Information processing device, information processing method and program

Abstract

To accurately determine identity of a person who uses a plurality of object accounts.SOLUTION: An information processing device comprises a specification unit and a determination unit. The specification unit specifies a first acquaintance account group and a second acquaintance account group associated with each of a first object account and a second object account. The determination unit determines identity of persons who use the first and second object accounts on the basis of similarity between a first person group and a second person group who use each of the first acquaintance account group and the second acquaintance account group.SELECTED DRAWING: Figure 1

Description

[Technical field]

[0001] The present invention relates to an information processing device, an information processing method, and a program. [Background technology]

[0002] Various SNS (social networking services) are widely used, and the same person may use multiple accounts. When using information provided on SNS (SNS information) for various purposes such as marketing and personnel surveys of job seekers and university applicants, it is useful to be able to determine the identity of a person using multiple accounts.

[0003] For example, Patent Document 1 discloses a reliability analysis system that determines whether multiple accounts belong to the same person by calculating the similarity between an account and a friend account of the account, weighting the similarity based on the reliability of the account.

[0004] In the reliability analysis system described in Patent Document 1, the similarity derived from the friend account is the similarity of the subject image extracted from the posted images obtained by acquiring the posted images of the friend accounts based on the friend lists of each of account A and account B. Also, the similarity derived from the account is the similarity of the subject image extracted from the posted images of each of account A and account B. In the reliability analysis system described in Patent Document 1, when the reliability of account A and account B is low, the similarity derived from the friend account is emphasized. [Prior art documents] [Patent documents]

[0005] [Patent Document 1] International Publication No. 2021 / 260841 Summary of the Invention [Problem to be solved by the invention]

[0006] Generally, even if the person using the friend accounts included in the friend lists of account A and account B is the same, the person may post different posted images to each of the friend accounts. In such cases, the similarity derived from the friend accounts described in Patent Document 1 may not be a value that appropriately indicates whether account A and account B are derived from the same person.

[0007] In view of the above-mentioned problems, one example of an object of the present invention is to provide an information processing device, an information processing method, a program, etc. that are capable of accurately determining the identity of a person who uses multiple target accounts. [Means for solving the problem]

[0008] According to one aspect of the present invention, a method for identifying a first acquaintance account group and a second acquaintance account group associated with a first target account and a second target account, respectively, includes: and a determination means for determining the identity of a person using the first target account and the second target account based on a similarity between a first group of people and a second group of people using the first acquaintance account group and the second acquaintance account group, respectively. An information processing device is provided.

[0009] According to one aspect of the present invention, one or more computers are Identifying a first acquaintance account group and a second acquaintance account group associated with the first target account and the second target account, respectively; Determining the identity of the person using the first target account and the person using the second target account based on a similarity between a first group of people and a second group of people who use the first group of acquaintance accounts and the second group of acquaintance accounts, respectively. A method for processing information is provided.

[0010] According to one aspect of the invention, one or more computers include: Identifying a first acquaintance account group and a second acquaintance account group associated with the first target account and the second target account, respectively; A program is provided for determining the identity of persons using the first target account and the second target account based on the similarity between a first group of persons and a second group of persons using the first group of acquaintance accounts and the second group of acquaintance accounts, respectively. Effect of the Invention

[0011] According to one aspect of the present invention, it is possible to accurately determine the identity of a person who uses multiple target accounts. [Brief description of the drawings]

[0012] [Figure 1] FIG. 1 is a diagram illustrating an overview of an information processing device. [Diagram 2] 1 is a flowchart showing an overview of information processing. [Diagram 3] FIG. 1 illustrates an example of a configuration of an information processing system. [Figure 4] FIG. 2 is a diagram illustrating an example of a functional configuration of an information processing device. [Diagram 5] FIG. 4 illustrates an example of the functional configuration of a determination unit. [Figure 6] FIG. 2 is a diagram illustrating an example of a physical configuration of an information processing device. [Figure 7] 1 is a flowchart showing an example of information processing; [Figure 8] 13 is a flowchart illustrating an example of a determination process. [Figure 9] FIG. 11 is a diagram showing an example of a first accuracy. [Figure 10] FIG. 2 is a diagram illustrating an example of a functional configuration of a determination unit. [Figure 11] 13 is a flowchart showing another example of the identification process. [Figure 12] FIG. 11 is a diagram showing an example of a second accuracy. [Figure 13] FIG. 13 is a diagram showing another example of the first accuracy. [Figure 14]FIG. 13 is a diagram showing another example of the second accuracy. [Figure 15] FIG. 13 is a diagram showing another example of the first accuracy. DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS

[0013] Hereinafter, an embodiment of the present invention will be described with reference to the drawings. In all the drawings, the same components are denoted by the same reference numerals, and the description thereof will be omitted as appropriate.

[0014] [Outline of the embodiment] 1 is a diagram showing an overview of the information processing device 102. The information processing device 102 includes an identifying unit 122 and a determining unit 123.

[0015] The identification unit 122 identifies a first acquaintance account group and a second acquaintance account group associated with the first target account and the second target account, respectively. The determination unit 123 determines the identity of the persons using the first target account and the second target account based on the similarity between the first group of people and the second group of people using the first group of acquaintance accounts and the second group of acquaintance accounts, respectively.

[0016] According to this information processing device 102, it is possible to accurately determine the identity of a person who uses multiple target accounts.

[0017] FIG. 2 is a flowchart showing an overview of information processing.

[0018] The identification unit 122 identifies a first acquaintance account group and a second acquaintance account group associated with the first target account and the second target account, respectively (step S102). The determination unit 123 determines the identity of the persons using the first target account and the second target account based on the similarity between the first group of persons and the second group of persons using the first group of acquaintance accounts and the second group of acquaintance accounts, respectively (step S104).

[0019] This information processing makes it possible to accurately determine the identity of a person who uses multiple target accounts.

[0020] [Embodiment 1] (Example of configuration of information processing system 100) The information processing system 100 is a system for determining the identity of a person who uses multiple target accounts. The information processing system 100 includes one or multiple SNS (social networking service) management devices 101 and an information processing device 102.

[0021] Each of the one or more SNS management devices 101 is a device for providing an SNS and, for example, managing SNS information. The information processing device 102 is a device for determining the identity of a person who uses multiple target accounts (hereinafter, this will also be referred to as "target person identity"). The information processing device 102 determines the target person identity using a group of related accounts associated with each of a first target account and a second target account. The information processing device 102 determines the target person identity using, for example, SNS information of the group of related accounts.

[0022] One or more SNS management devices 101 and information processing devices 102 are connected to each other via a network NT so as to be able to transmit and receive information to and from each other. The network NT is, for example, a communication line configured using wired or wireless connections or a combination of these.

[0023] 3 is a diagram showing an example of the configuration of the information processing system 100. Each of the first SNS management device 101a and the second SNS management device 101b shown in the figure is an example of the SNS management device 101. That is, the figure shows an example in which the information processing system 100 is provided with two SNS management devices 101. As described above, the information processing system 100 may be provided with one or more SNS management devices 101, and the number of SNS management devices 101 provided in the information processing system 100 is not limited to two.

[0024] (About SNS information) SNS information is information used to provide an SNS, and is managed by one or more SNS management devices 101. For example, the first SNS management device 101a manages first SNS information, which is SNS information for providing the first SNS. For example, the second SNS management device 101b manages second SNS information, which is SNS information for providing the second SNS. The first SNS and the second SNS are different SNSs.

[0025] For example, the SNS information includes, for each account, one or more of the following: (1) user ID (Identification), (2) profile information, (3) account association information, (4) other SNS account information, (5) posting information, (6) exchange information, etc. In the SNS information, for example, the user ID is associated with other information.

[0026] The account is an account registered on a SNS, and the same applies below.

[0027] (1) A user ID is information for identifying each account on an SNS. For example, a user ID is automatically assigned when a person who uses an SNS registers as a user on the SNS. For example, the user ID does not have to be changeable by the user.

[0028] (2) Profile information is information about a user, and is registered by the user, for example. The profile information may include, for example, one or more of a display name, a date of birth, an address, a school, contact information (such as a telephone number or an email address), and any comments written for self-introduction, etc.

