KR101662585B1 - Method for Recommending Service Providing Shop by Using Location Based Social Networking Service - Google Patents

Abstract

Discloses a method for recommending an LBSNS-based service provider and an apparatus therefor.
It collects check-in records from terminals and assigns weights to service providers classified by categories based on check-in records, measures similarity among users based on the score of service providers, evaluates users based on similarities and scores Derive predictive values, calculate distances between the user's current location and the service provider's location, and provide estimated vendors using estimated estimates and distance calculations.

Description

[0001] The present invention relates to a method for recommending a service provider using location-based SNS,

The present embodiment relates to a service provider recommendation method using a location-based SNS.

The contents described below merely provide background information related to the present embodiment and do not constitute the prior art.

The location based SNS (Social Networking Service) uses the terminal to grasp the user's location information, and then provides new information by applying Machine to Machine, Augmented Reality, and the like.

Location-based SNS allows users to add a simple text and a photograph to a specific place in the current location when they check their current location, and to share the record with the people using the same SNS. In addition, the location based SNS may list the names of nearby places based on the user's current location, or may provide photographs and photos left by other users to places near the user. Here, "place" means a company that provides services.

However, existing location - based SNS has the problem of providing information of all nearby places according to the user 's current location.

It is necessary to provide a place at a distance from the current location of the user by measuring weights for each location existing within the zone range set according to the user's selection in the existing location-based SNS.

The present embodiment is based on the fact that the service provider's checkpoint record information of service providers within a predefined zone range based on the current location of a specific terminal, the weight information of service providers, And a recommendation company list extracted based on the distance information between the service provider locations selected by the prediction score and the current location of the terminal.

According to an embodiment of the present invention, a check-in record collection unit collects check-in record information on service provider information existing within a predetermined zone range from the entire terminal group, respectively. A weight calculation unit for calculating a weight for each predetermined service category based on the check-in record information; An evaluation similarity degree calculating unit that extracts evaluation scores assigned to each of the service provider information, calculates evaluation similarity information among the terminals included in the entire terminal group based on the evaluation score and the weight; An evaluation prediction value calculation unit for calculating an evaluation prediction value of the service provider within the zone range based on the evaluation score and the evaluation degree of similarity information; A distance value calculation unit for calculating a distance value between the location information of the specific terminal among the entire terminal groups within the area range and the location information of the recommended service provider information extracted according to the estimated estimation value; And a recommendation company extracting unit for generating recommendation information of the place based on the estimated estimation value and the distance value.

According to another aspect of the present invention, a check-in record collection process for collecting check-in record information on service provider information existing within a predetermined zone range from all terminal groups, respectively; A weight calculation step of calculating weights of predetermined service categories based on the check-in record information; An evaluation similarity degree calculating step of extracting an evaluation score assigned to each of the service provider information and calculating evaluation similarity information among the terminals included in the entire terminal group based on the evaluation score and the weight; An estimated predicted value calculation step of calculating an estimated predicted value of the service provider within the zone based on the evaluation score and the evaluation similarity information; A distance value calculation step of calculating a distance value between the position information of the specific terminal among the all terminal groups within the zone range and the position information of the recommended service provider information extracted according to the estimated predicted value; And a recommender company extracting step of generating place recommendation information based on the estimated estimated value and the distance value.

According to another aspect of the present invention, it is possible to calculate the weight for each category of the service provider for the communication terminal based on the check-in record of the communication terminal, and to calculate the weight of the service provider having the largest weight among the service providers existing within the predetermined zone range The distance between the current position of the communication terminal and the position of the service provider having the estimated estimated value equal to or greater than the reference value is calculated, And provides the information on the service provider to the communication terminal.

As described above, according to the present embodiment, the user has the effect of being able to receive the weight information given to the service provider classified according to the category based on the check-in record of the terminal, from the place-based service apparatus.

