JP6679667B2 - Generation device, generation method, and generation program - Google Patents

Description

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

  Conventionally, various commercial transactions are performed via the Internet. For example, on the Internet, a store that manages stores and users, and a platform that mediates business transactions between users are provided.

  As a technique related to the above-mentioned commercial transaction, a technique is known in which the credit degree of the credit of the business operator is calculated based on the behavior of the user on the network.

JP, 2016-18932, A

  However, there is room for improvement in the method of seeking the credit of the target person of the commercial transaction. For example, in a commercial transaction, the completion of the actual delivery of the product, such as smooth delivery of the product or delivery of the product, can be a factor for determining the credit of the target person of the commercial transaction. However, in the related art, although the credibility is calculated based on the behavior history of the user on the network, etc., it is mentioned that the credibility is calculated from various viewpoints such as information regarding actual delivery of goods after the establishment of the commercial transaction. Not not.

  The present application has been made in view of the above, and an object of the present invention is to provide a generation device, a generation method, and a generation program capable of determining the credibility from various viewpoints.

  The generation device according to the present application is based on an acquisition unit that acquires information related to distribution of a product that is a target of a commercial transaction, and based on the information related to the distribution acquired by the acquisition unit, a product in the commercial transaction among the target persons of the commercial transaction. A generation unit that generates a model for calculating the creditworthiness of the purchaser of the purchaser, the acquisition unit, as the information about the physical distribution, the behavior information on the network of the purchaser after the delivery of the product. It is characterized in that the generation unit generates a model for calculating the creditworthiness of the purchaser based on the behavior information on the purchaser's network after the delivery of the product.

  According to one aspect of the embodiment, it is possible to determine the credibility from various viewpoints.

FIG. 1 is a diagram illustrating an example of a generation process according to the embodiment. FIG. 2 is a diagram illustrating a configuration example of the generation system according to the embodiment. FIG. 3 is a diagram illustrating a configuration example of the generation device according to the embodiment. FIG. 4 is a diagram illustrating an example of the store 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 diagram illustrating an example of a store model storage unit according to the embodiment. FIG. 7 is a diagram illustrating an example of the user model storage unit according to the embodiment. FIG. 8 is a flowchart (1) showing a processing procedure by the generation device according to the embodiment. FIG. 9 is a flowchart (2) showing a processing procedure by the generation device according to the embodiment. FIG. 10 is a hardware configuration diagram illustrating an example of a computer that realizes the function of the generation device.

  Hereinafter, modes (hereinafter, referred to as “embodiments”) for carrying out the generation device, the generation method, and the generation program according to the present application will be described in detail with reference to the drawings. Note that the generation device, the generation method, and the generation program according to the present application are not limited by this embodiment. Also, in each of the following embodiments, the same parts are designated by the same reference numerals, and duplicated description will be omitted.

[1. Example of generation process]
First, an example of the generation process according to the embodiment will be described with reference to FIG. FIG. 1 is a diagram illustrating an example of a generation process according to the embodiment. In FIG. 1, an example of a generation process executed by the generation device 100 according to the embodiment will be described. Specifically, in FIG. 1, in order to calculate the credibility of a store that opens at a predetermined commercial transaction site on the network and a user who uses the commercial transaction site based on the information about the distribution of goods by the generation device 100. An example in which the process of generating the model (calculation formula) is performed will be described.

  In the example shown in FIG. 1, the generation device 100, the user terminal 10, the web server 30, and the delivery company device 50 are communicatively connected via a communication network (for example, the Internet) not shown.

  The generation device 100 illustrated in FIG. 1 is a server device that generates a model for calculating the creditworthiness of a target person of a commercial transaction. The generation device 100 generates, for example, a model for calculating the credibility of a product provider (store) or a product purchaser (user) as a target person of a commercial transaction. It should be noted that in the embodiment, a store that opens in a shopping mall is taken as an example of a product provider, but the provider is not limited to this example, and may be, for example, a transaction between individuals or an exhibitor on an auction site. Good.

  The user terminal 10 shown in FIG. 1 is an information processing device used by a user. Specifically, the user terminal 10 allows the user to browse a web page, purchases a product at a website (for example, a shopping mall on a network), and posts an evaluation of product information (a so-called review). Used for. In the example of FIG. 1, the user terminal 10 is, for example, a smartphone or a tablet terminal.

  The web server 30 shown in FIG. 1 is a server device that provides various web pages when accessed from the user terminal 10. In the example shown in FIG. 1, the web server 30 provides a shopping mall site on the network. In the shopping mall provided by the web server 30, each business operator opens a store that handles products of various categories.

  In addition, the web server 30 may acquire information regarding user behavior on the network via the website to be provided. The information regarding the user behavior is stored in, for example, a storage unit included in the web server 30 or a predetermined external storage device. The information on the user behavior on the network means the information transmitted from the user terminal 10 according to the user's operation and the user's behavior in the service when using the service (shopping mall in the example of FIG. 1) provided by the web server 30. Is the information that indicates. For example, the user behavior on the network is purchase behavior in a shopping mall, posting of reviews by users to each store in the shopping mall, and the like. The web server 30 may acquire not only user behavior but also data such as a comment returned by the store administrator in response to a review from the user.

  The delivery company device 50 is a server device used by the delivery company. In the example of FIG. 1, the delivery company device 50 is used by the delivery company 40, which is an example of the delivery company. The delivery company device 50 receives a request for shipping of a product from a store that opens in a shopping mall. Then, the delivery company device 50 generates delivery information that is information in which the scheduled delivery date and time of the delivery item, the delivery destination, and the like are registered. The delivery company 40 delivers to the delivery destination based on the delivery information generated by the delivery company device 50. Although not shown in FIG. 1, there may be a plurality of delivery companies 40. That is, the store may select any of the plurality of delivery companies 40 to request the shipping of the product. In the following, the delivery company may be read as the delivery company device 50. For example, the description that “the delivery company 40 transmits information” may actually indicate the situation that “the delivery company device 50 used by the delivery company 40 transmits information”.

  The delivery company device 50 also provides the generation device 100 with information regarding physical distribution. Information related to physical distribution is, for example, a target of commercial transaction such as completion of delivery to the user, change of delivery date and time from the user, return of goods delivered to the user, etc. It contains various information related to the delivery of goods.

  By the way, in a commercial transaction site on a network such as a shopping mall provided by the web server 30, it is desired to measure the credibility of a user or a store (or a store administrator who manages the store), which is a target of the commercial transaction, for smooth operation. There is a request. For example, in the case of a store, such a credit is an index value such as sales of a product or an evaluation value from a user. If the user is a user, the credibility can be an index value such as the number of transactions and whether or not the purchase price is transferred. By calculating the credibility, the web server 30 can, for example, refuse the opening of a store with a low credibility or restrict the use of a user with a low credibility, so that the smooth operation can be performed.

  Here, in a commercial transaction, the completion of actual delivery of the product, such as smooth delivery of the product or delivery of the product without fail, can be a factor for determining the credit of the target person of the commercial transaction. Therefore, the generation device 100 according to the embodiment cooperates with, for example, the delivery company device 50 or the like, acquires information regarding the physical distribution of the person who is the subject of the commercial transaction, and generates a model for calculating the creditworthiness based on the information regarding the physical distribution. As a result, the generation device 100 can calculate the credibility based on the actual data on the commercial transaction site such as delivery and receipt of the product. Hereinafter, the generation processing according to the embodiment will be described along the flow with reference to FIG. 1.

  In the example shown in FIG. 1, the shopping mall provided by the web server 30 has a store A01 operated by a store administrator 70. Although not shown in FIG. 1, the shopping mall provided by the web server 30 has a considerable number of stores that can obtain a sufficient amount of information for performing the generation processing according to the embodiment. It shall be.

  The user terminal 10 accesses the web server 30 according to the operation by the user U01, which is an example of a user who uses the shopping mall. Although not shown in the example of FIG. 1, there are a plurality of users and user terminals 10, and a considerable number of accesses to obtain a sufficient amount of information for performing the generation process according to the embodiment. I'm going. The user U01 who has accessed the shopping mall uses the shopping mall through actions such as purchasing and sending reviews (step S11).