[0029] A display name is, for example, a name that a user uses to identify himself / herself to other users on an SNS.

[0030] In detail, for example, the display name is a name arbitrarily set by the user. The display name may be a name that is not duplicated among multiple users who use the SNS (i.e., a name that can identify each user on the SNS), or may be a name that allows duplication among multiple users. Examples of display names that allow duplication among multiple users include the user's real name, a nickname other than the real name, etc. The real name may be the last name only, the first name only, or the last name and first name.

[0031] (3) Account association information (hereinafter simply referred to as "association information") is information for associating an account identified by a user ID associated with the association information with other accounts used on the same SNS.

[0032] The association information includes, for example, information for identifying the other account (other account information). This allows an account identified using a user ID associated with the association information to be associated with the other account identified using the other account information included in the association information. Note that the method of associating the other account is not limited to this.

[0033] The accounts associated by the association information may be set according to the management policy of the SNS, for example, accounts that the user has permitted to be associated, etc. Typical examples of such accounts include accounts used by acquaintances, friends, relatives (parents, siblings, children, etc.), family members, spouses, lovers, colleagues, etc.

[0034] The association information may further include relationship information, which is information indicating a relationship between the user and a person who uses another account, such as an acquaintance, a friend, a relative (parent, sibling, child, etc.), a family member, a spouse, a partner, a colleague, etc.

[0035] (4) The other SNS account information is information for identifying accounts used by the user on other SNSs. The other SNS account information includes, for example, link information to other SNSs and accounts used by the user on the other SNSs.

[0036] (5) Posted information is information posted by a user on an SNS. The posted information may include, for example, one or more of text, images, etc.

[0037] (6) The transferred information is information transferred between an account identified by a user ID associated with the transferred information and another account. The transferred information includes one or more of the following: information sent from an account identified by a user ID to another account, information received by an account identified by a user ID from another account, etc.

[0038] The information exchanged includes, for example, one or more of a comment, a reply to a comment, a conversation, etc. A comment is text, an image, etc. received from another account in response to a post. A reply is text, an image, etc. sent from an account identified by a user ID in response to the comment. A conversation is text, an image, etc. sent or received directly (e.g., not related to a post) between an account and another account.

[0039] It should be noted that the information included in the SNS information is not limited to the examples given here.

[0040] For example, the posted information may further include location information indicating the location where the posted information was sent. For example, the exchange information may further include location information indicating the location where the exchange information was sent. This location information may be acquired using, for example, a GPS (Global Positioning System) function provided in the terminal that sent the information. The exchange information may include, for example, at least one of the time when the exchange information was sent and the time when the exchange information was received. The time may be expressed, for example, by a date and a time.

[0041] (Terms related to accounts) The following terms are used in relation to accounts in this disclosure: (1) multiple target accounts, (2) related accounts, and (3) acquaintance accounts.

[0042] (1) The multiple target accounts are accounts that are used to determine the identity of a person who uses them. For example, the multiple target accounts may be accounts that are appropriately selected as targets for determining the identity of a target person.

[0043] The plurality of target accounts may include a first target account and a second target account. The first target account and the second target account may be, for example, different target accounts arbitrarily selected from the plurality of target accounts.

[0044] In the embodiment, an example will be described in which the first target account and the second target account are accounts used in the SNS provided by the first SNS management device 101a and the second SNS management device 01b, respectively. In detail, for example, the first target account and the second target account are accounts selected as targets for determining the identity of a target person from among accounts used in the first SNS and the second SNS, respectively.

[0045] The multiple target accounts may include multiple accounts selected from accounts used in an SNS provided by one SNS management device 101. In this case, the first target account and the second target account may be accounts used in an SNS provided by the one SNS management device 101.

[0046] (2) The related account group is composed of one or more related accounts. A related account is an account associated with a target account. For example, a related account is one or more other accounts associated with the target account through association information. In detail, for example, a related account is one or more other accounts associated with the target account through association information associated with the user ID in SNS information including the user ID corresponding to the target account.

[0047] (3) The acquaintance account group is composed of one or more acquaintance accounts. An acquaintance account is one or more accounts used by a person who has a predetermined relationship with the person using the target account among related accounts. The predetermined relationship is a deep relationship, for example, a relationship in which information is exchanged. In this case, the acquaintance account group may be identified using, for example, exchange information included in the SNS information of at least one of the target account and its related account group.

[0048] In detail, for example, the acquaintance account group may be identified on the condition that the transfer information includes at least one conversation, a mutual conversation, etc., between the target account and the related account. In this case, when at least one of the following is satisfied: the transfer information of the related account includes a conversation with the target account, and the transfer information of the target account includes a conversation with the related account, the related account may be identified as an acquaintance account.

[0049] The predetermined relationship is not limited to this, and may be changed as appropriate. For example, an acquaintance account may be specified using at least one of a comment included in the exchange information, a reply to a comment, and the like, together with or instead of a conversation.

[0050] (Example of Functional Configuration of Information Processing Device 102) 4 is a diagram showing an example of the functional configuration of the information processing device 102. The information processing device 102 functionally includes an SNS information acquisition unit 121, an identification unit 122, and a determination unit 123, for example.

[0051] The SNS information acquisition unit 121 acquires SNS information between a plurality of target accounts and a group of acquaintance accounts identified by the identification unit 122 for each of the target accounts.

[0052] For example, the SNS information acquisition unit 121 acquires SNS information between a first target account and a first acquaintance account group identified for the first target account from the first SNS management device 101a, and acquires SNS information between a second target account and a second acquaintance account group identified for the second target account from the second SNS management device 101b.

[0053] The identification unit 122 identifies a group of acquaintance accounts associated with each of the multiple target accounts.

[0054] For example, the identification unit 122 identifies a first acquaintance account group and a second acquaintance account group associated with the first target account and the second target account, respectively.

[0055] The determination unit 123 determines the identity of the people using the multiple target accounts based on the similarity of the people using the acquaintance accounts identified by the identification unit 122 for each of the multiple target accounts.

[0056] The similarity of the group of people is expressed, for example, using an acquaintance similarity, which is a value calculated based on a first certainty. The first certainty is a value indicating the likelihood that the people using the acquaintance accounts are the same. The first certainty may be calculated, for example, using SNS information associated with the acquaintance account (for example, SNS information associated with the user ID of the acquaintance account).

[0057] In detail, for example, the determination unit 123 determines whether the people who use the first target account and the second target account are the same people based on the similarity between the first person group and the second person group. The first person group and the second person group are people who use the first acquaintance account group and the second acquaintance account group, respectively.

[0058] 5 is a diagram showing an example of the functional configuration of the determination section 123. The determination section 123 functionally includes a first accuracy calculation section 124, a similarity calculation section 125, and an identity determination section 126, for example.

[0059] The first accuracy calculation unit 124 calculates a first accuracy for a combination of acquaintance accounts constituting an acquaintance account group identified for each of the different target accounts.

[0060] In detail, for example, the first accuracy calculation unit 124 calculates the first accuracy for each combination of a first acquaintance account constituting the first acquaintance account group and a second acquaintance account constituting the second acquaintance account group.

[0061] The first certainty is a value indicating the likelihood that the person using the first acquaintance account and the second acquaintance account is the same person. The first certainty is calculated based on the similarity of the SNS information associated with the first acquaintance account and the second acquaintance account.

[0062] The similarity calculation unit 125 uses the first certainty calculated by the first certainty calculation unit 124 to calculate an acquaintance similarity indicating the similarity of a group of people who use the acquaintance account group identified for each of the multiple target accounts.

[0063] In detail, for example, the similarity calculation section 125 uses the first certainty calculated by the first certainty calculation section 124 to calculate an acquaintance similarity, which is a value indicating the similarity between the first person group and the second person group.

[0064] The similarity calculation unit 125 functionally includes, for example, a common acquaintance specification unit 125a and an acquaintance similarity calculation unit 125b.

