JP6601823B2 - Determination apparatus, determination method, and determination program - Google Patents

Description

  The present invention relates to a determination device, a determination method, and a determination program.

  2. Description of the Related Art Conventionally, techniques for detecting frauds related to objects in various services such as Internet auctions have been provided. For example, there is provided a technique for applying a mathematical model having a condition of fraudulent behavior as a condition and patroling a transaction item that is highly likely to be fraudulent.

Japanese Patent No. 4921875

  However, with the above-described conventional technology, it may be difficult to efficiently determine a suspicious object that may violate the terms of use. For example, when a mathematical model is used, it may be difficult to flexibly change the conditions of the fraud pattern, etc., and it may be difficult to efficiently determine a suspicious object that may violate the terms of use.

  The present application has been made in view of the above, and an object thereof is to provide a determination device, a determination method, and a determination program for efficiently determining a suspicious object that may violate the terms of use.

  The determination apparatus according to the present application satisfies a predetermined condition related to the specification by specifying a violation target that is a target determined to violate a use rule of the predetermined service among users who use the predetermined service. The acquisition unit that acquires the behavior information of the target user extracted as a user, the behavior information about one target included in the behavior information of the target user acquired by the acquisition unit, and the possibility of violating the terms of use And a determining unit that determines whether the one target is the suspected object based on a predetermined model used for determining a suspected object.

  According to one aspect of the embodiment, there is an effect that it is possible to efficiently determine a suspicious object that may violate the terms of use.

FIG. 1 is a diagram illustrating an example of a determination process according to the embodiment. FIG. 2 is a diagram illustrating a configuration example of the determination system according to the embodiment. FIG. 3 is a diagram illustrating a configuration example of the determination apparatus according to the embodiment. FIG. 4 is a diagram illustrating an example of an auction information storage unit according to the embodiment. FIG. 5 is a diagram illustrating an example of a user information storage unit according to the embodiment. FIG. 6 is a flowchart illustrating an example of the determination process according to the embodiment. FIG. 7 is a sequence diagram illustrating an example of a determination process according to the embodiment. FIG. 8 is a diagram illustrating another configuration example of the auction information storage unit according to the embodiment. FIG. 9 is a flowchart illustrating another example of the determination process according to the embodiment. FIG. 10 is a hardware configuration diagram illustrating an example of a computer that realizes the function of the determination apparatus.

  Hereinafter, a mode for carrying out a determination device, a determination method, and a determination program according to the present application (hereinafter referred to as “embodiment”) will be described in detail with reference to the drawings. Note that the determination device, the determination method, and the determination program according to the present application are not limited to the embodiment. In the following embodiments, the same portions are denoted by the same reference numerals, and redundant description is omitted.

(Embodiment)
[1-1. Determination process〕
An example of the determination process according to the embodiment will be described with reference to FIG. FIG. 1 is a diagram illustrating an example of a determination process according to the embodiment. In FIG. 1, the determination device 100 (see FIG. 3) acquires information related to an auction (hereinafter also referred to as “auction information”) from the service providing device 50 (see FIG. 2) that provides an auction service. A case where it is determined whether or not the included exhibit is a suspected exhibit is shown. It should be noted that the exhibit here refers to various products and services that are exhibited in the auction service provided by the service providing apparatus 50. Hereinafter, “product or service” may be simply referred to as “product”.

  In the following, an exhibit that is determined to violate the service terms of service is referred to as a “violated item”, and an item that is determined to be in violation of the service terms of service is referred to as a “suspected item”. There is a case. Exhibits that violate the terms of service for use here include, for example, products that are offensive to public order and morals, products that are likely to be used for crimes, and products that infringe on the rights of others (such as copyright). Note that the above is an example, and what kind of product (target) is a violating product (violating target) or a suspicious product (suspected target) may vary depending on the service terms of service.

  For example, the determination apparatus 100 determines whether the exhibit is a suspected exhibit based on the user behavior information. In the example of FIG. 1, the determination apparatus 100 illustrates a case in which information regarding an exhibit added to the watch list in the auction service is used among the behavior information of the user who uses the auction service. For example, the determination apparatus 100 uses information related to the exhibit added to the watch list among the user information stored in the user information storage unit 122 (FIG. 5).

  The watch list here is a predetermined list associated with the user, and when the user adds the item to his / her watch list, the user can select the highest bid price, the remaining bid amount of the item. It is possible to confirm the time or receive a predetermined notification such as an e-mail when the auction end time of the exhibit is approaching. For example, each user browses auction information (exhibits) on a site where an auction service is provided, and designates (selects) an exhibit having a predetermined relationship by showing interest or interest. , Add items to your watchlist. For example, each user designates (selects) an exhibit that he / she wishes to purchase or grasps the bidding process, thereby adding the exhibit to his / her watch list. For example, the watch list of each user includes an exhibit that reflects each user's hobbies and preferences according to the designation of the exhibit for each user. In the following, a case where the selection of an exhibit to be added to the watch list is designated is shown, but the designation of the exhibit may be any user action. For example, the user designation may include the user bookmarking information including a predetermined target. For example, the user designation may include the user bookmarking a web page containing the exhibit. For example, the user designation may include that the user browses information including a predetermined target for a predetermined time or more. For example, the designation of the user may include the user browsing a web page including the exhibit for a predetermined time or more. Note that the above is an example, and any action (for example, purchase of a product or use of a service) may be designated by the user as long as the action can be specified by the action of the user.

  For example, the watch list LT1 in FIG. 1 indicates the watch list of the user U1 identified by the user ID “U1”. As described above, when “user U * (* is an arbitrary numerical value)” is described, it indicates that the exhibit is a user identified by the user ID “U *”. For example, when “user U2” is described, the user is a user identified by the user ID “U2”.

  In the following, when “exhibit AID * (* is an arbitrary numerical value)” is described, it indicates that the exhibit is an exhibit in an auction identified by an auction ID “AID *”. For example, when “exhibit AID1” is described, the exhibit is an exhibit in an auction identified by an auction ID “AID1”.

  In the example of FIG. 1, the watch list LT1 of the user U1 includes an exhibit AID1, an exhibit AID4, and an exhibit AID3. In the example of FIG. 1, each node corresponding to each user is illustrated by a circle, and each node corresponding to each auction information (exhibit) is illustrated by a rectangle. For example, the exhibit AID1 may be an exhibit related to a cartoon, and the exhibit AID4 or the exhibit AID3 may be an exhibit related to an animation.

  For example, the circular node at the left end in FIG. 1 indicates a node corresponding to the user U1. Further, for example, the node on the right side of the node corresponding to the user U1 in FIG. 1 indicates the node corresponding to the user U2. For example, the square node at the left end in FIG. 1 indicates the exhibit AID1 in the auction identified by the auction ID “AID1”. Further, for example, the node on the right side of the node corresponding to the exhibit AID1 in FIG. 1 indicates the exhibit AID2 in the auction identified by the auction ID “AID2”.

  In addition, an arrow extending from a circular node corresponding to each user in FIG. 1 to a square node corresponding to each auction information (exhibit) includes each auction information (exhibit) in the watch list of each user. Indicates whether or not.

  For example, the arrow WL1-1 extending from the node corresponding to the user U1 in FIG. 1 to the node corresponding to the exhibit AID1 indicates that the exhibit AID1 is included in the watch list LT1 of the user U1. Further, for example, an arrow WL1-2 extending from a node corresponding to the user U1 in FIG. 1 to a node corresponding to the exhibit AID3 indicates that the exhibit AID3 is included in the watch list LT1 of the user U1. Further, for example, an arrow WL1-3 extending from a node corresponding to the user U1 in FIG. 1 to a node corresponding to the exhibit AID4 indicates that the exhibit AID4 is included in the watch list LT1 of the user U1. As described above, the arrows WL1-1 to WL1-3 extending from the node corresponding to the user U1 in FIG. 1 to the nodes of the exhibits AID1, AID3, and AID4 indicate the exhibits included in the watch list LT1 of the user U1. .

  For example, the arrow WL2-1 in FIG. 1 indicates that the exhibit AID2 is included in the watch list of the user U2, and the arrow WL2-2 indicates that the exhibit AID3 is included in the watch list of the user U2. Further, for example, the arrow WL2-3 indicates that the exhibit AID4 is included in the watch list of the user U2, and the arrow WL2-4 indicates that the exhibit AID5 is included in the watch list of the user U2.