  The web server 30 acquires various information transmitted from the user terminal 10. For example, the web server 30 acquires information indicating that the user U01 has purchased a predetermined product in the store A01. Further, the web server 30 may acquire information regarding the evaluation of the store A01 by the user U01. The information regarding the evaluation from the user U01 is, for example, text data posted as a review, a score for the store A01 (evaluation value for the store, which is indicated by, for example, five-level numerical value).

  In addition, the web server 30 may acquire information regarding delivery that occurs with respect to an order placed by the user terminal 10. For example, the web server 30 acquires the information that the store A01, which has received the order for the product from the user U01, has requested the delivery company device 50 to ship the product. Further, the web server 30 may acquire, as the information regarding the physical distribution, information indicating whether or not the store A01 has been able to send the product without any problem. For example, the web server 30 may have determined that the product ordered by the user U01 is not out of stock in the store A01, or within a predetermined period from the order (for example, within a period from the start of the delivery procedure defined by the shopping mall. Specifically, , Within 24 hours, etc.), information such as whether or not the store A01 has performed the shipping procedure of the product.

  After that, when the store A01 requests the delivery company device 50 to send the product (step S12), the delivery company 40 sends the product to the user U01 (step S13).

  The delivery company device 50 acquires information on the distribution of the product. For example, whether the delivery company device 50 was at home on the delivery date and time designated by the user U01 (in other words, whether the receipt of the product was completed in one delivery), or whether the delivery date and time was changed frequently. Get whether or not. Further, the delivery company device 50 may acquire information such as whether or not the delivery company 40 has received an unreasonable complaint when delivering to the user U01. The delivery company device 50 acquires such information based on, for example, feedback from the terminal device owned by the delivery company 40.

  In this way, in the shopping mall, it is assumed that a large number of users have placed orders for various stores and a large number of products have been delivered.

  The generation device 100 acquires information about a store and a user, including information about the above-described commercial transaction and information about distribution of goods in the commercial transaction from the web server 30 (step S14).

  In addition, the generation device 100 acquires, from the delivery company device 50, information regarding physical distribution when the product is actually delivered (step S15).

  Then, the generation device 100 generates a model for calculating the creditworthiness of the target person of the commercial transaction based on the acquired information (step S16). For example, the generation device 100 generates a model for calculating the store credibility and a model for calculating the user credibility, respectively.

  For example, the generation device 100 generates a model that outputs a predetermined index value (score) when the information of the store or the user whose credit is calculated is input. Although details will be described later, for example, the generation device 100 sets various information regarding physical distribution as features (determination factors), performs scoring on information corresponding to each feature, and finally sets the information as a target of credit calculation. Generate a model that outputs the credibility of the store or the user as a score.

  For example, the generation device 100 assigns a minimum score to the store evaluation value without mentioning a user who frequently posts a term set as a negative word or a comment on a commerce platform such as a shopping mall. A model may be generated in which the user who behaves as if he / she is being operated has a relatively low credibility. Alternatively, the generation device 100 generates a model in which the credibility of a user who makes an unreasonable complaint to the delivery company 40 or a user who has not specified a delivery date and time but is at home is relatively low. You may.

  In addition, the generation device 100 stores, for example, a store in which a returned product of a purchased product has a high return rate, a store in which a product for which an order has been accepted is out of stock, or a store in which information such as the fact that the out-of-stock is not cleared quickly is acquired. For, a model may be generated in which the reliability is calculated to be relatively low.

  As described above, the generation device 100 according to the embodiment acquires the information regarding the physical distribution of the product that is the target of the commercial transaction, and generates the model that calculates the creditworthiness of the target person of the commercial transaction based on the acquired information regarding the physical distribution.

  That is, the generation device 100 according to the embodiment generates a model for calculating the creditworthiness of the store from the viewpoint of distribution of merchandise, as well as the financial information and transaction information generally used for measuring the creditworthiness of the store. . Further, the generation device 100 generates not only transaction information and behavior information generally used for measuring the user's creditworthiness, but also a model for calculating the user's creditworthiness from the viewpoint of distribution of goods. . In this way, the generation device 100 can generate a model based not only on the information on the shopping mall, which is a platform for commercial transactions, but also on information that only the delivery company 40 can know and information related to the actual shipment of products. it can. Thereby, the generation device 100 can determine the credibility of the store or the user from various viewpoints. In addition, the generation device 100 acquires the information regarding the physical distribution of the user or the store in real time and inputs it to the model to calculate the credit rating. Therefore, the generation device 100 can calculate the credibility of the store or the user by using the data with high freshness. Hereinafter, the configuration and the like of the generation device 100 that performs the above processing and the generation system 1 including the generation device 100 will be described in detail.

[2. Generation system configuration]
The configuration of the generation system 1 including the generation device 100 according to the embodiment will be described with reference to FIG. 2. FIG. 2 is a diagram illustrating a configuration example of the generation system 1 according to the embodiment. As illustrated in FIG. 2, the generation system 1 according to the embodiment includes a user terminal 10, a store terminal 20, a web server 30, a delivery company device 50, and a generation device 100. These various devices are communicatively connected by wire or wirelessly via a network N (for example, the Internet). The number of devices included in the generation system 1 illustrated in FIG. 2 is not limited to the illustrated number, and the generation system 1 may include a plurality of user terminals 10 or the like, for example.

  The user terminal 10 is, for example, a smart phone, a desktop PC (Personal Computer), a notebook PC, a tablet terminal, a mobile phone, a PDA (Personal Digital Assistant), an information processing device such as a wearable device (Wearable Device). Is. The user terminal 10 acquires the web page (for example, the web page of the store A01 shown in FIG. 1) from the website provided by the web server 30 by accessing the web server 30 according to the operation by the user. Then, the user terminal 10 displays the acquired web page on a display device (for example, a liquid crystal display). In the present specification, the user and the user terminal 10 may be regarded as the same. For example, "the user accesses the web server 30" may actually mean "the user terminal 10 used by the user accesses the web server 30".

  The store terminal 20 is an information processing device used by a company that manages the store (the store manager 70 in the example of FIG. 1). Specifically, the store terminal 20 executes information processing relating to the operation of a store in a shopping mall, and information processing for requesting a shipping company to ship the product when the user orders the product. .

  The web server 30 is a server device that provides various web pages when accessed from the user terminal 10. In the example of FIG. 1, the web server 30 provides the website corresponding to a shopping mall, and provides the web page of the store A01 currently opened in the shopping mall. However, the web page provided by the web server 30 is not limited to this, and the web server 30 may be, for example, a news site, a weather forecast site, a shopping site, a finance (stock price) site, a route search site, a map providing site, a travel site, Various web pages regarding restaurant introduction sites, web blogs, etc. may be provided.

  Further, the web server 30 may obtain information on each network, which is information on each website. The information on the network is, for example, information transmitted from the user terminal 10 in accordance with a user's operation when using services provided by various websites. For example, the information on the network includes information about a search query at a search site, information about a shopping action at a shopping site and a review from a user, information about a message posted by a user at an SNS (Social Networking Service) site, and the like.

  In addition, the web server 30 may acquire the behavior regarding the behavior of the store administrator, which is information on each website. For example, the web server 30 may acquire the comment of the store administrator who responded to the user review, the comment of the store administrator who answered the user who wishes to receive the product, and the like.

  The delivery company device 50 is a server device used by the delivery company. The delivery company device 50 receives a request for shipping of a product from a store that opens in a shopping mall. Further, the delivery company device 50 provides the generation device 100 with information related to the distribution of goods.

  As described above, the generation device 100 is a server device that acquires information regarding the distribution of a product that is a target of a commercial transaction and generates a model that calculates the creditworthiness of the target person of the commercial transaction based on the acquired information regarding the distribution. . The generation device 100 may also serve as the above-mentioned web server 30. That is, the generation device 100 itself may provide a shopping mall, and the generation device 100 itself may acquire information from the user terminal 10 that has accessed the shopping mall.