[0065] The common acquaintance identification unit 125a uses the first accuracy to identify a common acquaintance account that is a combination of a first acquaintance account and a second acquaintance account used by the same person. For example, the common acquaintance account may be identified such that both the first acquaintance account and the second acquaintance account are different from other common acquaintance accounts.

[0066] The acquaintance similarity calculation unit 125b calculates an acquaintance similarity by using the first accuracy calculated for the common acquaintance account identified by the common acquaintance identification unit 125a.

[0067] The identity determination unit 126 determines the identity of the person using multiple target accounts, based on the acquaintance similarity calculated by the similarity calculation unit 125. For example, the identity determination unit 126 determines the identity of the person using the first target account and the second target account, based on the acquaintance similarity calculated by the similarity calculation unit 125.

[0068] (Example of a physical configuration of the information processing system 100) The information processing system 100 is physically composed of one or more SNS management devices 101 and information processing devices 102 that are connected via a network NT. Each of the one or more SNS management devices 101 and the information processing devices 102 is composed of a single device that is physically different.

[0069] It is preferable that one or more SNS management devices 101 and information processing devices 102 each have the same physical configuration. Here, an example of the physical configuration will be described with reference to the drawings, taking the information processing device 102 as an example.

[0070] 6 is a diagram showing an example of the physical configuration of the information processing device 102. The information processing device 102 physically includes, for example, a bus 1010, a processor 1020, a memory 1030, a storage device 1040, a network interface 1050, an input interface 1060, and an output interface 1070.

[0071] The bus 1010 is a data transmission path for transmitting and receiving data among the processor 1020, memory 1030, storage device 1040, network interface 1050, input interface 1060, and output interface 1070. However, the method of connecting the processor 1020 and other components to each other is not limited to bus connection.

[0072] The processor 1020 is implemented by a central processing unit (CPU) or a graphics processing unit (GPU).

[0073] The memory 1030 is a main storage device realized by a RAM (Random Access Memory) or the like.

[0074] The storage device 1040 is an auxiliary storage device realized by a hard disk drive (HDD), a solid state drive (SSD), a memory card, a read only memory (ROM), or the like. The storage device 1040 stores program modules for realizing the functions of a device (information processing device 102 in the example of FIG. 6) that includes the storage device 1040. The processor 1020 loads each of these program modules into the memory 1030 and executes them to realize the function corresponding to the program module.

[0075] The network interface 1050 is an interface for connecting a device having the network interface 1050 (in the example of FIG. 6, the information processing device 102) to the network NT.

[0076] The input interface 1060 is an interface for a user to input information, and is configured with, for example, a touch panel, a keyboard, a mouse, and the like.

[0077] The output interface 1070 is an interface for presenting information to a user, and is configured, for example, by a liquid crystal panel, an organic EL (Electro-Luminescence) panel, or the like.

[0078] The physical configuration of the information processing system 100 is not limited to this. For example, the multiple SNS management devices 101 may be configured as a single device, and the single device may have the functions of the multiple SNS management devices 101. Also, one or more SNS management devices 101 and the information processing device 102 may be configured as a single device, and the single device may have the functions of one or more SNS management devices 101 and the information processing device 102. The multiple SNS management devices 101 here may be a part of the multiple SNS management devices 101 included in the information processing system 100, or may be all of them. Also, the single device may be physically configured in the same manner as the information processing device 102 illustrated in FIG. 6, for example.

[0079] (Example of operation of information processing system 100) From here, the operation of the information processing system 100 will be described with reference to the drawings. In the information processing system 100, for example, the information processing device 102 executes information processing. The information processing is processing for determining the identity of a person who uses multiple target accounts.

[0080] The information processing is started, for example, when the designation of multiple target accounts is accepted. Note that the trigger for starting the information processing is not limited to this.

[0081] Hereinafter, information processing will be described using an example in which the identity of a person using a first target account and a second target account included in a specified number of target accounts is determined.

[0082] FIG. 7 is a flowchart showing an example of information processing.

[0083] The SNS information acquisition unit 121 acquires SNS information of a first target account and a second target account from the first SNS management device 101a and the second SNS management device 101b, respectively (Step S101).

[0084] For example, the SNS information acquisition unit 121 acquires the first SNS information of the first target account (i.e., the first SNS information associated with the user ID of the first target account) from the first SNS management device 101a. Also, for example, the SNS information acquisition unit 121 acquires the second SNS information of the second target account (i.e., the second SNS information associated with the user ID of the second target account) from the second SNS management device 101b.

[0085] Here, the SNS information acquisition unit 121 may acquire at least the association information and the transfer information associated with the user IDs of the first target account and the second target account.

[0086] The identifying unit 122 identifies a first acquaintance account group and a second acquaintance account group by using the SNS information acquired in step S101 (step S102).

[0087] For example, the identifying unit 122 identifies a first acquaintance account group that satisfies a predetermined relationship from a first related account group associated by association information included in the first SNS information.

[0088] In detail, for example, the identification unit 122 refers to the transfer information of one or more first related accounts constituting the first related account group, and identifies the account of one or more user IDs associated with the transfer information including the conversation as the first acquaintance account. In this way, the identification unit 122 identifies a first acquaintance account group consisting of one or more first acquaintance accounts.

[0089] Also, for example, the identifying unit 122 identifies a second acquaintance account group that satisfies a predetermined relationship from a second related account group associated by the association information included in the second SNS information.

[0090] In detail, for example, the identification unit 122 refers to the transfer information of one or more second related accounts constituting the second related account group, and identifies the account of one or more user IDs associated with the transfer information including the conversation as the second acquaintance account. In this way, the identification unit 122 identifies a second acquaintance account group consisting of one or more second acquaintance accounts.

[0091] The SNS information acquisition unit 121 acquires SNS information of the first acquaintance account group and the second acquaintance account group identified in step S102 from the first SNS management device 101a and the second SNS management device 101b, respectively (step S103).

[0092] For example, the SNS information acquisition unit 121 acquires the first SNS information of the first acquaintance account group (i.e., the first SNS information associated with each user ID of one or more first acquaintance accounts) from the first SNS management device 101a. Also, for example, the SNS information acquisition unit 121 acquires the second SNS information of the second acquaintance account group (i.e., the second SNS information associated with each user ID of one or more second acquaintance accounts) from the second SNS management device 101b.

[0093] The determination unit 123 determines whether the people who use the first and second target accounts are the same people based on the similarity between the first and second groups of people (step S104). The first and second groups of people here are the people who use the first and second groups of acquaintance accounts identified in step S102, respectively.

[0094] For example, the determination unit 123 uses the SNS information acquired in step S103 to obtain a first accuracy for each combination of a first acquaintance account and a second acquaintance account included in each of the first acquaintance account group and the second acquaintance account group.Then, the determination unit 123 calculates an acquaintance similarity using the first accuracy.The determination unit 123 uses the acquaintance similarity to determine the target person identity between the first target account and the second target account.

[0095] FIG. 8 is a flowchart showing an example of the determination process (step S104).

[0096] The first accuracy calculation unit 124 calculates a first accuracy for each combination of the first acquaintance account and the second acquaintance account included in each of the first acquaintance account group and the second acquaintance account group identified in step S102 (step S104a).

[0097] For example, the first accuracy calculation unit 124 calculates the first accuracy using the SNS information acquired in step S103. In general, the SNS information of accounts used by the same person is highly similar. Therefore, the first accuracy calculation unit 124 calculates the degree of similarity (similarity) of the SNS information between the first acquaintance account and the second acquaintance account for each combination of the first acquaintance account and the second acquaintance account as the first accuracy.

[0098] 9 is a diagram showing an example of a first accuracy calculated for each combination of the first acquaintance accounts A-1 to A-3 and the second acquaintance accounts B-1 to B-3. Each of the first accuracy illustrated in the figure corresponds to a similarity of SNS information for each combination of the first acquaintance accounts A-1 to A-3 and the second acquaintance accounts B-1 to B-3.

[0099] A common method may be used to calculate the similarity of the SNS information. For example, the similarity of the SNS information is at least one of the similarity of the text and the similarity of the image included in the SNS information, or a value obtained by combining these similarities (for example, a simple average value or an average value weighted by the data amount of the text and the image).

