WO2010070876A1

WO2010070876A1 - Information processing device, information processing method, and program

Info

Publication number: WO2010070876A1
Application number: PCT/JP2009/006867
Authority: WO
Inventors: 吉井伸一郎
Original assignee: サイジニア株式会社
Priority date: 2008-12-17
Filing date: 2009-12-15
Publication date: 2010-06-24
Also published as: JP2010146153A; JP5271686B2

Abstract

Conventionally it has not been possible to output target object information using the information of multiple types of operations by a user with respect to the target object. This information processing device is able to output target object information using the information of multiple types of operations by a user with respect to the target object, being equipped with: a link information creation unit which reads two or more pieces of operation information, detects two or more target object identifiers which are connected via a user identifier possessed by each of said two or more pieces of operation information, and creates link information, which is information that indicates a link relationship between two or more target objects and is information that has the strength of the link between two or more target objects; an intra-group identifier acquisition unit which uses the created link information to acquire one target object identifier that has been received and a target object identifier having a degree-of-relation strength exceeding a prescribed value; and an intra-group information output unit which outputs target object information, which is information pertaining to the target object identifier acquired by the intra-group identifier acquisition unit or to the target object.

Description

Information processing apparatus, information processing method, and program

The present invention relates to an information processing apparatus that recommends information using information on two or more types of operations (purchasing, browsing, etc.) on two or more users' objects (products, information, etc.), for example. It is.

2. Description of the Related Art Conventionally, there has been an information processing system that simultaneously realizes both a highly reliable content recommendation based on an item name and item value that are of high interest to a user and a content recommendation that takes into consideration the order of content usage (see Patent Document 1). . This system stores a content usage history information storage management unit that stores and manages content usage history information of a user, a content usage transition information calculation unit that calculates content usage transition information from content usage history information, and stores content usage transition information Content recommendation information is generated based on the content usage transition information storage management unit to be managed, the content metadata information storage management unit to store and manage content metadata information, content usage history information, content usage transition information and content metadata information A content recommendation information generation unit.

Also, there is a system that extracts features for each individual item name and recommends content based on the features for each individual item name (see Patent Document 2). This system acquires the target item-specific information of the target user with respect to the preset item name, refers to the acquired user item-specific information, and sets the item name in advance. This is a system that extracts an item value of the number of appearances equal to or greater than the threshold value, acquires content information including the item value as a value of the target item name, and recommends the acquired content information to the user.

There is also a system that improves the possibility of product purchase and realizes a comprehensive recommendation service (see Patent Document 3). In this system, when a user purchases music software by accessing the server of music software distribution shop A via a network connection service with a mobile phone, the server of shop A transmits the purchase information to the center. Is a system that retrieves the concert information from the singer from the recommendation rules and sends the recommendations to the mobile phone via the Internet connection service. In this system, when a user purchases a concert ticket to the server of the ticket sales shop B by a mobile phone, the server of the shop B transmits the purchase information to the center, and the center transmits the concert information of the purchase information. This is a system that searches for a reservation status of an airplane or the like on the date of the event from a recommendation rule and transmits the recommendation to a mobile phone.

There is also a recommendation engine technology called GroupLens that automatically ranks Internet news (Non-patent Document 1). Furthermore, many studies on recommendations have been made centering on a technique called collaborative filtering (Non-Patent Documents 2 to 5).
Japanese Patent Laying-Open No. 2005-293384 (first page, FIG. 1 etc.) JP 2004-362011 A (first page, FIG. 1 etc.) JP 2002-117292 A (first page, FIG. 1 etc.) Resnick, P., Iacovou, N., Suchak, M., Bergstrom, P., Riedl, J .: GroupLens: An Open Architecture for Collaborative Filtering of Netnews.Proceedings of the 1994 Computer Supported Collaborative Work Conference, pp.175- 186 (1994). Balabanovic, M. and Shoham, Y .: Fab: Content-Based, Collaborative Recommendation.Communications of the ACM, Vol. 40, Herlocker, J. L., Konstan, J. A., Borchers, A. and Riedl, J .: An Algorithmic Framework for Performing Collaborative Filtering, Proceedings of the 22nd annual international ACM SIGIR, pp. 230-237 (1999). Sarwar, B., Karypis, G., Konstan, J. and Riedl, J .: Item-Based Collaborative Filtering Recommendation Algorithms, Proceedings of the 10th International Conference on World Wide Web, pp.285-295 (2001). Linden, G .., Smith, B., and York, J .: Amazon.com Recommendations: Item-to-Item Collaborative Filtering, Internet Computing, IEEE,

However, in the conventional system, the objects and users are grouped according to the history of two or more kinds of operations (for example, purchase, information browsing, etc.) of the user to perform on one or more objects (for example, products and services). It was not done.

Therefore, the accuracy of product recommendations was low. Moreover, the process of introducing a friend to the user has not been performed.

The information processing apparatus according to the first aspect of the present invention provides operation information having a user identifier for identifying a user, an object identifier for identifying an object operated by the user, and operation identification information for identifying the operation. Two or more pieces of operation information are read from the operation information storage unit that can be stored as described above and the operation information storage unit, and two or more object identifiers connected via user identifiers of the two or more pieces of operation information are detected. A link information generation unit that generates link information that is information indicating a link relationship between two or more objects, and has link strength between the two or more objects, and one object identifier And using the link information generated by the link information generation unit, an object identifier having a degree of association greater than or equal to the one object identifier received by the previous reception unit is acquired. An in-loop identifier obtaining unit; and an in-group information output unit that outputs object information obtained by the in-group identifier obtaining unit or object information that is information related to the object identified by the object identifier. Information processing apparatus.

With this configuration, it is possible to output information on an object using information on a plurality of types of operations on the object of the user.

In addition, the information processing apparatus according to the second aspect of the present invention is different from the first aspect in that the operation-specific weight information including operation identification information and weight information that is information about the link weight is stored for each operation. And further comprising a weight information storage unit, wherein the link information generation unit detects two or more object identifiers connected via user identifiers of the two or more operation information, and the two or more object objects Related information acquisition means for acquiring related information, which is information indicating a link relationship between them, operation identification information acquisition means for acquiring operation identification information included in each of the two or more pieces of operation information, and the operation identification information acquisition means The weight information acquisition unit that acquires the weight information paired with the operation identification information obtained from the weight information storage unit for each operation and the weight information acquired by the weight information acquisition unit is acquired by the related information acquisition unit. Relevance calculation means for calculating a relevance degree indicating a relevance degree between two or more objects, related information acquired by the related information acquisition means, and relevance calculated by the relevance degree calculation means This is an information processing apparatus comprising link information forming means for forming link information using the degree.

In the information processing apparatus according to the third aspect of the present invention, in the first or second aspect of the invention, the receiving unit receives one object identifier from the terminal device, and the in-group information output unit Is an information processing apparatus that transmits, to the terminal apparatus, object information that is an object identifier acquired by the in-group identifier acquisition unit or information related to the object identified by the object identifier.

With this configuration, recommendations can be realized using information on a plurality of types of operations on the user's object.

The information processing apparatus according to the fourth aspect of the present invention provides an object identifier and advertisement information that is information for promoting the object identified by the object identifier, for either the first or second invention, An object advertisement information storage unit capable of storing the object advertisement information having the object identifier information, and the in-group information output unit targets the advertisement information paired with the object identifier acquired by the in-group identifier acquisition unit. An information processing apparatus comprising: advertisement information acquisition means acquired from a physical advertisement information storage unit; and advertisement information transmission means for transmitting advertisement information acquired by the advertisement information acquisition means to the terminal device.

With this configuration, advertisement information can be output using information on a plurality of types of operations on the user's object.

The information processing apparatus according to the fifth aspect of the present invention includes operation information including a user identifier for identifying a user, an object identifier for identifying an object operated by the user, and operation identification information for identifying the operation. Two or more operation information storage units that can be stored, and two or more user identifiers that are connected to each other by reading out two or more pieces of operation information from the operation information storage unit and having object identifiers of the two or more pieces of operation information A link information generation unit that generates link information that is information indicating a link relationship between two or more users, and has information on the link strength between the two or more users, and one user identifier. Using the link information generated by the reception unit and the link information generation unit, the user identifier received by the previous reception unit and the user identifier having a degree of association greater than or equal to a predetermined value are obtained. An intra-group identifier obtaining unit and an intra-group information output unit that outputs user information obtained by the intra-group identifier obtaining unit or user information that is information relating to a user identified by the user identifier. It is.

With this configuration, user information can be output using information on a plurality of types of operations on the user's object.

In addition, the information processing apparatus according to the sixth aspect of the invention relates to the fifth aspect of the invention by the operation-specific weight information having the operation identification information and the weight information that is information about the link weight. A weight information storage unit, wherein the link information generation unit detects two or more user identifiers connected via an object identifier included in each of the two or more pieces of operation information, and Related information acquisition means for acquiring related information, which is information indicating the link relation of the above, operation identification information acquisition means for acquiring operation identification information included in each of the two or more pieces of operation information, and acquired by the operation identification information acquisition means The weight information acquisition unit that acquires the weight information paired with the operation identification information from the weight information storage unit for each operation and the weight information acquired by the weight information acquisition unit are acquired by the related information acquisition unit. Relevance level calculating means for calculating a relevance level indicating a degree of relevance between two or more users, related information acquired by the related information acquiring means, and relevance level calculated by the relevance level calculating means Is an information processing apparatus comprising link information forming means for forming link information.

The information processing apparatus according to the seventh aspect of the invention is the information processing apparatus according to any one of the fifth and sixth aspects, wherein the receiving unit receives one user identifier from the terminal device, and the in-group information output unit is The information processing apparatus transmits user information acquired by the intra-group identifier acquisition unit or user information that is information related to a user identified by the user identifier to the terminal apparatus.

According to the information processing system according to the present invention, for example, it is possible to improve the accuracy of recommending products and the like.

Hereinafter, embodiments of the information processing system and the like will be described with reference to the drawings. In addition, since the component which attached | subjected the same code | symbol in embodiment performs the same operation | movement, description may be abbreviate | omitted again.

(Embodiment 1)

In the present embodiment, a plurality of types of operations on two or more objects (products, contents, services, etc.) of two or more users are accepted, and link relationship information between the objects is obtained from each of the plurality of types of operations. The information processing system 1 that generates, groups the objects from the link-related information, acquires information about the objects belonging to at least one group, and outputs the information is described. Here, the operation refers to an operation for purchasing a product using the electronic commerce system, a browsing operation of information about the product or service, information about the product or service, or information about the product or service. This includes various operations performed by the user, such as an operation for adding a web page to a favorite, an operation for tagging a product or service, and an operation for adding information (such as an attribute value) to the product or service. In the present embodiment, a weight corresponding to the type is given to the operation, and the information processing system 1 that generates link information between objects using the weight will be described. Moreover, in this Embodiment, the output of a target object demonstrates the case where it is a recommendation of a target object. Furthermore, in the present embodiment, a case will be described in which the output of an object is an output of advertisement information searched using an object identifier as a key.