  Note that the generation device 100 may be provided with the information on the distribution of the merchandise subject to the commercial transaction from the web server 30 or the delivery company device 50. For example, the generation device 100 may crawl the network to obtain the information. You may acquire using the predetermined program etc. which are acquired.

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

(About the communication unit 110)
The communication unit 110 is realized by, for example, a NIC (Network Interface Card) or the like. The communication unit 110 is connected to a communication network by wire or wirelessly, and transmits / receives information to / from the user terminal 10 or the like via the communication network.

(About the 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 (Flash Memory), or a storage device such as a hard disk or an optical disk. The storage unit 120 according to the embodiment includes a store information storage unit 121, a user information storage unit 122, a store model storage unit 123, and a user model storage unit 124. Hereinafter, each storage unit will be described in order.

(About the store information storage unit 121)
The store information storage unit 121 stores information about stores that open stores on a predetermined commercial transaction site. For example, the generation device 100 acquires the information stored in the store information storage unit 121 from the web server 30 or the delivery company device 50 via the network N. Here, FIG. 4 illustrates an example of the store information storage unit 121 according to the embodiment. As shown in FIG. 4, the store information storage unit 121 has items such as “store ID” and “store feature information”. In addition, the items of "store feature information" are small items such as "return rate", "order cancellation rate", "out-of-stock product rate", "out-of-stock average period", "store evaluation value", and "user review index value". Contains items.

  The “store ID” indicates identification information that identifies a store that is open on a predetermined commercial transaction site. In this specification, the identification information as shown in FIG. 4 is common with the reference numeral used in the description. For example, the store identified by the store ID “A01” indicates “store A01”.

  The “store feature information” indicates information that can be a feature in the model generation processing (modeling) by the generation device 100.

  The “returned goods rate” indicates a rate of returned goods from the user within a predetermined period (for example, one month) of the goods shipped to the user due to a mistake on the store side or a malfunction of the goods. The “order cancellation rate” indicates the rate at which the store side canceled the product ordered by the user for some reason. Cancellation of an order occurs when, for example, it is determined that the product is out of stock after the order is placed, or the ordered product cannot be procured.

  The “out-of-stock product rate” indicates the rate of out-of-stock products out of the products handled by the store. The “out-of-stock average period” indicates the average period during which any product is out of stock in the store. For example, the out-of-stock average period indicates an average period during which a product runs out of stock and the out-of-stock state is resolved in a predetermined statistical period (for example, one year). For example, in a store that deals with out-of-stock relatively quickly, the period is calculated to be relatively short.

  “Store evaluation value” indicates an evaluation value of a store on a platform such as a shopping mall. The store evaluation value is indicated by, for example, an average value of numerical values of five-level evaluation selected by the user. The store evaluation value may be an evaluation given by a manager of the shopping mall or the like.

  “User review index value” indicates an index value that can be an evaluation of a review posted by a user in the store. In the embodiment, the user review index value is indicated by a numerical value of 100 levels. The user review index value is, for example, a word or phrase that is negatively evaluated by the user in all text data of the review (for example, "delivery is late", "out of stock", or "bad packaging"). Is calculated by the web server 30, the generation device 100, or the like based on the amount included in the. Various known techniques may be used to calculate the user review index value. For example, the generation device 100 labels a review posted to a store having a relatively high store evaluation value as correct answer data (for example, a store whose user review index value is determined to be “100”), and the review is performed. A model for calculating the user review index value may be generated by learning the words and phrases included in.

  That is, in FIG. 4, as an example of the data stored in the store information storage unit 121, in the store feature information of the store A01 whose store ID is “A01”, the return rate is “3%” and the order cancellation rate is "4%", out-of-stock product rate "6%", average out-of-stock period "16 days", store evaluation value "3.5", user review index value "75". ".

  Although not shown in FIG. 4, the store information storage unit 121 may store various types of information related to the store in addition to the above-mentioned information. For example, the store information storage unit 121 may store information such as the sales amount of the store, the financial status of the capital, and the number of years of the store. Further, the store information storage unit 121 stores the number of users who continue to use the store (for example, users who perform actions such as accessing again within a week) and the customer unit price of the users (for example, in a predetermined period). Information such as the purchase amount per user), the number of times a store, a store name, or a product has been searched for in a predetermined period, and the rate of increase in the number of searches may be stored. In addition, the store information storage unit 121 may store a page view of the store, the number of unique users who access the store, and the like. Further, the generation device 100 may generate a model for calculating the trustworthiness of the store by using these pieces of information as features.

(Regarding the user information storage unit 122)
The user information storage unit 122 stores information about a user who is a purchaser of a product in a commercial transaction. Here, FIG. 5 illustrates an example of the user information storage unit 122 according to the embodiment. As shown in FIG. 5, the user information storage unit 122 has items such as “user ID” and “user feature information”. In addition, the item of "user feature information" includes small items such as "return rate", "intermediate cancellation rate", "review suitability", "delivery success rate", "delivery date / time change rate", and "delivery company review index value". Contains items.

  The “returned goods rate” indicates a ratio of the number of goods returned to the store within a predetermined period (for example, one month) of the goods shipped from the store due to the user's convenience. The “intermediate cancellation rate” indicates the ratio of the number of products ordered in the shopping mall that were canceled due to the user's convenience before the products were shipped.

  The “review suitability” indicates an index value of the content posted by the user on a platform such as a shopping mall. In the embodiment, the review suitability is represented by a numerical value of 100 levels. The review suitability is, for example, the ratio of words or phrases that abuse the store in all the text data of the reviews posted by the user, or the store that does not purchase the product is given an unnaturally low rating. It is assumed that the calculation is performed by the generation device 100 or the web server 30 based on the behavior or the like. For the review suitability, various known techniques may be used as in the user review index value shown in FIG.

  The “delivery success rate” indicates the rate at which the delivery company delivers the product to the user (the user receives the product) according to the designated date and time. For example, the delivery success rate may be the success rate of the first delivery, or the delivery success rate of the first delivery or the redelivery (up to the second delivery). For example, a user with a high delivery success rate is determined to be a user who is trusted by the shopping mall (or delivery company).

  The “delivery date / time change rate” indicates the rate at which the delivery date / time is changed by the user for the delivery company. For example, a user whose delivery date / time change rate is extremely high is determined to be a user who is not trusted by the shopping mall (or delivery company).

  The “delivery company review index value” is an index value indicating the evaluation of the user by the delivery company. In the embodiment, the delivery company review index value is represented by a numerical value of 100 levels. For example, the delivery company review index value may be calculated based on a score or the like transmitted from the delivery company that actually delivered the user. Alternatively, the delivery company review index value is the number of times that a problem behavior such as "a complaint was received from the user" or "a delivery date and time was specified but not at home" was reported from the delivery company that actually delivered the delivery to the user. Alternatively, it may be calculated based on the ratio or the like.

  That is, in FIG. 5, as an example of the data stored in the user information storage unit 122, the user feature information of the user U01 whose user ID is “U01” has a return rate of “5%” and a midway cancellation rate of "13%", the review suitability is "55", the delivery success rate is "60%", the delivery date / time change rate is "45%", and the delivery company review index value is "40". It indicates that there is.

  Although not shown in FIG. 5, the user information storage unit 122 may store various kinds of information regarding the user in addition to the above-described information. For example, in the user information storage unit 122, attribute information such as the age, sex, and place of residence of the user, the total purchase amount in the store, the average purchase amount in the store during a predetermined period, or the product purchased in the past. The list or the like may be stored. Further, the generation device 100 may generate a model for calculating the trustworthiness of the user by using these pieces of information as features.

(About the store model storage unit 123)
The store model storage unit 123 stores information about a model for calculating the store credit. Here, FIG. 6 illustrates an example of the store model storage unit 123 according to the embodiment. As shown in FIG. 6, the store model storage unit 123 has items such as “store model ID” and “feature”. The “feature” item includes a small item corresponding to the store feature information shown in FIG. 4 and a small item indicating the correspondence between each feature result and the score.

  The “store model ID” indicates identification information that identifies a model for store. The “feature” indicates information regarding the feature for calculating the creditworthiness of the store.

