JP2023072524A - Recommendation device, recommendation method and recommendation program - Google Patents

Abstract

To recommend a restaurant and a companion that match a person's hobbies and tastes to the person who pursues a fresh drinking party.SOLUTION: A recommendation device 10 creates user profile information including a result of a user's character analysis for a restaurant, and stores it in a storage unit 12. Then, when the recommendation device 10 receives a matching request from the user for a restaurant or companion, it outputs other users or restaurants whose matching rate with the user who requests matching is equal to or larger than a predetermined threshold value, based on the profile information and restaurant information stored in the storage unit 12.SELECTED DRAWING: Figure 2

Description

The present invention relates to a recommendation device, a recommendation method, and a recommendation program for recommending restaurants and companions to users.

People who like drinking parties may be wondering which restaurant to go to and who to go with. Here, it is conceivable that the person chooses a store that he or she often visits, but there is a possibility that the food and the like are fixed and lack freshness. Also, it is conceivable to select a shop with a high popularity ranking, but there is a possibility that it does not suit the taste of the person. Furthermore, if the scope of the drinking party community is fixed, it may not be fresh because people will always go out drinking with the same members.

JP 2014-140118 A

However, conventionally, no technology has been proposed for recommending a restaurant or a companion that matches the person's tastes and preferences to a person who is pursuing a fresh drinking party. Accordingly, an object of the present invention is to recommend restaurants and companions that suit the person's tastes and preferences to a person who is pursuing a fresh drinking party.

In order to solve the above-described problems, the present invention provides a profile information creation unit that creates profile information including the result of character analysis of the user for each restaurant and stores it in a storage unit; an input reception unit that receives a request for matching of a store or matching of a companion when using the restaurant; a user who requests the matching based on profile information and restaurant information stored in the storage unit; A matching unit that calculates a match rate with other users or a match rate with each restaurant, and an output processing unit that outputs other users or restaurants whose match rate is equal to or higher than a predetermined threshold. do.

According to the present invention, it is possible to recommend shops and companions that suit the person's tastes and tastes to a person who is pursuing a fresh drinking party.

FIG. 1 is a diagram for explaining an outline of the operation of the recommendation device. FIG. 2 is a diagram illustrating a configuration example of a recommendation device. FIG. 3 is a diagram showing an example of personal data. FIG. 4 is a diagram showing an example of creating profile information. FIG. 5 is a diagram showing an example of information output from the recommendation device. FIG. 6 is a flowchart illustrating an example of a processing procedure of the recommendation device. FIG. 7 is a diagram illustrating a configuration example of a computer that executes a recommendation program.

EMBODIMENT OF THE INVENTION Hereinafter, the form (embodiment) for implementing this invention is demonstrated, referring drawings. The invention is not limited to the embodiments described below.

[overview]
First, an overview of the operation of the recommendation device of this embodiment will be described with reference to FIG. For example, the recommendation device receives input of personal data (for example, the user's name, favorite store, comments about the store, etc.) from the user. Note that the recommendation device stores directly usable data in the database (storage unit) out of the personal data input by the user. On the other hand, the recommendation device performs text-based emotion analysis on data requiring processing (for example, comments about a store), and stores the result of the emotion analysis in the database as well. As a result, the user's name, favorite store, emotion analysis result, etc. are stored in the database.

After that, the recommendation device receives an input of a target (for example, store, person) to be searched from the user ((1)). For example, the recommendation device receives a request for matching of a store or a person (a companion to the store) from the user. The recommendation device also accepts an input of a tag indicating a condition used for matching (for example, the genre of the store that the user wants to search for), if necessary ((2)).

Then, the recommendation device matches the information input by the user with the data acquired from the database, and returns the matching result (that is, the store or the person whose tastes and tastes are similar to those of the user) to the user. In this way, the recommendation device also uses the results of emotion analysis of the user's comments on the store to match the store and the person. As a result, the recommendation device can recommend a store or person that matches the user's tastes and preferences, taking into account the user's personality and the like.

[Configuration example]
Next, a configuration example of the recommendation device will be described with reference to FIG. The recommendation device 10 includes a communication processing unit 11 , a storage unit 12 and a control unit 13 .

