 100, 90 points, and the subfactor scores for external attractiveness are 30, 50, 75, 25, respectively. Subfactor scores for 80, 90, and social attractiveness are assumed to be 66, 80, and 71, respectively.

Thereafter, a process of deriving lower factor values (LFV) is performed by calculating lower factor scores (LFS) and lower factor weight (LFW). Here, the lower factor scores LFS and the lower factor values LFV are preferably calculated for each category. In addition, since the description of the lower weight LFW has been made in detail above, further description thereof will be omitted.

Thereafter, a process of deriving an upper factor score (UFS) is performed by summing the lower factor values (LFV) for each category, and an upper factor weight (UFW) is applied to each derived upper factor score (UFS). ), A process of deriving an Upper Factor Value (UFV) is performed. Thereafter, the sum of all derived upper factor values UFV is summed to derive a mate value (MV). In this example, the mate value (MV) was derived to be 63 (about 62.55). However, the numerical values described with reference to FIG. 4 are only examples and may be variously changed according to the weights and the user's answers.

Hereinafter, a matching method according to an embodiment of the present invention will be described with reference to FIG. 5. 5 is a flowchart illustrating a matching method according to an embodiment of the present invention. In the following description, descriptions overlapping with the above-mentioned parts will be omitted.

First, a step of classifying a category for each item of questionnaire information in the matching device 100 is performed (S110), and transmitting the classified questionnaire information to the user terminal 10. As mentioned above, the category may include a first information category, a second information category, and a third information category. The category may also be a category for appearance attractiveness, social attractiveness, and internal attractiveness. Here, as mentioned above, the category does not include age which may adversely affect the objective analysis.

Thereafter, the user terminal 10 inputs data (S120) and transmits the input data back to the matching device 100 (S130).

The matching apparatus 100 derives a lower factor score based on the received data (S135), and derives the lower factor values by calculating the lower factor score and the lower weight (S140). Here, since the description of the lower weight and the description of the operation process have been described in detail above, further description thereof will be omitted.

Thereafter, the matching apparatus 100 derives the upper factor scores by summing the lower factor values for each category (S145), and derives the upper factor values by calculating the upper factor score and the upper weight (S150). Since the description of the derivation process of the upper factor score and the upper factor value has been described in detail above, further description thereof will be omitted.

Thereafter, a step (S160) of deriving a mate value is performed by summing all upper factor values for each category derived through the step S150.

Thereafter, matching of the spouse candidates is performed based on a difference between the mate value of the user and the mate value of the candidate users derived in step S160 (S170). The matching made through the step S170 may be made based on a comparison of the Euclidean distance between the user's mate value and the candidate users' mate value and a predetermined threshold value.

When the matching is completed, the information on the spouse candidates that are the matching result may be transmitted to the user terminal 10 again.

6 is a flowchart illustrating a method of deriving a higher weight according to an embodiment of the present invention. In the following description, portions overlapping with those described with reference to FIGS. 1 and 2 will be omitted.

First, step S210 of performing leveling on the basis of attractiveness for each category is performed. Also, in step S210, the lower representative group may be extracted through the above-described leveling.

Thereafter, step S220 is performed to generate question cards by combining each sub representative group so that one sub representative group belongs to each category. As mentioned above, lower representative groups are groups created by leveling categories, ie, ranking a predetermined number. For example, assuming leveling is performed with three grades, three sub-groups may be created per category. Here, the question cards are preferably generated such that there are two or less lower representative groups of the same level.

Thereafter, a step S230 of checking whether a question request through the question card has been received is performed, and if the question request is received, control returns to step S240, otherwise control returns to step S230 again.

In step S240, some of the question cards generated in step S220 are extracted. As mentioned above, the question cards generated in step S220 are generated a considerable number of question cards through a combination of sub-groups by category. Accordingly, when all of them are presented to the user, the user may feel a burden on the answer. Therefore, it is preferable to derive only a part of the optimized algorithm and present it to the plurality of users.

Thereafter, step S250 is performed to calculate the upper weight by applying the data answered from the plurality of users to Equation 1 mentioned above. Here, since the description of the upper weight has been described in detail above, further description thereof will be omitted.

Thereafter, the step S260 of storing the higher weight derived in step S250 is performed.