[0100] The method for calculating the first accuracy is not limited to this.

[0101] The similarity calculation unit 125 calculates an acquaintance similarity using the first certainty calculated in step S104a (step S104b).

[0102] In detail, for example, the common acquaintance identification unit 125a uses the first accuracy to identify a common acquaintance account that is a combination of a first acquaintance account and a second acquaintance account used by the same person (step S104b1).

[0103] For example, the common acquaintance identification unit 125a narrows down combinations of the first acquaintance account and the second acquaintance account using a predetermined accuracy threshold. For example, when the first accuracy illustrated in FIG. 9 is calculated and the accuracy threshold is 0.5, the common acquaintance identification unit 125a identifies combinations of the first acquaintance account and the second acquaintance account whose accuracy threshold is 0.5 or more. In the example of FIG. 9, the common acquaintance identification unit 125a identifies combinations that correspond to the underlined first accuracy (i.e., the combination of A-1 and B-1, the combination of A-3 and B-1, and the combination of A-2 and B-2).

[0104] The common acquaintance identification unit 125a identifies a common acquaintance account from the narrowed down combination of the first acquaintance account and the second acquaintance account. At this time, the common acquaintance identification unit 125a may identify the common acquaintance account such that, for example, both the first acquaintance account and the second acquaintance account are different from each other among the common acquaintance accounts.

[0105] In detail, for example, the common acquaintance identification unit 125a excludes the first acquaintance accounts and the second acquaintance accounts that have already been identified as common acquaintance accounts in order of the first certainty, and identifies a combination of the first acquaintance account and the second acquaintance account as the common acquaintance account.

[0106] In the example of FIG. 9, the common acquaintance identification unit 125a identifies the combination of A-1 and B-1, whose first accuracy is 0.9, as a common acquaintance account. Next, the common acquaintance identification unit 125a identifies the combination of A-2 and B-2, whose first accuracy is 0.8, as a common acquaintance account. The next combination with the highest first accuracy is the combination of A-3 and B-1, whose first accuracy is 0.7. However, B-1 has already been identified as a common acquaintance account in combination with A-1. Therefore, the common acquaintance identification unit 125a does not identify the combination of A-3 and B-1 as a common acquaintance account.

[0107] As a result of such processing, in the example of FIG. 9, the common acquaintance identification unit 125a identifies each combination of A-1 and B-1, and A-2 and B-2 as a common acquaintance account.

[0108] The acquaintance similarity calculation unit 125b calculates an acquaintance similarity by using the first accuracy calculated for the mutual acquaintance account identified in step S104b1 (step S104b2).

[0109] For example, the acquaintance similarity calculation unit 125b calculates the acquaintance similarity by dividing the sum of the first certainties calculated for the mutual acquaintance accounts by the smaller of the number of first acquaintance accounts and the number of second acquaintance accounts.

[0110] In the example of Fig. 9, the acquaintance similarity is 0.57, which is the sum of the first certainties 0.9 and 0.8 corresponding to the combination of A-1 and B-1 and the combination of A-2 and B-2, respectively, identified as mutual acquaintance accounts, divided by 3. Here, "3" corresponds to the smaller value of the number of people in the first acquaintance account and the number of people in the second acquaintance account. In the example of Fig. 9, the number of people in both is 3, so 3 is used as the smaller value.

[0111] The method of calculating the acquaintance similarity is not limited to this. For example, the acquaintance similarity may be the number of common acquaintance accounts, that is, the number of combinations of first acquaintance accounts and second acquaintance accounts identified as common acquaintance accounts.

[0112] The identity determination unit 126 determines whether the people using the first target account and the second target account are the same, based on the acquaintance similarity calculated in step S104b2 (step S104c), and ends the information processing.

[0113] For example, the identity determination unit 126 determines the identity of the target person based on the result of comparison between the acquaintance similarity calculated by the similarity calculation unit 125 and a predetermined similarity threshold value.

[0114] In more detail, for example, if the acquaintance similarity is 0.57 and the similarity threshold is 0.5, the identity determination unit 126 determines that the person using the first target account and the second target account is the same because the acquaintance similarity is equal to or greater than the similarity threshold. In contrast, for example, if the acquaintance similarity is less than the similarity threshold, the identity determination unit 126 determines that the person using the first target account and the second target account is not the same.

[0115] The identity determination unit 126 may output the determination result. For example, the identity determination unit 126 may display the determination result on a display unit (not shown). The determination result may include whether the first target account and the second target account are the same or not. The determination result may further include an acquaintance similarity.

[0116] However, the output method is not limited to this.

[0117] As described above, according to this embodiment, the information processing device 102 includes the specification unit 122 and the determination unit 123.

[0118] The identification unit 122 identifies a first acquaintance account group and a second acquaintance account group associated with the first target account and the second target account, respectively. The determination unit 123 determines the identity of the persons using the first target account and the second target account based on the similarity between the first group of people and the second group of people using the first group of acquaintance accounts and the second group of acquaintance accounts, respectively.

[0119] This allows for the use of similarity between the first group of people and the second group of people who use the first group of acquaintance accounts and the second group of acquaintance accounts, respectively, to determine the identity of the person who uses the first target account and the second target account. In general, the higher the similarity between the first group of people and the second group of people, the more likely it is that the person who uses the first target account and the second target account is the same. This allows for accurate determination of the identity of the person who uses multiple target accounts.

[0120] According to this embodiment, the identification section 122 includes a first accuracy calculation section 124 , a similarity calculation section 125 , and an identity determination section 126 .

[0121] The first accuracy calculation unit 124 calculates a first accuracy for each combination of a first acquaintance account constituting the first acquaintance account group and a second acquaintance account constituting the second acquaintance account group. The first accuracy indicates the likelihood that the person using the first acquaintance account and the second acquaintance account is the same person.

[0122] The similarity calculation unit 125 uses the obtained first accuracy to calculate an acquaintance similarity, which is a value indicating the similarity between the first person group and the second person group.

[0123] The identity determination unit 126 determines the identity of the person using the first target account and the second target account based on the acquaintance similarity.

[0124] This makes it possible to determine the identity of the person using the first target account and the second target account by using the similarity between the first group of people and the second group of people who use the first group of acquaintance accounts and the second group of acquaintance accounts, respectively. Therefore, it becomes possible to accurately determine the identity of the person using multiple target accounts.

[0125] According to this embodiment, the similarity calculation section 125 includes a common acquaintance specification section 125a and an acquaintance similarity calculation section 125b.

[0126] The common acquaintance identification unit 125a uses the first accuracy to identify a common acquaintance account that is a combination of a first acquaintance account and a second acquaintance account used by the same person. The acquaintance similarity calculation unit 125b calculates an acquaintance similarity using the first accuracy calculated for the identified common acquaintance account.

[0127] This makes it possible to determine the identity of the person using the first target account and the second target account by using the similarity between the first group of people and the second group of people who use the first group of acquaintance accounts and the second group of acquaintance accounts, respectively. Therefore, it becomes possible to accurately determine the identity of the person using multiple target accounts.

[0128] According to this embodiment, the common acquaintance account is specified such that both the first acquaintance account and the second acquaintance account are different from other common acquaintance accounts.

[0129] By identifying such mutual acquaintance accounts, it is possible to determine the overall similarity between the first group of people who use the first group of acquaintance accounts and the second group of people who use the second group of acquaintance accounts, respectively. Therefore, it is possible to accurately determine the identity of a person who uses multiple target accounts.

[0130] According to this embodiment, the first accuracy is calculated based on the similarity of the SNS information associated with the first acquaintance account and the second acquaintance account.

[0131] Generally, when the same person uses a first acquaintance account and a second acquaintance account, there is a high possibility that their SNS information is similar. Therefore, based on the similarity of the SNS information, it is possible to appropriately calculate the likelihood that the person using the first acquaintance account and the second acquaintance account is the same. Therefore, it is possible to accurately determine the identity of a person using multiple target accounts.

[0132] [Embodiment 2] In this embodiment, an example will be described in which, when there are multiple acquaintance accounts used by the same person in the same SNS, the multiple acquaintance accounts are integrated into one acquaintance account.