The communication processing unit 11 communicates with other devices wirelessly or by wire. The communication processing unit 11 is a communication interface that transmits and receives various information to and from other devices connected via a network or the like. The communication processing unit 11 is implemented by a NIC (Network Interface Card) or the like, and communicates between another device (for example, a user's terminal device) and the control unit 13 via an electric communication line such as a LAN (Local Area Network) or the Internet. communication between

For example, the communication processing unit 11 receives the user's personal data and a matching request from the user's terminal device via the network, and transmits the matching result to the user's terminal device.

The storage unit 12 is a storage device such as a HDD (Hard Disk Drive), an SSD (Solid State Drive), an optical disc, or the like. Note that the storage unit 12 may be a semiconductor memory such as a RAM (Random Access Memory) or a flash memory in which data can be rewritten. The storage unit 12 stores an OS (Operating System) and various programs executed by the recommendation device 10 . Furthermore, the storage unit 12 stores various information used in executing the program.

The storage unit 12 includes, for example, a profile information storage unit 121 and a restaurant information storage unit 122 . The profile information storage unit 121 stores user profile information created by the control unit 13 . The restaurant information storage unit 122 stores information on restaurants to be matched. The restaurant information storage unit 122 may be installed in the storage unit 12 of the recommendation device 10 or may be installed in a device external to the recommendation device 10 .

The control unit 13 controls the entire recommendation device 10 . The control unit 13 is, for example, an electronic circuit such as a CPU (Central Processing Unit) or an MPU (Micro Processing Unit), or an integrated circuit such as an ASIC (Application Specific Integrated Circuit) or an FPGA (Field Programmable Gate Array). The control unit 13 also has an internal memory for storing programs defining various processing procedures and control data, and executes each processing using the internal memory. Further, the control unit 13 functions as various processing units by running various programs.

The control unit 13 includes a profile information creation unit 131 , a personality analysis unit 132 , an input reception unit 133 , a matching unit 134 and an output processing unit 135 .

When the profile information creating unit 131 receives input of personal data (see, for example, FIG. 3) from the user, the profile information creating unit 131 creates the user's profile information using the personal data. Personal data includes, for example, the user's name, favorite restaurant (favorite restaurant), favorite food (food preferences), tags, comments on the restaurant, user attribute information (for example, user's hobby, career, gender, occupation, etc.). etc.) etc.

The above tags are information indicating matching conditions, for example, information indicating attributes of shops or users (for example, women only, students only, etc.) to be matched. Note that the tag may be information indicating a condition to be excluded from matching. By using tags, user-desired conditions can be reflected in the matching of shops and people.

Also, the comments on the store are, for example, comments on the user's favorite store, and if there is a store that did not give a good impression, it may include the reason and the comment.

As shown in FIG. 4, for example, the profile information creation unit 131 creates profile information by using simple data such as favorite stores and favorite foods among the user's personal data as they are. With regard to comments on , the profile information is created using the result of the user's personality analysis by the personality analysis unit 132 . The created profile information is stored in profile information storage section 121 of storage section 12 .

It should be noted that each user's profile information can be browsed by other users, but among the information included in the profile information, for example, the content described in tags, comments on shops that did not give a good impression, etc. Other users may be restricted from viewing information that should not be seen by other users.

Returning to the description of FIG. The character analysis unit 132 analyzes the character of the person who wrote the text by text analysis. For example, the personality analysis unit 132 analyzes the user's personality by text analysis of the user's comments on the store. Here, when the personality analysis unit 132 analyzes the user's personality, the personality analysis unit 132 also considers, for example, the result of the emotion analysis of the user.

Personality analysis is performed, for example, by text analysis of text data of user's comments. and quantification from a plurality of viewpoints such as extroversion, curiosity, thinking ability, and emotionality of the user's personality (see "Results of Personality Analysis" shown in FIG. 4). Personality analysis is performed, for example, using techniques described in (1) to (3) below. Character analysis may be performed by a so-called personality test.

(1) How to create training data and analyze the user's personality with a model trained with the training data https://www.ai-gakkai.or.jp/jsai2016/webprogram/2016/pdf/278.pdf
(2) Japanese evaluative polarity dictionary oseti
A tool that scores whether Japanese words are positive or negative. You can use this tool to analyze whether user comments are passive or positive.
(3) Text sentiment analysis ML-Ask
A method of estimating emotion, intensity of emotion, negative/positive classification, etc. by text analysis.

Note that, for example, the personality analysis unit 132 uses, among the user's comments, not only the comments about the favorite store (the store with a good impression) but also the comments about the store with the unfavorable impression of the user. Conduct sentiment analysis.