FIG. 1 is a conceptual diagram of an information processing system 1 in the present embodiment. The information processing system 1 includes an information processing device 11 and one or more terminal devices 12. The information processing apparatus 11 and the terminal apparatus 12 are connected by a network such as the Internet, for example, and can communicate with each other. For example, the information processing apparatus 11 is a server apparatus on the network, and the terminal apparatus 12 is a user terminal.

FIG. 2 is a block diagram of the information processing system 1 in the present embodiment. The information processing apparatus 11 includes an operation information storage unit 111, an operation information reception unit 112, an operation information storage unit 113, a link information generation unit 114, a reception unit 115, an intra-group identifier acquisition unit 116, an intra-group information output unit 117, A weight information storage unit 118 and an object advertisement information storage unit 119 are provided.

The link information generation unit 114 includes related information acquisition means 1141, operation identification information acquisition means 1142, weight information acquisition means 1143, relevance calculation means 1144, and link information configuration means 1145.

The in-group information output unit 117 includes an advertisement information acquisition unit 1171 and an advertisement information transmission unit 1172.

The terminal device 12 includes an input reception unit 121, an information transmission unit 122, an information reception unit 123, and an information output unit 124.

The operation information storage unit 111 can store two or more pieces of operation information. The operation information is information including a user identifier for identifying a user, an object identifier for identifying an object operated by the user, and operation identification information for identifying an operation. The user identifier is, for example, an ID or a name. The operations include, for example, operations for purchasing products and services displayed on the screen of the terminal device 12 (such as pressing a purchase button) and products and services displayed on the screen of the terminal device 12. Information browsing operations, operations for registering products, services, contents, etc. displayed on the screen of the terminal device 12 in a favorite list, input information for products, services, contents, etc. ( (The content of the information does not matter), an operation for attaching a mark (such as a tag), and an operation for inputting an attribute value. The target object is a product, service, person, or the like. Any object may be used as long as it is included in a certain concept (category). Furthermore, the object identifier is an ID such as a product ID, a name, or the like. The operation information storage unit 111 is preferably a non-volatile recording medium, but can also be realized by a volatile recording medium. The process in which the operation information is stored in the operation information storage unit 111 does not matter. For example, the operation information may be stored in the operation information storage unit 111 via a recording medium, and the operation information transmitted via a communication line or the like is stored in the operation information storage unit 111. Alternatively, the operation information input via the input device may be stored in the operation information storage unit 111.

The operation information receiving unit 112 receives operation information. The operation information receiving unit 112 receives operation information directly or indirectly from an external device (for example, the terminal device 12 used by the user). The operation information receiving unit 112 is usually realized by a wireless or wired communication means, but may be realized by a means for receiving a broadcast.

The operation information storage unit 113 stores the operation information stored by the operation information receiving unit 112 in the operation information storage unit 111. The operation information storage unit 113 can be usually realized by an MPU, a memory, or the like. The processing procedure of the operation information storage unit 113 is usually realized by software, and the software is recorded on a recording medium such as a ROM. However, it may be realized by hardware (dedicated circuit).

The link information generation unit 114 generates link information using two or more pieces of operation information stored in the operation information storage unit 111. Specifically, the link information generation unit 114 reads two or more pieces of operation information from the operation information storage unit 111, and two or more object identifiers connected via the user identifiers of the two or more pieces of operation information. Is detected, and link information that is information indicating a link relationship between two or more objects and having strength of a link between the two or more objects is generated. “Detect two or more target identifiers connected via a user identifier” means that the same user identifier (attribute values that can be acquired by the user identifier (eg, age, age range, gender, hobby, residential area, The two object identifiers that are paired with each other are determined to be related to each other, and the two object identifiers are connected to each other. It is done continuously. In addition, “detect two or more object identifiers connected via a user identifier” means that the same user identifier (attribute values (for example, age, age range, gender, hobby, residence that can be acquired by the user identifier) It is also possible to consider that it includes a region, an affiliated organization, etc.) All two sets of object identifiers of two or more object identifiers paired with the object identifier are acquired. The link information includes all sets of two object identifiers, link and strength information, and the data structure is not limited. All sets of two object identifiers are, for example, “(product A, product B) (product A, product C) (product A, product B) (product C, product D)... This is a set of information of object identifier pairs in a link relationship. “(Product A, Product B) (Product A, Product C) (Product A, Product B) (Product C, Product D)...” Has at least two (Product A, Product B). Therefore, in this example, it can be said that the strength of the link between “product A” and “product B” is 2 or more. When the link information includes link strength information, the link information is, for example, “(product A, product B, 2) (product A, product C, 1) (product C, product D, 5)... Is. (Product A, Product B, 2) indicates that there is a link between “Product A” and “Product B”, and its strength is “2”. In addition, when the link information generation unit 114 generates link information, it is preferable to use operation identification information. For example, it is preferable that the link information generation unit 114 configures link strength information using weight information corresponding to operation identification information. The weight information corresponding to the operation identification information is stored in the operation-specific weight information storage unit 118. The link information generation unit 114 performs processing for associating products and services purchased by users having the same attributes, such as products and services purchased by the same user. The link information may not have weight information. The same applies to other embodiments. The link information generation unit 114 can usually be realized by an MPU, a memory, or the like. The processing procedure of the link information generation unit 114 is usually realized by software, and the software is recorded on a recording medium such as a ROM. However, it may be realized by hardware (dedicated circuit).

The related information acquisition unit 1141 detects the two or more object identifiers connected via the user identifiers included in each of the two or more pieces of operation information, and is information indicating the link relationship between the two or more objects. Get information. The related information is, for example, a set of two object identifiers.

The operation identification information acquisition unit 1142 acquires operation identification information included in two or more pieces of operation information.

The weight information acquisition unit 1143 acquires the weight information paired with the operation identification information acquired by the operation identification information acquisition unit 1142 from the operation-specific weight information storage unit 118.

The degree-of-association calculating unit 1144 uses the weight information acquired by the weight information acquiring unit 1143 to calculate the degree of association indicating the degree of association between two or more objects with respect to the related information acquired by the related information acquiring unit 1141. To do. The degree-of-association calculating unit 1144 acquires, for example, the number of links between two objects as the degree of association. In addition, the degree-of-association calculating unit 1144 calculates, for example, a sum of one or more pieces of weight information (in this case, the weight information is a numerical value) corresponding to one or more links between two objects, and the sum is calculated. Get as relevance.

The link information configuring unit 1145 configures link information using the related information acquired by the related information acquiring unit 1141 and the related degree calculated by the related degree calculating unit 1144.

The related information acquisition unit 1141, the operation identification information acquisition unit 1142, the weight information acquisition unit 1143, the relevance degree calculation unit 1144, and the link information configuration unit 1145 can be usually realized by an MPU, a memory, or the like. The processing procedure of the related information acquisition unit 1141 and the like is usually realized by software, and the software is recorded on a recording medium such as a ROM. However, it may be realized by hardware (dedicated circuit).

The accepting unit 115 accepts one object identifier. The reception here is, for example, reception. The acceptance may be, for example, acceptance of manual input from a user, reading from a storage medium, or sending from another procedure (function, method, etc.). For example, the reception unit 115 receives one object identifier from the terminal device 12. The accepting unit 115 can be realized by, for example, a wireless or wired communication unit.

The in-group identifier acquisition unit 116 uses the link information generated by the link information generation unit 114 to use a link between the object identifier received by the reception unit 115 and the strength of the degree of association greater than or equal to a predetermined level ( Usually, the object identifier having the information stored in the storage medium in the in-group identifier acquisition unit 116 is acquired in advance. Here, “the strength of the degree of association above a predetermined level” is, for example, other information from a bipartite graph constructed using an object identifier and other information (user identifier, user attribute value, etc.). In the case where a partial graph using two or more object identifiers is configured, a relationship that is connected to one object identifier in a predetermined relationship (for example, the link strength is equal to or greater than a threshold value). For example, the in-group identifier acquisition unit 116 uses the link information generated by the link information generation unit 114 to obtain an object identifier having a strength of a predetermined degree of association with the one object identifier received by the reception unit 115. get. The in-group identifier acquisition unit 116 uses the link information generated by the link information generation unit 114 to target objects belonging to the same group as the object identified by the one object identifier received by the reception unit 115. The object identifier is acquired and placed on the memory. There is no limitation on the algorithm for acquiring the object identifier of the object belonging to the group.

For example, a partial graph including the relationship between objects as described above is called a relationship network. Finding an object in the same group as an object is to divide the graph to maximize some amount of object community structure in the relational network. As an index for the same group to form an appropriate community structure, there is a concept of modularity.

For example, the in-group identifier acquisition unit 116 calculates local modularity (R) by an algorithm using Equation 1 below. And based on this parameter | index (R), the target object which belongs to the same group is specified, and those target object identifiers are acquired.

That is, now, in the relationship network to be analyzed (part graph above), the base node v _m of interest (see FIG. 3). Base node v _m of interest is the one object identifier reception unit 115 has received the above. The base node v _m is an object identifier (network node) that is a base for extracting a group of object identifiers. Here, the node set of groups that are extracted about the node v _m and C. Further, a node set that is not included in C and is adjacent to at least one node of C is U. Furthermore, let C be a node set adjacent to U. At this time, the local modularity R of C is calculated according to Equation 1 above. In Formula 1, B _ij is the weight of the link between v _i and v _j when nodes v _i and v _j are connected and either one is included in B. Also. δ (i, j) is 1 when v _i εB and v _j εC, or v _i εC and v _j εB, and 0 otherwise. That is, T is the sum of the weights of all the links of the nodes included in B, and I is the sum of the weights of the links connected to the non-U nodes among all the links of B. By the base node v _m of interest repeating an operation for capturing a node adjacent in sequence and C, can be obtained C as R is maximized as a group of nodes v _m.

Further, the in-group identifier acquisition unit 116 may acquire the object identifier by the following second algorithm. That is, an object identifier that is directly connected to the one object identifier received by the receiving unit 115 with a link strength that is equal to or greater than a threshold (or greater than the threshold) may be acquired.

Further, the in-group identifier obtaining unit 116 may obtain the object identifier by the following third algorithm. That is, the in-group identifier obtaining unit 116 directly connects the one object identifier received by the receiving unit 115 to the target identifier that is directly connected with the strength of the link that is equal to or greater than the threshold (or greater than the threshold). You may acquire the connected object identifier and the object identifier directly connected with the intensity | strength of a link more than a threshold value (or larger than a threshold value).

Further, the in-group identifier obtaining unit 116 may obtain the object identifier by the following fourth algorithm. That is, the in-group identifier obtaining unit 116 directly connects the one object identifier received by the receiving unit 115 to the target identifier that is directly connected with the strength of the link that is equal to or greater than the threshold (or greater than the threshold). The connected object identifier and the object identifier directly connected with the strength of the link greater than or equal to the threshold (or greater than the threshold) are acquired. Then, recursively, the object identifiers connected with the link strength equal to or higher than the threshold (or larger than the threshold) are acquired recursively.