According to the present embodiment, the user has the effect of being able to receive the evaluation prediction score for the service provider of the category from the location-based service device according to the evaluation score of other terminal users who have given a high weight to the same category.

According to the present embodiment, the user has the effect of being able to receive the service provider located at the closest distance from the location-based service device based on the evaluation prediction score of the service provider of the category and the user's current location.

1 is a block diagram schematically illustrating a service provider recommendation system using a location-based SNS according to an embodiment of the present invention.
2 is a block diagram schematically showing a configuration of a location-based service apparatus according to the present embodiment.
3 is a diagram illustrating a method of obtaining a weight for each category of a service provider.
4 is a diagram illustrating a method for obtaining a distance between a current location of a user U and a recommended service provider.
5 is a flowchart illustrating a service provider recommendation system using a location-based SNS according to an embodiment of the present invention.
6 is a diagram illustrating a result of assigning a weight to each restaurant category for each user.
7 is a diagram showing the similarities between the user U, the user 2, the user 3, and the user 4.
FIG. 8 is a diagram showing how the user U has a certain degree of preference for each cafe based on the evaluation scores of the users 2, 3 and 4 having the same weight as the weight of the user U, .
9 is a view showing a result of measuring the distance score according to the distance between the current position of the user U and the recommendation cafe.
10 is a diagram showing a recommendation place obtained by applying the ratio of the evaluation predicted value and the distance point value to the recommendation place score obtained by adding the evaluation predicted value and the distance score value.

Hereinafter, the present embodiment will be described in detail with reference to the accompanying drawings. It should be noted that, in adding reference numerals to the constituent elements of the drawings, the same constituent elements are denoted by the same reference numerals whenever possible, even if they are shown in different drawings. In the following description of the present invention, a detailed description of known functions and configurations incorporated herein will be omitted when it may make the subject matter of the present invention rather unclear.

In describing the components of the present invention, terms such as first, second, A, B, (a), and (b) may be used. These terms are intended to distinguish the constituent elements from other constituent elements, and the terms do not limit the nature, order or order of the constituent elements. When a component is described as being "connected", "coupled", or "connected" to another component, the component may be directly connected to or connected to the other component, It should be understood that an element may be "connected," "coupled," or "connected."

1 is a block diagram schematically illustrating a service provider recommendation system using a location-based SNS according to an embodiment of the present invention.

The service provider recommendation system 100 using the location-based SNS according to the present embodiment includes a terminal 110, a communication network 120, a location-based service device 130, and a location-based application 112.

The terminal 110 of the service provider recommendation system 100 using the location-based SNS transmits a service request message to the location-based service apparatus 130 in order to receive the service provider recommendation service using the location-based SNS, And receives a corresponding service response message from the location-based service device 130.

The terminal 110 is a terminal capable of transmitting and receiving various data via the communication network 120 according to a user's key operation or a voice command. The terminal 110 may be a tablet PC, a laptop, a personal computer (PC), a portable multimedia player (PMP), a portable multimedia player And may be any of various digital devices such as a PSP (PlayStation Portable), a wireless communication terminal, a smart phone, and a mobile communication terminal. Here, the application may be a program executed on an operating system such as a Mac OS or an Android OS, or downloaded from the terminal 110 or stored in the terminal 110. The terminal 110 transmits a service request message to receive the service provider recommendation service using the location-based SNS from the location-based service device 130 using the installed location-based application 112. The terminal 110 receives a service response message corresponding to the service request message transmitted using the installed location based application 112 from the location based service apparatus 130 through the communication network 120. [ The service response message received by the terminal 110 includes recommender information provided by the location-based service apparatus 130.