  In the embodiment, as an example of the model generated by the generation device 100, when the result of the store feature information is input, a score corresponding to the result of each input feature is calculated, and the calculated score is added to the store. Take a model that outputs the credit rating of

  For example, when the information about the store whose return rate is “3%” is input to the store model MS01 shown in FIG. 6, the score “7” corresponding to the return rate result “˜3” is calculated. It Similarly, the score corresponding to each feature is calculated, and the credit score (score) of the store is calculated from the sum of the calculated scores. For example, in the store model MS01 shown in the embodiment, it is assumed that the higher the score, the higher the credibility of the store is calculated.

  Note that the correspondence between the result and the score illustrated in FIG. 6 is an example, and the generation device 100 may derive the correspondence between the result and the score using various known techniques. For example, the generation device 100 acquires information on a large number of samples of stores and statistically analyzes the acquired information to generate correspondence between feature results and scores as shown in FIG. Good. Specifically, the generation device 100 may generate the model such that the average value of the acquired results of each feature is the average of the scores (for example, the result of which the score is calculated as “5”). Further, as will be described in detail later, the generation device 100 may generate the model by using a predetermined learning process or the like without being limited to the statistical method. That is, the generation device 100 generates any model as long as it is a model capable of calculating the creditworthiness of a target person of a commercial transaction (for example, a store) on the basis of the information on the distribution of the commodity to be commercialized. Good.

  That is, in FIG. 6, the store model MS01 identified by the store model ID “MS01” has the “returned goods rate”, “order cancellation rate”, “out-of-stock product rate”, “out-of-stock average period”, and “store evaluation value”. , And “user review index value”, the score is calculated based on the result information of the features, and the credit level of the store is output based on the calculated score.

(About user model storage unit 124)
The user model storage unit 124 stores information about a model for calculating the creditworthiness of the user. Here, FIG. 7 illustrates an example of the user model storage unit 124 according to the embodiment. As shown in FIG. 7, the user model storage unit 124 has items such as “user model ID” and “feature”. Further, the “feature” item includes a small item corresponding to the user feature information shown in FIG. 5 and a small item indicating the correspondence between each feature result and the score.

  The “user model ID” indicates identification information that identifies the model for the user. The “feature” indicates information regarding a feature for calculating the trustworthiness of the user.

  In the embodiment, as an example of the model generated by the generation device 100, when the result of the user feature information is input, a score corresponding to the result of each input feature is calculated, and the user is calculated based on the sum of the calculated scores. Take a model that outputs the credit rating of

  For example, when the information of the user whose return rate is “5%” is input to the user model MU01 shown in FIG. 7, the score “5” corresponding to the return rate result “˜5” is calculated. It Similarly, a score corresponding to each feature is calculated, and a credit value (score) of the user is calculated by a value obtained by adding the calculated scores. For example, in the user model MU01 shown in the embodiment, it is assumed that the higher the score, the higher the credibility of the store is calculated.

  Note that the correspondence between the result and the score illustrated in FIG. 7 is an example, and the generation device 100 uses the various known techniques in the same manner as the store model illustrated in FIG. May be derived. That is, the generation device 100 generates any model as long as it is a model capable of calculating the creditworthiness of the target person (for example, user) of the commercial transaction based on the information on the physical distribution of the commodity to be commercialized. Good.

  That is, in FIG. 7, the user model MU01 identified by the user model ID “MU01” has the “returned goods rate”, “mid-term cancellation rate”, “review suitability”, “delivery success rate”, “delivery date / time change rate”. , A model in which a score is calculated based on the result information of each feature of the “delivery company review index value” and the user's credibility is output based on the calculated score.

(About the control unit 130)
The control unit 130 is a controller, and includes, for example, a CPU (Central Processing Unit), an MPU (Micro Processing Unit), or the like, which stores various programs (an example of a generation program) stored in a storage device inside the generation apparatus 100. (Corresponding) is executed 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 ASIC (Application Specific Integrated Circuit) or an FPGA (Field Programmable Gate Array).

  As illustrated in FIG. 3, the control unit 130 according to the embodiment includes an acquisition unit 131, a generation unit 132, and a calculation unit 133, and implements or executes the functions and actions of information processing described below. The internal configuration of the control unit 130 is not limited to the configuration shown in FIG. 3 and may be another configuration as long as it is a configuration for performing information processing described later. Further, the connection relationship between the processing units included in the control unit 130 is not limited to the connection relationship illustrated in FIG. 3 and may be another connection relationship.

(About the acquisition unit 131)
The acquisition unit 131 acquires various kinds of information. For example, the acquisition unit 131 acquires information regarding the distribution of the product that is the target of the commercial transaction.

  Specifically, the acquisition unit 131 acquires, as the information regarding physical distribution, a return rate of returned products after the store has shipped the products. For example, the acquisition unit 131 may acquire the return rate calculated from the transaction status in the shopping mall from the web server 30. Alternatively, the acquisition unit 131 may acquire, from the delivery company device 50, the information regarding the shipping and returning of the product, and may acquire the product return rate based on the acquired information. The acquisition unit 131 acquires, for example, a product return rate for each store that opens a shopping mall.

  In addition, the acquisition unit 131 may acquire, as the information regarding physical distribution, shipping information indicating whether or not shipping of the product has been completed when the store receives the order for the commercial transaction. It should be noted that being able to complete the shipment of the product means, for example, that the product is not out of stock, and that the user can respond to the order without any problem. For example, the acquisition unit 131 may acquire the shipping information from the web server 30 or may acquire from the delivery company device 50 that the delivery of the product to the user has been completed. Note that the acquisition unit 131 may calculate information such as the order cancellation rate and the out-of-stock product rate shown in FIG. 4 based on the shipping information and acquire the calculated numerical value. Further, the acquisition unit 131 may appropriately acquire the out-of-stock product ratio of the store, the average out-of-stock period, and the store evaluation value from the web server 30 as the information regarding the physical distribution.

  In addition, the acquisition unit 131 may acquire, as the information regarding the physical distribution, a user review regarding the shipment of products by the store. For example, the acquisition unit 131 acquires, from the web server 30, a user review posted in a shopping mall for an arbitrary store. In addition, the acquisition unit 131 may calculate the user review index value and the like illustrated in FIG. 4 based on a user review related to shipping of products. In this case, the acquisition unit 131 performs morphological analysis on the user reviews, for example, when collecting information about texts such as user reviews, and further appears in reviews such as tf-idf (Term Frequency-Inverse Document Frequency). An algorithm for scoring each word to be used may be used to acquire only the word having a high weight. Then, the acquisition unit 131 may digitize the user reviews based on the ratio of negative words such as “slow”, “bad”, and “miscellaneous” included in the reviews. As described above, various known techniques may be used for such processing. That is, the acquisition unit 131 may use any method as long as the information (for example, a numerical value) that can evaluate the store based on the user review can be acquired.

  Further, the acquisition unit 131 may further acquire, as the information about the store, information about the evaluation by the user of the store at a predetermined commercial transaction site, together with the information about the physical distribution. For example, the acquisition unit 131 may acquire the number of reactions from the user to the store and the numerical value of the page view or the like of the store or the product.

  In addition, the acquisition unit 131 may acquire information regarding the transition of the number of reactions from the user to the store or the product, or the transition of the evaluation value evaluated by the user for the store or the product. That is, the acquisition unit 131 may acquire the change in the number of posted reviews and the change in the score in a predetermined period. Accordingly, the acquisition unit 131 can acquire information about a tendency that a store that has once received a low evaluation from the user has received a high evaluation in recent years.

  In addition, the acquisition unit 131 may acquire such information when the financial information of the store can be acquired from, for example, a financial institution or a financial management company. When the acquisition unit 131 acquires the financial information, the generation unit 132, which will be described later, may generate a model in which the credit information is calculated by adding the financial information.

  In addition, the acquisition unit 131 may acquire information regarding the physical distribution of the user. For example, the acquisition unit 131, as the information on the distribution, corresponds to the return application rate (for example, the “return rate” shown in FIG. 5) in which the user has made an application for returning the product after the user purchased the product. ) To get. For example, the acquisition unit 131 may acquire information from the web server 30 that stores transactions between the user and the store, or may acquire information from the delivery company device 50 requested by the user to return to the store. May be.