  For example, the arrow WL3-1 in FIG. 1 indicates that the exhibit AID3 is included in the watch list of the user U3, and the arrow WL3-2 indicates that the exhibit AID4 is included in the watch list of the user U3. For example, the arrow WL3-3 indicates that the exhibit AID5 is included in the watch list of the user U3.

  For example, the arrow WL4-1 in FIG. 1 indicates that the exhibit AID5 is included in the watch list of the user U4, and the arrow WL4-2 indicates that the exhibit AID6 is included in the watch list of the user U4. Below, when it demonstrates without distinguishing arrow WL1-1-WL4-2 etc., it may describe as arrow WL. In the example of FIG. 1, a circular node group corresponding to each user and a rectangular node group corresponding to each auction information (exhibit) are connected by an arrow WL depending on whether or not the watch list is added. A graph GR11 is shown. For example, the graph GR11 is a bipartite graph.

  For example, the determination apparatus 100 extracts (generates) the graph GR11 from information on the watch list such as each user U1 to U4 stored in the user information storage unit 122 (see FIG. 5). Hereinafter, the determination process will be described using the graph GR11 in FIG.

  First, in the example of FIG. 1, the exhibit AID3 is determined as a violation exhibit (step S11). For example, in the administrator device 20 (see FIG. 2) used by a predetermined administrator who manages the auction service, it is determined that the exhibit AID3 is a violation exhibit. In this case, the determination device 100 acquires information indicating that the exhibit AID3 is a violation exhibit from the administrator device 20.

  Thereafter, the determination apparatus 100 extracts a target user based on the violation exhibit. For example, the determination apparatus 100 extracts, as target users, users who include the exhibit AID3, which is a violation exhibit, in the watch list. In the example of FIG. 1, the determination apparatus 100 extracts a user U1 that includes the exhibit AID3 in the watch list LT1 as a target user (step S12). In the example of FIG. 1, the determination apparatus 100 extracts the user U2 including the exhibit AID3 in the watch list as the target user (step S13). In the example of FIG. 1, the determination apparatus 100 extracts the user U3 including the exhibit AID3 in the watch list as the target user (step S14). Note that the determination apparatus 100 does not extract the user U4 that does not include the exhibit AID3 in the watch list as a target user.

  Thereafter, the determination apparatus 100 determines the suspected exhibit based on the exhibit that the target user has added to the watch list in addition to the violation exhibit. For example, the determination apparatus 100 determines an exhibit whose number included in the target user's watch list is equal to or greater than a predetermined threshold as a suspected exhibit. In the example of FIG. 1, the determination apparatus 100 determines an exhibit that includes two or more numbers in the target user's watch list as a suspected exhibit.

  In the example of FIG. 1, as shown by the arrow WL1-1, the exhibit AID1 is included only in the watch list LT1 of the user U1. Therefore, the determination apparatus 100 determines that the number of items included in the target user's watch list is “1” and is less than the threshold value “2” and that the exhibit AID1 is not a suspected exhibit (step S15).

  In the example of FIG. 1, the exhibit AID2 is included only in the watch list of the user U2, as indicated by an arrow WL2-1. Therefore, the determination apparatus 100 determines that the item AID2 is not a suspicious item, assuming that the number included in the watch list of the target user is “1” and less than the threshold value “2” (step S16).

  In the example of FIG. 1, as shown by arrows WL1-3, WL2-3, and WL3-2, the exhibit AID4 is included in the watch list of three users U1, U2, and U3. Therefore, the determination apparatus 100 determines that the exhibit AID4 is a suspected exhibit, assuming that the number included in the watch list of the target user is “3” and is equal to or greater than the threshold “2” (step S17).

  In the example of FIG. 1, as shown by arrows WL2-4 and WL3-3, the exhibit AID5 is included in the watch lists of two users U2 and U3. Therefore, the determination apparatus 100 determines the exhibit AID5 as a suspected exhibit, assuming that the number included in the watch list of the target user is “2” and is equal to or greater than the threshold “2” (step S18). Further, the exhibit AID6 is not included in any of the three watch lists of the users U1, U2, and U3 that are target users, and therefore the determination device 100 does not determine the exhibit AID6. As described above, in the example of FIG. 1, the determination device 100 determines the exhibits AID4 and AID5 as the suspected exhibits. Further, the determination device 100 provides the administrator device 20 with information related to the exhibits AID4 and AID5 determined to be suspected exhibits, which will be described in detail later.

  As described above, the determination apparatus 100 may violate the terms of use by extracting a user whose violation list is included in the watch list as a target user and setting the display target included in the user's watch list as a determination target. It is possible to efficiently determine a suspicious subject having a characteristic. For example, the determination apparatus 100 includes a small number of violating exhibits as a starting point (seed), and is included in the watch list of a user who has added the violating items to the watch list, that is, a user who is interested in the violating items. Other exhibit items to be judged are subject to judgment.

  As a result, the determination apparatus 100 assumes that a user who is interested in the violation exhibit is a user who is interested in the violation exhibit (hereinafter, “high sensitivity user”). The suspected exhibit is determined based on the behavior information of the user. Note that such a high-sensitivity user is not a user who is cheating himself, but merely a user who has a specific hobby and is different from a user who should be excluded from the auction service. Therefore, the determination device 100 does not exclude high-sensitivity users, and allows the high-sensitivity users to use the auction service while paying attention to the actions of the high-sensitivity users, so that the administrator of the auction service can perform patrol. An increase in cost to be performed can be suppressed.

  Therefore, the determination apparatus 100 narrows down the target for determining whether or not the item is a violation item by using the action information of the high-sensitivity user such as addition to the watch list of the high-sensitivity user and determining the suspected item. can do. In this manner, the determination apparatus 100 suppresses an increase in the target of the determination process by narrowing down the determination target as to whether or not the exhibit is a violation exhibit using the high-sensitivity user behavior information as the target user. Can do. As a result, the determination system 1 including the determination device 100 can efficiently determine the violating exhibits without using all of the enormous items that are exhibited in the auction service as the objects to be determined as violating items. It becomes possible.

[1-2. (Target users)
In the above-described example, in order to simplify the description, the case where the users U1, U2, and U3 who have added the exhibit AID3 that is one violated exhibit to the watch list is the target user is shown. The target user is not limited to the above, and may be extracted based on various conditions.

  For example, the determination apparatus 100 may perform the determination process on a user who has added a suspected exhibit to the watch list without being limited to the violation exhibit. In this case, the determination apparatus 100 sets the user U4 who has added the exhibit AID5 determined to be a suspected exhibit in step S18 in FIG. 1 as a target user. Thereby, the determination apparatus 100 can repeatedly determine the suspected exhibit without waiting for determination (determination) as to whether the suspected exhibit is a violating exhibit.

  For example, the determination apparatus 100 may perform the determination process for a user who has added a plurality of violating exhibits or suspected exhibits to the watch list. For example, the determination apparatus 100 may perform the determination process with a user whose number of violating items or suspicious items added to the watch list is a predetermined threshold or more as a target user. For example, the determination apparatus 100 may perform the determination process with a user whose number of violating exhibits or suspected exhibits being added to the watch list is three or more as a target user.

  In addition, for example, the determination apparatus 100 may perform the determination process by setting a user whose ratio of the violation item or the suspicious item is equal to or more than a predetermined threshold among the items included in the watch list as a target user. For example, the determination apparatus 100 may perform the determination process by setting, as a target user, a user who has a percentage of violating exhibits or suspected exhibits among the exhibits included in the watch list.

  Further, for example, when the ratio of the violation exhibits that the user has added to the watch list is equal to or greater than a predetermined threshold among the violation exhibits belonging to the predetermined category, the determination apparatus 100 performs the determination process with the user as the target user. You may go. For example, when the percentage of violation exhibits that the user has added to the watch list is 60% or more among the violation exhibits belonging to the pharmaceutical category, the determination apparatus 100 may perform the determination process with the user as the target user. Good. Note that the determination apparatus 100 may change the condition as to which user is the target user according to various information such as the number of users using the auction service and the number of exhibits.