Further, the in-group identifier obtaining unit 116 may obtain the object identifier by the following fifth algorithm. That is, the in-group identifier acquiring unit 116 includes all the target identifiers directly connected to the one target identifier received by the receiving unit 115, each target identifier directly connected, and more than a threshold value. You may acquire the object identifier connected directly with the intensity | strength of a link (or larger than a threshold value).

Further, the in-group identifier acquisition unit 116 may acquire the object identifier by the following sixth algorithm. In other words, the in-group identifier acquisition unit 116, from among all the object identifiers directly connected to the one object identifier received by the receiving unit 115, in order from the highest link strength (x May be a natural number of 1 or more).

Further, the in-group identifier acquisition unit 116 may acquire the object identifier by the following seventh algorithm. That is, the in-group identifier acquisition unit 116, among all the object identifiers directly connected to the one object identifier received by the receiving unit 115, is ranked in order of increasing link strength from the top x% (x May obtain an object identifier of greater than 0 and less than 100).

Furthermore, the in-group identifier obtaining unit 116 may obtain the object identifier by the following eighth algorithm (this algorithm is referred to as “mutual importance factor algorithm”). The mutual importance addition algorithm is based on a link weight (link weight A) relative to another object identifier relative to one object identifier and a relative one viewed from another object identifier. This is an algorithm for determining an object identifier in a group using a mutual importance-added link strength C calculated using a link weight (link weight B) with the object identifier of the group as a parameter. An arithmetic expression for calculating the mutual importance-added link strength C is, for example, Expression 2.

Expression 2 is an example of an expression for calculating the mutual importance-added link strength C between the object (v _m ) and the object (v _a ). Further, in Equation 2, v and the sum of the weights of all links of _m, which is the sum of the weights of links affixed to the object to be adjacent from v _m.

Then, the in-group identifier acquisition unit 116 calculates the mutual importance-added link strength for all the object identifiers directly connected to the one object identifier, and the mutual importance-added link strength is large. The top x object identifiers (x is a natural number greater than or equal to 1) may be acquired, or the top x% (x is greater than 0 and less than 100) object identifiers may be acquired. Then, an object identifier whose mutual importance-added link strength is equal to or greater than a threshold may be acquired.

Further, a specific method of calculating the mutual importance-added link strength will be described with reference to FIG. In FIG. 4, the sum of the weights of all the links of the object (v _m ) is 200. The sum of the weights of all links of the object _{(v a)} is a 10000. The sum of the weights of all links of the object (v _b ) is 20. The weight of the link between v _m v _a is 100. The weight of the link between v _m v _b is 5.

The link strength A between v _m v _a is “100/200”, and the link strength B between v _m v _a is “100/10000”. The mutual importance-added link strength C between v _{m and} v _a is “(100/200) × (100/10000) = 1/200”.

On the other hand, the link strength A between v _m v _b is “5/200”, and the link strength B between v _m v _b is “5/20”. The mutual importance-added link strength C between v _m v _b is “(5/200) × (5/20) = 1/160”.

In other words, mutual significance-adding link level viewed from the object _{(v m)} C is towards the object _{(v b)} is larger than the object _{(v a).} As described above, from the viewpoint of the object (v _m ), the object (v _b ) is more easily selected as the object in the group.

In addition, there can be various algorithms for the in-group identifier acquiring unit 116 to acquire an object identifier existing in the same group as the one object identifier received by the receiving unit 115.

Normally, if the object identifier received by the receiving unit 115 is different, the set of object identifiers acquired by the in-group identifier acquiring unit 116 is different.

The in-group identifier acquisition unit 116 can be usually realized by an MPU, a memory, or the like. The processing procedure of the in-group identifier acquisition unit 116 is usually realized by software, and the software is recorded on a recording medium such as a ROM. However, it may be realized by hardware (dedicated circuit).

The in-group information output unit 117 outputs the object identifier that is the object identifier acquired by the in-group identifier acquisition unit 116 or information related to the object identified by the object identifier. Here, the output is, for example, transmission to the terminal device 12. Output refers to display on a display, projection using a projector, printing on a printer, sound output, transmission to an external device, storage in a recording medium, processing results to other processing devices or other programs, etc. Delivery etc. may be sufficient. The object information is, for example, advertisement information about the object or information that explains the object in detail. The object information may be anything as long as it is information about the object.

The intra-group information output unit 117 can be realized by, for example, a wireless or wired communication means.

The advertisement information acquisition unit 1171 acquires the advertisement information paired with the object identifier acquired by the in-group identifier acquisition unit 116 from the object advertisement information storage unit 119. The advertisement information acquisition unit 1171 can be usually realized by an MPU, a memory, or the like. The processing procedure of the advertisement information acquisition unit 1171 is usually realized by software, and the software is recorded in a recording medium such as a ROM. However, it may be realized by hardware (dedicated circuit).

The advertisement information transmission unit 1172 transmits the advertisement information acquired by the advertisement information acquisition unit 1171 to the terminal device 12. The advertisement information transmitting unit 1172 is usually realized by a wireless or wired communication unit, but may be realized by a broadcasting unit.

The operation-specific weight information storage unit 118 can store operation-specific weight information. The operation-specific weight information includes operation identification information and weight information that is information about the link weight. The operation-specific weight information storage unit 118 is preferably a nonvolatile recording medium, but can also be realized by a volatile recording medium. The process of storing the operation-specific weight information in the operation-specific weight information storage unit 118 does not matter. For example, the operation-specific weight information may be stored in the operation-specific weight information storage unit 118 via the recording medium, and the operation-specific weight information transmitted via the communication line or the like is stored in the operation-specific weight information storage unit. Alternatively, the operation-specific weight information input via the input device may be stored in the operation-specific weight information storage unit 118. When the weight information corresponding to the operation is the same regardless of the operation, the weight information storage unit 118 for each operation is not necessary.

The target advertisement information storage unit 119 can store target advertisement information. The object advertisement information includes an object identifier and advertisement information that is information for promoting the object identified by the object identifier. The target advertisement information storage unit 119 is preferably a non-volatile recording medium, but can also be realized by a volatile recording medium. The process in which the object advertisement information is stored in the object advertisement information storage unit 119 is not limited. For example, the target advertisement information may be stored in the target advertisement information storage unit 119 via a recording medium, and the target advertisement information transmitted via a communication line or the like is stored in the target advertisement information storage unit. 119 may be stored, or the target advertisement information input via the input device may be stored in the target advertisement information storage unit 119.

The input reception unit 121 receives input from the user. The input is, for example, an instruction to purchase a product, an instruction to browse product information (instruction to browse a web page), an instruction to give a mark that the product information is favorite, an input of input information such as a keyword or a color, and the like. . The input includes inputting various information and data. The input means for such instructions and information may be anything such as a keyboard, mouse or menu screen. The input receiving unit 121 can be realized by a device driver for input means such as a keyboard, control software for a menu screen, or the like.

The information transmitting unit 122 transmits the instruction, information, and the like received by the input receiving unit 121 to the information processing apparatus 11. The information transmission unit 122 is usually realized by a wireless or wired communication unit, but may be realized by a broadcasting unit.

The information receiving unit 123 receives information from the information processing device 11 and other devices. There may be various kinds of information to be received. The information receiving unit 123 is usually realized by a wireless or wired communication means, but may be realized by a means for receiving a broadcast.

The information output unit 124 outputs the information received by the information receiving unit 123. Here, output refers to display on a display, projection using a projector, printing on a printer, sound output, transmission to an external device, storage in a recording medium, other processing device or other program, etc. It is a concept including delivery of processing results. The information output unit 124 may be considered as including or not including an output device such as a display or a speaker. The information output unit 124 can be implemented by output device driver software, or output device driver software and an output device.

Next, the operation of the information processing system 1 will be described. First, the operation of the information processing apparatus 11 will be described using the flowcharts of FIGS.

(Step S501) The operation information receiving unit 112 determines whether or not operation information has been received. If operation information is received, it will go to step S502, and if operation information is not received, it will go to step S503.

(Step S502) The operation information storage unit 113 stores the operation information received in step S501 in the operation information storage unit 111. The process returns to step S501.

(Step S503) The link information generation unit 114 determines whether it is timing to generate link information. If it is the timing to generate link information, go to step S504, and if it is not the timing to generate link information, go to step S505. The link information generation timing is, for example, when the receiving unit 115 receives an instruction from a user, when the operation information receiving unit 112 receives operation information, or periodically (for example, every day, 23: 30 etc.).

(Step S504) The link information generation unit 114 performs link information generation processing. The link information generation process is a process of generating link information and writing it at least temporarily to a storage medium. The process returns to step S501. The link information generation process will be described with reference to the flowchart of FIG. The link information here is information including two object identifiers, for example.

(Step S505) The receiving unit 115 determines whether or not an object identifier has been received. If the object identifier is accepted, the process goes to step S506, and if the object identifier is not accepted, the process returns to step S501. Here, normally, the reception unit 115 receives the object identifier from the terminal device 12.

(Step S506) The in-group identifier acquisition unit 116 performs an in-group object identifier acquisition process using the link information generated in step S504. The in-group object identifier acquisition process is a process of acquiring one or more object identifiers belonging to the same group as the object identifier received in step S505. Note that the object identifier belonging to the same group as the object identifier received in step S505 may be zero. The in-group object identifier acquisition process will be described with reference to the flowchart of FIG.

(Step S507) The in-group information output unit 117 configures the object information using the object identifier acquired in Step S506. The object information is one or more pieces of information among the name, specifications, price, image data, object identifier, etc. of the object (for example, a product).

(Step S508) The in-group information output unit 117 outputs the object information configured in step S507. The output here is usually transmission of object information to the terminal device 12 that has transmitted the object identifier received in step S505. The process returns to step S501.

In the flowchart of FIG. 5, the link information generation process in step S504 is performed in advance, and the link information may be stored in a storage medium (not shown) in advance.

In the flowchart of FIG. 5, the in-group object identifier acquisition process in step S506 is performed in advance, and the in-group object identifier (one or more object identifiers) corresponding to each object identifier is stored in advance. (Not shown) may be stored.

Further, in the flowchart of FIG. 5, the object information may be advertisement information. In such a case, the advertisement information acquisition unit 1171 acquires, from the target advertisement information storage unit 119, one or more pieces of advertisement information that are paired with one or more target identifiers acquired by the intra-group identifier acquisition unit 116. Then, the advertisement information transmission unit 1172 transmits one or more pieces of advertisement information acquired by the advertisement information acquisition unit 1171 to the terminal device 12.

Further, in the flowchart of FIG. 5, the process is terminated by powering off or interruption for aborting the process.

Next, the link information generation processing in step S504 will be described using the flowchart in FIG.

(Step S601) The link information generation unit 114 substitutes 1 for the counter i.

