Content recommendation system, content recommendation method, content recommendation apparatus, program, and information storage medium

1. A content recommendation system, comprising:

one or more processors configured to:

store an attribute value of each of one or a plurality of attributes for each of a plurality of contents;

store a feature vector representing a feature of each of the plurality of contents;

obtain a preference vector representing a feature of contents preferred by a user;

apply a first selection to select a part of a given group of the plurality of contents according to a successively generated condition of the attribute value of each of the one or the plurality of attributes,

wherein in an event the condition of the attribute value includes a plurality of conditions, the one or more processors are further configured to select a first set of contents from the group based on a part of the plurality of conditions, and receive selection of a second set of contents among the first set of contents from a user apparatus based on remaining of the plurality of conditions;

apply a second selection to select a part or all of the group of the plurality of contents based on a degree of similarity between the feature vector and the preference vector of each of the contents belonging to the group of the plurality of contents; and

present the contents which are selected by applying the first selection and the second selection in an overlapping manner to the plurality of contents.

2. The content recommendation system according to claim 1 , wherein the one or more processors are configured to:

select a part of the plurality of the contents in the first selection,

select a part or all of the contents selected by the first selection in the second selection, and

present the contents selected by the second selection.

3. The content recommendation system according to claim 1 , wherein the one or more processors are further configured to successively obtain a condition for the attribute values of the one or the plurality of attributes, and successively generate another condition based on the obtained condition, and wherein the first selection is to select a part of the given group of the plurality of contents according to the successively generated other condition.

4. The content recommendation system according to claim 1 , wherein the one or more processors are configured to generate the condition based on random digits in the first selection.

5. The content recommendation system according to claim 4 , further comprising:

a memory configured to store a degree of a user preference with respect to each attribute value,

wherein the one or more processors are further configured to select attribute values of the one or the plurality of attributes in accordance with a probability based on the degree of the user preference stored in the memory, and determine the condition to be used by the first selection according to the selected attribute values.

6. The content recommendation system according to claim 5 , wherein the one or more processors are further configured to:

obtain user operation information with respect to the presented content; and

update storage contents in the memory, based on the user operation information.

7. A content recommendation method, comprising:

obtaining a preference vector representing a feature of contents preferred by a user;

storing an attribute value of each of one or a plurality of attributes for each of a plurality of contents;

applying a first selection to select a part of a given group of the plurality of contents by successively generating a condition of the attribute value of each of the one or the plurality of attributes,

wherein in an event the condition of the attribute value includes a plurality of conditions, a first set of contents is selected from the group based on a part of the plurality of conditions, and a selection of a second set of contents among the first set of contents is received from a user apparatus based on remaining of the plurality of conditions;

storing a feature vector representing a feature of each of the plurality of contents;

applying a second selection to select a part or all of the group of contents, according to a degree of similarity between the feature vector and the preference vector of each of the contents belonging to the group of the plurality of contents; and

presenting the contents which are selected by applying the first selection and the second selection in an overlapping manner to the plurality of contents.

8. A content recommendation apparatus, comprising:

one or more processors configured to:

obtain a preference vector representing a feature of contents preferred by a user;

obtain a feature vector representing a feature of each of the contents;

apply a first selection to select a part of a given group of contents according to a successively generated condition of the attribute value of each of the contents,

wherein in an event the condition of the attribute value includes a plurality of conditions, the one or more processors are further configured to select a first set of contents from the group based on a part of the plurality of conditions, and receive selection of a second set of contents among the first set of contents from a user apparatus based on remaining of the plurality of conditions;

apply a second selection to select a part or all of the group of contents based on a degree of similarity between the feature vector and the preference vector of the contents; and

generate a list of contents selected by applying the first selection and the second selection in an overlapping manner to the plurality of contents.

9. A content recommendation method, comprising:

obtaining a preference vector representing a feature of contents preferred by a user;

obtaining a feature vector representing a feature of the contents;

applying a first selection to select a part of a given group of contents according to a successively generated condition of an attribute value of attributes of each of the contents,

wherein in an event the condition of the attribute value includes a plurality of conditions, a first set of contents is selected from the group based on a part of the plurality of conditions, and a selection of a second set of contents among the first set of contents is received from a user apparatus based on remaining of the plurality of conditions;

applying a second selection to select a part or all of the group of contents according to a degree of similarity between the feature vector and the preference vector of contents belonging to the given group of the contents; and

generating a list of contents selected by applying the first selection and the second selection in an overlapping manner to the contents.

10. A non-transitory computer-readable medium including a set of computer-executable instructions, which when executed by a computer, perform operations comprising:

obtaining a preference vector representing a feature of contents preferred by a user;

obtaining a feature vector representing a feature of the contents;

applying a first selection to select a part of a given group of contents according to a successively generated condition of an attribute value of attributes of each of the contents,

wherein in an event the condition of the attribute value includes a plurality of conditions, a first set of contents is selected from the group based on a part of the plurality of conditions, and a selection of a second set of contents among the first set of contents is received from a user apparatus based on remaining of the plurality of conditions;

applying a second selection to select a part or all of the group of contents according to a degree of similarity between the feature vector and the preference vector of each of contents belonging to the group of contents; and

presenting the contents selected by applying the first selection and the second selection in an overlapping manner to the contents.

11. A non-transitory computer-readable information storage medium for storing a set of computer-executable instructions which when executed by a computer, perform operations comprising:

obtaining a preference vector representing a feature of contents preferred by a user;

obtaining a feature vector representing a feature of the contents;

applying a first selection to select a part of a given group of contents according to a successively generated condition of an attribute value of attributes of each of the contents,

wherein in an event the condition of the attribute value includes a plurality of conditions, a first set of contents is selected from the group based on a part of the plurality of conditions, and a selection of a second set of contents among the first set of contents is received from a user apparatus based on remaining of the plurality of conditions;

applying a second selection to select a part or all of the group according to a degree of similarity between the feature vector and the preference vector of each of the contents belonging to the given group of the contents; and

generating a list of contents selected by applying the first selection and the second selection in an overlapping manner to the contents.