[1-3. Use of information outside the watch list)
In the above-described example, the example in which the determination process is performed based on the information related to the exhibits included in the user's watch list has been described. However, the determination apparatus 100 can use any information as long as it can be used for the determination process. The determination process may be performed using. For example, the determination apparatus 100 may perform the determination process by appropriately using various information regarding the user's behavior. For example, the determination apparatus 100 may perform the determination process using information regarding various actions in the user's auction service. For example, the determination apparatus 100 may perform the determination process using a successful bid history, a bid history, or a browsing history in the user's auction service. For example, the determination apparatus 100 may perform the determination process with a user who makes a successful bid, bids, or browses for a violation item or a suspected item in an auction service as a target user.

  Further, for example, the determination apparatus 100 may perform the determination process using the usage information in the other service of the user. For example, the determination apparatus 100 may perform the determination process using information related to the purchase history of the user's product. In this case, the determination apparatus 100 may perform the determination process using information related to the purchase history in the electronic commerce service other than the auction service. In addition, for example, the determination apparatus 100 may perform the determination process using information regarding products added to a predetermined list such as a favorite list or a cart in the electronic commerce service. For example, the determination apparatus 100 may perform the determination process for a user who has added a violation product or a suspected product to a predetermined list such as a favorite list or a cart. In this case, the determination apparatus 100 may perform the determination process with a user whose number of violating products or suspicious products added to the predetermined list is equal to or greater than a predetermined threshold as a target user.

  In addition to the above, the determination apparatus 100 may perform the determination process using other information on the user's Internet. For example, the determination apparatus 100 may perform the determination process using information related to a visit frequency to a predetermined site, access time, and the like. In this case, the determination apparatus 100 may perform the determination process with a user whose visit frequency or access time to an illegal site is equal to or greater than a predetermined threshold as a target user. Moreover, the determination apparatus 100 may perform the determination process using information regarding a device (terminal apparatus) used by the user.

[1-4. (Judgment target = content (moving image))
In the above-described example, the example in which the determination process is performed on an exhibit in the auction service is shown. However, the determination apparatus 100 may perform the determination process on any target. For example, the determination apparatus 100 may perform determination processing on content such as a moving image. In this case, the determination apparatus 100 may perform the determination process on other content that the user who has shown interest in the content determined as illegal content is interested in, for example, illegally uploaded. Specifically, the determination apparatus 100 may perform the determination process using the other content included in the predetermined list of the user who includes the illegal content in the predetermined list such as a favorite as the target content.

[1-5. (Judgment target = user)
For example, the determination apparatus 100 may perform a determination process for the user. For example, the determination apparatus 100 may perform the determination process for a user who exchanges (transmits / receives) illegal money. In this case, the determination apparatus 100 may perform a determination process on another user to whom a user determined as a violating user has exchanged money by a money laundering (fund washing) action or the like. In addition, for example, the determination apparatus 100 performs a determination process on another user who exchanges money with a user who has illegally performed illegal activities such as trafficking of prohibited items such as ivory or organ sales. May be.

[1-6. (Judgment timing)
For example, the determination apparatus 100 may determine the timing of the determination process using various information as appropriate. For example, since the number of exhibits is enormous, the determination apparatus 100 may change the priority of performing the determination process for each exhibit according to the accuracy of the violation of the exhibit. For example, the determination apparatus 100 includes a predetermined character string that prompts short-term use (a successful bid) such as “prompt decision price” or “short term” in the product information such as the title and description of the exhibit, You may raise the priority which performs the determination process for the exhibit. Further, for example, the determination apparatus 100 may increase the priority for performing the determination process on an exhibit that is exhibited in a specific period such as midnight or a weekend.

  For example, the determination apparatus 100 may vary the timing of performing the determination process according to the user behavior pattern estimated based on the user behavior information. In the example of FIG. 1, when the action frequency of the user U1 in the auction service for several days from the 25th of every month is higher than that in other periods, the determination apparatus 100 may A determination process may be performed based on the information. For example, the determination apparatus 100 may perform the determination process by extracting a user who has a characteristic pattern as described above and confirming the user's behavior information according to the characteristic behavior pattern. .

[1-7. Judgment of concealment (hidden words, etc.)
For example, when the exhibit is an unknown product (target), the determination apparatus 100 may perform processing on the product. For example, the determination device 100 may determine the exhibit as a violation exhibit or a suspected exhibit when the exhibit is an unknown product (target). For example, the determination apparatus 100 may determine that the exhibit AID 55 whose exhibit name is a predetermined slang “Hidden word A” is an unknown product (target) and that the exhibit AID 55 is a violating exhibit or a suspected exhibit. Good.

  Moreover, the determination apparatus 100 may determine whether or not an unknown exhibit name indicates an infringing target using the slang list information. For example, when an unknown exhibit name is included in the slang list information, the determination apparatus 100 may determine the exhibit as a violation exhibit or a suspected exhibit. For example, the determination apparatus 100 may determine the exhibit AID 55 as an infringing exhibit or a suspected exhibit when the secret term “Kanji A” included in the exhibit name is included in the list of secret terms.

[1-8. (Judgment of violation exhibits)
For example, the determination apparatus 100 may determine whether the exhibit is a violation exhibit. For example, the determination apparatus 100 may determine whether or not a suspected exhibit is a violation exhibit among the exhibits. For example, the determination apparatus 100 may determine an exhibit that has been attracting attention from an extremely sensitive user as a violation exhibit. For example, the determination apparatus 100 may determine that an exhibit whose high-sensitivity user added to the watch list is equal to or greater than a predetermined threshold is a violation exhibit. Further, for example, the determination apparatus 100 may determine an exhibit in which the ratio of highly sensitive users is equal to or greater than a predetermined threshold among the users who have added one exhibit to the watch list as a violation exhibit.

  For example, the determination apparatus 100 performs evaluation by adding a plurality of evaluation information (purchasing and other service use) including a watch list, and setting a threshold when the tendency is remarkable in evaluation from a plurality of viewpoints. May be. For example, the determination apparatus 100 may determine an exhibit as a violation exhibit based on each evaluation value (score) from the viewpoint of a plurality of evaluations. For example, the determination device 100 may determine one exhibit as a violation exhibit when the sum of evaluation values (scores) from a plurality of viewpoints regarding one exhibit is equal to or greater than a predetermined threshold. For example, the determination apparatus 100 determines that the sum of the scores calculated by multiplying the number of high-sensitivity users who specified one exhibit in each viewpoint related to one exhibit and the weight of each viewpoint is equal to or greater than a predetermined threshold. In some cases, one exhibit may be determined as a violating exhibit. For example, the determination apparatus 100 multiplies the number of high-sensitivity users who added one exhibit to the watch list (X1) by the weight (W1) of the additional viewpoint of the watch list for one exhibit. You may calculate the score (S1) regarding addition of a watch list. Further, for example, the determination apparatus 100 multiplies the number of high-sensitivity users who browsed information related to one exhibit for a predetermined time or more (X2) and the weight (W2) from the viewpoint of viewing information for one exhibit. Thus, a score (S2) related to browsing of information may be calculated. In addition, for example, the determination apparatus 100 calculates a total score by adding scores from various viewpoints such as the score (S1) and the score (S2), and if the total score is equal to or greater than a predetermined threshold, May be determined as a violation exhibit. Note that the above is an example, and the determination apparatus 100 may determine violation exhibits using various information as appropriate.

[2. (Configuration of judgment system)
As illustrated in FIG. 2, the determination system 1 includes a terminal device 10, an administrator device 20, a service providing device 50, and a determination device 100. The terminal device 10, the administrator device 20, the service providing device 50, and the determination device 100 are connected via a predetermined network N so as to be communicable by wire or wirelessly. FIG. 2 is a diagram illustrating a configuration example of the determination system according to the embodiment. The determination system 1 illustrated in FIG. 2 may include a plurality of terminal devices 10, a plurality of administrator devices 20, a plurality of service providing devices 50, and a plurality of determination devices 100. Good.

  The terminal device 10 is an information processing device used by a user. The terminal device 10 receives various operations by the user. Hereinafter, the terminal device 10 may be referred to as a user. That is, hereinafter, the user can be read as the terminal device 10. The terminal device 10 described above is realized by, for example, a smartphone, a tablet terminal, a notebook PC (Personal Computer), a desktop PC, a mobile phone, a PDA (Personal Digital Assistant), or the like.

  The manager device 20 is an information processing device used by a predetermined manager who manages the auction service. The administrator device 20 is realized by, for example, a smartphone, a tablet terminal, a notebook PC, a desktop PC, a mobile phone, a PDA, or the like. For example, the predetermined manager uses the manager device 20 to determine whether the item is a violating item.