(Step S602) The link information generation unit 114 determines whether or not the i-th user identifier exists. If the i-th user identifier exists, the process proceeds to step S603, and if the i-th user identifier does not exist, the process returns to the upper process. The link information generation unit 114 searches the operation information stored in the operation information storage unit 111 or the user identifier group management table stored by means not shown separately, and determines whether the i-th user identifier exists. Judge whether or not. The i-th (i is 1, 2,...) User identifier is a unique user identifier.

(Step S603) The link information generation unit 114 substitutes 1 for the counter j.

(Step S604) The link information generation unit 114 determines whether or not the jth object identifier exists. If the jth object identifier exists, the process proceeds to step S605, and if the jth object identifier does not exist, the process proceeds to step S615.

(Step S605) The link information generation unit 114 substitutes “j + 1” for the counter k.

(Step S606) The link information generation unit 114 determines whether or not the kth object identifier exists. If the kth object identifier exists, the process proceeds to step S607, and if the kth object identifier does not exist, the process proceeds to step S614.

(Step S607) The link information generation unit 114 reads all operation information including the i-th user identifier from the operation information storage unit 111.

(Step S608) The related information acquisition unit 1141 of the link information generation unit 114 determines whether or not both the jth object identifier and the kth object identifier exist in the operation information read in Step S607. Judging. If both exist, go to step S609, otherwise go to step S613. Here, if both the j-th object identifier and the k-th object identifier exist, the related information acquisition unit 1141 has related information including the j-th object identifier and the k-th object identifier. And place it in memory.

(Step S609) The operation identification information acquisition unit 1142 acquires all the operation identification information included in the operation information including the jth object identifier or the kth object identifier, and arranges it on the memory. Here, the operation identification information acquisition unit 1142 can acquire one or more operation identification information.

(Step S610) The weight information acquisition unit 1143 reads the weight information corresponding to each of the one or more pieces of operation identification information acquired in Step S609 from the operation-specific weight information storage unit 118.

(Step S611) The degree-of-association calculating unit 1144 calculates the degree of association using the one or more pieces of weight information acquired in Step S610. The calculation formula for calculating the relevance is, for example, the sum of one or more pieces of weight information. Further, the relevance calculation means 2144 may calculate the relevance without using the weight information. In such a case, the relevance calculation unit 2144 may use, for example, the number of links as the relevance. In addition, the algorithm which calculates a computing equation and a relevance degree does not ask | require.

(Step S612) The link information generation unit 114 writes (jth object identifier, kth object identifier, relevance) in the buffer. Here, the jth object identifier and the kth object identifier are the information acquired in step S608, and the relevance is the information acquired in step S611.

(Step S613) The link information generation unit 114 increments the counter k by 1. The process returns to step S606.

(Step S614) The link information generation unit 114 increments the counter j by 1. The process returns to step S604.

(Step S615) The link information generation unit 114 increments the counter i by 1. The process returns to step S602.

In the flowchart of FIG. 6, the data structure to be written in step S612 is not limited.

Next, the in-group object identifier acquisition processing in step S506 will be described using the flowchart of FIG.

In the flowchart of FIG. 7, the following setting is made. In the analysis subject to relation network (part graph above), the base node v _m of interest (see FIG. 3). Base node v _m of interest is the one object identifier reception unit 115 has received the above. The base node v _m is an object identifier (network node) that is a base for extracting a group of object identifiers. Here, the node set of groups that are extracted about the node v _m and C. Further, a node set that is not included in C and is adjacent to at least one node of C is U. Furthermore, let C be a node set adjacent to U.

(Step S701) The in-group identifier obtaining unit 116 stores one object identifier in the buffer C, obtains an initial value of the adjacency matrix (β) of B, and arranges the initial value on the memory.

(Step S702) The intra-group identifier obtaining unit 116 reads the object identifier paired with the one object identifier from the link information and stores it in the buffer U.

(Step S703) The in-group identifier obtaining unit 116 determines whether or not the number of object identifiers in the buffer C is equal to or less than a threshold value. The threshold value here is stored in advance. Further, the “determination as to whether or not the threshold value is less than or equal to the threshold value” may be “determination as to whether or not the threshold value is smaller than”. If it is less than the threshold value, the process goes to step S704, and if it is not less than the threshold value, the process returns to the higher level process.

(Step S704) The in-group identifier obtaining unit 116 substitutes 1 for the counter j.

(Step S705) The in-group identifier obtaining unit 116 determines whether or not the j-th object identifier is present in the buffer U. If the jth object identifier exists, the process goes to step S706, and if not, the process goes to step S708.

(Step S706) The in-group identifier obtaining unit 116 executes the following Equation 3 to obtain ΔR _j and arranges it on the memory.

Note that x, y, and z in Equation 3 are as follows. That is, “x” is the sum of the weights of all links to B of v _j . “Y” is the sum of the weights of links added to T when v _j is selected as C. “Z” is the sum of the link weights reduced from T when v _j is selected as C. Further, Formula 3 is a formula conceptually similar to Formula 1, and is a simplified formula that requires a small amount of calculation.

(Step S707) The in-group identifier obtaining unit 116 increments the counter j by 1. The process returns to step S705.

(Step S708) The in-group identifier acquisition unit 116 acquires a j-th object identifier that maximizes ΔR _j .

(Step S709) The in-group identifier acquisition unit 116 adds the object identifier acquired in step S708 to the buffer C.

(Step S710) The in-group identifier acquisition unit 116 acquires an object identifier that is paired with the object identifier acquired in step S708.

(Step S711) The in-group identifier acquiring unit 116 adds a new adjacent object identifier to the buffer U.

(Step S712) The in-group identifier acquisition unit 116 updates R and B. The process returns to step S703. Note that β is updated by updating B.

As described above, the in-group object identifier acquisition process is not limited to the process of the flowchart of FIG.

Next, the operation of the terminal device 12 will be described. The input reception unit 121 of the terminal device 12 receives input of operation information, an object identifier, and the like from the user. For example, the input reception unit 121 receives operation information (for example, “user A, product 1, purchase”) including a purchase instruction for a product from the user. In addition, when the user A tries to purchase a product and browses the product information of a product 2, the input reception unit 121 receives the object identifier “product 2”. In the operation information “user A, product 1, purchase”, “user A” is a user identifier, “product 1” is an object identifier, and “purchase” is operation identification information.

Next, the information transmitting unit 122 transmits the operation information received by the input receiving unit 121 and information such as the object identifier to the information processing apparatus 11.

Next, the information receiving unit 123 receives information from the information processing apparatus 11 and other devices. The information is, for example, object information that is information about an object identifier belonging to the same group as the object identifier “product 2”. Such object information is information (for example, advertisement information) such as a product recommended by the user A. Then, the information output unit 124 outputs the information received by the information receiving unit 123.

Hereinafter, a specific operation of the information processing system 1 in the present embodiment will be described. A conceptual diagram of the information processing system 1 is shown in FIG.

Now, it is assumed that the server apparatus or the information processing apparatus 11 (not shown) holds the object management table shown in FIG. When the server device holds the object management table, it is assumed that the server device is connected to the network. The object management table is a table for managing objects. Here, the object is a product, particularly an article to be worn such as clothes or shoes. The target object management table is a table that stores one or more target object records that are information on products or services that are targets of electronic commerce. The object management table includes “ID”, “object identifier”, and “object”. “ID” is information for identifying a table record and exists for table management. The “object identifier” is information for identifying an object, and here is an object ID. However, the “object identifier” may be a product name or the like, and may be considered as information including an object attribute to be described later. The “object” stores one or more attribute values of the object. The attribute value includes “product name”, “product type”, “size”, and the like. “Product type” indicates the type of product.

Further, the operation-specific weight information storage unit 118 of the information processing apparatus 11 holds the operation-specific weight information management table shown in FIG. The operation-specific weight information management table is a table that holds one or more records having “operation identification information” and “weight information”.

The user A of the terminal device 12 accesses a device (hereinafter referred to as the information processing device 11) that holds the object management table and performs an electronic commerce (E of D company E). -You are logged in to the shopping site. Then, for example, the terminal device 12 receives a website for electronic commerce from the information processing apparatus 11, interprets the website, and displays a screen as shown in FIG. Since the process of displaying the website is a so-called web browser process and is a known technique, detailed description thereof is omitted. It is assumed that the user A inputs the user identifier “A” when logging in to a site that conducts electronic commerce. Further, using the screen of FIG. 10 and the like, the user can perform operations such as “purchase”, “put into shopping basket”, and “view” on the product. “Browse” is an operation of depressing the anchor “detail” in FIG. 10 and outputting detailed product information. Here, for example, when the “purchase” operation is performed immediately after performing the “add to shopping cart” operation, only the “purchase” operation is recorded.

Next, the user enters the desired product (for example, the product with the object identifier “1”) into the shopping cart (by pressing the “Add to shopping cart” button) while looking at the screen of FIG. It is assumed that an operation (for example, an operation of pressing a purchase button not shown) is performed. Then, the input reception unit 121 receives the user identifier “A” and the object identifier “1”. The information transmitting unit 122 configures information “user identifier: A, object identifier: 1, operation identifier: purchase”, and transmits the information to the information processing apparatus 11. The information “user identifier: A, object identifier: 1, operation identification information: purchase” is an example of the operation information described above, and the user A purchases a product identified by the object identifier “1”. It means that.

The operation information receiving unit 112 of the information processing apparatus 11 receives operation information “user identifier: A, object identifier: 1, operation identification information: purchase”. Then, the operation information storage unit 113 acquires the time when the operation information is received from a clock (not shown), and changes the operation information to the operation information having the structure of “user identifier, object identifier, operation identification information, time information”. Then, the operation information accumulation unit 113 accumulates the changed operation information in the operation information storage unit 111.

Further, it is assumed that users B and C, who are users other than user A, have also performed the above-described product purchase operation, operation to put in the shopping cart, or browsing operation. Then, it is assumed that the operation information accumulation unit 113 of the information processing apparatus 11 accumulates the operation information in the operation information storage unit 111 as in the above processing. Assume that the operation information management table shown in FIG. 11 is accumulated in the operation information storage unit 111. Here, the operation information management table stores operation information, which is information indicating a history of purchase and browsing of past products and the like. That is, here, the operation information is information indicating that the user has generated an action such as purchasing a product or the like, viewing information about the product, or putting the product or the like into the shopping cart, and the user identifier And an object identifier, operation identification information, and time information. The operation information management table stores one or more records having “ID” and “operation information”. The “operation information” includes “user identifier”, “object identifier”, “operation identification information”, and “time information”. Here, “operation identification information” includes “purchase: 1”, “add to shopping basket: 2”, “view: 3”, and the like. “Browsing” means outputting a web page on which detailed information such as a product is described. Further, the type of “operation identification information” is not limited to the above three types. “Purchase: 1” indicates that the identifier of the operation identification information “purchase” is “1”.

Further, according to the operation information management table shown in FIG. 11, each user (for example, user A to user F) can purchase, browse, etc. for the product (for example, any one of product 1 to product 10) shown in FIG. 12. It can be seen that the operation (action) was performed. In FIG. 12, the attribute value “1” means “purchase”, “2” means “add to shopping basket”, “3” means “view”, and “3, 2, 1” means “view” “shopping”. It indicates that three operations of “add to basket” and “purchase” have been performed.

