Providing device, providing method, and providing program

Abstract

Providing useful information about your target audience. [Solution] The providing device according to the present application includes a receiving unit, a generating unit, a classification unit, a grouping unit, and a providing unit. The receiving unit receives attribute information of users belonging to a predetermined category from a first business operator. The generating unit generates a classification model that classifies users included in the user information using user information previously accumulated by a second business operator, and classifies users having the attribute information received by the receiving unit into the same category. The classification unit uses the classification model generated by the generating unit to classify users included in the user information into the predetermined category. The grouping unit groups the users classified by the classification unit. The providing unit provides statistical information about users grouped into the same set by the grouping unit to the first business operator.

Description

[Technical field]

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

[0002] Conventionally, various techniques have been proposed for analyzing huge amounts of data exchanged over the Internet from various aspects, with the aim of utilizing the data in business situations, etc. For example, a technique is known that analyzes customers by taking into account seasonal trends using purchase history data, etc. [Prior art documents] [Patent documents]

[0003] [Patent Document 1] JP 2015-146145 A Summary of the Invention [Problem to be solved by the invention]

[0004] However, conventional techniques leave room for improvement in providing useful information about target users.

[0005] The present application has been made in consideration of the above, and aims to provide a providing device, a providing method, and a providing program capable of providing useful information related to a target user. [Means for solving the problem]

[0006] The providing device according to the present application includes a receiving unit, a generating unit, a classifying unit, a grouping unit, and a providing unit. The receiving unit receives attribute information of users belonging to a predetermined category from a first business operator. The generating unit generates a classification model that is a model for classifying users included in the user information using user information previously accumulated by a second business operator, and classifies users having the attribute information received by the receiving unit into the same category. The classifying unit classifies users belonging to the predetermined category from among users included in the user information, using the classification model generated by the generating unit. The grouping unit groups the users classified by the classifying unit. The providing unit provides statistical information on users grouped into the same set by the grouping unit to the first business operator. Effect of the Invention

[0007] According to one aspect of the embodiment, useful information about a target user can be provided. [Brief description of the drawings]

[0008] [Figure 1] FIG. 1 is a diagram illustrating an example of information processing according to an embodiment. [Diagram 2] FIG. 2 is a diagram illustrating an example of statistical information based on a search history according to the embodiment. [Diagram 3] FIG. 3 is a diagram illustrating an example of statistical information based on a purchase history according to the embodiment. [Figure 4] FIG. 4 is a diagram showing another example of statistical information based on search histories according to the embodiment. [Diagram 5] FIG. 5 is a diagram illustrating an example of a configuration of a providing device according to the embodiment. [Figure 6] FIG. 6 is a diagram illustrating an example of statistical information regarding search histories for each category according to the embodiment. [Figure 7] FIG. 7 is a flowchart illustrating an example of a processing procedure by the providing device according to the embodiment. [Figure 8] FIG. 8 is a diagram showing an example of a method for providing statistical information according to a modified example. [Figure 9] FIG. 9 is a hardware configuration diagram illustrating an example of a computer that realizes the functions of the providing device according to the embodiment or the modification. DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS

[0009] Below, a detailed description will be given of a form (hereinafter referred to as "embodiment") for implementing the providing device, providing method, and providing program according to the present application with reference to the drawings. Note that the providing device, providing method, and providing program according to the present application are not limited to the embodiment described below. Furthermore, the embodiments described below can be appropriately combined to the extent that the processing contents are not contradictory. Furthermore, the same parts in the embodiments described below are given the same reference numerals, and duplicated descriptions will be omitted.

[0010] [1. Overview of information processing] Hereinafter, an example of information processing according to the embodiment will be described with reference to the drawings. Fig. 1 is a diagram showing an example of information processing according to the embodiment. Note that the information processing described below is not limited to the example described below, and can be executed in parallel for any number of carrier terminals.

[0011] As shown in FIG. 1, a providing system 1 according to an embodiment includes an operator terminal 10 and a providing device 100. The operator terminal 10 and the providing device 100 are each connected to a network N (for example, see FIG. 5) by wire or wirelessly. The network N is a communication network such as a LAN (Local Area Network), a WAN (Wide Area Network), a telephone network (such as a mobile phone network or a fixed telephone network), a regional IP (Internet Protocol) network, or the Internet. The network N may include a wired network or a wireless network. The operator terminal 10 and the providing device 100 can communicate with each other through the network N.

[0012] The business operator terminal 10 shown in FIG. 1 is an information processing device managed by a business operator X (an example of a "first business operator"). For example, the business operator X independently and repeatedly carries out a business of providing a specific product or service to consumers. The business operator terminal 10 is typically a desktop or notebook personal computer. The business operator terminal 10 may be realized by any information processing terminal such as a smartphone, a tablet, or a PDA (Personal Digital Assistant).

[0013] Furthermore, the operator terminal 10 can display the information provided by the providing device 100 using a web browser or an application. When the operator terminal 10 receives control information for realizing a display process of the information from the providing device 100 or the like, the operator terminal 10 realizes the display process according to the control information.

[0014] The business operator terminal 10 also collects customer information related to the business run by the business operator X and manages the collected customer information. The business operator terminal 10 also analyzes the customer information collected by the business operator X to identify the labels of users belonging to a predetermined category (one example of "attribute information"). For example, the business operator terminal 10 identifies labels such as "purchasing a refrigerator" and "annual income of 10 million yen or more" for a customer who belongs to the category of "residing in Chuo Ward", "age in 50s", and "gender male". The business operator terminal 10 then provides the providing device 100 with information on the labels identified for each predetermined category at any timing.