  The service providing apparatus 50 is an information processing apparatus that provides an auction service that is an electronic commerce service. For example, the service providing apparatus 50 accepts an item for sale from a user (exhibitor) and accepts a user's bid for the exhibit. Further, the service providing apparatus 50 provides auction information in the auction service to the determination apparatus 100.

  The determination apparatus 100 is an information processing apparatus that determines whether one target related to a user's behavior is a suspicious target that may violate the terms of use based on the user's behavior information. For example, the determination apparatus 100 uses a model learned with a target determined by a predetermined administrator as a suspected object as a positive example and a target that the predetermined administrator did not determine as a suspected object as a negative example. It may be determined whether the subject is a suspected subject. For example, the determination apparatus 100 learns a model (determination model) so as to output a high score (for example, “1” or the like) when action information regarding an object that is a positive example is input, and uses the determination model. Thus, it may be determined whether one object is a suspected object. For example, the determination apparatus 100 learns a determination model so as to output a low score (for example, “0” or the like) when action information related to a negative example target is input, and uses the determination model to It may be determined whether or not the subject is a suspicious subject. Note that the determination apparatus 100 may acquire a determination model from an external information processing apparatus, or may acquire a determination model from the storage unit 120 (see FIG. 3) in which the determination model is stored in advance. For example, the determination apparatus 100 uses a model that is learned by using an exhibit determined by a predetermined administrator as a suspected exhibit as a positive example and an exhibit that the predetermined administrator does not determine as a suspected exhibit as a negative example. Thus, it may be determined whether one exhibit is a suspected exhibit. For example, the determination apparatus 100 outputs a high score (for example, “1”, etc.) when a user's behavior information related to an exhibit including information on an exhibit that is a positive example is input. (Determination model) may be learned, and using the exhibit determination model, it may be determined whether one exhibit is a suspected exhibit. For example, the determination apparatus 100 outputs a low score (for example, “0”, etc.) when a user's behavior information related to an exhibit including information on an exhibit that is a negative example is input. And using the exhibit determination model, it may be determined whether one exhibit is a suspected exhibit. For example, the determination apparatus 100 inputs user behavior information regarding one exhibit including information on one exhibit to the exhibit determination model, and the score output by the exhibit determination model is equal to or greater than a predetermined threshold. , It may be determined that one exhibit is a suspected exhibit. The determination apparatus 100 may acquire the exhibit determination model from an external information processing apparatus, or may acquire the exhibit determination model from the storage unit 120 in which the exhibit determination model is stored in advance. Further, for example, the determination apparatus 100 uses a model learned by using a user who is determined as a suspect user by a predetermined administrator as a positive example and a user who is not determined as a suspect user by a predetermined administrator as a negative example. It may be determined whether one user is a suspect user. For example, the determination apparatus 100 learns a model (user determination model) so as to output a high score (for example, “1” or the like) when the action information of the user who is a positive example is input, and the user determination model May be used to determine whether one user is a suspect user. For example, the determination apparatus 100 learns a user determination model so as to output a low score (for example, “0” or the like) when a negative example of user behavior information is input, and uses the user determination model. It may be determined whether one user is a suspect user. For example, the determination apparatus 100 inputs one user's action information to the user determination model, and when the score output by the user determination model is equal to or greater than a predetermined threshold, the action target included in the one user's action information It may be determined that the other user is a suspect user. Further, for example, the determination apparatus 100 inputs behavior information of one user to the user determination model, and determines that the one user is a suspect user when the score output by the user determination model is equal to or greater than a predetermined threshold. May be. Note that the determination apparatus 100 may acquire a user determination model from an external information processing apparatus, or may acquire a user determination model from the storage unit 120 in which the user determination model is stored in advance. For example, the determination device 100 provides the administrator device 20 with information related to the suspected exhibit. Further, for example, the determination apparatus 100 acquires information on the violating exhibit from the manager apparatus 20. Note that the determination device 100 may determine whether the exhibit is a violation exhibit. For example, the determination apparatus 100 may determine whether or not a suspected exhibit is a violation exhibit among the exhibits. For example, the determination apparatus 100 uses a model that is learned by using an exhibit that a predetermined administrator has determined as an infringing exhibit as a positive example and an exhibit that the predetermined administrator has not determined to be an infringing exhibit as a negative example. Thus, it may be determined whether or not the exhibit such as the suspected exhibit is a violation exhibit.

[3. (Configuration of judgment device)
Next, the configuration of the determination apparatus 100 according to the embodiment will be described with reference to FIG. FIG. 3 is a diagram illustrating a configuration example of the determination apparatus 100 according to the embodiment. As illustrated in FIG. 3, the determination apparatus 100 includes a communication unit 110, a storage unit 120, and a control unit 130. The determination apparatus 100 includes an input unit (for example, a keyboard and a mouse) that receives various operations from an administrator of the determination apparatus 100 and a display unit (for example, a liquid crystal display) for displaying various types of information. May be.

(Communication unit 110)
The communication unit 110 is realized by, for example, a NIC (Network Interface Card). The communication unit 110 is connected to a network (for example, the network N in FIG. 2) by wire or wireless, and transmits / receives information to / from the terminal device 10.

(Storage unit 120)
The storage unit 120 is realized by, for example, a semiconductor memory device such as a RAM (Random Access Memory) or a flash memory, or a storage device such as a hard disk or an optical disk. As shown in FIG. 3, the storage unit 120 according to the embodiment includes an auction information storage unit 121 and a user information storage unit 122.

(Auction information storage unit 121)
The auction information storage unit 121 according to the embodiment stores information related to the auction. For example, the auction information storage unit 121 stores various types of information such as products (exhibits) that have been exhibited in the auction. FIG. 4 is a diagram illustrating an example of an auction information storage unit according to the embodiment. FIG. 4 shows an example of information related to an auction stored in the auction information storage unit 121. As shown in FIG. 4, the auction information storage unit 121 includes items such as “auction ID”, “status”, “exhibition name”, and “exhibitor ID” as information related to the auction.

  “Auction ID” indicates identification information for identifying an auction. “Status” indicates a state relating to violation of an exhibit in a corresponding auction. “Exhibit name” indicates the name of a product (exhibit) that has been exhibited in the corresponding auction. The “exhibitor ID” indicates identification information for identifying a user who has exhibited the corresponding product.

  For example, in the example shown in FIG. 4, the status of the exhibit AID1 in the auction identified by the auction ID “AID1” is “normal (0)”, that is, an exhibit that is not determined to be a suspected exhibit or a violated exhibit. Indicates that there is. Further, for example, in the example shown in FIG. 4, the exhibit name of the exhibit AID1 indicates “product A”. In the example of FIG. 4, the exhibit name is abstractly illustrated as “product A” or the like, but it is assumed that a specific exhibit name (title) is stored in “exhibit name”. Further, for example, in the example illustrated in FIG. 4, the seller of the product identified by the auction ID “AID1” is the user identified by the seller ID “SE11”.

  Further, for example, in the example shown in FIG. 4, the status of the exhibit AID3 in the auction identified by the auction ID “AID3” is “violation (2)”, that is, the exhibit determined to be a violation exhibit. It shows that. Further, for example, in the example illustrated in FIG. 4, the exhibit name of the exhibit AID3 is “product C”. Further, for example, in the example illustrated in FIG. 4, the seller of the product identified by the auction ID “AID3” is the user identified by the seller ID “SE31”.

  Further, for example, in the example shown in FIG. 4, the status of the exhibit AID4 in the auction identified by the auction ID “AID4” is “suspect (1)”, that is, the exhibit determined to be the suspected exhibit. It shows that. Further, for example, in the example illustrated in FIG. 4, the exhibit name of the exhibit AID4 indicates “product D”. Further, for example, in the example illustrated in FIG. 4, the seller of the product identified by the auction ID “AID4” is the user identified by the seller ID “SE41”.

  The auction information storage unit 121 is not limited to the above, and may store various information according to the purpose. For example, the auction information storage unit 121 may store information related to the date and time when the product is successfully bid. The auction information storage unit 121 may store information indicating the number of bids that have been bid. The auction information storage unit 121 may store information indicating an image such as a photograph of a product.