And the link information generation part 114 performs the following link information generation processing from the information of FIG. That is, in accordance with the operation of the flowchart of FIG. 6, the link information generation unit 114 acquires the first user identifier “A”. Next, the link information generation unit 114 reads all operation information including the first user identifier “A” from the operation information storage unit 111. Then, the link information generation unit 114 obtains the operation information “(A, 1, 1) (A, 4, 2) (A, 8, 1)”. The operation information has a structure of (user identifier, object identifier, operation identification information), and excludes time information. The link information generation unit 114 extracts the object identifiers “1”, “4”, and “8” from the operation information “(A, 1, 1) (A, 4, 2) (A, 8, 1)”. "(1, 4, 7) (1, 8, 10) (4, 8, 7)" which is weighted link information including all combinations of the object identifiers is obtained. Then, the link information generation unit 114 writes a plurality of weighted link information “(1, 4, 7) (1, 8, 10) (4, 8, 7)” in the buffer. Note that “7” of “(1, 4, 7)” is the sum of the weight information “5” of the operation “purchase: 1” and the weight information “2” of the operation “add to the shopping basket: 2”. is there. That is, the degree-of-association calculating unit 1144 calculates the sum of weight information corresponding to operation identification information indicating operations performed on the objects indicated by the two object identifiers as the degree of association.

Next, the link information generation unit 114 acquires the second user identifier “B”. Then, the link information generation unit 114 reads all operation information including the second user identifier from the operation information storage unit 111. Then, the link information generation unit 114 obtains operation information “(B, 1, 2) (B, 3, 3, 1) (B, 5, 1) (B, 9, 1)”. Then, the link information generation unit 114 acquires the weight information “2” corresponding to the operation identification information “2” of the operation information (B, 1, 2) from the table of FIG. Further, the link information generation unit 114 acquires the weight information “1, 5” corresponding to the operation identification information “3, 1” of the operation information (B, 3, 3, 1) from the table of FIG. Similarly, the link information generation unit 114 acquires the weight information “5” and “5” corresponding to the operation identification information of the operation information (B, 5, 1) (B, 9, 1) from the table of FIG. . Then, the link information generation unit 114 includes “(1, 3, 8) (1, 5, 7) (1, 9, 7) (3, 5, 11) (3, 9, 11) (5, 9, 10) ". The link information generation unit 114 then adds the weighted link information “(1, 3, 8) (1, 5, 7) (1, 9, 7) (3, 5, 11) (3, 9, 11). (5, 9, 10) "is added to the buffer. The link information generation unit 114 also executes this process for the third and subsequent user identifiers “C”, “D”, “E”, and “F”. Then, the link information generation unit 114 obtains a data group illustrated in FIG. The data constituting the data group in FIG. 13 has a structure of (jth object identifier, kth object identifier, weight information). The link information generation unit 114 accumulates the link information group of FIG. 13 in a storage medium. This storage medium may be a volatile storage medium or a non-volatile storage medium. For example, the weight information of the data (3, 5, 24) in FIG. 13 is “24”, which is different from “11” in the above (3, 5, 11). This is because the value of the weight information is increased by the processes for C, “D”, “E”, and “F”.

The process in which the link information generation unit 114 acquires the link information group in FIG. 13 is a process for generating a partial graph in FIG. 15 from the bipartite graph in FIG. The bipartite graph of FIG. 14 is a graph having a user identifier and an object identifier as nodes. In FIG. 14, the thickness of the line indicates the number of operations, and the types of operations are not distinguished. The partial graph in FIG. 15 is a graph having an object identifier as a node, and weight information is given.

The partial graph in FIG. 15 is a graph created by linking the object identifiers connected by the same user identifier from the bipartite graph in FIG. 14 in such a manner that the user identifier is deleted.

In such a situation, for example, the user A uses the terminal device 12 to access the website of the company D and, for example, puts the product 7 into the shopping basket (presses the “add to shopping cart” button). To do. Then, the input reception part 121 receives the information that the goods 7 were put into the shopping cart. Then, the information transmission unit 122 configures information of “user identifier: A, object identifier: 7”, and transmits the information to the information processing apparatus 11.

Next, the object identifier receiving unit 115 receives information including the object identifier “7”. Then, the in-group identifier acquisition unit 116 acquires the object identifier group in the group as follows. That is, the in-group identifier acquisition unit 116 uses, for example, the third algorithm described above to identify a node (target identifier) that is directly connected from the target identifier “7” with a link strength of “13” or higher. Get all. It is assumed that the in-group identifier acquisition unit 116 holds “13” that is a threshold value in advance.

Then, the in-group identifier obtaining unit 116 obtains “5”, “9”, and “10”. Next, the object identifier “3” connected with the object identifier “5” or “9” or “10” with the link strength of “13” or more is acquired. As a result, the in-group identifier acquisition unit 116 acquires the object identifiers “3”, “5”, “9”, and “10” and arranges them on the memory. FIG. 16 is a schematic diagram showing a target identifier group belonging to the same group as the target identifier “7” acquired by the intra-group identifier acquiring unit 116.

The in-group information output unit 117 uses the object identifiers “3”, “5”, “9”, and “10” to acquire object information that is information related to the object identified by the object identifier. First, the in-group information output unit 117 determines whether or not the object identifier of the object purchased by the user A exists among the object identifiers “3”, “5”, “9”, and “10”. Judging. Here, the in-group information output unit 117 searches the operation information management table of FIG. 11 using the user identifier “A” as a key, and acquires the object identifier. Then, the in-group information output unit 117 performs processing for removing the acquired object identifier from the object identifiers “3”, “5”, “9”, and “10”. Here, there is no object identifier to be excluded, and the intra-group information output unit 117 holds the object identifiers “3”, “5”, “9”, and “10” as they are.

Next, the in-group information output unit 117 uses the identifiers of the object identifiers “3”, “5”, “9”, and “10” as keys, and object information (for example, “product name”, “price”, “image”, etc.) ) Is read out from the object management table of FIG.

Next, the in-group information output unit 117 sends the read object information (such as “product name”, “price”, “image”, etc. corresponding to the object identifiers “3”, “5”, “9”, “10”) to the terminal. Transmit to device 12. The advertisement information acquisition unit 1171 of the in-group information output unit 117 searches the target advertisement information storage unit 119 using the read target object information as a key, acquires the advertisement information, and the advertisement information transmission unit 1172 Needless to say, the advertisement information may be transmitted to the terminal device 12.

Next, the information receiving unit 123 of the terminal device 12 receives object information (such as “product name”, “price”, and “image” corresponding to the object identifiers “3”, “5”, “9”, and “10”). . Next, the information output unit 124 outputs the received object information to the display. The object information is information on a product recommended to the user A. The object information is information on a product group that has a certain relationship with the product 7 that the user A has put in the shopping cart. In addition, the output aspect of object information is not ask | required.

As mentioned above, according to this Embodiment, the recommendation precision of goods etc. can be improved. Specifically, according to the present embodiment, it is possible to search for information such as products rich in serendipity. Serendipity is a term that refers to the ability and ability to find something that is different from what you are looking for when you are looking for something. It is an important ability for the next generation recommendation system. It is considered to be.

In addition, according to this Embodiment, it was outputting target object information as a method of recommendation, such as goods. However, you may recommend goods etc. by another method.

In addition, according to the present embodiment, the recommendation of the product or the like is performed with the user putting the product into the shopping basket as a trigger. However, when a user browses detailed information such as products or purchases a product, or when a user moves focus to the product, the product is recommended. Also good.

In the present embodiment, the operation identified by the operation identification information is not limited, as described above. Needless to say, the plurality of operations handled by the information processing apparatus may be operations that are completely unrelated. The unrelated operations include, for example, “purchase”, “tagging”, “data input (for example, input of impressions and opinions about the object)”, and the like. The same applies to other embodiments.

In the present embodiment, the weight information corresponding to a plurality of operations may be the same. In such a case, the operation-specific weight information storage unit 118 may not exist. In such a case, the weight information acquisition unit 1143 acquires the same weight information regardless of the operation identification information. In this case, the information processing apparatus is included in the following information processing apparatus. That is, an operation information storage unit capable of storing two or more pieces of operation information including a user identifier for identifying a user, an object identifier for identifying an object operated by the user, and operation identification information for identifying the operation. Two or more pieces of operation information are read from the operation information storage unit, two or more object identifiers connected via user identifiers of the two or more pieces of operation information are detected, and two or more object pieces are detected. Link information generating unit that generates link information that is information indicating a link relationship and has link strength between the two or more objects, a receiving unit that receives one object identifier, and the link information An in-group identifier acquisition unit that acquires an object identifier having a degree of association greater than or equal to the one object identifier received by the previous reception unit using the link information generated by the generation unit; An information processing apparatus for and a group in the information output portion that outputs object information, which is information about the object which the in-group identifier acquiring unit is identified by the acquired object identifier or the object identifier.

In the present embodiment, the weight information corresponding to each of the plurality of operations may change dynamically. For example, recommendations such as products may be made by outputting object information, etc., and weight information corresponding to each of a plurality of operations may be dynamically changed by a user action on the recommendation. The user action is, for example, purchase of recommended products, browsing of recommended products, and the like. In such a case, the information processing apparatus includes a reception unit and a weight information update unit. A reception part receives a user's action with respect to a recommendation. The weight information update unit acquires the object information of the action received by the reception unit, acquires one or more pieces of operation identification information that cause the object identified by the object information to be recommended, The weight information corresponding to a plurality of operations is updated so as to increase the weight of the weight information corresponding to each operation identification information. The same applies to other embodiments.

In the present embodiment, the weight information corresponding to each of a plurality of operations may be customized for each user or appropriately. By changing the weight corresponding to each of the plurality of operations, it is possible to change the operation information to be noticed. For example, Mr. A may attach importance to the operation “purchase” connection, but Mr. B may attach importance to the operation “browsing” connection, acquire an object, and make a recommendation for a product or the like. The same applies to other embodiments.

For example, the weight information corresponding to each of the plurality of operations may be defined differently for each user. For example, the weight information corresponding to each of a plurality of operations may be automatically set for each user in proportion to the frequency of each operation of the user. That is, for example, if the user A has performed the operation “Purchase” 50 times, the operation “Place in shopping cart” 32 times, and the operation “Browse” 96 times, the weight information of the operation “Purchase” is 50 The weight information for “Add to shopping basket” may be automatically set to 32, and the weight information for operation “Browse” may be automatically set to 96. The weight information is automatically set by, for example, weight information setting means (not shown). Note that setting means writing operation identification information and weight information in the operation-specific weight information storage unit 118.

Also, automatic setting of weight information may be performed by other algorithms. For example, the weight information of each operation may be automatically calculated and set by an increasing function using the sum of the number of operations of all users as a parameter.