[0133] In this embodiment, for the sake of simplicity, the differences from the first embodiment will be mainly described, and the description of the points in common with the first embodiment will be omitted as appropriate.

[0134] The information processing device according to this embodiment functionally includes, for example, an identification unit 222 replacing the identification unit 222 according to the first embodiment. Except for this, the information processing device according to this embodiment may include components similar to those of the information processing device 100 according to the first embodiment functionally.

[0135] The identification unit 222, like the identification unit 122 according to the first embodiment, identifies a first acquaintance account group and a second acquaintance account group associated with the first target account and the second target account, respectively. For each of the first acquaintance account and the second acquaintance account, the identification unit 222 uses an integrated account that integrates accounts used by the same person.

[0136] 10 is a diagram showing an example of the functional configuration of the identification unit 222. The identification unit 222 includes a first acquaintance account identification unit 222a, a second accuracy calculation unit 222b, and a second acquaintance account identification unit 222c.

[0137] The first acquaintance account identifying unit 222a identifies a group of acquaintance accounts associated with the target account, similarly to the identifying unit 122 according to the first embodiment.

[0138] For example, the first acquaintance account identifying unit 222a, like the identifying unit 122 according to the first embodiment, identifies a first acquaintance account group and a second acquaintance account group associated with the first target account and the second target account, respectively.

[0139] The second certainty calculation unit 222b calculates a second certainty indicating the likelihood that the person using the account is the same for each of the acquaintance accounts identified by the first acquaintance account identification unit 222a.

[0140] For example, the second accuracy calculation unit 222b calculates a second accuracy indicating the likelihood that the person using the first acquaintance account group identified by the first acquaintance account identification unit 222a is the same. Also, for example, the second accuracy calculation unit 222b calculates a second accuracy indicating the likelihood that the person using the second acquaintance account group identified by the first acquaintance account identification unit 222a is the same.

[0141] The second acquaintance account identification unit 222c uses the second accuracy to generate an integrated account that integrates related accounts used by the same person from the group of acquaintance accounts identified by the first acquaintance account identification unit 222a, and identifies the group of acquaintance accounts.

[0142] For example, the second acquaintance account identification unit 222c identifies a combination of first acquaintance accounts for which the second accuracy calculated for the first acquaintance account group satisfies a predetermined condition, and generates an integrated account by integrating the combination of first acquaintance accounts. Then, the second acquaintance account identification unit 222c identifies a first acquaintance account group consisting of the generated integrated account and first acquaintance accounts that have not been identified as an integrated account.

[0143] For example, the second acquaintance account identification unit 222c identifies a combination of second acquaintance accounts for which the second accuracy calculated for the second acquaintance account group satisfies a predetermined condition, and generates an integrated account by integrating the combination of second acquaintance accounts. Then, the second acquaintance account identification unit 222c identifies a second acquaintance account group consisting of the generated integrated account and second acquaintance accounts that have not been identified as an integrated account.

[0144] (Example of operation of information processing system) The information processing according to this embodiment will be described with reference to FIG.

[0145] Step S101 is executed as in the first embodiment.

[0146] Next, a determination process (step S202) according to this embodiment is executed instead of the determination process (step S102) according to embodiment 1. In step S202, the determination unit 122 uses the SNS information acquired in step S101 to determine a first acquaintance account group and a second acquaintance account group, similar to step S102 according to embodiment 1.

[0147] Step S202 differs from step S102 in embodiment 1 in that if there are accounts in each of the first acquaintance account group and the second acquaintance account group that are used by the same person, an integrated account that integrates those accounts is used.

[0148] FIG. 11 is a flowchart showing another example of the identification process (step S202).

[0149] The first acquaintance account identifying unit 222a identifies a first acquaintance account group and a second acquaintance account group using the SNS information acquired in step S101, similarly to the identifying process (step S102) according to the first embodiment (step S202a).

[0150] The second accuracy calculation unit 222b calculates a second accuracy for each of the first acquaintance account group and the second acquaintance account group identified in step S202a (step S202b).

[0151] For example, the second accuracy calculation unit 222b calculates the second accuracy for each combination of first acquaintance accounts constituting the first acquaintance account group using the SNS information acquired in step S101. Also, for example, the second accuracy calculation unit 222b calculates the second accuracy for each combination of second acquaintance accounts constituting the second acquaintance account group using the SNS information acquired in step S101.

[0152] Fig. 12 is a diagram showing an example of the second accuracy. Fig. 12(a) is a diagram showing an example of the second accuracy for a first acquaintance account group (i.e., each combination of first acquaintance accounts). Fig. 12(b) is a diagram showing an example of the second accuracy for a second acquaintance account group (i.e., each combination of second acquaintance accounts).

[0153] The method of calculating the second accuracy from the SNS information may be the same as the method of calculating the first accuracy from the SNS information in the first embodiment.

[0154] When an integrated account is generated using the second accuracy, the second acquaintance account identification unit 222c identifies an acquaintance account group consisting of the integrated account and acquaintance accounts that have not been identified as the integrated account (step S202c).

[0155] For example, when the first acquaintance account group includes a combination in which the second accuracy calculated for the first acquaintance account group is equal to or greater than a predetermined reference value, the second acquaintance account identifying unit 222c generates an integrated account by integrating the combination of the first acquaintance accounts. Then, the second acquaintance account identifying unit 222c identifies the integrated account and the first acquaintance accounts not identified as the integrated account as the first acquaintance account group.

[0156] For example, when the second acquaintance account group includes a combination in which the calculated second accuracy is equal to or greater than a predetermined reference value, the second acquaintance account identifying unit 222c generates an integrated account by integrating the combination of second acquaintance accounts. Then, the second acquaintance account identifying unit 222c identifies the integrated account and the second acquaintance accounts not identified as the integrated account as the second acquaintance account group.

[0157] 12 is calculated in step S202b, and the reference value is 0.6, the second acquaintance account identification unit 222c generates an integrated account SA-1 by integrating the combination of A-1 and A-3. In this case, the second acquaintance account identification unit 222c identifies SA-1, which is an integration of A-1 and A-3, and A-2 as the first acquaintance account group. In addition, since an integrated account is not generated for the second acquaintance account group, the second acquaintance account identification unit 222c identifies B-1, B-2, and B-3 as the second acquaintance account group.

[0158] Next, the SNS information acquisition unit 121 acquires SNS information of the first acquaintance account group and the second acquaintance account group identified in step S202a from the first SNS management device 101a and the second SNS management device 101b, respectively (step S103).

[0159] That is, for the integrated account SA-1, SNS information of each of the acquaintance accounts A-1 and A-3 that each constitute the integrated account SA-1 is obtained.

[0160] When an integrated account is generated, the determination unit 123 determines the identity of the person using the multiple target accounts based on the similarity of a group of people using the acquaintance accounts group including the integrated account (step S104).

[0161] If an integrated account is not generated, the determination unit 123 may execute step S104 similar to that of embodiment 1. Therefore, an example of step S104 when an integrated account is generated will be described below. Note that, although an example will be described in which the integrated account is included in the identified first acquaintance account group, the integrated account may be included in at least one of the identified first acquaintance account group and second acquaintance account group.

[0162] As in embodiment 1, the first accuracy calculation unit 124 calculates a first accuracy for each combination of a first acquaintance account and a second acquaintance account included in each of the first acquaintance account group and the second acquaintance account group identified in step S102 (step S104a).

[0163] FIG. 13 is a diagram showing another example of the first certainty calculated for each combination of the first acquaintance accounts SA-1 and A-3 and the second acquaintance accounts B-1 to B-3.

[0164] For example, the first accuracy for a combination including the integrated account SA-1 may be calculated based on the first accuracy between each of the acquaintance accounts A-1 and A-3 constituting the integrated account SA-1 and each of the other accounts B-1 to B-3. Note that the first accuracy for a combination not including the integrated account SA-1 may be the same as that in the first embodiment.

[0165] In detail, for example, the first accuracy between the integrated account SA-1 and another account B-1 may be the maximum value, average value, etc. of the first accuracy between each of the acquaintance accounts A-1, A-3 that constitute the integrated account and the other account B-1.