As described above, the personality analysis unit 132 analyzes the user's emotion using comments about the restaurant that did not give a good impression. According to the model obtained by the method, a person who makes a lot of aggressive comments (eg, angry, disgusted, negative comments) can be classified as aggressive, emotional, and the like. Thereby, the character analysis unit 132 can more accurately identify the character and personality of the user.

The input accepting unit 133 accepts a matching request from the user for a shop or companion. Note that the request for matching may include, for example, tags indicating conditions used for matching (for example, limited to students, limited to members of society, limited to types of food).

Upon receiving a matching request from a user, the matching unit 134 refers to the profile information and restaurant information in the storage unit 12 to calculate the matching rate between the user requesting matching and other users or shops. .

For example, when the matching unit 134 calculates the matching rate between the user requesting matching and other users, information described in each user's profile information (for example, favorite store, favorite food, tag, user (attribute information of users, results of personality analysis of users, etc.) are similar to each other.

For example, the matching unit 134 determines the degree of similarity between users for each item included in the user's profile information (for example, favorite store, favorite food, tag, user's attribute information, user's personality analysis result, etc.). is described, the match rate between users is calculated.

For example, among the items included in the profile information, the matching unit 134 collects information described in items such as attribute information and tags using a similar word dictionary prepared in advance, and then It is determined whether or not the same information is described between users. Then, the matching unit 134 may calculate the matching rate between the users based on the ratio of the number of items in which the same information is described among the users.

Also, the matching unit 134 may determine the degree of similarity of the information described in the profile information of each user, for example, using machine learning or AI. Furthermore, the matching unit 134 may determine the degree of similarity of the information described in the profile information of each user by combining machine learning or AI with each of the methods described above.

Among the items included in the profile information, the matching unit 134 may, for example, obtain numerical information indicating the result of the user's personality analysis (see, for example, FIG. 4), or , the information obtained by inverting the above numerical value is used to calculate the matching rate between users. In this way, the matching unit 134 uses the information obtained by inverting the numerical value indicating the result of the personality analysis of the user to calculate the matching rate between the users. It is possible to calculate the match rate by taking into account the case where there is a match in a complementary relationship rather than in a complementary relationship.

Also, the matching unit 134 may calculate the degree of similarity between users by using the information of each item included in the user's profile information as a feature amount. For example, a model or rule for calculating the degree of similarity between users is prepared based on the feature amount of each item of information included in the user's profile information. The degree of similarity between users may be calculated as a match rate between users.

Further, for example, when the matching unit 134 calculates the matching rate between the user requesting matching and the restaurant, the information described in the profile information of the user requesting matching and the result of text analysis of restaurant information The matching rate is calculated according to the extent to which .

For example, the matching unit 134 uses the information of each item included in the user's profile information and the result of text analysis of the restaurant information in advance to create a model for calculating the degree of matching between the user and the restaurant. A rule is prepared, and the match rate between the user and the store is calculated using the above model and rule.

Note that the matching unit 134 may calculate either (1) the matching rate between the user requesting matching and other users, or (2) the matching rate between the user requesting matching and the store. and both can be calculated.

The output processing unit 135 outputs users and shops whose match rate calculated by the matching unit 134 is equal to or higher than a predetermined threshold. For example, the output processing unit 135 outputs information on users and stores (recommended users and stores) whose match rate is equal to or higher than a predetermined threshold (see FIG. 5). When outputting a recommended user or store, the output processing unit 135 may also output information related to the user or store (for example, a photo provided by the user or store).

Further, after the output processing unit 135 outputs users and stores (recommended users and stores) whose match rate is equal to or higher than a predetermined threshold value, addition of tags from the user may be accepted.

In this case, the matching unit 134 narrows down the matching results using the conditions indicated by the tags added by the user (for example, restricted to students, restricted to members of society, types of food, etc.). Then, the output processing unit 135 outputs the results of the narrowed-down matching (recommended user and store list).

According to such a recommendation device 10, it is possible to recommend a user or a store that matches the user's tastes and preferences, taking into consideration the user's personality.

Note that the recommendation device 10 may change the threshold value of the match rate based on an instruction input by the user who requested matching.