Needless to say, the user may manually set the weight information.

Furthermore, the processing in the present embodiment may be realized by software. Then, this software may be distributed by software download or the like. Further, this software may be recorded on a recording medium such as a CD-ROM and distributed. This also applies to other embodiments in this specification. Note that the software that implements the information processing apparatus according to the present embodiment is the following program. In other words, this program reads two or more pieces of operation information from a storage medium, detects two or more object identifiers connected via user identifiers of the two or more pieces of operation information, and detects two or more pieces of object identifiers. A link information generating unit that generates link information that is information indicating a link relationship between two or more objects, and is information having a link strength between the two or more objects, and a receiving unit that receives one object identifier And using the link information generated by the link information generation unit, an in-group identifier acquisition unit that acquires one target identifier received by the previous reception unit and a target identifier having a degree of association greater than or equal to a predetermined level; In-group information output that outputs the object identifier acquired by the in-group identifier acquisition unit or object information that is information related to the object identified by the object identifier. Program for functioning as a part, is.

In the above program, the link information generation unit detects two or more object identifiers connected via user identifiers included in the two or more pieces of operation information, and a link relationship between the two or more objects. Related information acquisition means for acquiring related information that is information indicating operation, operation identification information acquisition means for acquiring operation identification information included in each of the two or more pieces of operation information, and operation identification information acquired by the operation identification information acquisition means Two or more targets for the related information acquired by the related information acquisition means using the weight information acquisition means for acquiring the weight information paired with the storage information from the storage medium and the weight information acquired by the weight information acquisition means Using a relevance calculation means for calculating a relevance degree indicating a relevance degree between objects, the relevance information obtained by the relevance information acquisition means, and the relevance degree calculated by the relevance degree calculation means, It is preferable to function as comprising link information structure unit constituting the click information.

In the above program, the receiving unit receives one object identifier from the terminal device, and the in-group information output unit is the object identifier acquired by the in-group identifier acquiring unit, or the object identifier. It is preferable to cause the object information, which is information relating to the object identified in (2), to function as what is transmitted to the terminal device.

In the above program, the intra-group information output unit includes an advertising information acquisition unit that acquires, from the storage medium, advertising information that is paired with the object identifier acquired by the intra-group identifier acquisition unit, and the advertising information acquisition unit includes: It is preferable that the acquired advertisement information function as an advertisement information transmission unit that transmits the advertisement information to the terminal device.

(Embodiment 2)

In the present embodiment, a plurality of types of operations on two or more objects (products, contents, services, etc.) of two or more users are accepted, and information on link relationships between users is generated from each of the plurality of types of operations. The information processing system 2 that groups users from the link-related information, acquires information about users belonging to at least one group, and outputs the information will be described. In the present embodiment, a weight corresponding to the type is given to the operation, and the information processing system 2 that generates link information between users using the weight will be described.

FIG. 1 is a conceptual diagram of an information processing system 2 in the present embodiment. FIG. 17 is a block diagram of the information processing system 2 in the present embodiment. The information processing system 2 includes an information processing device 21 and a terminal device 12.

The information processing apparatus 21 includes an operation information storage unit 111, an operation information reception unit 112, an operation information storage unit 113, a link information generation unit 214, a reception unit 215, an intra-group identifier acquisition unit 216, an intra-group information output unit 217, A weight information storage unit 118 and a user information storage unit 219 are provided.

The link information generation unit 214 includes related information acquisition means 2141, operation identification information acquisition means 2142, weight information acquisition means 2143, relevance calculation means 2144, and link information configuration means 2145.

The link information generation unit 214 generates link information. The link information is information indicating a link relationship between two or more users, and is information having a link strength between two or more users. The link information generation unit 214 reads two or more pieces of operation information from the operation information storage unit 111, detects two or more user identifiers connected via the object identifiers of the two or more pieces of operation information, and links Generate information. The link information generation unit 214 can usually be realized by an MPU, a memory, or the like. The processing procedure of the link information generation unit 214 is usually realized by software, and the software is recorded on a recording medium such as a ROM. However, it may be realized by hardware (dedicated circuit).

The related information acquisition unit 2141 detects two or more user identifiers connected via object identifiers included in two or more pieces of operation information, and is related information that is information indicating a link relationship between the two or more users. To get. The related information is, for example, two user identifiers. Further, the related information may be considered as a set of two user identifiers, for example.

The operation identification information acquisition unit 2142 acquires operation identification information included in each of two or more pieces of operation information.

The weight information acquisition unit 2143 acquires the weight information paired with the operation identification information acquired by the operation identification information acquisition unit 2142 from the operation-specific weight information storage unit 118.

The degree-of-association calculating unit 2144 uses the weight information acquired by the weight information acquiring unit 2143 to calculate the degree of association indicating the degree of association between two or more users with respect to the related information acquired by the related information acquiring unit 2141. . The degree-of-association calculating unit 2144 acquires, for example, the number of links between two users as the degree of association. In addition, the degree-of-association calculating unit 2144 calculates, for example, a sum of one or more pieces of weight information (in this case, the weight information is a numerical value) corresponding to one or more links between two users, Get as a degree.

The link information configuring unit 2145 configures link information using the related information acquired by the related information acquiring unit 2141 and the relevance calculated by the relevance calculating unit 2144.

Related information acquisition means 2141, operation identification information acquisition means 2142, weight information acquisition means 2143, relevance degree calculation means 2144, and link information configuration means 2145 can usually be realized from an MPU, memory, or the like. The processing procedure of the related information acquisition unit 2141 and the like is usually realized by software, and the software is recorded on a recording medium such as a ROM. However, it may be realized by hardware (dedicated circuit).

The accepting unit 215 accepts one user identifier. The reception here is, for example, reception. The acceptance may be, for example, acceptance of manual input from a user, reading from a storage medium, or sending from another procedure (function, method, etc.). For example, the reception unit 215 receives one user identifier from the terminal device 12. The accepting unit 115 can be realized by, for example, a wireless or wired communication unit.

The intra-group identifier acquisition unit 216 uses the link information generated by the link information generation unit 214 to use the strength of the degree of association of one user identifier received by the reception unit 215 with a predetermined level or higher (normally, And the user identifier having the information stored in the storage medium in the in-group identifier acquisition unit 216 in advance. Here, the “strength of the degree of association more than a predetermined value” means, for example, that two or more user identifiers are used by excluding the object identifier from the bipartite graph constructed using the user identifier and the object identifier. This is a relationship that is connected to one user identifier in a predetermined relationship when a partial graph is configured. The algorithm by which the in-group identifier acquisition unit 216 acquires the user identifier is the same as the algorithm by which the in-group identifier acquisition unit 116 acquires the object identifier (described in the first embodiment). That is, the in-group identifier acquisition unit 116 and the in-group identifier acquisition unit 216 are different only in whether the information to be acquired is an object identifier or a user identifier, and the algorithm is the same. Similarly to the intra-group identifier acquiring unit 116, the intra-group identifier acquiring unit 216 acquires a user identifier using the eighth algorithm or the other algorithm from the first algorithm using Equation 1 described in the first embodiment. Can do. Further, the in-group identifier acquisition unit 216 normally acquires one or more user identifiers, but there may be a case where it cannot be acquired. The in-group identifier acquisition unit 216 can be usually realized by an MPU, a memory, or the like. The processing procedure of the in-group identifier acquisition unit 216 is usually realized by software, and the software is recorded on a recording medium such as a ROM. However, it may be realized by hardware (dedicated circuit).

The intra-group information output unit 217 outputs the user identifier acquired by the intra-group identifier acquisition unit 216 or user information that is information related to the user identified by the user identifier. For example, the intra-group information output unit 217 searches the user information storage unit 219 using the user identifier as a key, and acquires user information. Then, the in-group information output unit 217 may output the acquired user information. The user information may be any information related to the user, such as an attribute value such as the user's name, age, and address, a contact address such as the user's e-mail address and telephone number. Here, output refers to display on a display, projection using a projector, printing on a printer, sound output, transmission to an external device (such as the terminal device 12), storage in a recording medium, other processing devices, It is a concept that includes delivery of processing results to other programs. The in-group information output unit 217 may be considered as including or not including an output device such as a display or a speaker. The intra-group information output unit 217 can be realized by output device driver software, or output device driver software and output device.

The user information storage unit 219 stores one or more sets of user identifiers and user information. The user information storage unit 219 is preferably a non-volatile recording medium, but can also be realized by a volatile recording medium. The process in which user information etc. are memorize | stored in the user information storage part 219 is not ask | required. For example, user information or the like may be stored in the user information storage unit 219 via a recording medium, and user information or the like transmitted via a communication line or the like may be stored in the user information storage unit 219. Alternatively, the user information input via the input device may be stored in the user information storage unit 219.

Next, the operation of the information processing system 2 will be described. First, the operation of the information processing apparatus 21 will be described using the flowchart of FIG. In the flowchart of FIG. 18, the description of the same steps as those of the flowchart of FIG. 5 is omitted.

(Step S1801) The link information generation unit 214 performs link information generation processing. The link information generation process is a process of generating link information and writing it at least temporarily to a storage medium. The process returns to step S501. The link information generation process will be described with reference to the flowchart of FIG. The link information here is, for example, information including two user identifiers.

(Step S1802) The receiving unit 215 determines whether or not a user identifier has been received. If a user identifier is accepted, the process goes to step S1803. If a user identifier is not accepted, the process returns to step S501. Here, normally, the reception unit 215 receives a user identifier from the terminal device 12.

(Step S1803) The intra-group identifier acquisition unit 216 performs an intra-group user identifier acquisition process using the link information generated in step S1801. The intra-group user identifier acquisition process is a process of acquiring one or more user identifiers belonging to the same group as the user identifier received in step S1802. Note that the user identifier belonging to the same group as the user identifier accepted in step S1802 may be zero. The intra-group user identifier acquisition process will be described with reference to the flowchart of FIG.

(Step S1804) The intra-group information output unit 217 searches the user information storage unit 219 using the user identifier acquired in step S1803, and acquires user information.

(Step S1805) The in-group information output unit 217 outputs the user information acquired in step S1804. The output here is usually transmission of user information to the terminal device 12 that has transmitted the user identifier accepted in step S1802. The process returns to step S501.

In the flowchart of FIG. 18, the link information generation process in step S1801 is performed in advance, and the link information may be stored in a storage medium (not shown) in advance.

In the flowchart of FIG. 18, the intra-group user identifier acquisition process in step S1802 is performed in advance, and an intra-group user identifier (one or more user identifiers) corresponding to each user identifier is stored in advance in a storage medium (not shown). You may store in.

Further, in the flowchart of FIG. 18, the processing is terminated by powering off or interruption for aborting the processing.

Next, step S1801 link information generation processing will be described using the flowchart of FIG.

(Step S1901) The link information generation unit 214 substitutes 1 for the counter i.