(User information storage unit 122)
The user information storage unit 122 according to the embodiment stores various types of information regarding the user. FIG. 5 is a diagram illustrating an example of a user information storage unit according to the embodiment. For example, the user information storage unit 122 stores auction information added to the watch list by the user and information related to the user's action history. In the example of FIG. 5, the user information storage unit 122 includes items such as “user ID”, “watch list”, and “history information”.

  “User ID” indicates identification information for identifying a user. The “watch list” indicates auction information (exhibits) added to the watch list by the corresponding user. “History information” indicates information related to the action history of the corresponding user.

  The “watch list” includes items such as “auction ID” and “date and time”. For example, “auction ID” indicates information for identifying an auction, that is, information for identifying an exhibit. “Date and time” indicates the date and time when the corresponding product or the like was settled. “Date and time” indicates the date and time when the corresponding auction information is added to the watch list. In the example of FIG. 5, information stored in “date and time” is illustrated by a symbol such as “dt10”, but “date and time” may be “18 November 2016, 21:01:43” or the like. It is assumed that a specific date and time is stored.

  The “behavior history” includes items such as “behavior” and “date and time”. Although not shown in FIG. 5, the “behavior history” may include items related to identification information such as “behavior ID” for identifying each behavior. “Behavior” indicates the specific content of the behavior of the corresponding user. “Date and time” indicates the date and time when the corresponding user action was performed.

  For example, in the example shown in FIG. 5, the user (user U1) identified by the user ID “U1” added the auction information (exhibit AID1) identified by the auction ID “AID1” to the watch list at the date dt10. It shows that. Further, for example, in the example shown in FIG. 5, the user U1 adds auction information (exhibit AID4) identified by the auction ID “AID4” at the date and time dt11 to the watch list, and uses the auction ID “AID3” at the date and time dt12. This indicates that the identified auction information (exhibit AID3) has been added to the watch list.

  For example, in the example illustrated in FIG. 5, the user (user U1) identified by the user ID “U1” indicates that the content of the page A is browsed at the date and time dt1. In the example illustrated in FIG. 5, the user U1 indicates that a search using the query “query B” is performed on the date and time dt5. Further, in the example shown in FIG. 5, the user U1 indicates that the exhibit AID1 is added to the watch list at the date and time dt10.

  Note that the user information storage unit 122 is not limited to the above, and may store various types of information according to the purpose. For example, the user information storage unit 122 may store information related to auction information (exhibits) for which the user bids as an action history. Further, for example, the user information storage unit 122 may store information related to user attributes. For example, the user information storage unit 122 may store demographic attribute information and psychographic attribute information. For example, the user information storage unit 122 may store information such as name, age, sex, home, work place, interest, family structure, income, lifestyle, and the like.

(Control unit 130)
Returning to the description of FIG. 3, the control unit 130 is a controller, and is stored in a storage device inside the determination apparatus 100 by, for example, a CPU (Central Processing Unit), an MPU (Micro Processing Unit), or the like. Various programs (corresponding to an example of a determination program) are implemented by using the RAM as a work area. The control unit 130 is a controller, and is realized by an integrated circuit such as an application specific integrated circuit (ASIC) or a field programmable gate array (FPGA).

  As illustrated in FIG. 3, the control unit 130 includes an acquisition unit 131, an extraction unit 132, a determination unit 133, and a provision unit 134, and functions and functions of information processing such as determination processing described below. Realize or execute. Note that the internal configuration of the control unit 130 is not limited to the configuration illustrated in FIG. 3, and may be another configuration as long as the information processing described below is performed.

(Acquisition part 131)
The acquisition unit 131 acquires various types of information. For example, the acquisition unit 131 acquires various types of information from the auction information storage unit 121, the user information storage unit 122, and the like. The acquisition unit 131 may acquire various types of information from an external information processing apparatus. The acquisition unit 131 acquires various types of information from the terminal device 10, the administrator device 20, and the service providing device 50. In the example of FIG. 1, the acquisition unit 131 acquires information indicating that the exhibit AID3 is a violation exhibit from the manager device 20.

  For example, the acquisition unit 131 acquires action information of a user who satisfies a predetermined condition that a user who uses a predetermined service for a violation target that is determined to violate a usage rule for the predetermined service satisfies a predetermined condition. To do. For example, when the number of violation targets specified by the user is equal to or greater than a predetermined threshold, the acquiring unit 131 acquires the behavior information of the user. For example, when the ratio of violation targets among the targets specified by the user is equal to or greater than a predetermined threshold, the acquisition unit 131 acquires the behavior information of the user.

  For example, the acquisition unit 131 acquires user behavior information that satisfies a condition regarding the designation of the suspicious target. Further, for example, the acquisition unit 131 acquires action information of a user whose violation target included in a predetermined list associated with the user satisfies a predetermined condition. Further, for example, the acquiring unit 131 acquires user behavior information in which the number of violation targets included in a predetermined list associated with the user is equal to or greater than a predetermined threshold. For example, the acquisition unit 131 acquires the behavior information of the user who added the violation target to a predetermined list associated with the user. In addition, for example, the acquisition unit 131 acquires the behavior information of the user who specified the violation exhibit that is determined to violate the terms of use of the auction service. In the example of FIG. 1, the acquisition unit 131 acquires the behavior information of the user U1 that includes the exhibit AID3 determined to be a violation exhibit in the watch list LT1.

  Further, for example, when the ratio of the suspicious target specified by the user among the violation targets belonging to the predetermined category is equal to or greater than a predetermined threshold, the acquiring unit 131 acquires the behavior information of the user. Details of this point will be described later.

(Extractor 132)
The extraction unit 132 extracts various information. For example, the extraction unit 132 extracts a target user. For example, the extraction unit 132 extracts the target user based on the violation exhibit. In the example of FIG. 1, the extraction unit 132 extracts, as target users, users who include the exhibit AID3 that is a violation exhibit in the watch list. In the example of FIG. 1, the extraction unit 132 extracts the user U1 that includes the exhibit AID3 in the watch list LT1 as the target user. In the example of FIG. 1, the extraction unit 132 extracts the user U2 including the exhibit AID3 in the watch list as the target user. In the example of FIG. 1, the extraction unit 132 extracts the user U3 including the exhibit AID3 in the watch list as the target user.

(Determination part 133)
The determination unit 133 determines various types of information. For example, the determination unit 133 determines, based on the user behavior information acquired by the acquisition unit 131, whether one target related to the user behavior is a suspicious target that may violate the terms of use. For example, the determination unit 133 determines whether one target that has not been determined to be a violation target is a suspected target. For example, the determination unit 133 determines whether one target user included in the user behavior information is a suspicious target.

  Further, for example, the determination unit 133 determines whether the one target designated by the user is a suspicious target. Further, for example, the determination unit 133 varies the timing for determining whether or not one target is a suspected target according to the user's behavior pattern estimated based on the user's behavior information. In addition, for example, the determination unit 133 determines whether one target is a suspected object based on a determination condition in which one of the plurality of types related to the seriousness of violation in a predetermined service varies depending on the corresponding type. Determine.

  For example, when the determination unit 133 determines that one target is a suspicious target, the determination unit 133 determines whether another target specified by another user specifying the one target is a suspicious target. In addition, for example, when a user who has been determined to be a suspicious target designates another target, the determination unit 133 determines whether the other target is a suspicious target. Further, for example, the determination unit 133 determines whether the target determined as the suspected target is a violation target.

  Further, for example, the determination unit 133 determines whether one target included in the predetermined list is a suspected target based on the user behavior information acquired by the acquisition unit 131. Further, for example, the determination unit 133 determines whether one exhibit specified by the user is a suspected exhibit that may violate the terms of use, based on the user behavior information acquired by the acquisition unit 131. To do.

  In the example of FIG. 1, the determination unit 133 determines that the number of items included in the target user's watch list is “1” and is less than the threshold value “2” and that the exhibit AID1 is not a suspected exhibit. In the example of FIG. 1, the determination unit 133 determines that the number included in the watch list of the target user is “1” and is less than the threshold value “2” and that the exhibit AID2 is not a suspected exhibit. In the example of FIG. 1, the determination unit 133 determines that the number of items included in the target user's watch list is “3” and the threshold value “2” or more is the exhibit AID4 as a suspected exhibit. Further, in the example of FIG. 1, the determination unit 133 determines that the number of items included in the target user's watch list is “2” and is equal to or greater than the threshold value “2”, and the exhibit AID5 is a suspected exhibit.