For example, if the user requesting matching wants to include in the range of recommendation users and stores that are slightly different from his/her tastes and preferences (=users and stores that are newer to the user), the recommendation device 10 may set the matching rate An instruction is input to lower the threshold. Then, the recommendation device 10 uses a relatively low match rate threshold value to output users and stores based on the instruction input. As a result, the recommendation device 10 can recommend users and shops with a relatively low match rate. As a result, the user can get to know users and shops that are newer to him/herself.

In addition, when outputting users and shops using a relatively low match rate threshold, the recommendation device 10 places users and shops with a lower match rate higher on the screen among users and shops with a match rate equal to or higher than the above threshold. may be displayed. By doing so, it becomes easier for the user to check users and shops that are newer to him on the screen.

Also, when the user requesting matching wishes to be recommended a user or a store that matches his tastes and preferences, he/she inputs an instruction to the recommendation device 10 to increase the threshold of the matching rate. Then, the recommendation device 10 uses a relatively high matching rate threshold value to output users and stores based on the instruction input. As a result, the recommendation device 10 can recommend users and shops with a relatively high match rate. As a result, the user can know users and shops that match his tastes and tastes.

[Example of processing procedure]
Next, an example of the processing procedure of the recommendation device 10 will be described with reference to FIG. For example, the recommendation device 10 receives input of the user's personal data via the communication processing unit 11 (S1). Of the information included in the input personal data of the user, the personality analysis unit 132 analyzes the user's personality using the comment about the store (S2).

After that, the profile information creating unit 131 creates user profile information using the result of the personality analysis performed in S2 (S3). For example, the profile information creation unit 131 uses the personal data of the user input in S1 as they are, such as favorite stores and favorite foods, and uses the personality analysis results obtained in S2 for comments on stores. Create your profile information.

Then, the profile information creating section 131 stores the profile information created in S3 in the profile information storage section 121 of the storage section 12 (S4).

After that, when the input reception unit 133 receives an input of a request for matching from the user (S5), the matching unit 134 refers to the profile information and the restaurant information in the storage unit 12, and A match rate with other users and each shop is calculated (S6). Then, the output processing unit 135 outputs other users and stores whose matching rates are equal to or higher than a predetermined threshold (S7).

By executing the above process, the recommendation device 10 can output users and stores (recommended users and stores) that match the user's tastes and preferences, taking into consideration the user's personality and the like.

[others]
In addition, when the matching unit 134 performs matching of users and shops, for example, the matching may be performed in consideration of each user's location information obtained by GPS or the like, the location of the shop, and the like. Further, in this case, when the user inputs a matching request to the recommendation device 10, the user may specify a geographical range or the like as a matching condition. By doing so, the matching unit 134 can perform matching considering the location of the user and the store.

In addition, if the personal data of the user includes information about the user who did not give a good impression, disliked personality, and disliked ingredients, the matching unit 134 may perform matching while considering the above information. By doing so, the matching unit 134 can output stores and users more suited to the tastes and preferences of the user.

Further, among the processes described in the above embodiments, all or part of the processes described as being performed automatically can be performed manually, or the processes described as being performed manually can be performed manually. can also be performed automatically by known methods. In addition, information including processing procedures, specific names, various data and parameters shown in the above documents and drawings can be arbitrarily changed unless otherwise specified. For example, the various information shown in each drawing is not limited to the illustrated information.

Also, each component of each device illustrated is functionally conceptual, and does not necessarily need to be physically configured as illustrated. In other words, the specific form of distribution and integration of each device is not limited to the one shown in the figure, and all or part of them can be functionally or physically distributed and integrated in arbitrary units according to various loads and usage conditions. Can be integrated and configured.

Also, the above-described embodiments and modifications can be appropriately combined within a range that does not contradict the processing contents. As described above, some of the embodiments of the present application have been described in detail based on the drawings. It is possible to carry out the invention in other forms with modifications.

[program]
Moreover, it can be implemented by installing a program for realizing the functions of the recommendation device 10 described in the above embodiment in a desired information processing device (computer). For example, the information processing device can function as the recommendation device 10 by causing the information processing device to execute the program provided as package software or online software. The information processing apparatus referred to here includes desktop or notebook personal computers, rack-mounted server computers, and the like. In addition, information processing devices include smart phones, mobile communication terminals such as mobile phones and PHSs (Personal Handyphone Systems), and PDAs (Personal Digital Assistants). Alternatively, the recommendation device 10 may be implemented in a cloud server.