(Step S1902) The link information generation unit 214 determines whether or not the i-th object identifier exists. If the i-th object identifier exists, the process proceeds to step S1903, and if the i-th object identifier does not exist, the process returns to the higher-level process. The link information generation unit 214 searches the operation information stored in the operation information storage unit 111 or the object identifier group management table stored by means not shown separately, and the i-th object identifier exists. Judge whether to do. The i-th object identifier (i is 1, 2,...) Is a unique object identifier.

(Step S1903) The link information generation unit 214 substitutes 1 for the counter j.

(Step S1904) The link information generation unit 214 determines whether or not the j-th user identifier exists. If the jth user identifier exists, the process goes to step S1905, and if the jth user identifier does not exist, the process goes to step S1915.

(Step S1905) The link information generation unit 214 substitutes “j + 1” for the counter k.

(Step S1906) The link information generation unit 214 determines whether or not the kth user identifier exists. If the kth user identifier exists, the process goes to step S1907, and if the kth user identifier does not exist, the process goes to step S1914.

(Step S1907) The link information generation unit 214 reads all operation information including the i-th object identifier from the operation information storage unit 111.

(Step S1908) The related information acquisition unit 2141 of the link information generation unit 214 determines whether or not both the jth user identifier and the kth user identifier exist in the operation information read in step S1907. To do. If both exist, go to step S1909, and if not, go to step S1913. Here, if both the jth user identifier and the kth user identifier exist, the related information acquisition unit 2141 acquires related information including the jth user identifier and the kth user identifier, Place on memory.

(Step S1909) The operation identification information acquisition unit 2142 acquires all the operation identification information included in the operation information including the jth user identifier or the kth user identifier, and arranges it on the memory. Here, the operation identification information acquisition unit 2142 can acquire one or more operation identification information.

(Step S1910) The weight information acquisition unit 2143 reads the weight information corresponding to each of the one or more pieces of operation identification information acquired in step S1909 from the operation-specific weight information storage unit 118.

(Step S1911) The degree-of-association calculating unit 2144 calculates the degree of association using the one or more pieces of weight information acquired in step S1910. The calculation formula for calculating the relevance is, for example, the sum of one or more pieces of weight information. Further, the relevance calculation means 2144 may calculate the relevance without using the weight information. In such a case, the relevance calculation unit 2144 may use, for example, the number of links as the relevance. In addition, the algorithm which calculates a computing equation and a relevance degree does not ask | require.

(Step S1912) The link information generation unit 214 writes (jth user identifier, kth user identifier, relevance) in the buffer. Here, the jth user identifier and the kth user identifier are information acquired in step S1908, and the degree of association is information acquired in step S1911.

(Step S1913) The link information generation unit 214 increments the counter k by 1. The process returns to step S1906.

(Step S1914) The link information generation unit 214 increments the counter j by 1. The process returns to step S1904.

(Step S1915) The link information generation unit 214 increments the counter i by 1. The process returns to step S1902.

Note that, in the flowchart of FIG. 19, the data structure to be written in step S1912 does not matter.

Next, the intra-group user identifier acquisition process in step S1803 will be described with reference to the flowchart of FIG. In the flowchart of FIG. 20, the difference compared with the flowchart of FIG. 7 is only that the object identifier is replaced with the user identifier. If both are considered as nodes, FIG. 7 and FIG. 20 are flowcharts of the same processing, and thus description thereof is omitted.

Hereinafter, a specific operation of the information processing system 2 in the present embodiment will be described. A conceptual diagram of the information processing system 2 is shown in FIG.

Now, it is assumed that the server device or the information processing device 21 (not shown) holds the object management table shown in FIG.

Further, the operation-specific weight information storage unit 118 of the information processing apparatus 21 holds the operation-specific weight information management table shown in FIG.

As in the specific example of the first embodiment, the operation information storage unit 111 performs the operation of the user A and the processing of the terminal device 12 and the processing of the information processing device 21 described in the specific example of the first embodiment. Suppose that the operation information management table shown in FIG. 11 is accumulated.

Further, according to the operation information management table shown in FIG. 11, each user (for example, user A to user F) can purchase, browse, etc. for the product (for example, any one of product 1 to product 10) shown in FIG. 12. It can be seen that the operation (action) was performed.

Then, the link information generation unit 214 performs the following link information generation process from the information of FIG. The link information generation process here is a process for constructing a partial graph in which the object identifier is deleted from the bipartite graph having the object identifier and the user identifier.

That is, the link information generation unit 214 acquires the first object identifier “1” in accordance with the operation of the flowchart of FIG. Next, the link information generation unit 214 reads all operation information including the first object identifier “1” from the operation information storage unit 111. Then, the link information generation unit 214 obtains operation information “(A, 1, 1) (B, 1, 2)”. In this operation information, time information is excluded. The link information generation unit 114 takes out the user identifiers “A” and “B” from the operation information “(A, 1, 1) (B, 1, 2)” and adds weights including all combinations of the two user identifiers. Link information (A, B, 2) is obtained. The link information generation unit 214 then writes a plurality of weighted link information (A, B, 2) in the buffer. Note that “2” in (A, B, 2) is the total number of operations (number of links). That is, the relevance calculation means 2144 calculates the number of operations performed on each object indicated by the two object identifiers as the relevance. That is, the relevance calculation means 2144 calculates the relevance only by the number of operations without using the weight information for each type of operation. As described in the specific example of the first embodiment, it is needless to say that the relevance calculation unit 2144 may calculate the relevance using the weight information.

Then, the link information generation unit 214 performs the same processing for the second and subsequent object identifiers, and obtains a data group shown in FIG. The data constituting the data group in FIG. 21 has a structure of (jth user identifier, kth user identifier, weight information). The link information generation unit 214 accumulates the link information group of FIG. 21 in a storage medium.

The process in which the link information generation unit 214 acquires the link information group in FIG. 21 is a process for generating a partial graph in FIG. 22 from the bipartite graph in FIG. The partial graph in FIG. 22 is a graph having a user identifier as a node, and weight information is given. The weight information is the numerical value of FIG.

In such a situation, a technology in which the information processing apparatus 21 dynamically forms a community will be described.

For example, it is assumed that the user “E” inputs the user identifier “E” to the terminal device 12 and connects to the information processing device 21. That is, it is assumed that the user identifier “E” is transmitted from the terminal device 12 to the information processing device 21.

Next, the receiving unit 215 receives the user identifier “E”. Then, the in-group identifier acquisition unit 216 selects a user who has a conversation with the user “E” in chat, SNS, or the like using an algorithm as described below.

That is, the in-group identifier acquisition unit 216 acquires all the nodes (user identifiers) directly connected with the user identifier “E” and the link strength “5” or more. Then, the in-group identifier acquisition unit 216 obtains “B” and “F”. Next, the user identifier “C” connected to the user identifier “B” or “F” with the link strength of “5” or more is acquired. As a result, the in-group identifier acquisition unit 216 acquires the user identifiers “B”, “C”, and “F” and arranges them on the memory.

The in-group information output unit 217 uses the user identifiers “B”, “C”, and “F” to acquire each person's user information (for example, a user profile or an e-mail address) from the user information storage unit 219. Then, the in-group information output unit 217 transmits the acquired user information to the terminal device 12.

Next, the terminal device 12 receives and outputs user information of three people “B”, “C”, and “F”.

As described above, according to the present embodiment, it is possible to introduce a person who matches the user's action (a person who will match the user's preference). Specifically, according to the present embodiment, it is possible to present information on a person who is rich in serendipity.

Note that according to the present embodiment, the presentation of human information is triggered by the user accessing the information processing apparatus 21 (for example, logging in). However, the information may be presented by an explicit instruction from the user or another trigger.

In the present embodiment, the weight information corresponding to each of the plurality of operations may be the same or different. When the weight information corresponding to each of the plurality of operations is the same, the operation-specific weight information storage unit 118 may not exist. In such a case, the weight information acquisition unit 1143 acquires the same weight information regardless of the operation identification information. In this case, the information processing apparatus is included in the following information processing apparatus. That is, an operation information storage unit capable of storing two or more pieces of operation information including a user identifier for identifying a user, an object identifier for identifying an object operated by the user, and operation identification information for identifying the operation. , Reading two or more pieces of operation information from the operation information storage unit, detecting two or more user identifiers connected via an object identifier included in each of the two or more pieces of operation information, and linking between two or more users A link information generation unit that generates link information that is information indicating a relationship and has link strength between the two or more users, a reception unit that receives one user identifier, and the link information generation unit An intra-group identifier acquisition unit that acquires a user identifier having a degree of association greater than or equal to the one user identifier received by the previous reception unit using the generated link information; An information processing apparatus for and a group in the information output unit for outputting user information related to the user of the in-group identifier acquiring unit is identified by a user identifier or the user identifier acquired.

Furthermore, the software that realizes the information processing apparatus in the present embodiment is the following program. That is, this program reads two or more pieces of operation information from a storage medium, detects two or more user identifiers connected via the object identifiers of the two or more pieces of operation information, A link information generation unit that generates link information that is information indicating a link relationship between the two users, and has information on the link strength between the two or more users, a reception unit that receives one user identifier, An intra-group identifier acquisition unit that acquires a user identifier having a degree of association greater than or equal to the one user identifier received by the previous reception unit using the link information generated by the link information generation unit, and the intra-group identifier In-group information output that outputs user information acquired by the acquisition unit or user information that is information related to the user identified by the user identifier. Program for functioning as a part, is.

In the above program, the link information generation unit detects two or more user identifiers connected via an object identifier included in the two or more pieces of operation information, and a link relationship between the two or more users. Related information acquisition means for acquiring related information that is information indicating operation, operation identification information acquisition means for acquiring operation identification information included in each of the two or more pieces of operation information, and operation identification information acquired by the operation identification information acquisition means The weight information that is paired with the weight information acquisition means that acquires the weight information from the storage medium, and the weight information acquired by the weight information acquisition means, the related information acquired by the related information acquisition means, two or more Using the degree-of-association calculating means for calculating the degree of association indicating the degree of association between users, the related information acquired by the related-information acquiring means, and the degree of association calculated by the related-degree calculating means , It is preferred that to function as comprising a link information forming means constituting the link information.

In the program, the reception unit receives one user identifier from the terminal device, and the intra-group information output unit is identified by the user identifier acquired by the intra-group identifier acquisition unit or the user identifier. It is preferable to cause user information, which is information relating to a user, to function as one that transmits to the terminal device.

FIG. 23 shows the external appearance of a computer that executes the program described in this specification to realize the information processing apparatus and the like according to the above-described embodiment. The above-described embodiments can be realized by computer hardware and a computer program executed thereon. FIG. 23 is an overview diagram of the computer system 340, and FIG. 24 is a diagram showing an internal configuration of the computer system 340. As shown in FIG.

23, the computer system 340 includes a computer 341 including an FD drive 3411 and a CD-ROM drive 3412, a keyboard 342, a mouse 343, and a monitor 344.