  Further, the acquisition unit 131 may acquire, as the information regarding the physical distribution, information indicating that the user has canceled the order before shipping or receiving the product after the user orders the product. The acquisition unit 131 may calculate the midway cancellation rate illustrated in FIG. 5 based on the information and acquire the calculated numerical value.

  In addition, the acquisition unit 131 may acquire a user review regarding delivery of products as the information regarding distribution. Further, the acquisition unit 131 may calculate the review suitability shown in FIG. 5 based on the acquired user review and acquire the calculated numerical value.

  Further, the acquisition unit 131 may acquire, as the information regarding the physical distribution, product receipt information indicating whether or not the user received the product at the designated delivery date and time of the product. The acquisition unit 131 acquires product receipt information from the delivery company device 50, for example. Then, the acquisition unit 131 calculates the delivery success rate, the delivery date / time change rate, and the like illustrated in FIG. 5 based on the acquired information, and acquires the calculated numerical value.

  Further, the acquisition unit 131 may acquire, as the information related to the physical distribution, the evaluation information that is the information transmitted from the delivery company that has delivered the product to the user and that indicates the evaluation result of the user. The acquisition unit 131 acquires the evaluation information from the delivery company device 50, for example. Then, the acquisition unit 131 calculates the delivery company review index value and the like shown in FIG. 5 based on the acquired information, and acquires the calculated numerical value.

  The acquisition unit 131 appropriately stores the acquired information in the storage unit 120. For example, the acquisition unit 131 stores the acquired information about the store in the store information storage unit 121. The acquisition unit 131 also stores the acquired information about the user in the user information storage unit 122.

  Note that the acquisition unit 131 may randomly acquire information on various stores and users without specifying a store or a user who acquires information. For example, the acquisition unit 131 uses a program such as a search robot used for a search engine or the like to crawl the Internet, thereby acquiring information about a store or a user at any time or updating the acquired information. May be.

(Regarding the generation unit 132)
The generation unit 132 generates a model for calculating the creditworthiness of the target person of the commercial transaction based on the information on the physical distribution acquired by the acquisition unit 131.

  For example, the generation unit 132 generates a model for calculating the creditworthiness of the provider (the store in the embodiment) of the product in the commercial transaction as the target person of the commercial transaction.

  Specifically, the generation unit 132 generates a model for calculating the creditworthiness of the store based on the return rate acquired by the acquisition unit 131. For example, the generation unit 132 generates a model in which the higher the return rate in the store, the lower the credibility is calculated, and the lower the return rate is, the higher the credibility is calculated.

  The generation unit 132 also generates a model for calculating the creditworthiness of the store based on the shipping information acquired by the acquisition unit 131. Specifically, the generation unit 132 generates a model based on an order cancellation rate, an out-of-stock product rate, or the like calculated based on shipping information. For example, the generation unit 132 generates a model in which the higher the order cancellation rate or the out-of-stock product rate, the lower the credit rating, and the lower the order cancellation rate or the out-of-stock product rate, the higher the credit rating. The generation unit 132 may generate a model in which the shorter the average out-of-stock period is, the higher the credibility is calculated, and the longer the average out-of-stock period is, the lower the credibility is calculated.

  In addition, the generation unit 132 generates a model for calculating the creditworthiness of the store based on a user review regarding shipping of products by the store. Specifically, the generation unit 132 generates a model based on a user review index value calculated based on a user review, a store evaluation value acquired with the user review, and the like. For example, the generation unit 132 generates a model in which the higher the store evaluation value or the user review index value, the higher the credibility is calculated, and the lower the store evaluation value or the user review index value, the lower the credibility.

  In addition, the generation unit 132 generates a model for calculating the credibility of the purchaser of the product in the commercial transaction (the user in the shopping mall in the embodiment) as the target person of the commercial transaction.

  For example, the generation unit 132 generates a model for calculating the creditworthiness of the user based on the return application rate made by the user. Specifically, the generation unit 132 generates a model in which the higher the return application rate (corresponding to the return rate shown in FIG. 5), the lower the credit rating, and the higher the return application rate, the lower the credit rating. . Further, the generation unit 132 may generate a model in which the higher the midway cancellation rate, the lower the credibility is calculated, and the lower the midway cancellation rate is, the higher the credibility is calculated.

  In addition, the generation unit 132 generates a model for calculating the creditworthiness of the user based on the user review regarding the shipment of products by the store. Specifically, the generation unit 132 generates the model based on the review suitability and the like calculated based on the user review. For example, the generation unit 132 generates a model in which the higher the review suitability is, the higher the credit is calculated, and the lower the review suitability is, the lower the trust is calculated.

  Further, the generation unit 132 generates a model for calculating the creditworthiness of the user based on the product receipt information indicating whether or not the user received the product at the designated delivery date and time of the product. Specifically, the generation unit 132 generates a model based on the delivery success rate, the delivery date / time change rate, or the like calculated based on the product receipt information. For example, the generation unit 132 calculates that the higher the success rate of delivery or the lower the delivery date / time change rate, the higher the credibility, and the lower the delivery success rate or the higher the delivery date / time change rate, the lower the credibility. A simple model.

  The generation unit 132 also generates a model for calculating the creditworthiness of the user based on the evaluation information indicating the result of the evaluation of the user by the delivery company, which is the information transmitted from the delivery company that delivers the product to the user. To generate. Specifically, the generation unit 132 generates a model based on the delivery company review index value calculated based on the evaluation information. For example, the generation unit 132 generates a model in which the higher the shipping company review index value, the higher the credibility is calculated, and the lower the shipping company review index value, the lower the credibility.

  For example, the generation unit 132 inputs information on each feature of the target store and the user as shown in FIG. 6 and FIG. 7, calculates a score of each feature corresponding to the input result, and calculates the calculated score. Generate a model that sums and outputs the total score.

  The model output by the generation unit 132 is not limited to the above example, and any model can be used as long as it can calculate (numerize) the creditworthiness based on the information about the physical distribution as illustrated above. May be

  For example, the generation unit 132, as a positive example (for example, the top 1000 stores with a high evaluation value in a shopping mall), the result information of each feature of a store and a negative example (for example, the lower 1000 with a low evaluation value in a shopping mall). The model may be generated by learning the result information of each feature of the store (which is the subject store) with a regression equation. For example, the generation unit 132 creates the following expression (1).

y = ω ₁ · x ₁ + ω ₂ · x ₂ + ω ₃ · x ₃ ··· + ω _N · x _N ··· (1) (N is an arbitrary number)

  The above formula (1) is created, for example, for each individual store. In the above formula (1), “y” indicates whether the store is a positive example or a negative example. For example, if it is a positive example, "1" is input to "y", and if it is a negative example, "0" is input to "y".

Further, in the above equation (1), “x” is the feature information of the store and corresponds to the explanatory variable in the regression equation. Further, in the above formula (1), “ω” is a coefficient of “x” and represents a predetermined weight value. Specifically, “ω ₁ ” is a weight value of “x ₁ ”, “ω ₂ ” is a weight value of “x ₂ ”, and “ω ₃ ” is a weight value of “x ₃ ”. Is. As described above, the above expression (1) is a variable including the explanatory variable “x” corresponding to the characteristic information extracted from the information about the physical distribution and the predetermined weight value “ω” (for example, “ω ₁ · x _{1”). ]} )) Are combined. For example, in the above formula (1), “x ₁ ” is the “returned goods rate” shown in FIG. 4, and “x ₂ ” is the “order cancellation rate” shown in FIG. 4.

The generating unit 132 generates the above formula (1) for each store. Then, the generation unit 132 uses the generated expression as a sample of machine learning. Then, the generation unit 132 derives a value corresponding to the predetermined weight value “ω” by performing a calculation process (regression learning) of a sample formula. That is, the generation unit 132 determines a predetermined weight value “ω” that satisfies the above equation (1). In other words, the generation unit 132 determines the weight value “ω” indicating the influence of the predetermined explanatory variable on the objective variable “y”. For example, if the "return rate" significantly contributes to the phenomenon of "credibility (evaluation value in a shopping mall in this example)", it corresponds to the "return rate". The value of the weight value “ω ₁ ” is calculated to be large as compared with other variables.