The location-based service device 130 implements various functions such as receiving a service request message, collecting a check-in record, calculating an evaluation similarity, calculating an estimation predicted value, calculating a distance value, extracting a recommender, and transmitting a service response message. The location based service device 130 uses a communication network 120 that supports CDMA, WCDMA, LTE, Wi-Fi, Wibro, etc. as well as various communication interfaces or protocols such as wired and wireless communication such as HTTP, FTP, TCP and UDP And receives a service request message from the terminal 110. The location-based service device 130 collects check-in records for service provider information from a plurality of terminals. The location-based service device 130 assigns weights to categories of the service provider based on the collected check-in record information. Here, the check-in record information includes at least one of name information, category information, coordinate information, place evaluation score information, and text, photograph, and moving picture information of a place checked in by the user. The location-based service device 130 calculates an evaluation similarity degree between other users having the same weight as the specific terminal user based on the place evaluation score information included in the check-in record. The location-based service device 130 calculates an estimated estimation value of a service provider existing within a predetermined zone range based on the evaluation similarity. In addition, the location-based service device 130 calculates the distance value based on the location of the service providers having a high estimated estimation value within a predetermined zone range and the current location of the user terminal 110. Here, the distance value represents the distance between the current location of the terminal and the location of each of the service providers having a high estimated value. The location-based service device 130 extracts a recommending company based on the estimated estimation value and the distance value derived from the above, and transmits it to the terminal 110 in a service response message.

Here, the location-based application 112 installed in the terminal 110 may be used to collect the check-in records described above as the function of the location-based service device 130, calculate the weight, calculate the evaluation similarity degree, calculate estimated evaluation value, . ≪ / RTI >

2 is a block diagram schematically showing a configuration of a location-based service apparatus according to the present embodiment.

Referring to FIG. 2, the location-based service device 130 may include a module for implementing check-in record collection, weight calculation, evaluation similarity degree calculation, estimated estimation value calculation, distance value calculation, and recommendation company extraction.

The terminal 110 includes a check-in record collecting unit 210, a weight calculating unit 220, an evaluation similarity calculating unit 230, an estimated predicted value calculating unit 240, a distance value calculating unit 250, ).

The check-in record collecting unit 210 collects check-in record information for a service provider within a predetermined area or area range from the terminal 110. Also, the check-in record collecting unit 210 collects the check-in record information by classifying the service providing companies by service category.

The weight calculation unit 220 receives the check-in record information and calculates a weight for each service provider classified according to the service category based on the check-in record information. The weight calculation unit 220 calculates a weight by Equation (1). The user V is a user of the first terminal and a user U is a user of the second terminal, which will be described below, including Equation (1). User 2, User 3, and User 4 are users who use any one of a plurality of terminal devices.

W _vk denotes the weight of category k at the service provider indicated in the check-in record information of user V. [ k = 1, 2, 3, ... , m represents the number of categories of service providers checked in by user V, uf _vk means the number of occurrences of the category k indicated in the check-in record information of the user V. [ The higher the number of occurrences of the category k, the higher the weight.

3 is a diagram illustrating a method of obtaining a weight for each category of a service provider.

FIG. 3 shows the check-in record 320 in the zone area 310 set in the terminal 110. FIG. The check-in record 320 shown in FIG. 3 is a record in which the user V checks in the zone range 310 set in the terminal 110. The check-in record 320 containing the record of the check-in by the user V includes the service provider's category and the service provider's order of visiting the user. The service provider represents, for example, a restaurant. [Table 1] shows category names of restaurants.

Small category of restaurants Aa Limited diet Ai Chicken Ag Shabu Ab pork belly Aj Giblet Ar bakery Ac Pork barbecue Ak Pork feet As hamburger Name Bulgogi Al Steak house Horse Pizza Ae Flower sirloin Am Seafood Au Curry Af Smoked duck An Japanese food Av Fusion restaurant Ag roasted chicken soup Ao Chinese food Aw Italian Restaurant Ah Samgyetang Ap Curry Ax French restaurant

[Table 1] shows that Aa, Ab, ... , Aw, Ax, etc. are assigned. Here, among the check-in records 320 checked by the user V, the small category of the restaurant indicates chicken roasted chicken as Ag, and the visiting order of restaurants is ninth. In the check-in record 330 of the user V, it can be seen that the user V checked in the restaurant twice, which provides the chicken fry tang, out of the restaurants classified according to the category. In the check-in record 330 of the user V, it is possible to determine how many times the user V visits the restaurant by category, and to use the information to calculate the weight for each category visited by each user.