(Providing unit 134)
The providing unit 134 provides various information. For example, the providing unit 134 provides various information to the administrator device 20. For example, the providing unit 134 provides the administrator device 20 with information regarding the suspected exhibit. For example, the providing unit 134 provides various types of information to the terminal device 10 and the service providing device 50.

[4. (Judgment process flow)
Next, the procedure of determination processing by the determination system 1 according to the embodiment will be described with reference to FIG. FIG. 6 is a flowchart illustrating an example of the determination process according to the embodiment.

  As illustrated in FIG. 6, the determination apparatus 100 acquires auction information (step S101). For example, the determination apparatus 100 acquires auction information from the auction information storage unit 121. For example, the determination apparatus 100 acquires auction information from the service providing apparatus 50.

  Moreover, the determination apparatus 100 acquires user information (step S102). For example, the determination apparatus 100 acquires user information from the user information storage unit 122. For example, the determination apparatus 100 acquires user information from the terminal device 10.

  Thereafter, the determination apparatus 100 extracts, as target users, users whose violation lists or suspicious items are included in the watch list (step S103). In the example of FIG. 1, the determination apparatus 100 extracts users U1, U2, and U3 that include the exhibit AID3 in the watch list as target users.

  And the determination apparatus 100 determines whether the exhibit contained in a target user's watch list is a suspicious object based on a user's action information (step S104). In the example of FIG. 1, the determination device 100 determines that the item AID1 is not a suspicious item, assuming that the number included in the watch list of the target user is “1” and less than the threshold value “2”. In the example of FIG. 1, the determination apparatus 100 determines that the item AID2 is not a suspicious item because the number included in the watch list of the target user is “1” and is less than the threshold value “2”. In the example of FIG. 1, the determination apparatus 100 determines that the exhibit AID4 is a suspected exhibit, assuming that the number included in the watch list of the target user is “3” and is equal to or greater than the threshold “2”. In the example of FIG. 1, the determination apparatus 100 determines the exhibit AID5 as a suspected exhibit on the assumption that the number included in the watch list of the target user is “2” and the threshold is “2” or more.

[5. (Judgment process flow)
Next, the procedure of determination processing by the determination system 1 according to the embodiment will be described with reference to FIG. FIG. 7 is a sequence diagram illustrating an example of a determination process according to the embodiment.

  As shown in FIG. 7, the determination apparatus 100 acquires auction information from the service providing apparatus 50 (step S201). For example, the determination apparatus 100 acquires auction information as shown in the auction information storage unit 121 (see FIG. 4) from the service providing apparatus 50.

  Moreover, the determination apparatus 100 acquires user information from the terminal device 10 (step S202). For example, the determination apparatus 100 acquires, from the terminal device 10, information and action history regarding each user's watch list as shown in the user information storage unit 122 (see FIG. 5). Note that, for example, the determination apparatus 100 may acquire information and action history regarding each user's watch list as shown in the user information storage unit 122 (see FIG. 5) from another external device such as the service providing apparatus 50. .

  Moreover, the determination apparatus 100 acquires violation exhibit information from the manager apparatus 20 (step S203). For example, the determination apparatus 100 acquires information indicating that the exhibit AID3 is a violation exhibit from the administrator device 20.

  Thereafter, the determination apparatus 100 extracts a target user (step S204). In the example of FIG. 1, the determination apparatus 100 extracts users U1, U2, and U3 that include the exhibit AID3 in the watch list as target users.

  Thereafter, the determination apparatus 100 determines a suspected exhibit (step S205). In the example of FIG. 1, the determination device 100 determines that the item AID1 is not a suspicious item, assuming that the number included in the watch list of the target user is “1” and less than the threshold value “2”. In the example of FIG. 1, the determination apparatus 100 determines that the item AID2 is not a suspicious item because the number included in the watch list of the target user is “1” and is less than the threshold value “2”. In the example of FIG. 1, the determination apparatus 100 determines that the exhibit AID4 is a suspected exhibit, assuming that the number included in the watch list of the target user is “3” and is equal to or greater than the threshold “2”. In the example of FIG. 1, the determination apparatus 100 determines the exhibit AID5 as a suspected exhibit on the assumption that the number included in the watch list of the target user is “2” and the threshold is “2” or more.

  Thereafter, the determination apparatus 100 provides the suspected exhibit information to the manager apparatus 20 (step S206). For example, the determination device 100 provides the administrator device 20 with information indicating that the exhibits AID4 and AID5 are determined to be suspected exhibits.

  The administrator device 20 that has received the suspected exhibit information from the determination device 100 determines whether the suspected exhibit is a violation exhibit (step S207). For example, the manager of the manager device 20 determines whether each suspected exhibit is a violating exhibit by confirming the contents of each suspected exhibit. For example, the administrator of the administrator device 20 determines whether or not the exhibits AID4 and AID5 are violating exhibits by confirming the contents of the exhibits AID4 and AID5 determined as the suspected exhibits by the determination device 100. .

  Thereafter, the manager device 20 transmits the violation article information to the determination device 100 (step S208). For example, when the administrator of the administrator device 20 determines that the exhibits AID4 and AID5 are violation items, the administrator device 20 transmits information indicating that the items AID4 and AID5 are violation items to the determination device 100. Send.

[6. Other configuration examples of auction information storage unit]
Not limited to the above embodiment, the determination apparatus 100 may store various types of information with various configurations. For example, the determination apparatus 100 may store information regarding the type of auction. This point will be described with reference to FIGS. FIG. 8 is a diagram illustrating another configuration example of the auction information storage unit according to the embodiment.

(Auction information storage unit 121A)
The auction information storage unit 121A in FIG. 8 stores information related to the auction. For example, the auction information storage unit 121A stores various types of information such as products (exhibits) that have been exhibited in the auction. As shown in FIG. 8, the auction information storage unit 121A includes items such as “auction ID”, “status”, “exhibition name”, “type”, and “exhibitor ID” as information related to the auction. Thus, the auction information storage unit 121A is the same as the auction information storage unit 121 shown in FIG. 4 except that the item “type” is included.

  “Type” indicates the degree (rank) related to the illegality of the exhibits in the corresponding auction. In the example of FIG. 8, “*” of the type “type *” is assumed to have a higher illegality rank in order from A, and the rank of the type “type E” is the highest. For example, the type “type A” of the exhibit AID1 and the exhibit AID2 indicates that the rank regarding illegality is low. Further, for example, the type “type E” of the exhibit AID3 indicates that the rank regarding illegality is high. Further, for example, the type “type C” of the exhibit AID4 indicates that the rank related to illegality is slightly high. In addition, the rank of illegality of types A to E is appropriately given according to the level of illegality of violation of public order and morals, fear of use for crimes or infringement of rights of others (copyright etc.), for example. Take it.

  In the above-described auction information storage unit 121A, the case where “type” is stored for all exhibits has been shown, but “type” may be stored only for suspected items or violated items.

[7. Other flow of judgment processing]
Next, another flow of determination processing in the determination system 1 according to the embodiment will be described with reference to FIG. FIG. 9 is a flowchart illustrating another example of the determination process according to the embodiment. Specifically, FIG. 9 is a flowchart illustrating a procedure of determination processing based on the type of each exhibit in the determination system 1 according to the embodiment.

  As shown in FIG. 9, the determination apparatus 100 acquires auction information (step S301). For example, the determination apparatus 100 acquires auction information from the auction information storage unit 121A. For example, the determination apparatus 100 acquires auction information from the service providing apparatus 50.

  Moreover, the determination apparatus 100 acquires user information (step S302). For example, the determination apparatus 100 acquires user information from the user information storage unit 122. For example, the determination apparatus 100 acquires user information from the terminal device 10.

  Thereafter, the determination apparatus 100 extracts, as target users, users whose violation lists or suspected exhibits are included in the watch list (step S303). Note that the determination apparatus 100 extracts the target user based on conditions that vary according to the type of the violating exhibit or the type of the suspected exhibit.

  For example, if the watch list includes at least one violating item or suspicious item of type E, the determination apparatus 100 extracts the user as the target user. Further, for example, when the watch list includes five violation exhibits or suspicious exhibits of type C, the determination apparatus 100 extracts the user as a target user. In addition, for example, when the determination apparatus 100 includes ten violation exhibits or suspicious exhibits of type A in the watch list, the determination apparatus 100 extracts the user as a target user. Further, for example, the determination apparatus 100 targets users who have individual scores of types A to E as 1 to 5, and the total of individual scores of violating exhibits or suspected exhibits included in the watch list is equal to or greater than a predetermined threshold. Extract as a user.