  In the above example, the return rate and the order cancellation rate are shown as features, but when the return rate and the order cancellation rate are substituted into equation (1), they can be used as explanatory variables by a predetermined process. May be converted into a numeric value. For example, the generator 132 normalizes and uses these numerical values by a known method. In addition, in the generation process using the above equation (1), the left side is not set to “1” or “0”, but a predetermined error is assumed, and the value obtained by squaring the difference from the error is the minimum value. The optimum solution of “ω” may be calculated using a method such as the least squares method that approximates Further, the generation unit 132 may make various design changes, such as a positive example of a store having a high evaluation value in a shopping mall, and a positive example of a store that meets other predetermined conditions. Further, the generation unit 132 may generate a model not only for the store but also for the user by a similar method.

  Although notation is omitted in the above example, the generation unit 132 may generate the model using any feature regarding the store or the user. The model generation method illustrated is an example, and the model generated by the generation unit 132 is not limited to the above example. That is, the generation unit 132 is a model that is generated based on information about physical distribution, and is a known model as long as it is a model that outputs the credibility of the target person of the commercial transaction when the information about the target person of the commercial transaction is input. A model different from the above example may be appropriately generated by combining the methods. For example, in the above example, an example in which a model is generated by regression analysis is shown, but the generation unit 132 may generate a model by another statistical process, or a model using a neural network, etc. May be generated. In the learning process (machine learning), various techniques such as linear regression, logistic regression, support vector machine, decision tree, and hazard analysis may be used.

  The generation unit 132 stores the generated store model in the store model storage unit 123. Further, the generation unit 132 stores the generated user model in the user model storage unit 124.

(About the calculation unit 133)
The calculation unit 133 calculates the creditworthiness of the target person of the commercial transaction. Specifically, the calculation unit 133 inputs the information of the target person of a certain commercial transaction into the model generated by the generation unit 132, and calculates the credibility of the target person of the relevant commercial transaction.

  For example, the calculation unit 133 outputs the score of the store by inputting the information about the physical distribution in the store into the model for the store generated by the generation unit 132. The output score indicates the credibility of the store. Further, the calculation unit 133 outputs the score of the user by inputting the information regarding the physical distribution of the user into the user model generated by the generation unit 132. The output score indicates the credibility of the user.

  The calculation unit 133 calculates the credibility of the store or the user based on the output score. The calculation unit 133 may use the output score itself as the credibility of the store or the user, or may perform processing such as normalizing the output score and use the value calculated after the processing as the credibility of the store or the user. . For example, the calculation unit 133 may perform the process of normalizing the score output from the model into a numerical value of 100 levels, and use the value of 1 to 100 calculated after the process as the trustworthiness of the store or the user.

  For example, the calculation unit 133 may receive a request from the web server 30 and calculate the creditworthiness of the user or the store, or may calculate the creditworthiness of all the users or the store related to a certain shopping mall. .

[4. Processing procedure)
Next, a procedure of generation processing by the generation device 100 according to the embodiment will be described with reference to FIGS. 8 and 9. FIG. 8 is a flowchart (1) showing a processing procedure by the generation device 100 according to the embodiment.

  As illustrated in FIG. 8, the generation device 100 acquires information about a store and a user from, for example, the web server 30 (step S101). In addition, the generation device 100 acquires information regarding physical distribution in a commercial transaction from the delivery company (step S102).

  Then, the generation device 100 statistics the acquired information (step S103). The generation device 100 generates each model for calculating the trustworthiness of the user and the store based on the result of the statistical processing (step S104).

  Subsequently, the generation device 100 stores each generated model in the storage unit 120 (step S105).

  Next, with reference to FIG. 9, a procedure of a credit degree calculation process by the generation device 100 according to the embodiment will be described. FIG. 9 is a flowchart (2) showing a processing procedure by the generation device 100 according to the embodiment.

  As illustrated in FIG. 9, the generation device 100 determines whether the information of the target person is acquired (step S201). If the information has not been acquired, the generation device 100 waits until the information is acquired (step S201; No).

  On the other hand, when the information of the target person is acquired (step S201; Yes), the generation device 100 inputs the acquired information to the store or the model for the user (step S202).

  Then, the generation device 100 outputs the score from the model (step S203). Further, the generation device 100 calculates the creditworthiness of the store or the user based on the output score (step S204).

[5. Modification)
The generation device 100 according to the above-described embodiment may be implemented in various different forms other than the above-described embodiment. Therefore, in the following, another embodiment of the generation device 100 will be described.

[5-1. Data to be input to the model]
In the above-described embodiment, the generation device 100 has shown the example in which the information about the store or the user is input to the generated model to calculate the credibility. Here, the generation device 100 may associate the acquisition timing of the information used for generating the model with the information of the store or the user input to the model.

  Since the information acquired by the generation device 100 is information on a commercial transaction site such as a shopping mall, there is a possibility that the information may be affected by the time. For example, there may be a difference in the number of shipments, stock status, etc. for each store between the time when transactions are actively performed, such as the end of the year, and other times. Therefore, the generation device 100 stores the time when the information is acquired to generate the model, and when the information of the store or the user to be processed is input, the information used to generate the model is acquired. Enter the information acquired at a time similar to the time when Thereby, the generation device 100 can perform the generation process in which the temporal influence of the output score is taken into consideration.

[5-2. Information amount)
In the above embodiment, the generation device 100 has shown an example of generating a model based on various information that can be acquired on the network. Here, the generation device 100 may perform the processing by using only information acquired from general users who use various websites exceeding a certain threshold.

  For example, reviews about products in a certain store, user evaluations, and the like may show a biased tendency when not based on a certain number or more of data. In this case, the data having a tendency biased to the regression equation affects the generation device 100, and thus the generation device 100 may generate a model that cannot accurately calculate the credibility of the store or the user. Therefore, the generation device 100 may use, as the data to be handled in the generation process of the model, only those in which the total number of scores and reviews sent from the user to the store exceeds a certain number. Thereby, the generation device 100 can generate a model that outputs a highly reliable score.

[5-3. Information variations]
In the above embodiment, the generation device 100 has shown an example of generating a model based on a user review or the like posted in a shopping mall or the like. Here, the variation of information handled by the generation device 100 will be described in more detail.

  For example, the generation device 100 may acquire, as information included in the user review, morphological analysis of the acquired words and information collected for each part of speech. Specifically, the generation device 100 acquires the aggregation result in which the noun categories are classified into people, things, places, and the like. Further, the generation device 100 may acquire a classification result such as whether each word has a positive attribute or a negative attribute, or a determination result such as an intention determination of the dialogue when the message has a dialogue format.

  In addition, the generation device 100 may acquire the voice information transmitted from the user as an example of the user review. That is, the generation device 100 may acquire, as voice information corresponding to a user review, voice recognition of voice transmitted from a user who uses voice search or voice input.

  Further, the generation device 100 may extract only a specific part of speech for the acquired word. For example, the generation device 100 may use a part-of-speech that can briefly describe the situation of the store or the user, such as a noun or an adjective for processing. Thereby, the generation device 100 can reduce the processing load without degrading the accuracy of the generated model.

  Further, the generation device 100 may use only the words registered in advance for the score calculation process. For example, the generation device 100 may use a word such as “good” or “bad”, “(delivery) is slow” or “fast” that can directly express the evaluation of the physical distribution in the processing. Such registration is performed, for example, by the administrator of the generation device 100.

  Further, the generation device 100 may acquire text data such as user reviews not only on the platform of the shopping mall but also widely on the network. For example, the generation device 100 may acquire text data corresponding to a user review from an SNS, a user's email, a web page on which information about a shopping mall is posted, or the like.