The evaluation similarity calculating unit 230 measures the degree of similarity between the users based on the evaluation score measured by the service provider for each user within the set range. The evaluation similarity calculating unit 230 obtains the evaluation similarity by the following equation (2).

W _uv represents the degree of similarity between user U and user V. In Equation (2), the degree of similarity between the user U and the user V is limited, but the similarity between all users can be measured. i represents one of m service providers. S _ui represents the evaluation score that user U evaluated for the first service provider (i). S _vi represents the evaluation score of the user V evaluated for the first service provider (i). S _u represents the average score of the evaluation scores that the user U has evaluated for the service provider in the set area range. S _v represents the average score of the rating of the service provider that the user V has evaluated for the service provider in the set coverage area. σ _u represents the standard deviation of the user rated U's rating for service providers in the defined area range. σ _v represents the standard deviation of the average score that the user V has assessed for the service provider in the set coverage area. It can be understood that the similarity between user U and user V is higher as W _{uv, which} is similarity between user U and user V, has a value close to zero.

The estimated estimated value calculation unit 240 calculates an estimated estimated value by predicting how much a certain user will have a preference degree with respect to the service provider within the set range. Here, the estimated estimation value may be an evaluation score of a specific user based on an evaluation score of the specific user of the specific service provider, an average evaluation score of the specific service provider within the range of the specific user, . That is, evaluation scores of other users having the same weight for the service provider category are used. A method of obtaining the predicted value by the estimated predicted value calculation unit 240 is shown in the following equation (3).

And P _uj represents the estimated estimation value of the user U for the second service provider (j). j denotes one of m recommended service providers. S _u represents the average score of the evaluation scores that the user U has evaluated for the service provider in the set area range. S _v represents the average score of the rating of the service provider that the user V has evaluated for the service provider in the set coverage area. S _vj represents the evaluation score that user V has evaluated for the second service provider (j). W _uv represents the degree of similarity between user U and user V. The predicted evaluation value P _uj of the user U to the second service provider j is the average evaluation score of the user U, the evaluation score of the user V on the second service provider j, the similarity between the user U and the user V A high evaluation prediction value is obtained.

The distance value calculation unit 250 calculates a distance between a position of a specific user and a recommended service provider that receives a high estimated value based on the estimated estimated value within the set range. Here, the recommendation service provider is selected on the basis of the degree of similarity between users and the score of users. If similar users can score as high as 0, 1, 2, 3, 4, 5 for example, a service provider rated 4 or 5 can be considered a referral service provider. The distance between a specific user's location and a referral service provider can be obtained based on the Euclidian distance method. Here, based on the Euclidian distance method, the distance between a specific user's location and the recommended service provider is obtained, but it can be obtained by other methods. A method of obtaining the distance between a specific user's location and a recommended service provider using the Euclidian distance method is shown in Equation (4).

L _uj represents the result of calculating the distance between the user U's current location and the recommended service provider using the Euclidian distance method. CL _u denotes the coordinates of the user U's current position. PL _uj is the coordinates of the referral service provider.

4 is a diagram illustrating a method for obtaining a distance between a current location of a user U and a recommended service provider.

4 shows the current location coordinates of the user U and the location coordinates of the recommended service providers. The distance value calculation unit 250 can calculate the distance between the current location of the user U based on the coordinates 410 of the recommended service provider a and the coordinates 420 of the recommended service provider b. Obtain the distance between the user U's current location and the recommended service provider a, obtain the distance between the current user's current location and the recommended service provider b, and then take a reciprocal to determine if a larger value occurs. If the reciprocal is taken and a larger value appears, it can be seen as a recommendation service provider closer to the user U's current location.