  For example, the determination apparatus 100 extracts, as target users, users whose sum of individual scores of the violating exhibits or suspected exhibits included in the watch list is a threshold “10” or more. For example, when a certain user's watch list includes a class A violation exhibit and a class D suspicious exhibit, the determination apparatus 100 has an individual score “1” of the class A violation exhibit and a class D suspicious exhibit. Are added together to calculate a total score “5 (= 1 + 4)”. In this case, since the total score “5” is less than the threshold value “10”, the determination apparatus 100 does not extract the user as the target user.

  Further, for example, when a certain user's watch list includes three violation items of type B and suspicious items of type E, the determination apparatus 100 determines the individual score “2” and the type of each violation item of type B The total score “11 (= 2 * 3 + 5)” is calculated by summing up the individual scores “5” of the suspicious exhibits of E. In this case, since the total score “11” is equal to or greater than the threshold “10”, the determination apparatus 100 extracts the user as the target user. Note that the individual score of the violating exhibit may be higher than the individual score of the suspected exhibit even for the same type. For example, the individual score of the violating exhibit may be 1.5 times the individual score of the suspected exhibit.

  And the determination apparatus 100 determines whether each exhibit is a suspicious object based on the determination conditions according to the classification of each exhibit included in a target user's watch list (step S304). For example, when the exhibit is type E, and the number of users who include the exhibit in the watch list is one, the determination apparatus 100 determines the exhibit as a suspicious object. For example, when the exhibit is type C and there are five users including the exhibit in the watch list, the determination apparatus 100 determines the exhibit as a suspicious object. For example, when the exhibit is type A and there are ten users who include the exhibit in the watch list, the determination apparatus 100 determines the exhibit as a suspicious object.

[8. effect〕
As described above, the determination apparatus 100 according to the embodiment includes the acquisition unit 131 and the determination unit 133. The acquisition unit 131 acquires the behavior information of the user who satisfies the predetermined condition that the user using the predetermined service with respect to the violation target which is determined to violate the usage rule of the predetermined service satisfies the predetermined condition. Based on the user behavior information acquired by the acquisition unit 131 and a predetermined model used to determine a suspicious target that may violate the terms of use, the determination unit 133 determines whether one target related to the user behavior is Determine if you are suspected of violating the Terms of Service.

  Thereby, the determination apparatus 100 according to the embodiment uses one of the objects related to the user's action based on the user's action information and the predetermined model used for determining the suspicious object that may violate the terms of use. It is possible to determine whether or not there is a suspicious object that may violate the contract, and to efficiently determine the suspicious object that may violate the use contract.

  Moreover, in the determination apparatus 100 according to the embodiment, the determination unit 133 determines whether or not one target that has not been determined to be a violation target is a suspected target.

  Thereby, the determination apparatus 100 according to the embodiment may determine whether one undetermined target is a suspicious target as a violation target, and may sequentially violate the terms of use by sequentially determining the undetermined target. A certain suspicious object can be determined efficiently.

  Moreover, in the determination apparatus 100 according to the embodiment, the determination unit 133 determines whether one target user included in the user behavior information is a suspicious target.

  Thereby, the determination apparatus 100 according to the embodiment determines whether one target user included in the user behavior information is a suspicious target, and sequentially determines the target from the target included in the user behavior information. It is possible to efficiently determine a suspicious object that may violate the above.

  Moreover, in the determination apparatus 100 according to the embodiment, the determination unit 133 determines whether one target specified by the user is a suspicious target.

  Thereby, the determination apparatus 100 according to the embodiment can determine whether the one target designated by the user is the suspicious object, and can efficiently determine the suspicious object that may violate the terms of use.

  In the determination apparatus 100 according to the embodiment, the acquisition unit 131 acquires the behavior information of the user when the number of violation targets specified by the user is equal to or greater than a predetermined threshold.

  Thereby, when the number of violation targets specified by the user is equal to or greater than a predetermined threshold, the determination apparatus 100 according to the embodiment acquires the user's behavior information and identifies a suspected target that may violate the terms of use. It can be determined efficiently.

  In the determination apparatus 100 according to the embodiment, the acquisition unit 131 acquires the behavior information of the user when the ratio of violation targets among the targets specified by the user is equal to or greater than a predetermined threshold.

  Thereby, the determination apparatus 100 according to the embodiment may acquire behavior information of the user and violate the terms of use when the ratio of violation targets among the targets specified by the user is equal to or greater than a predetermined threshold. The suspicious object can be determined efficiently.

  Moreover, in the determination apparatus 100 according to the embodiment, the acquisition unit 131 acquires the behavior information of the user when the ratio of violation targets specified by the user among the violation targets belonging to the predetermined category is equal to or greater than a predetermined threshold. To do.

  Thereby, the determination apparatus 100 according to the embodiment acquires the action information of the user when the ratio of the violation target specified by the user among the violation targets belonging to the predetermined category is equal to or greater than the predetermined threshold, It is possible to efficiently determine a suspicious object that may violate the above.

  Moreover, in the determination apparatus 100 according to the embodiment, the acquisition unit 131 acquires user behavior information that satisfies a condition regarding the designation of the suspicious target.

  Thereby, the determination apparatus 100 which concerns on embodiment can acquire the user's action information which satisfy | fills the conditions regarding designation | designated of a suspicious object, and can determine the suspicious object which may violate a usage rule efficiently.

  Moreover, in the determination apparatus 100 according to the embodiment, the determination unit 133 varies the timing for determining whether or not one target is a suspected target, according to the user's behavior pattern estimated based on the user's behavior information. .

  Thereby, the determination apparatus 100 according to the embodiment can be used by changing the timing for determining whether one target is a suspicious target according to the user's behavior pattern estimated based on the user's behavior information. It is possible to efficiently determine a suspicious object that may violate the rules.

  Further, in the determination apparatus 100 according to the embodiment, the determination unit 133 selects one of a plurality of types related to the seriousness of violation in a predetermined service based on a determination condition that varies depending on a type to which one target corresponds. To determine whether the target of is suspected.

  As a result, the determination apparatus 100 according to the embodiment allows the one target to be suspected based on a determination condition that varies depending on the type to which the one target corresponds among the plurality of types related to the seriousness of violation in a predetermined service. It is possible to determine whether the subject is a target and efficiently determine a suspicious subject that may violate the terms of use.

  In the determination apparatus 100 according to the embodiment, when the determination unit 133 determines that one target is a suspicious target, the determination unit 133 determines whether another target specified by another user who specifies the one target is a suspicious target. .

  Accordingly, when the determination apparatus 100 according to the embodiment determines that one target is a suspicious target, the determination apparatus 100 determines whether another target specified by another user specifying the one target is a suspicious target, It is possible to efficiently determine a suspected object that may be violated.

  Moreover, in the determination apparatus 100 according to the embodiment, the determination unit 133 determines whether or not the other target is the suspicious target when the user who is determined to be the suspicious target specifies the other target.

  Thereby, the determination apparatus 100 according to the embodiment may determine whether or not the other target is the suspicious target when the user who is determined to be the suspicious target specifies the other target, and violates the terms of use. It is possible to efficiently determine a suspicious subject having a characteristic.

  Moreover, in the determination apparatus 100 according to the embodiment, the determination unit 133 determines whether the target determined as the suspected target is a violation target.

  Thereby, the determination apparatus 100 which concerns on embodiment can determine whether the object determined to be a suspicion object is a violation object, and can efficiently determine the suspicion object that may violate the terms of use.

  In the determination apparatus 100 according to the embodiment, the acquisition unit 131 acquires the action information of the user who added the violation target to the predetermined list associated with the user. The determination unit 133 determines whether one target included in the predetermined list is a suspicious target based on the user behavior information acquired by the acquisition unit 131.

  Thereby, the determination apparatus 100 according to the embodiment determines whether one target included in the predetermined list is a suspicious object based on the user behavior information, and identifies a suspicious object that may violate the terms of use. It can be determined efficiently.