[0166] Also, for example, the first accuracy for a combination including the integrated account SA-1 and each of the other accounts B-1 to B-3 may be the degree of similarity between the integrated SNS information that integrates the SNS information of the acquaintance accounts A-1 and A-3 and the SNS information of each of the other accounts B-1 to B-3.

[0167] In detail, for example, the first accuracy calculation unit 124 generates integrated SNS information by integrating the SNS information of each of the acquaintance accounts A-1 and A-3 that constitute the integrated account. The integrated SNS information may be generated, for example, by supplementing information missing from one of the acquaintance accounts A-1 and A-3 that constitute the integrated account with information from the other acquaintance accounts A-1 and A-3 that constitute the integrated account.

[0168] Then, the first accuracy calculation unit 124 calculates the degree of similarity between the generated integrated SNS information and the SNS information of each of the other accounts B-1 to B-3. The value thus calculated may be used as the first accuracy between the integrated account SA-1 and each of the other accounts B-1.

[0169] The similarity calculation unit 125 calculates the acquaintance similarity using the first certainty calculated in step S104a (step S104b), as in the first embodiment.

[0170] For example, the similarity calculation unit 125 identifies mutual acquaintance accounts in descending order of first certainty for combinations of a first acquaintance account and a second acquaintance account whose first certainty is equal to or greater than the certainty threshold (step S104b1).

[0171] In identifying the common acquaintance accounts, the similarity calculation unit 125 may exclude the first acquaintance account and the second acquaintance account that have already been identified as the common acquaintance account. This makes it possible to prevent the first acquaintance account or the second acquaintance account that has already been identified as the common acquaintance account from being identified again as a common acquaintance account in combination with another second acquaintance account or the first acquaintance account, respectively.

[0172] In more detail, for example, when the first certainty illustrated in Fig. 15 is calculated and the certainty threshold is 0.5, the common acquaintance identification unit 125a identifies combinations of first acquaintance accounts and second acquaintance accounts whose certainty threshold is equal to or greater than 0.5. In the example of Fig. 15, the common acquaintance identification unit 125a identifies the combinations that correspond to the underlined first certainty (i.e., the combination of SA-1 and B-1, and the combination of A-2 and B-2).

[0173] Then, the common acquaintance identification unit 125a excludes the first acquaintance accounts and the second acquaintance accounts that have already been identified as common acquaintance accounts in order of highest first certainty, and identifies combinations of the first acquaintance accounts and the second acquaintance accounts as common acquaintance accounts.

[0174] By performing the process of step S104b1, in the example of FIG. 13, the common acquaintance identification unit 125a identifies the combinations of SA-1 and B-1, and A-2 and B-2 as common acquaintance accounts.

[0175] The acquaintance similarity calculation unit 125b calculates an acquaintance similarity by using the first accuracy calculated for the mutual acquaintance account identified in step S104b1 (step S104b2).

[0176] In the example of FIG. 13, the acquaintance similarity is 0.8, obtained by dividing the sum of the first certainties 0.8 and 0.8 corresponding to the combination of SA-1 and B-1 and the combination of A-2 and B-2 identified as common acquaintance accounts, respectively, by 2. Here, "2" corresponds to the smaller of the number of first acquaintance accounts and the number of second acquaintance accounts. In the example of FIG. 13, the number of first acquaintance accounts is 2 and the number of second acquaintance accounts is 3, so the former number 2 is used. In other words, the integrated account is treated as one account.

[0177] As in the first embodiment, the identity determination unit 126 determines whether the people using the first target account and the second target account are the same, based on the acquaintance similarity calculated in step S104b2 (step S104c), and ends the information processing.

[0178] As described above, according to this embodiment, in each of the first acquaintance account and the second acquaintance account, accounts used by the same person are integrated.

[0179] This makes it possible to use more appropriate similarities between the first and second groups of people who use the first and second acquaintance accounts, respectively, in order to determine the identity of a person who uses the first and second target accounts, making it possible to accurately determine the identity of a person who uses multiple target accounts.

[0180] [Embodiment 3] In this embodiment, an example will be described in which relationship information is used when calculating the first accuracy. Target accounts that share a common acquaintance account, for example, a parent, lover, family member, or other such close or intimate relationship, are likely to be used by the same person.

[0181] Therefore, in this embodiment, an example is described in which the first accuracy is calculated for each combination of a first acquaintance account group and a second acquaintance account group, in which the first relationship and second relationship information indicate a predetermined relationship, and a second related account group and a first related account group.

[0182] In this embodiment, for the sake of simplicity, the differences from the above-described embodiment will be mainly described, and descriptions of the points in common with the above-described embodiment will be omitted as appropriate.

[0183] The information processing device according to this embodiment may include components similar to those of the information processing device according to the second embodiment in terms of functionality, for example.

[0184] (Example of operation of information processing system) The information processing according to this embodiment will be described with reference to FIG.

[0185] Step S101 is executed as in the first embodiment.

[0186] In the identification process (step S202) according to the present embodiment, similarly to step S102 according to the first embodiment, a first acquaintance account group and a second acquaintance account group associated with the first target account and the second target account, respectively, are identified.

[0187] In S202 according to this embodiment, if there are accounts in the first acquaintance account group and the second related account group that are used by the same person, an integrated account that integrates those accounts is used. Also, if there are accounts in the second acquaintance account group and the first related account group that are used by the same person, an integrated account that integrates those accounts is used.

[0188] The details of the identification process (step S202) according to this embodiment will be described with reference to FIG.

[0189] The first acquaintance account identifying unit 222a identifies a first acquaintance account group and a second acquaintance account group using the SNS information acquired in step S101, similarly to the identifying process (step S102) according to the first embodiment (step S202a).

[0190] For example, the first acquaintance account identification unit 222a identifies a related account whose relationship information satisfies a predetermined relationship as an acquaintance account. The predetermined relationship in this embodiment may be appropriately determined, and is preferably, for example, a very close relationship such as a parent, a lover, or a family member.

[0191] The second accuracy calculation unit 222b calculates the second accuracy of each of the first acquaintance account group and the second acquaintance account group identified in step S202a, and the first related account group and the second related account group (step S202b).

[0192] Fig. 14 is a diagram showing another example of the second certainty. Fig. 14(a) is a diagram showing an example of the second certainty for each of the first acquaintance accounts and the first related account. Fig. 14(b) is a diagram showing an example of the second certainty for each of the second acquaintance accounts associated with second relationship information indicating a predetermined relationship among the second acquaintance account group and the first related account.

[0193] Here, the first relationship information is relationship information included in the first target account and indicates a relationship with the first acquaintance account, and the second relationship information is relationship information included in the second target account and indicates a relationship with the second acquaintance account.

[0194] In the example of Figure 14, it is assumed that among the first related accounts A-1 to A-5, the first related accounts that satisfy a predetermined relationship are A-1 and A-2, and that among the second related accounts B-1 to B-4, the second related account that satisfies a predetermined relationship is B-3.

[0195] When an integrated account is generated using the second accuracy, the second acquaintance account identification unit 222c identifies an acquaintance account group consisting of the integrated account and acquaintance accounts that have not been identified as the integrated account (step S202c).

[0196] 14 is calculated in step S202b, and when the reference value is 0.6, the second acquaintance account identification unit 222c generates an integrated account SA-1 by integrating the combination of A-1 and A-3. In this case, the second acquaintance account identification unit 222c identifies SA-1, which is an integration of A-1 and A-3, and A-2 as the first acquaintance account group. In addition, since an integrated account is not generated for the second acquaintance account group, the second acquaintance account identification unit 222c identifies B-3 as the second acquaintance account group.

[0197] Next, the SNS information acquisition unit 121 acquires SNS information of the first acquaintance account group and the second acquaintance account group identified in step S202a (step S103), as in the second embodiment.

[0198] When an integrated account is generated, the determination unit 123 determines the identity of the person using the multiple target accounts based on the similarity of the person group using the acquaintance account group (step S104). Here, when an integrated account is generated, the acquaintance account group may include the integrated account. In this case, the integrated account may be included in at least one of the identified first acquaintance account group and second acquaintance account group.