24, in addition to the FD drive 3411 and the CD-ROM drive 3412, the computer 341 stores an MPU 3413, a bus 3414 connected to the CD-ROM drive 3412 and the FD drive 3411, and a program such as a bootup program. ROM 3415 for connection, MPU 3413, RAM 3416 for temporarily storing application program instructions and providing a temporary storage space, and hard disk 3417 for storing application programs, system programs, and data . Although not shown here, the computer 341 may further include a network card that provides connection to the LAN.

A program that causes the computer system 340 to execute the functions of the information processing apparatus and the like of the above-described embodiment is stored in the CD-ROM 3501 or FD 3502, inserted into the CD-ROM drive 3412 or FD drive 3411, and further the hard disk 3417. May be transferred to. Alternatively, the program may be transmitted to the computer 341 via a network (not shown) and stored in the hard disk 3417. The program is loaded into the RAM 3416 at the time of execution. The program may be loaded directly from the CD-ROM 3501, the FD 3502, or the network.

The program does not necessarily include an operating system (OS) or a third-party program that causes the computer 341 to execute the functions of the information processing apparatus according to the above-described embodiment. The program only needs to include an instruction portion that calls an appropriate function (module) in a controlled manner and obtains a desired result. How the computer system 340 operates is well known and will not be described in detail.

In the above program, in a transmission step for transmitting information, a reception step for receiving information, etc., processing performed by hardware, for example, processing performed by a modem or an interface card in the transmission step (only performed by hardware). Not included) is not included.

Further, the computer that executes the program may be singular or plural. That is, centralized processing may be performed, or distributed processing may be performed.

Further, in each of the above embodiments, it goes without saying that two or more communication means (operation information receiving unit, receiving unit, etc.) existing in one device may be physically realized by one medium.

In each of the above embodiments, each process (each function) may be realized by centralized processing by a single device (system), or by distributed processing by a plurality of devices. May be.

The present invention is not limited to the above-described embodiment, and various modifications are possible, and it goes without saying that these are also included in the scope of the present invention.

As described above, the information processing system according to the present invention has an effect that information can be output using information on a plurality of types of operations on a user's object, and is useful as a recommendation engine system or the like.

Conceptual diagram of information processing system 1 according to Embodiment 1 Block diagram of the information processing system Conceptual diagram of the relationship network to be analyzed Diagram explaining the algorithm for calculating the link importance considering the mutual importance Flow chart for explaining the operation of the information processing apparatus A flowchart for explaining the operation of the link information generation process Flowchart for explaining object identifier acquisition processing in the group Figure showing the object management table The figure which shows the weight information management table according to the same operation Figure showing a screen example of the website Figure showing the same operation information management table The figure which shows the information which can be acquired from the same operation information management table The figure which shows the data group which the link information generation part acquired Conceptual diagram of the bipartite graph Conceptual diagram of the same part graph Schematic diagram showing the same object identifier group Block diagram of an information processing system in the second embodiment Flow chart for explaining the operation of the information processing apparatus A flowchart for explaining the operation of the link information generation process Flow chart for explaining the operation of the user identifier acquisition process in the same group The figure which shows the data group which the link information generation part acquired Conceptual diagram of the same part graph Overview of the computer system The figure which shows the internal configuration of the computer system

1, 2

Information processing system

11, 21 Information processing device 12 Terminal device 111 Operation information storage unit 112 Operation information reception unit 113 Operation

information storage unit

114, 214 Link information generation unit 115 Object

identifier reception unit

115, 215

reception unit

116, 216 In-group

identifier acquisition unit

117, 217 In-group information output unit 118 Information storage unit 119 Object advertisement information storage unit 121 Input reception unit 122 Information transmission unit 123 Information reception unit 124 Information output unit 219 User

information storage unit

1141, 2141 Related Information acquisition means 1142, 2142 Operation identification information acquisition means 1143, 2143 Information acquisition means 1144, 2144 Relevance calculation means 1145, 2145 Link information configuration means 1171 Advertisement information acquisition means 1172 Advertisement information transmission means

Claims

An operation information storage unit capable of storing two or more pieces of operation information including a user identifier for identifying a user, an object identifier for identifying an object operated by the user, and operation identification information for identifying the operation;
Two or more pieces of operation information are read from the operation information storage unit, two or more object identifiers connected via user identifiers of the two or more pieces of operation information are detected, and a link between the two or more objects is detected. A link information generating unit that generates link information that is information indicating a relationship and is information having a link strength between the two or more objects;
A reception unit for receiving one object identifier;
Using the link information generated by the link information generation unit, an in-group identifier acquisition unit that acquires an object identifier having a strength of a predetermined degree of association with the one object identifier received by the previous reception unit;
An information processing apparatus comprising: an object identifier obtained by the in-group identifier obtaining unit or an object information output unit that outputs object information that is information relating to an object identified by the object identifier.
An operation-specific weight information storage unit that stores operation-specific weight information having operation identification information and weight information that is information about link weights;
The link information generation unit
Related information for detecting two or more object identifiers connected via a user identifier included in each of the two or more operation information, and acquiring related information that is information indicating a link relationship between the two or more objects. Acquisition means;
Operation identification information acquisition means for acquiring operation identification information included in each of the two or more pieces of operation information;
Weight information acquisition means for acquiring weight information paired with the operation identification information acquired by the operation identification information acquisition means from the operation-specific weight information storage unit;
Relevance calculation means for calculating relevance indicating the relevance degree between two or more objects with respect to the related information acquired by the related information acquisition means using the weight information acquired by the weight information acquisition means;
The information processing apparatus according to claim 1, further comprising: link information configuring means that configures link information using the related information acquired by the related information acquiring means and the related degree calculated by the related degree calculating means.
The reception unit
Receiving one object identifier from the terminal device;
The in-group information output unit
The information processing according to claim 1 or 2, wherein the object identifier acquired by the in-group identifier acquisition unit or the object information that is information related to the object identified by the object identifier is transmitted to the terminal device. apparatus.
A target advertisement information storage unit capable of storing target advertisement information having a target identifier and advertisement information that is information for promoting the target identified by the target identifier;
The in-group information output unit
Advertising information acquisition means for acquiring advertisement information paired with the object identifier acquired by the in-group identifier acquisition unit from the object advertisement information storage unit;
The information processing apparatus according to claim 1, further comprising: an advertisement information transmitting unit that transmits the advertisement information acquired by the advertisement information acquiring unit to the terminal device.
An operation information storage unit capable of storing two or more pieces of operation information including a user identifier for identifying a user, an object identifier for identifying an object operated by the user, and operation identification information for identifying the operation;
Two or more pieces of operation information are read from the operation information storage unit, two or more user identifiers connected via the object identifiers of the two or more pieces of operation information are detected, and a link relationship between two or more users A link information generating unit that generates link information that is information indicating the link strength between the two or more users.
A reception unit for receiving one user identifier;
Using the link information generated by the link information generation unit, an intra-group identifier acquisition unit that acquires one user identifier received by the previous reception unit and a user identifier having a degree of association of a predetermined level or more;
An information processing apparatus comprising: a user identifier acquired by the intra-group identifier acquisition unit or an intra-group information output unit that outputs user information that is information relating to a user identified by the user identifier.
An operation-specific weight information storage unit that stores operation-specific weight information having operation identification information and weight information that is information about link weights;
The link information generation unit
Related information acquisition for detecting two or more user identifiers connected via object identifiers of the two or more pieces of operation information and acquiring related information that is information indicating a link relationship between the two or more users. Means,
Operation identification information acquisition means for acquiring operation identification information included in each of the two or more pieces of operation information;
Weight information acquisition means for acquiring weight information paired with the operation identification information acquired by the operation identification information acquisition means from the operation-specific weight information storage unit;
Relevance calculation means for calculating a relevance degree indicating a relevance degree between two or more users with respect to the related information acquired by the related information acquisition means using the weight information acquired by the weight information acquisition means;
The information processing apparatus according to claim 5, further comprising: link information configuring means that configures link information using the related information acquired by the related information acquiring means and the related degree calculated by the related degree calculating means.
The reception unit
Receiving one user identifier from the terminal device;
The in-group information output unit
The information processing apparatus according to claim 5, wherein the user identifier acquired by the intra-group identifier acquisition unit or user information that is information related to a user identified by the user identifier is transmitted to the terminal device.
An information processing method realized by a link information generation unit, a reception unit, an in-group identifier acquisition unit, and an in-group information output unit,
The link information generation unit reads two or more pieces of operation information from the storage medium, detects two or more target identifiers connected via user identifiers of the two or more pieces of operation information, and detects two or more subjects. A link information generating step for generating link information, which is information indicating a link relationship between objects, and is information having a link strength between the two or more objects;
A reception step of receiving one object identifier by the reception unit;
Using the link information generated in the link information generation step, the intra-group identifier acquisition unit acquires an object identifier that is received in the previous reception step and has a degree of association greater than or equal to a predetermined object identifier. An in-group identifier acquisition step,
An in-group information output step for outputting the object identifier obtained by the in-group identifier obtaining step or the object information that is information on the object identified by the object identifier by the in-group information output unit; Information processing method provided.
An information processing method realized by a link information generation unit, a reception unit, an in-group identifier acquisition unit, and an in-group information output unit,
The link information generation unit reads two or more pieces of operation information from the storage medium, detects two or more user identifiers connected via the object identifiers of the two or more pieces of operation information, and two or more users Link information generating step for generating link information, which is information indicating a link relationship between the two or more users, and is information having link strength between the two or more users;
An accepting step of accepting one user identifier by the accepting unit;
Using the link information generated in the link information generation step, the intra-group identifier acquisition unit acquires a user identifier having a degree of association greater than or equal to the one user identifier received in the previous reception step. An in-group identifier acquisition step;
Information processing comprising: an intra-group information output step for outputting user information obtained by the intra-group identifier output unit by the intra-group identifier acquisition step or user information that is information relating to a user identified by the user identifier Method.
Computer
Two or more pieces of operation information are read from the storage medium, two or more object identifiers connected via user identifiers of the two or more pieces of operation information are detected, and a link relationship between the two or more objects is shown. A link information generating unit that generates link information that is information and information having a link strength between the two or more objects;
A reception unit for receiving one object identifier;
Using the link information generated by the link information generation unit, an in-group identifier acquisition unit that acquires an object identifier having a strength of a predetermined degree of association with the one object identifier received by the previous reception unit;
A program for functioning as an in-group information output unit that outputs an object identifier acquired by the in-group identifier acquisition unit or object information that is information relating to an object identified by the object identifier.
Computer
Information that reads two or more pieces of operation information from the storage medium, detects two or more user identifiers connected via the object identifiers of the two or more pieces of operation information, and indicates a link relationship between the two or more users A link information generating unit that generates link information that is information having link strength between the two or more users;
A reception unit for receiving one user identifier;
Using the link information generated by the link information generation unit, an intra-group identifier acquisition unit that acquires one user identifier received by the previous reception unit and a user identifier having a degree of association of a predetermined level or more;
A program for functioning as an intra-group information output unit for outputting user information acquired by the intra-group identifier acquisition unit or user information that is information relating to a user identified by the user identifier.