The recommended vendor supplier 250 selects a recommender suitable for the user based on the weight information, the similarity information, the predicted value information, and the distance information, and provides the selected recommender to the user. A method of selecting a recommended place is as shown in Equation (5).

V _u is a location recommendation value of the user U derived from the service provider recommendation system 100 using the location-based SNS. To obtain the recommendation value of the user U, obtain the recommended service provider extracted according to the predicted value of the user U calculated from the similarity degree between the other users. (L _uj ) between the current position CL _u of the user U and the position PL _uj of the recommended service provider, and obtains the value when the log is taken. Also, when comparing with the distance calculation value according to the position of other recommended service provider, a service provider having the highest value is obtained. Here, it can be seen that the recommendation service provider having the largest distance calculation value is located nearest to the current position CL _u of the user U. That is, V _u may be provided to user U as a recommendation service provider, which is a recommendation service provider that is located nearer to the other recommendation service providers than the other recommendation service providers.

5 is a flowchart illustrating a service provider recommendation system using a location-based SNS according to an embodiment of the present invention.

The check-in record record collecting unit 210 checks whether there is a check-in record for a service provider existing within the zone range set from the place-based terminal 110 (S510).

As a result of checking in step S510, if there is a check-in record, the weight calculating unit 220 determines whether there is weight information that is weighted for each service provider classified according to the service category based on check-in record information (S520).

As a result of checking in step S520, if there is weight information, a user having a similar weight based on the similarity calculated based on the evaluation score measured for the service provider within the zone range set for each user in the similarity calculating unit 220 (S530).

As a result of checking in step S530, if there is a user having a similar weight, the estimated estimated value calculating unit 240 determines whether there is an evaluation score that is evaluated for a service provider existing within a zone range in which users having similar weights are set S540). Here, the service providers evaluated by users with similar weights are selected based on the degree of similarity between users and the scores of users. If users with similar weights can score as high as 0, 1, 2, 3, 4, 5 for example, a service provider rated 4 or 5 can be considered a service provider.

As a result of checking in step S540, if there is a service provider evaluated by similar users, the recommender company extractor 260 determines the position of the recommender service provider having a high score based on the current position of the user, (S550). ≪ tb > < / TABLE > When a recommended service provider is provided, the location based social network service (LBSNS) based service provider recommendation service is terminated using location based SNS. If there is no check-in record in step S510, if there is no weight information in step S520, if there is no user having a similar weight in step S530, and if there is a service provider evaluated by similar users in step S540, Terminate service provider recommendation service based on LBSNS (Location Based Social Network Service).

Although it is described in Fig. 5 that steps S510 to S550 are sequentially executed, the present invention is not limited thereto.

The programmed source code of [Table 2] represents the process of FIG.

FIG. 6 to FIG. 10 are diagrams illustrating a process and a result of a service provider recommendation system using a location-based SNS that recommends a restaurant when a service provider is a restaurant.

6 is a diagram illustrating a result of assigning a weight to each restaurant category for each user.

6, in which the categories of the restaurants are divided according to the weight of the users, the service category is the restaurant category name and the category appearance frequency is the number of occurrences of the category among the restaurants checked in by the user. The most abundant category of user U is cafe (Au) # 73. User 2, user 3, and user 4 also have the largest number of cafes (Au) as user U. The restaurant category in which the user U is judged to have the highest weight among the restaurant categories can be regarded as the cafe having the highest occurrence frequency.

7 is a diagram showing the similarities between the user U, the user 2, the user 3, and the user 4.

 The user U, the user 2, the user 3, and the user 4 are the users having the highest weight for the cafe as shown in FIG. The similarity 710 between users can be obtained according to the formula definition of [Equation 2] described above. From the similarity level (710), the user with the highest similarity to the user U can be regarded as the user 2 whose similarity is -0.265580337. In addition, the user with the highest similarity to user 2 can be regarded as user 4 whose similarity is -0.036749697, while the user with the highest similarity with user 3 can be regarded as user 4 with similarity 0.405469572. The degree of similarity is high when the degree of similarity is close to zero.