[0199] A detailed example of step S104 when an integrated account is generated will be described below with reference to FIG.

[0200] The first accuracy calculation unit 124 calculates a first accuracy for each combination of one acquaintance account identified in step S102 and the other second related account (step S104a).

[0201] For example, the first accuracy calculation unit 124 calculates a first accuracy for each combination of a first acquaintance account included in the first acquaintance account group identified in step S102 and a second related account included in the second related account group. Also, for example, the first accuracy calculation unit 124 calculates a first accuracy for each combination of a second acquaintance account included in the second acquaintance account group identified in step S102 and a first related account included in the first related account group.

[0202] Fig. 15 is a diagram showing another example of the first accuracy. Fig. 15(a) is a diagram showing an example of the first accuracy calculated for each combination of the first acquaintance accounts SA-1, A-2 and the second acquaintance accounts B-1 to B-4. Fig. 15(b) is a diagram showing an example of the first accuracy calculated for each combination of the second acquaintance account B-3 and the first acquaintance accounts A-1 to A-4.

[0203] Here, a combination of an acquaintance account and an associated account that have a different relationship with the target account may be excluded when calculating the first accuracy because it is unlikely that the same person uses the combination. Therefore, in Fig. 15, the first accuracy of the combination of each of the first acquaintance accounts SA-1 and A-2 with the second acquaintance account B-3 and the combination of each of the first acquaintance accounts A-1 to A-2 with the second acquaintance account B-3 are not calculated.

[0204] Such a first certainty can also be said to be the likelihood that the first group of people and the second group of people are the same groups of people who use the second group of related accounts and the first group of related accounts, respectively. As described above, the first group of people and the second group of people are groups of people who use the first acquaintance account and the second acquaintance account, respectively.

[0205] The similarity calculation unit 125 calculates an acquaintance similarity using the first certainty calculated in step S104a (step S104b).

[0206] For example, the similarity calculation unit 125 identifies a mutual acquaintance account in the same manner as in the first embodiment (step S104b1).

[0207] By performing the process of step S104b1, in the example of FIG. 13, the common acquaintance identification unit 125a identifies the combinations of SA-1 and B-1, and A-2 and B-2 as common acquaintance accounts.

[0208] The acquaintance similarity calculation unit 125b calculates an acquaintance similarity by using the first accuracy calculated for the mutual acquaintance account identified in step S104b1 (step S104b2).

[0209] In the example of Fig. 13, the acquaintance similarity is 5.3, which is the sum of the first certainties 0.8 and 0.8 corresponding to the combination of SA-1 and B-1 and the combination of A-2 and B-2, respectively, identified as mutual acquaintance accounts, divided by 3. Here, "3" is the number of acquaintance accounts that satisfy the specified relationship.

[0210] For example, if multiple acquaintance accounts that satisfy a certain relationship include multiple acquaintance accounts with the same relationship, the multiple acquaintance accounts may be treated as one. For example, in the example of Figure 15, if the relationship of acquaintance account B-3 is not father but lover, the relationship between acquaintance account B-3 and acquaintance account A-1 is the same. In the example of Figure 15 modified in this way, the number of acquaintance accounts that satisfy the certain relationship is two.

[0211] As in the first embodiment, the identity determination unit 126 determines whether the people using the first target account and the second target account are the same, based on the acquaintance similarity calculated in step S104b2 (step S104c), and ends the information processing.

[0212] As described above, according to this embodiment, the first accuracy is calculated for each combination of the first related account and the second acquaintance account, and the combination of the second related account and the first acquaintance account.

[0213] A first related account is an account associated with a first target account. A first acquaintance account is an account among the first related accounts that satisfies a predetermined relationship. A second related account is an account associated with a second target account. A second acquaintance account is an account among the second related accounts that satisfies a predetermined relationship.

[0214] This makes it possible to obtain an acquaintance similarity indicating the degree to which acquaintance accounts used by a person who satisfies a predetermined relationship are commonly associated with the first target account and the second target account. In general, the higher the degree to which acquaintance accounts used by a person who satisfies a predetermined relationship are commonly associated with the first target account and the second target account, the higher the possibility that the person who uses the first target account and the second target account is the same. Therefore, it becomes possible to accurately determine the identity of a person who uses multiple target accounts.

[0215] [Embodiment 4] In the embodiment 1-2, an example has been described in which the first certainty is calculated for a combination of acquaintance accounts that constitute an acquaintance account group.

[0216] However, when one acquaintance account is associated with the other acquaintance account in the other SNS account information of the combination of acquaintance accounts, the first accuracy calculation unit 124 may set a predetermined value. Then, when the acquaintance account is not associated with the other SNS account information of the combination of acquaintance accounts, the first accuracy may be calculated.

[0217] In this case, the predetermined value may be the maximum value that the first certainty can take when the first certainty is a larger value as the certainty that the person using the acquaintance account is the same. Note that the predetermined value is not limited to this.

[0218] The method of using either the predetermined value or the calculated value as the first certainty by referring to the other SNS account information can be applied to any of the embodiments 1 to 3. In the embodiment 3, when an acquaintance account and a related account are associated in the other SNS account information, a predetermined value may be set as the first certainty for the combination of the acquaintance account and the related account.

[0219] As described above, according to this embodiment, the first certainty is set to a predetermined value when the first acquaintance account and the second acquaintance account are associated with each other as accounts used by the same person.

[0220] This allows the first accuracy to be set more accurately using SNS information, making it possible to accurately determine the identity of a person who uses multiple target accounts.

[0221] Although the embodiment and modified examples of the present invention have been described above with reference to the drawings, these are merely examples of the present invention, and various configurations other than those described above can also be adopted.

[0222] In addition, in the flowcharts used in the above description, multiple steps (processes) are described in order, but the order of execution of the steps performed in each of the embodiments is not limited to the order described. In each of the embodiments, the order of the steps shown in the figures can be changed to the extent that the content is not affected. In addition, the above-mentioned embodiments and modified examples can be combined to the extent that the content is not contradictory.

[0223] A part or all of the above-described embodiments can be described as, but are not limited to, the following supplementary notes.