An example of a computer that executes the above program (recommended program) will be described with reference to FIG. As shown in FIG. 7, computer 1000 includes memory 1010, CPU 1020, hard disk drive interface 1030, disk drive interface 1040, serial port interface 1050, video adapter 1060, and network interface 1070, for example. These units are connected by a bus 1080 .

The memory 1010 includes a ROM (Read Only Memory) 1011 and a RAM (Random Access Memory) 1012 . The ROM 1011 stores a boot program such as BIOS (Basic Input Output System). Hard disk drive interface 1030 is connected to hard disk drive 1090 . A disk drive interface 1040 is connected to the disk drive 1100 . A removable storage medium such as a magnetic disk or an optical disk is inserted into the disk drive 1100, for example. A mouse 1110 and a keyboard 1120 are connected to the serial port interface 1050, for example. For example, a display 1130 is connected to the video adapter 1060 .

Here, as shown in FIG. 7, the hard disk drive 1090 stores an OS 1091, application programs 1092, program modules 1093 and program data 1094, for example. Various data and information described in the above embodiments are stored in the hard disk drive 1090 and the memory 1010, for example.

Then, CPU 1020 reads out program module 1093 and program data 1094 stored in hard disk drive 1090 to RAM 1012 as necessary, and executes each procedure described above.

Note that the program modules 1093 and program data 1094 related to the above-described recommended programs are not limited to being stored in the hard disk drive 1090. For example, they may be stored in a removable storage medium and read by the CPU 1020 via the disk drive 1100 or the like. may be read. Alternatively, the program module 1093 and program data 1094 related to the above program are stored in another computer connected via a network such as LAN or WAN (Wide Area Network), and are read by CPU 1020 via network interface 1070. may be

10 recommendation device 11 communication processing unit 12 storage unit 13 control unit 121 profile information storage unit 122 restaurant information storage unit 131 profile information creation unit 132 personality analysis unit 133 input reception unit 134 matching unit 135 output processing unit

Claims (9)

a profile information creation unit that creates profile information including the result of character analysis of the user for each restaurant and stores it in a storage unit;
an input reception unit that receives a request from a user for matching of a restaurant used by the user or matching of a companion when using the restaurant;
a matching unit that calculates a match rate between the user requesting the matching and other users or a match rate with each restaurant based on the profile information and restaurant information stored in the storage unit;
A recommendation device, comprising: an output processing unit that outputs other users or restaurants whose matching rate is equal to or higher than a predetermined threshold. The recommendation device according to claim 1, wherein the profile information further includes at least one of the user's food preferences and favorite restaurants. 2. The recommendation device according to claim 1, further comprising: a personality analysis unit that analyzes the personality of the user using the user's comments on each restaurant. The matching unit
Based on the profile information and the restaurant information, calculating a match rate between the user requesting the matching and other users and a match rate with each restaurant,
The output processing unit is
2. The recommendation device according to claim 1, wherein other users and restaurants whose match rates are equal to or higher than a predetermined threshold are output as matching results. The matching unit
2. The recommendation device according to claim 1, wherein a matching rate between said matching requesting user and said other user is calculated based on profile information of said matching requesting user and said other user. The matching unit
The matching rate between the user who requested the matching and each restaurant is calculated based on the profile information of the user who requested the matching and the result of text analysis of the restaurant information. 2. The recommendation device according to 1. The threshold is
The recommendation device according to any one of claims 1 to 5, wherein the recommendation device can be changed based on an instruction of the user who requested the matching. A recommendation method executed by a recommendation device,
a step of creating profile information including the result of character analysis of the user for each restaurant and storing it in a storage unit;
a step of receiving a request from a user for matching of a restaurant used by the user or matching of a companion when using the restaurant;
a step of calculating a match rate between the user requesting the matching and other users or a match rate with each restaurant based on the profile information and restaurant information stored in the storage unit;
and a step of outputting other users or restaurants whose matching rate is equal to or higher than a predetermined threshold. a step of creating profile information including the result of character analysis of the user for each restaurant and storing it in a storage unit;
a step of receiving a request from a user for matching of a restaurant used by the user or matching of a companion when using the restaurant;
a step of calculating a match rate between the user requesting the matching and other users or a match rate with each restaurant based on the profile information and restaurant information stored in the storage unit;
A recommendation program for causing a computer to execute a step of outputting other users or restaurants whose match rate is equal to or higher than a predetermined threshold.

Images