FIG. 8 is a diagram showing how the user U has a certain degree of preference for each cafe based on the evaluation scores of the users 2, 3 and 4 having the same weight as the weight of the user U, .

In the recommendation place 810 of the user 2, the highest value 4.940859042 was obtained as the evaluation value of 'C cafe', and the recommendation place 820 of the user 3 obtained the highest value 4.879674101 as the evaluation value of 'F cafe' (830), it can be seen that 'M Cafe' got the highest value of 4.855078248 as the evaluation predicted value.

9 is a view showing a result of measuring the distance score according to the distance between the current position of the user U and the recommendation cafe.

The distance score value calculated in Fig. 9 is calculated using the Euclidian distance formula in the present invention, but can also be calculated in other ways. According to the distance score value, the cafe located at the closest distance to the user U is 'F Cafe'.

10 is a diagram showing a recommendation place obtained by applying the ratio of the evaluation predicted value and the distance point value to the recommendation place score obtained by adding the evaluation predicted value and the distance score value.

The recommendation place score is the sum of evaluation evaluation value and distance score value. According to the recommended place score, the first place is 'F Cafe', the second place is 'A Cafe', the third place is 'G Cafe', the fourth place is 'H Cafe', the fifth place is 'B Cafe' Cafe 'and 7th place' I cafe ', but when the ratio of the estimated value to the recommended place score is 0.8 and the distance score is 0.2,' H Cafe ', which was the 4th place, Can be confirmed. In addition, when the ratio of the predicted value to the recommendation place score is 0.2 and the distance score value is 0.8, it is possible to confirm that the 'C-cafe', which was the sixth place,

The foregoing description is merely illustrative of the technical idea of the present embodiment, and various modifications and changes may be made to those skilled in the art without departing from the essential characteristics of the embodiments. Therefore, the present embodiments are to be construed as illustrative rather than restrictive, and the scope of the technical idea of the present embodiment is not limited by these embodiments. The scope of protection of the present embodiment should be construed according to the following claims, and all technical ideas within the scope of equivalents thereof should be construed as being included in the scope of the present invention.

110: terminal 120: network
130: Location Based Service Device 140: Location Based Application
210: check-in record collection unit 220: weight calculation unit
230: evaluation similarity degree calculating unit 240: evaluation value calculating unit
250: distance value calculation unit 260: recommended vendor extraction unit

Claims (13)