  Moreover, in the determination apparatus 100 according to the embodiment, the acquisition unit 131 acquires the behavior information of the user who specified the violation exhibit that is determined to violate the auction service terms of use. Based on the user behavior information acquired by the acquisition unit 131, the determination unit 133 determines whether one exhibit designated by the user is a suspected exhibit that may violate the terms of use.

  Thereby, the determination apparatus 100 according to the embodiment determines whether the one exhibit designated by the user is a suspected exhibit that may violate the terms of use based on the user behavior information, and the terms of use are determined. It is possible to efficiently determine a suspicious object that may violate the above.

[9. Hardware configuration)
The determination apparatus 100 according to the embodiment described above is realized by a computer 1000 configured as shown in FIG. 10, for example. FIG. 10 is a hardware configuration diagram illustrating an example of a computer that realizes the function of the determination apparatus. The computer 1000 includes a CPU 1100, a RAM 1200, a ROM (Read Only Memory) 1300, an HDD (Hard Disk Drive) 1400, a communication interface (I / F) 1500, an input / output interface (I / F) 1600, and a media interface (I / F). ) 1700.

  The CPU 1100 operates based on a program stored in the ROM 1300 or the HDD 1400 and controls each unit. The ROM 1300 stores a boot program executed by the CPU 1100 when the computer 1000 is started up, a program depending on the hardware of the computer 1000, and the like.

  The HDD 1400 stores programs executed by the CPU 1100, data used by the programs, and the like. The communication interface 1500 receives data from other devices via the network N and sends the data to the CPU 1100, and transmits data generated by the CPU 1100 to other devices via the network N.

  The CPU 1100 controls an output device such as a display and a printer and an input device such as a keyboard and a mouse via the input / output interface 1600. The CPU 1100 acquires data from the input device via the input / output interface 1600. In addition, the CPU 1100 outputs the generated data to the output device via the input / output interface 1600.

  The media interface 1700 reads a program or data stored in the recording medium 1800 and provides it to the CPU 1100 via the RAM 1200. The CPU 1100 loads such a program from the recording medium 1800 onto the RAM 1200 via the media interface 1700, and executes the loaded program. The recording medium 1800 is, for example, an optical recording medium such as a DVD (Digital Versatile Disc) or PD (Phase change rewritable disk), a magneto-optical recording medium such as an MO (Magneto-Optical disk), a tape medium, a magnetic recording medium, or a semiconductor memory. Etc.

  For example, when the computer 1000 functions as the determination apparatus 100 according to the embodiment, the CPU 1100 of the computer 1000 implements the function of the control unit 130 by executing a program loaded on the RAM 1200. The CPU 1100 of the computer 1000 reads these programs from the recording medium 1800 and executes them. However, as another example, these programs may be acquired from other devices via the network N.

  As described above, some of the embodiments of the present application have been described in detail with reference to the drawings. It is possible to implement the present invention in other forms with improvements.

[10. Others]
In addition, among the processes described in the above embodiment, all or part of the processes described as being automatically performed can be performed manually, or the processes described as being performed manually can be performed. All or a part can be automatically performed by a known method. In addition, the processing procedures, specific names, and information including various data and parameters shown in the document and drawings can be arbitrarily changed unless otherwise specified. For example, the various types of information illustrated in each drawing is not limited to the illustrated information.

  Further, each component of each illustrated apparatus is functionally conceptual, and does not necessarily need to be physically configured as illustrated. In other words, the specific form of distribution / integration of each device is not limited to that shown in the figure, and all or a part thereof may be functionally or physically distributed or arbitrarily distributed in arbitrary units according to various loads or usage conditions. Can be integrated and configured.

  In addition, the processes described in the above-described embodiments can be appropriately combined within a range that does not contradict the processing contents.

  In addition, the “section (module, unit)” described above can be read as “means” or “circuit”. For example, the acquisition unit can be read as acquisition means or an acquisition circuit.

DESCRIPTION OF SYMBOLS 1 Determination system 100 Determination apparatus 121 Auction information storage part 122 User information storage part 130 Control part 131 Acquisition part 132 Extraction part 133 Determination part 134 Provision part 10 Terminal apparatus 20 Administrator apparatus 50 Service provision apparatus N Network

Claims (17)

Among users who use a predetermined service, a designation for a violation target that is determined to violate the terms of use of the predetermined service, and a target for obtaining the violation target or collecting information on the violation target An acquisition unit for acquiring behavior information of a target user extracted as a user who satisfies a predetermined condition regarding the specification by specifying the violation target as
Based on the behavior information related to one target included in the behavior information of the target user acquired by the acquisition unit, and a predetermined model used for determining a suspicious target that may violate the terms of use. A determination unit for determining whether or not the subject is the suspected subject,
A determination apparatus comprising: The determination unit
The determination apparatus according to claim 1, wherein it is determined whether the one target that has not been determined to be a violation target is a suspected target. The determination unit
The determination apparatus according to claim 1, wherein it is determined whether the one target included in the behavior information of the target user is a suspicious target. The determination unit
The determination apparatus according to any one of claims 1 to 3, wherein it is determined whether or not the one target designated by the target user is a suspicious target. The acquisition unit
5. The behavior information of the target user is acquired when the number of violation targets designated by the user is equal to or greater than a predetermined threshold, with the user as the target user. 6. Judgment device. The acquisition unit
The behavior information of the target user is acquired when the ratio of violation targets among the targets specified by the user is equal to or greater than a predetermined threshold, with the user as the target user. The determination apparatus according to item. The acquisition unit
The behavior information of the target user is acquired when the ratio of the violation target specified by the user among the violation targets belonging to the predetermined category is equal to or greater than a predetermined threshold, with the user as the target user. The determination apparatus according to any one of 1 to 6. The acquisition unit
The determination apparatus according to any one of claims 1 to 7, wherein action information of the target user is acquired by setting a user who satisfies a condition regarding the designation of the suspicious target as the target user. The determination unit
The timing for determining whether or not the one target is the suspicious target is varied according to a behavior pattern of the target user estimated based on the behavior information of the target user. The determination apparatus according to any one of the above. The determination unit
Of the plurality of types relating to the seriousness of violation in the predetermined service, it is determined whether or not the one target is a suspected target based on a determination condition that varies depending on a type to which the one target corresponds. The determination apparatus according to any one of claims 1 to 9. The determination unit
11. The method according to claim 1, wherein when the one target is determined to be a suspicious target, it is determined whether another target specified by another user specifying the one target is a suspicious target. The determination apparatus according to item. The determination unit
12. The method according to claim 1, wherein, when the user who is determined to be the suspicious object designates another object, whether or not the other object is the suspicious object is determined. The determination apparatus described. The determination unit
The determination apparatus according to claim 1, wherein it is determined whether the object determined as the suspected object is a violation object. The acquisition unit
The behavioral information of the target user is acquired by setting the target user as a target user for the violation target included in the predetermined list associated with the user,
The determination unit
14. The method according to claim 1, further comprising: determining whether one target included in the predetermined list is a suspicious target based on the behavior information of the target user acquired by the acquisition unit. Determining device according to. The acquisition unit
Get the behavior information of the user who specified the violated item that is determined to violate the terms of use of the auction service,
The determination unit
Based on the behavior information of the target user acquired by the acquisition unit, it is determined whether one exhibit designated by the target user is a suspected exhibit that may violate the terms of use. The determination apparatus according to any one of claims 1 to 14. A determination method executed by a computer,
Among users who use a predetermined service, a designation for a violation target that is determined to violate the terms of use of the predetermined service, and a target for obtaining the violation target or collecting information on the violation target An acquisition step of acquiring behavior information of a target user extracted as a user who satisfies a predetermined condition regarding the specification by specifying the violation target as
Based on the behavior information related to one target included in the behavior information of the target user acquired in the acquisition step, and a predetermined model used for determining a suspicious target that may violate the terms of use. A determination step of determining whether or not the subject is the suspected subject,
The determination method characterized by including. Among users who use a predetermined service, a designation for a violation target that is determined to violate the terms of use of the predetermined service, and a target for obtaining the violation target or collecting information on the violation target An acquisition procedure for acquiring behavior information of a target user extracted as a user who satisfies a predetermined condition regarding the specification by specifying the violation target as
Based on the behavior information related to one target included in the behavior information of the target user acquired by the acquisition procedure, and a predetermined model used for determining a suspicious target that may violate the terms of use. A determination procedure for determining whether or not the subject is the suspected subject,
The determination program characterized by causing a computer to execute.

Images