The matching method and apparatus according to the present invention can be implemented in the form of program instructions that can be executed by 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. Program instructions recorded on the media may be those specially designed and constructed for the purposes of the present invention, or they may be of the kind well-known and available to those having skill in the computer software arts. Examples of computer-readable recording media include magnetic media such as hard disks, floppy disks, and magnetic tape, optical media such as CD-ROMs, DVDs, and magnetic disks, such as floppy disks. Magneto-optical media, and any type of hardware device specifically configured to store and execute program instructions such as ROM, RAM, flash memory, and the like. Examples of program instructions may include high-level language code that can be executed by a computer using an interpreter as well as machine code such as produced by a compiler. Such hardware devices may be configured to operate as one or more software modules to perform the operations of the present invention, and vice versa.

The teachings of the present principles can be implemented as a combination of hardware and software. In addition, the software may be implemented as an application program that is actually implemented on the program storage unit. The application can be uploaded to and executed by a machine that includes any suitable architecture. Preferably, the machine may be implemented on a computer platform having hardware such as one or more central processing units (CPU), computer processor, random access memory (RAM), and input / output (I / O) interfaces. . In addition, the computer platform may include an operating system and micro instruction code. The various processes and functions described herein may be part of micro instruction code or part of an application program, or any combination thereof, and they may be executed by various processing apparatus including a CPU. In addition, various other peripheral devices such as additional data storage and printers may be connected to the computer platform.

Since some of the configuration system components and methods shown in the accompanying drawings are preferably implemented in software, the actual connections between the system components or process functional blocks may vary depending on how the principles of the invention are programmed. It should be further understood. Given the teachings herein, one of ordinary skill in the pertinent art will be able to contemplate these and similar implementations or configurations of the present principles.

Claims

Classifying a category for each item of questionnaire information;

Deriving a sub-factor score of each item based on the classified category;

Calculating a lower factor values by calculating lower factor scores and lower weights;

Deriving upper factor scores by adding lower factor values for each category;

A second calculating step of calculating upper factor values by calculating the upper factor scores and the upper weights; And

And summing the upper factor values to derive a mate value.
The method of claim 1,

And the category comprises a first information category, a second information category, and a third information category.
The method of claim 2,

The upper weight is,

Leveling is performed based on the degree of attractiveness for each category to extract the sub-representative group, and by generating each question card by combining each sub-representative group so that one sub-representative group belongs to the category, and then the plurality of question cards Matching Y = aA + bB + cC + d to the users' answers.

(Y represents respondents' preference for each question card, A, B, and C represent attractiveness for each category, a, b, and c represent utility values for attractiveness for each category, and d represents a constant)
The method of claim 3,

And the question cards are generated such that there are two or less lower representative groups of the same level.
The method of claim 3,

And when the question cards are provided to a plurality of users, only some of the question cards are extracted and provided.
The method of claim 3,

The higher weighted value is calculated based on a difference between a maximum utility value and a minimum utility value of the attractiveness of each category.
The method of claim 1,

Matching candidate users whose difference between a mate value of a user and a mate value of previously stored candidate users is less than or equal to a preset threshold to the spouse candidate of the user.
Categorize categories by questionnaire information, derive sub-factor scores for each item based on the classified categories, calculate sub-factor scores and sub-weights to derive sub-factor values, and calculate sub-factor values And a control unit for deriving upper factor scores by summing each other, calculating upper factor values by calculating upper factor scores and upper weights, and deriving a mate value by adding the upper factor values. Device.
The method of claim 8,

And the category comprises a first information category, a second information category, and a third information category.
The method of claim 9,

The upper weight is,

Leveling is performed based on the degree of attractiveness for each category to extract the sub-representative group, and by generating each question card by combining each sub-representative group so that one sub-representative group belongs to the category, and then the plurality of question cards And is derived by applying Y = aA + bB + cC + d to the users' answers.

(Y represents respondents' preference for each question card, A, B, and C represent attractiveness for each category, a, b, and c represent utility values for attractiveness for each category, and d represents a constant)
The method of claim 10,

And the question cards are generated such that there are two or less lower representative groups of the same level.
The method of claim 10,

And when the question cards are provided to a plurality of users, only some of the question cards are extracted and provided.
The method of claim 10,

And the higher weight is calculated based on a difference between a maximum utility value and a minimum utility value of the attractiveness of each category.
The method of claim 8,

The control unit,

And matching candidate users having a difference between a mate value of a user and a mate value of previously stored candidate users to a spouse candidate of the user.