[5-4. Credit level visualization)
The generation device 100 may perform a process of visualizing the calculated credibility. For example, when the generation device 100 receives a request for calculation of creditworthiness from a user or a store, the generation device 100 calculates the creditworthiness of the user or store according to the request. Then, the generation device 100 displays the calculated credibility on the screen of the user terminal 10 or the store terminal 20, for example. For example, the generation device 100 may display the calculated numerical value of the credibility, or may display it in a predetermined graph. As an example, the generation device 100 may visualize the credibility of the user or the store by using a chart or a pie chart in which the score of each feature information can be seen at a glance.

  In addition, the generation device 100 may perform a predetermined process using the credibility. For example, the generation device 100 (or the web server 30) grants a user with a credit rating exceeding a predetermined threshold a right to receive a novelty, or a store with a credit rating exceeding a predetermined threshold has an evaluation value in a shopping mall. You may perform processing, such as raising.

[6. Other]
Further, of the processes described in the above embodiment, all or part of the processes described as being automatically performed may be manually performed, or the processes described as manually performed may be performed. All or part of the process 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 above documents and drawings can be arbitrarily changed unless otherwise specified.

  Further, each component of each device shown in the drawings is functionally conceptual, and does not necessarily have to be physically configured as shown. That is, the specific form of distribution / integration of each device is not limited to that shown in the figure, and all or a part of the device may be functionally or physically distributed / arranged in arbitrary units according to various loads and usage conditions. It can be integrated and configured.

  For example, the information in the storage unit 120 illustrated in FIG. 3 may be held in an external storage server or the like without being held by the generation device 100. In this case, the generation device 100 acquires various stored information by accessing the storage server.

  In addition, for example, the above-described generation device 100 performs a generation process and the like with the front-end server side that mainly communicates with an external device such as acquiring various information and receiving a request for calculation of credit of the store. It may be distributed to the back-end server side to execute. In this case, for example, the front-end server has at least the acquisition unit 131. In addition, the backend server includes at least the generation unit 132.

[7. Hardware configuration)
Further, the generation device 100, the user terminal 10, etc., the store terminal 20, the web server 30, and the delivery company device 50 according to the above-described embodiment are realized by, for example, a computer 1000 configured as shown in FIG. 10. Hereinafter, the generation device 100 will be described as an example. FIG. 10 is a hardware configuration diagram illustrating an example of a computer 1000 that realizes the functions of the generation device 100. The computer 1000 has a CPU 1100, a RAM 1200, a ROM 1300, an HDD 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 starts up, a program dependent on the hardware of the computer 1000, and the like.

  The HDD 1400 stores a program executed by the CPU 1100, data used by the program, and the like. The communication interface 1500 receives data from other devices via the communication network 500 (corresponding to the network N shown in FIG. 2) and sends the data to the CPU 1100, and also transmits data generated by the CPU 1100 via the communication network 500 to other devices. To other devices.

  The CPU 1100 controls output devices such as a display and a printer and input devices such as a keyboard and a mouse via the input / output interface 1600. The CPU 1100 obtains data from an input device via the input / output interface 1600. The CPU 1100 also outputs the data generated via the input / output interface 1600 to the output device.

  The media interface 1700 reads a program or data stored in the recording medium 1800 and provides the program or data to the CPU 1100 via the RAM 1200. The CPU 1100 loads the 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 generation device 100, the CPU 1100 of the computer 1000 realizes the function of the control unit 130 by executing the program loaded on the RAM 1200. Further, each data in the storage unit 120 is stored in the HDD 1400. The CPU 1100 of the computer 1000 reads and executes these programs from the recording medium 1800. However, as another example, the CPU 1100 may acquire these programs from another device via the communication network 500.

[8. effect〕
As described above, the generation device 100 according to the embodiment has the acquisition unit 131 and the generation unit 132. The acquisition unit 131 acquires information regarding distribution of a product that is a target of a commercial transaction. The generation unit 132 generates a model for calculating the creditworthiness of the target person of the commercial transaction based on the information on the physical distribution acquired by the acquisition unit 131.

  In this way, the generation device 100 according to the embodiment generates a model for calculating the creditworthiness of the target person of the commercial transaction from the viewpoint of product distribution. Accordingly, the generation device 100 can generate the model based on the information related to the actual shipping of the product, and thus can generate the model capable of calculating the credit rating according to the actual situation. As a result, the generation device 100 can determine the credibility of the target person of the commercial transaction from various viewpoints.

  Further, the generation unit 132 generates a model for calculating the credibility of the provider of the product in the commercial transaction (store in the embodiment) as the target person of the commercial transaction.

  As described above, the generation device 100 according to the embodiment determines the creditworthiness of the provider from various viewpoints by generating a model that calculates the creditworthiness of the provider of the product in the commercial transaction based on the information about the physical distribution. be able to.

  Further, the acquisition unit 131 acquires, as the information regarding the physical distribution, the return rate in which the product is returned after the provider ships the product. The generation unit 132 generates a model for calculating the creditworthiness of the provider based on the return rate.

  As described above, the generation device 100 according to the embodiment generates a model based on the return rate, and thus, for example, the reliability is high for a provider who frequently returns merchandise or a provider who easily causes wasteful delivery of merchandise. It is possible to judge the creditworthiness of the provider from various points of view, such as calculating it low.

  Further, the acquisition unit 131 acquires, as the information regarding the distribution, shipping information indicating whether or not the shipping of the product has been completed when the provider receives the order for the commercial transaction. The generation unit 132 generates a model for calculating the creditworthiness of the provider based on the shipping information.

  As described above, the generation device 100 according to the embodiment provides the model from various viewpoints by generating a model based on the shipping information, for example, calculating a low credit rating for a provider who is likely to cancel due to lack of inventory. The creditworthiness of a person can be determined.

  In addition, the acquisition unit 131 acquires, as the information regarding the physical distribution, a user review regarding the shipment of the product by the provider. The generation unit 132 generates a model for calculating the creditworthiness of the provider based on the user review regarding the shipping of the product by the provider.

  As described above, the generation device 100 according to the embodiment generates a model based on a user review related to shipping, and thus, for example, a credit rating is given to a provider with a bad reputation from a user or a provider who easily causes a delay in products. It is possible to judge the creditworthiness of the provider from various points of view, such as calculating a low value.

  In addition, the generation unit 132 generates a model for calculating the credibility of the purchaser (the user in the embodiment) of the product in the commercial transaction as the target person of the commercial transaction.

  As described above, the generation device 100 according to the embodiment determines the creditworthiness of the purchaser from various viewpoints by generating a model that calculates the creditworthiness of the purchaser of the product in the commercial transaction based on the information about the physical distribution. be able to.

  Further, the acquisition unit 131 acquires, as the information regarding the distribution, the return application rate at which the purchaser has purchased the product and then applied for returning the product. The generation unit 132 generates a model for calculating the creditworthiness of the purchaser based on the return application rate.

  As described above, the generation device 100 according to the embodiment generates a model based on the return application rate, so that, for example, for a purchaser who frequently requests a return or a purchaser who tends to unnecessarily increase the delivery amount of goods. Can determine the creditworthiness of the purchaser from various perspectives, such as calculating the creditworthiness as low.

  In addition, the acquisition unit 131 acquires a user review regarding delivery of the product as information regarding distribution. The generation unit 132 generates a model for calculating the creditworthiness of the purchaser based on a user review regarding the shipment of products by the purchaser.

  As described above, the generation device 100 according to the embodiment generates a model based on the adequacy of the user review described by the user, and thus, for example, for a purchaser who takes an action such as frequently describing an unreasonable complaint. Can determine the creditworthiness of the purchaser from various perspectives, such as calculating the creditworthiness as low.

  Further, the acquisition unit 131 acquires, as the information regarding the physical distribution, product receipt information indicating whether or not the purchaser has received the product at the designated delivery date and time of the product. The generation unit 132 generates a model for calculating the creditworthiness of the purchaser based on the product receipt information.

  As described above, the generation device 100 according to the embodiment generates a model based on the degree of completion of delivery of a product (delivery success rate), the delivery date / time change rate, and the like. It is possible to judge the creditworthiness of a purchaser from various viewpoints, such as calculating a high creditworthiness for a purchaser who is not interested in a high purchaser but is interested in smooth logistics, or a purchaser who does not cause unnecessary redelivery. .