[0224] 1. A means for identifying a first acquaintance account group and a second acquaintance account group associated with the first target account and the second target account, respectively; and a determination means for determining the identity of a person using the first target account and the second target account based on a similarity between a first group of people and a second group of people using the first acquaintance account group and the second acquaintance account group, respectively. Information processing device. 2. The determination means is a first accuracy calculation means for calculating, for each combination of a first acquaintance account constituting the first acquaintance account group and a second acquaintance account constituting the second acquaintance account group, a first accuracy indicating the likelihood that the person using the first acquaintance account and the second acquaintance account are the same person; a similarity calculation means for calculating an acquaintance similarity, which is a value indicating a similarity between the first person group and the second person group, using the calculated first certainty; and an identity determination means for determining the identity of the person using the first target account and the person using the second target account based on the acquaintance similarity. 1. An information processing device according to the present invention. 3. The similarity calculation means A common acquaintance identification means for identifying a common acquaintance account, which is a combination of the first acquaintance account and the second acquaintance account used by the same person, using the first accuracy; and an acquaintance similarity calculation means for calculating the acquaintance similarity by using the first accuracy calculated for the identified common acquaintance account. 2. An information processing device according to the present invention. 4. The common acquaintance account is specified such that both the first acquaintance account and the second acquaintance account are different from each other common acquaintance account. 3. An information processing device according to the present invention. 5. The first accuracy is calculated based on a similarity of SNS information associated with the first acquaintance account and the second acquaintance account. 5. An information processing device according to any one of 2. to 4. 6. In each of the first acquaintance account and the second acquaintance account, accounts used by the same person are integrated. 6. An information processing device according to any one of 2. to 5. 7. The first accuracy is calculated for each combination of a first related account associated with the first target account and a second acquaintance account among the second related accounts associated with the second target account that satisfies a predetermined relationship, and a combination of the second related account and the first acquaintance account among the first related accounts that satisfies the predetermined relationship. 7. An information processing device according to any one of 2. to 6. 8. The first certainty is set to a predetermined value when the first acquaintance account and the second acquaintance account are associated with each other as accounts used by the same person. 8. An information processing device according to any one of 2. to 7. 9. The first acquaintance account and the second acquaintance account are accounts that exchange information between the first target account and the second target account, respectively. 9. An information processing device according to any one of 1. to 8. 10. one or more SNS management devices each for managing SNS information; and an information processing device according to any one of claims 1 to 9, The first target account and the second target account are accounts managed by the one or more SNS management devices. Information processing system. 11. One or more computers Identifying a first acquaintance account group and a second acquaintance account group associated with the first target account and the second target account, respectively; Determining the identity of the person using the first target account and the person using the second target account based on a similarity between a first group of people and a second group of people who use the first group of acquaintance accounts and the second group of acquaintance accounts, respectively. Information processing methods. 12. Determining the identity of the person includes: calculating a first accuracy indicating a likelihood that the first acquaintance account and the second acquaintance account are used by the same person for each combination of a first acquaintance account constituting the first acquaintance account group and a second acquaintance account constituting the second acquaintance account group; calculating an acquaintance similarity, which is a value indicating a similarity between the first person group and the second person group, using the calculated first accuracy; and determining whether the person using the first target account and the second target account is the same person based on the acquaintance similarity. 11. Information processing method described above. 13. The calculating of the acquaintance similarity includes: Using the first accuracy, a common acquaintance account that is a combination of the first acquaintance account and the second acquaintance account used by the same person is identified; Calculating the acquaintance similarity using the first accuracy calculated for the identified mutual acquaintance account. 12. Information processing method described above. 14. The common acquaintance account is specified such that both the first acquaintance account and the second acquaintance account are different from each other common acquaintance account. 13. Information processing method described above. 15. The first accuracy is calculated based on a similarity of SNS information associated with the first acquaintance account and the second acquaintance account. 15. An information processing method according to any one of 12. to 14. 16. In each of the first acquaintance account and the second acquaintance account, accounts used by the same person are integrated. 15. An information processing method according to any one of 12. to 15. 17. The first accuracy is calculated for each combination of a first related account associated with the first target account and a second acquaintance account among the second related accounts associated with the second target account that satisfies a predetermined relationship, and a combination of the second related account and the first acquaintance account among the first related accounts that satisfies the predetermined relationship. 17. An information processing method according to any one of 12. to 16. 18. The first certainty is set to a predetermined value when the first acquaintance account and the second acquaintance account are associated with each other as accounts used by the same person. 17. An information processing method according to any one of 12. to 17. 19. The first acquaintance account and the second acquaintance account are accounts that exchange information between the first target account and the second target account, respectively. 18. An information processing method according to any one of 11 to 18. 20. On one or more computers, Identifying a first acquaintance account group and a second acquaintance account group associated with the first target account and the second target account, respectively; A program for executing the process of determining the identity of the people using the first target account and the second target account based on the similarity between a first group of people and a second group of people who use the first group of acquaintance accounts and the second group of acquaintance accounts, respectively. twenty one. Determining the identity of the person includes: calculating a first accuracy indicating a likelihood that the first acquaintance account and the second acquaintance account are used by the same person for each combination of a first acquaintance account constituting the first acquaintance account group and a second acquaintance account constituting the second acquaintance account group; calculating an acquaintance similarity, which is a value indicating a similarity between the first person group and the second person group, using the calculated first accuracy; and determining whether the person using the first target account and the second target account is the same person based on the acquaintance similarity. 20. The program described in. twenty two. The calculating of the acquaintance similarity includes: Using the first accuracy, a common acquaintance account that is a combination of the first acquaintance account and the second acquaintance account used by the same person is identified; Calculating the acquaintance similarity using the first accuracy calculated for the identified mutual acquaintance account. 21. The program described in. twenty three. The common acquaintance account is specified such that both the first acquaintance account and the second acquaintance account are different from each other common acquaintance account. 22. The program described in. twenty four. The first accuracy is calculated based on a similarity of SNS information associated with the first acquaintance account and the second acquaintance account. 2. A program according to any one of 21. to 23. twenty five. In each of the first acquaintance account and the second acquaintance account, accounts used by the same person are integrated. 2. A program according to any one of 21. to 24. 26. The first accuracy is calculated for each combination of a first related account associated with the first target account and a second acquaintance account among the second related accounts associated with the second target account that satisfies a predetermined relationship, and a combination of the second related account and the first acquaintance account among the first related accounts that satisfies the predetermined relationship. 2. A program according to any one of 21. to 25. 27. The first certainty is set to a predetermined value when the first acquaintance account and the second acquaintance account are associated with each other as accounts used by the same person. 27. A program according to any one of 21. to 26. 28. The first acquaintance account and the second acquaintance account are accounts that exchange information between the first target account and the second target account, respectively. 27. A program according to any one of 20. to 27. [Explanation of symbols]

[0225] 100 Information Processing Systems 100 Information processing device 101 SNS management device 101a 1st SNS management device 101b 2nd SNS management device 102 Information processing equipment 121 SNS information acquisition department 122,222 Specific part 123 Judgment section 124 First Accuracy Calculation Unit 125 Similarity calculation unit 125a Common acquaintance identification section 125b Acquaintance similarity calculation unit 126 Identity determination section 222a First acquaintance account identification section 222b Second accuracy calculation section 222c Second acquaintance account identification section

Claims

1. An identification means for identifying a first acquaintance account group and a second acquaintance account group associated with the first target account and the second target account, respectively; and a determination means for determining the identity of a person using the first target account and a person using the second target account based on a similarity between a first group of people and a second group of people using the first acquaintance account group and the second acquaintance account group, respectively. Information processing device.

2. The determination means is a first accuracy calculation means for calculating, for each combination of a first acquaintance account constituting the first acquaintance account group and a second acquaintance account constituting the second acquaintance account group, a first accuracy indicating a likelihood that the person using the first acquaintance account and the second acquaintance account are the same person; a similarity calculation means for calculating an acquaintance similarity, which is a value indicating a similarity between the first person group and the second person group, using the calculated first certainty; and an identity determination means for determining the identity of the person using the first target account and the person using the second target account based on the acquaintance similarity. The information processing device according to claim 1 .

3. The similarity calculation means a common acquaintance identification means for identifying a common acquaintance account, which is a combination of the first acquaintance account and the second acquaintance account used by the same person, by using the first accuracy; and an acquaintance similarity calculation means for calculating the acquaintance similarity by using the first accuracy calculated for the identified common acquaintance account. The information processing device according to claim 2 .

4. The common acquaintance account is specified such that both the first acquaintance account and the second acquaintance account are different from each other common acquaintance account. The information processing device according to claim 3 .

5. The first accuracy is calculated based on a similarity of SNS information associated with the first acquaintance account and the second acquaintance account. The information processing device according to claim 2 .

6. In each of the first acquaintance account and the second acquaintance account, accounts used by the same person are integrated. The information processing device according to claim 2 .

7. The first accuracy is calculated for each combination of a first related account associated with the first target account and a second acquaintance account among second related accounts associated with the second target account that satisfies a predetermined relationship, and a combination of the second related account and the first acquaintance account among the first related accounts that satisfies the predetermined relationship. The information processing device according to claim 2 .

8. The first certainty is set to a predetermined value when the first acquaintance account and the second acquaintance account are associated with each other as accounts used by the same person. The information processing device according to claim 2 .

9. One or more computers Identifying a first acquaintance account group and a second acquaintance account group associated with the first target account and the second target account, respectively; Determining the identity of the person using the first target account and the person using the second target account based on a similarity between a first group of people and a second group of people using the first group of acquaintance accounts and the second group of acquaintance accounts, respectively. Information processing methods.

10. On one or more computers, Identifying a first acquaintance account group and a second acquaintance account group associated with the first target account and the second target account, respectively; A program for executing the process of determining the identity of the persons using the first target account and the second target account based on the similarity between a first group of persons and a second group of persons using the first group of acquaintance accounts and the second group of acquaintance accounts, respectively.

Images