US 12,105,759 B2
Recommendation system that selects an optimal algorithm for making an appropriate content recommendation to a user
Taku Ito, Chiyoda-ku (JP); Kunihiro Aiba, Chiyoda-ku (JP); and Yuri Sasaki, Chiyoda-ku (JP)
Assigned to NTT DOCOMO, INC., Chiyoda-ku (JP)
Appl. No. 18/001,179
Filed by NTT DOCOMO, INC., Chiyoda-ku (JP)
PCT Filed Apr. 19, 2021, PCT No. PCT/JP2021/015908
§ 371(c)(1), (2) Date Dec. 8, 2022,
PCT Pub. No. WO2021/251002, PCT Pub. Date Dec. 16, 2021.
Claims priority of application No. 2020-102576 (JP), filed on Jun. 12, 2020.
Prior Publication US 2023/0229708 A1, Jul. 20, 2023
Int. Cl. G06F 16/9035 (2019.01); G06Q 30/0601 (2023.01)
CPC G06F 16/9035 (2019.01) [G06Q 30/0631 (2013.01)] 10 Claims
OG exemplary drawing
 
1. A recommendation system configured to determine a content to be recommended to a target user in a service providing contents to a plurality of users including the target user using a target algorithm that is one algorithm selected among a plurality of algorithms each configured to determine a content to be recommended to the target user and having mutually-different features as trends in determination of contents, the recommendation system comprising circuitry configured to:
automatically acquire, via a communication network, first history information that is information representing histories relating to use of contents of the plurality of users;
calculate a use maturity representing maturity of use of the service for each of the plurality of users on the basis of the first history information;
acquire second history information including target algorithm information representing the target algorithm used when contents are recommended to each of the plurality of users and recommendation success/non-success information that is information representing whether or not the contents recommended using the target algorithm has been used by each of the plurality of users;
select the target algorithm on the basis of the second history information of a user group having a use maturity corresponding to the use maturity of the target user among the plurality of users; and
automatically determine a content to be recommended to the target user using the selected target algorithm and output, via the communication network, information representing the determined content to be recommended to the target user,
wherein the circuitry acquires at least one of the number of times of use information representing the number of times of use of the service of each of a plurality of users, use period information representing a period in which each of the plurality of users used the service, and content quantity information representing the number of contents used by each of the plurality of users as the first history information, and
wherein the circuitry calculates the use maturity of each of the plurality of users on the basis of at least one of the number of times of use information, the use period information, and the content quantity information.