  In addition, the acquisition unit 131 acquires, as the information regarding the physical distribution, the evaluation information that is the information transmitted from the delivery company that has delivered the product to the purchaser and that indicates the evaluation result of the purchaser. The generation unit 132 generates a model for calculating the creditworthiness of the purchaser based on the evaluation information.

  As described above, the generation device 100 according to the embodiment generates the model based on the reputation of the trader who actually delivered the product, and thus, for example, the purchaser who is likely to attach an unreasonable complaint to the carrier or the carrier between the carrier. It is possible to judge the creditworthiness of the purchaser from various points of view, such as calculating a low creditworthiness for the buyer who is easily shunned.

  The embodiments of the present application and some of the modifications of the embodiments have been described above in detail with reference to the drawings. However, these are examples, and the knowledge of a person skilled in the art including aspects described in the section of the disclosure of the invention will be understood. It is possible to carry out the present invention in other forms based on various modifications and improvements.

  Further, the above-described generation device 100 may be realized by a plurality of server computers, and depending on the function, it may be realized by calling an external platform or the like by an API (Application Programming Interface) or network computing. Can be changed flexibly.

  Further, the “section (section, module, unit)” described in the claims can be read as “means” or “circuit”. For example, the generation unit can be read as a generation unit or a generation circuit.

1 Generation System 10 User Terminal 20 Store Terminal 30 Web Server 50 Delivery Agent Device 100 Generation Device 110 Communication Unit 120 Storage Unit 121 Store Information Storage Unit 122 User Information Storage Unit 123 Store Model Storage Unit 124 User Model Storage Unit 130 Control Unit 131 Acquisition Unit 132 Generation Unit 133 Calculation Unit

Claims (18)

An acquisition unit that acquires information about the distribution of goods that are the subject of commercial transactions,
A generation unit that generates a model that calculates the creditworthiness of the purchaser of the product in the commercial transaction among the target persons of the commercial transaction based on the information about the physical distribution acquired by the acquisition unit,
Equipped with
The acquisition unit,
The post information on the network of the purchaser to the provider of the product in the commercial transaction after the identification information of the purchaser is acquired and the product is delivered based on the identification information, Acquire post information related to product logistics,
The generator is
A model for calculating the creditworthiness of the purchaser based on the post information acquired by the acquisition unit, which is identified based on the identification information, based on the post information related to distribution of the product on the network of the purchaser. Generate,
A generating device characterized by the above. The acquisition unit,
As the information related to the logistics, after the purchaser has purchased the product, the return application rate for applying to return the product is acquired,
The generator is
Generating a model for calculating the creditworthiness of the purchaser based on the return application rate,
The generation device according to claim 1, wherein The acquisition unit,
As the information on the physical distribution, obtain information on the number of products canceled by the purchaser before the products are shipped,
The generator is
A model for calculating the creditworthiness of the purchaser is generated based on information about the number of products canceled by the purchaser side before the product is shipped.
The generating device according to claim 1 or 2, characterized in that. The acquisition unit,
As the information on the physical distribution, the information about the change of the delivery date and time requested by the purchaser to the delivery company delivering the product is acquired,
The generator is
A model for calculating the creditworthiness of the purchaser is generated based on the information regarding the change of the delivery date and time requested by the purchaser to the delivery company delivering the product,
The generating device according to claim 1, wherein the generating device is a generator. The generator is
Further generating a model for calculating the creditworthiness of the provider of the product in the commercial transaction, based on posted information on the purchaser's network,
The generating device according to claim 1, wherein The acquisition unit,
As information posted on the purchaser's network, an index value indicating an evaluation of a user review in a store operated by the provider is acquired from information regarding a user review for the provider regarding delivery of the product,
The generator is
Generating a model for calculating the creditworthiness of the provider based on the index value,
The generation device according to claim 5, wherein The acquisition unit,
Acquiring the index value calculated based on the terms included in the user reviews posted to the store,
The generator is
Generating a model for calculating the creditworthiness of the provider based on the index value,
The generation device according to claim 6, characterized in that The acquisition unit,
Acquiring the index value calculated based on the correlation between a user review posted to a store highly evaluated for user reviews and a user review posted to a store operated by the provider,
The generator is
Generating a model for calculating the creditworthiness of the provider based on the index value,
The generation device according to claim 6, characterized in that The acquisition unit,
As the information on the logistics, after the provider has shipped the product, obtain a return rate of the product returned,
The generator is
Generate a model for calculating the creditworthiness of the provider based on the return rate
The generating apparatus according to claim 5, wherein the generating apparatus is a generating apparatus. The acquisition unit,
As the information on the physical distribution, obtain the shipping information indicating whether or not the shipping of the product could be completed when the provider accepted the order of the commercial transaction,
The generator is
Generating a model for calculating the creditworthiness of the provider based on the shipping information,
The generating device according to claim 5, wherein the generating device is a generating device. A generation method executed by a computer,
An acquisition process for acquiring information on the distribution of goods subject to commerce,
A generation step of generating a model for calculating the creditworthiness of the purchaser of the commodity in the commercial transaction among the target persons of the commercial transaction based on the information about the physical distribution acquired in the acquisition step;
Including,
The acquisition step is
The post information on the network of the purchaser to the provider of the product in the commercial transaction after the identification information of the purchaser is acquired and the product is delivered based on the identification information, Acquire post information related to product logistics,
The generation step is
A model for calculating the creditworthiness of the purchaser based on the post information acquired in the acquisition step, which is identified based on the identification information, and based on the post information related to the distribution of the product on the network of the purchaser. Generate,
A generation method characterized by the above. The acquisition step is
As the information on the physical distribution, obtain information on the number of products canceled by the purchaser before the products are shipped,
The generation step is
A model for calculating the creditworthiness of the purchaser is generated based on information about the number of products canceled by the purchaser side before the product is shipped.
The generating method according to claim 11, characterized in that. The acquisition step is
As the information on the physical distribution, the information about the change of the delivery date and time requested by the purchaser to the delivery company delivering the product is acquired,
The generation step is
A model for calculating the creditworthiness of the purchaser is generated based on the information regarding the change of the delivery date and time requested by the purchaser to the delivery company delivering the product,
The generating method according to claim 11 or 12, characterized in that. The generation step is
Further generating a model for calculating the creditworthiness of the provider of the product in the commercial transaction, based on posted information on the purchaser's network,
The method according to any one of claims 11 to 13, characterized in that. An acquisition procedure for acquiring information on the distribution of goods that are the subject of commercial transactions,
A generation procedure for generating a model for calculating the creditworthiness of the purchaser of the product in the commercial transaction among the target persons of the commercial transaction based on the information about the physical distribution acquired by the acquisition procedure;
To the computer,
The acquisition procedure is
The post information on the network of the purchaser to the provider of the product in the commercial transaction after the identification information of the purchaser is acquired and the product is delivered based on the identification information, Acquire post information related to product logistics,
The generation procedure is
A model for calculating the creditworthiness of the purchaser based on the post information acquired by the acquisition procedure, which is based on the post information related to the physical distribution of the product on the network of the purchaser identified based on the identification information. Generate,
A generation program characterized by the above. The acquisition procedure is
As the information on the physical distribution, obtain information on the number of products canceled by the purchaser before the products are shipped,
The generation procedure is
A model for calculating the creditworthiness of the purchaser is generated based on information about the number of products canceled by the purchaser side before the product is shipped.
The generation program according to claim 15, wherein The acquisition procedure is
As the information on the physical distribution, the information about the change of the delivery date and time requested by the purchaser to the delivery company delivering the product is acquired,
The generation procedure is
A model for calculating the creditworthiness of the purchaser is generated based on the information regarding the change of the delivery date and time requested by the purchaser to the delivery company delivering the product,
The generation program according to claim 15 or 16, characterized in that. The generation procedure is
Further generating a model for calculating the creditworthiness of the provider based on the posted information on the purchaser's network,
The generating program according to any one of claims 15 to 17, characterized in that.

Images