A check-in record collecting unit for collecting check-in record information on service provider information existing within a predetermined zone range from a plurality of terminals, respectively;
A weight calculation unit for calculating a weight for each service category based on the check-in record information;
An evaluation similarity degree calculating unit that extracts an evaluation score assigned to each of the service provider information and calculates an evaluation similarity degree among the terminals included in the plurality of terminals based on the evaluation score and the weight;
An evaluation prediction value calculation unit for calculating an evaluation prediction value for the service provider information within the zone range based on the evaluation score and the evaluation similarity;
A distance value calculation unit for calculating a distance value between the location information of the specific terminal among the plurality of terminals and the location information of the recommended service provider information extracted according to the estimated estimation value within the zone range; And
A recommendation company extracting unit for generating the place recommendation information based on the evaluation estimated value and the distance point value obtained by logarithm to the inverse number of the distance value,
Based service provider recommendation service device. The method according to claim 1,
The weight calculation unit may calculate,
(I) of the plurality of terminals checked in by the first terminal and the number of appearance frequencies (uf _vk ) of the specific category (k) indicated in the check-in record information of the first terminal for each service category checked in by the first terminal ) Is used to calculate the weight value. The method according to claim 1,
The evaluation similarity degree calculating unit may calculate,
Evaluation The average score (S _u of the second terminal to the service provider information of the first service provider of the second terminal of the plurality of terminals for (i) Score (S _uj) and the service provider information, ), The evaluation similarity degree is calculated by the evaluation score (S _vi ) of the first terminal with respect to the first service provider (i) and the evaluation average score (S _v ) of the first terminal with respect to the service provider information Based service provider recommendation service device. The method of claim 3,
The evaluation similarity degree calculating unit may calculate,
(S _uj ) of the second terminal and the evaluation average score (S _u ) of the second terminal, the difference between the evaluation score (S _vi ) of the first terminal and the evaluation average score _v) evaluation average score (S _v) a standard deviation (σ _v a) of the product of the difference between the value of the first terminal, the result of multiplying the standard deviation (σ _u) the evaluation average score (S _u) of the second terminal Wherein the rating similarity calculating unit calculates the evaluation similarity by using the rating similarity. The method according to claim 1,
Wherein the evaluation-
Evaluation The average score (S _u) of the second terminals of the plurality of terminals, Score (S _vj) of the first terminal to the second service provider (j) of the service provider information, and the evaluation of the first terminal The average score (S _v ), and the evaluation similarity. 6. The method of claim 5,
Wherein the evaluation-
(W _uv ) by multiplying the difference between the evaluation score (S _vj ) of the first terminal and the evaluation average score (S _v ) of the first terminal by the evaluation similarity degree (W _uv ) And calculates the estimated estimated value as a result of summing the average evaluation scores (S _u ) of the second terminals. The method according to claim 1,
The distance value calculation unit calculates,
_Wherein the distance value is calculated using current location information (CL _u ) of the second terminal among the plurality of terminals and location information (PL _uj ) difference information of service provider information existing within the zone range Based service provider recommendation service device. delete The method according to claim 1,
The recommender-
If it is determined that the distance point value is the highest value among the plurality of location information of the service provider information existing in the area range, it is determined that the distance is the closest distance to the current location information (CL _u ) of the second terminal among the plurality of terminals A feature-based location-based service provider recommendation service device. The method according to claim 1,
The recommender-
Selecting the service provider information in descending order of the estimated predictive value according to the estimated predictive value and generating the recommendation information of the place in ascending order of the distance value calculated by the distance value calculating unit from the selected service provider information A feature-based location-based service provider recommendation service device. A check-in record collection process for collecting check-in record information on service provider information existing within a predetermined zone range from a plurality of terminals, respectively;
A weight calculation step of calculating weights of predetermined service categories based on the check-in record information;
An evaluation similarity degree calculating step of extracting an evaluation score assigned to each of the service provider information, and calculating evaluation similarity information among the terminals included in the plurality of terminals based on the evaluation score and the weight;
An estimated predicted value calculating step of calculating an estimated predicted value for the service provider information within the zone based on the evaluation score and the evaluation similarity information;
A distance value calculating step of calculating a distance value between the position information of the specific terminal among the terminal groups within the range of the terminal and the position information of the recommended service provider information extracted according to the estimated estimation value; And
A recommendation company extracting process of generating place recommendation information based on the evaluation estimated value and the distance score value obtained by logarithm to the inverse number of the distance value
Based service provider recommendation method. Calculating a weight for each category of the service provider information for the communication terminal based on the check-in record of the communication terminal,
The estimated predicted value is calculated using the score of the other communication terminal with respect to the service provider information corresponding to the category having the largest weight among the service provider information existing within the predetermined zone range,
Calculating a distance value between a current location of the communication terminal and a location of a service provider information having an estimated estimation value equal to or greater than a reference value and providing the service provider information having the distance value less than or equal to a reference value to the communication terminal, And the location recommendation information is generated on the basis of the distance score value obtained by logarithm of the inverse number of the location-based service provider. 13. The method of claim 12,
And the other communication terminal means a terminal having the same weight as the communication terminal.

Images