[0015] The providing device 100 shown in FIG. 1 is an information processing device managed by an operator Y (an example of a "second operator") that independently and repeatedly provides various services on the Internet to users. For example, the providing device 100 is realized by a server device, a cloud system, or the like. The providing device 100 may function as a distribution device that distributes control information to a user terminal (not shown) used by a service user or a business operator terminal 10. Here, the control information is described in, for example, a script language such as JavaScript (registered trademark) or a style sheet language such as CSS (Cascading Style Sheets). The application itself distributed from the providing device 100 may be regarded as control information.

[0016] The providing device 100 provides various services on the Internet to service users via online content such as a portal site. The services provided by the providing device 100 include various services provided via web pages related to search engine sites, news sites, technology commentary sites, shopping sites, finance sites (stock price sites), route search sites, map providing sites, travel sites, restaurant introduction sites, web blogs, etc. The providing device 100 can also provide information to be displayed on various applications (e.g., portal applications, news applications, auction applications, weather forecast applications, shopping applications, finance (stock price) applications, route search applications, map providing applications, travel applications, restaurant introduction applications, blog viewing applications, etc.) installed in the business operator terminal 10.

[0017] Furthermore, the providing device 100 can receive search words input by the service user through the provision of the various services described above. Furthermore, the providing device 100 can accumulate the received search words as a search history (search log). Furthermore, the providing device 100 collects user attributes (e.g., demographic attributes such as age, sex, and region, and psychographic attributes estimated based on the usage history of online content of various services) based on the operation and browsing of the service user in various services, and the behavior history of the service user in various services, and stores them in association with a user ID. Furthermore, the providing device 100 may be a device that distributes information to be displayed on applications related to various services that are pre-installed in a user terminal (not shown) used by the service user to the user terminal. Furthermore, the providing device 100 may be a server device that distributes the application data itself.

[0018] In addition, the providing device 100 creates a classification model for the provider X based on the labels provided by the provider X using service user information previously accumulated by the provider Y, and provides statistical information based on each user classified by the created classification model.

[0019] As shown in Fig. 1, first, the providing device 100 receives, for each predetermined category, label information of a customer (user) belonging to a predetermined category from the business operator terminal 10 (step S1). In the example shown in Fig. 1, for example, the providing device 100 receives labels LA-1 and LA-2 of a user belonging to category CT-A, a label LB of a user belonging to category CT-B, and a label LC of a user belonging to category CT-C.

[0020] Next, the providing device 100 generates a classification model for classifying users having the label information received from the provider terminal 10 into the same category (step S2). That is, the providing device 100 generates a model for classifying service users included in the service user information, using the service user information (an example of "user information") previously accumulated by the provider Y.

[0021] For example, the providing device 100 uses learning data to learn a classification model that classifies (estimates) whether a user corresponding to input data belongs to a predetermined category corresponding to a label in response to input of input data. Specifically, the providing device 100 learns parameters such as connection coefficients (weights) between mutually connected nodes constituting a model (neural network).

[0022] Moreover, the learning of the classification model is performed using various machine learning techniques. For example, the providing device 100 learns the model parameters by a learning method using data to be input to the model and a classification label (correct answer label) indicating the output when the data is input, that is, a supervised learning method. Note that the above is only an example, and the providing device 100 may learn the model parameters by any learning method as long as the providing device 100 can learn the model parameters.

[0023] Here, learning of the classification model MA shown in Fig. 1 will be described with a concrete example. For example, an entity Y that manages the providing device 100 acquires sample data corresponding to both the label LA-1 ("purchase of refrigerator") and the label LA-2 ("annual income of 10 million yen or more") from the service user information. Then, the entity Y prepares learning data by assigning the category CT-A ("resident in Chuo Ward" + "in his 50s" + "male") corresponding to the labels LA-1 and LA-2 as a classification label (correct answer label) to the acquired sample data.

[0024] Next, the providing device 100 trains the prepared learning data into a model, and learns the above-mentioned parameters using a learning method such as backpropagation so that, when data associated with an arbitrary user corresponding to the label LA-1 and the label LA-2 is input, the score output by the model for classifying the relevant user into the category CT-A is equal to or greater than a predetermined threshold (so that a user belonging to the category CT-A can be correctly classified into the category CT-A). In this way, a classification model MA for classifying a service user into the category CT-A can be generated. Similarly, the providing device 100 can generate a classification model MB, a classification model MC, and the like. Note that the providing device 100 may generate a classification model such that the number of service users classified by the generated classification model is equal to or greater than a predetermined threshold.

[0025] The providing device 100 can employ any network, such as a deep neural network (DNN) or a support vector machine (SVM), as a model (network) for generating each classification model. In addition, the classification model may be a decision tree.

[0026] Next, the providing device 100 classifies users belonging to a predetermined category from among the service users included in the pre-stored service user information, using the classification model (step S3).

[0027] Next, the providing device 100 groups the users classified by the classification model (step S4). Hereinafter, an example of grouping the users classified into the category CT-A ("resident of Chuo Ward" + "50s" + "male") by the classification model MA will be described.

[0028] For example, the providing device 100 acquires data associated with each user belonging to category CT-A ("resident of Chuo Ward" + "age 50" + "male") from the service user information, and classifies (clusters) each user into groups using the acquired data. The grouping can be performed, for example, by comparing feature information calculated in advance for each user with each other and based on the similarity of the feature information. Here, the feature information may be information obtained by vectorizing the tendency of search words input by the user, the behavior history in various services, and the user attributes estimated from the behavior history, or may be information that simply quantifies the user attributes. The grouping method may be hierarchical or non-hierarchical. As a calculation method used for hierarchical grouping, any method such as Ward's method, group average method, shortest distance method, and longest distance method can be used. As a calculation method used for non-hierarchical grouping, any method such as k-means method can be used.

[0029] After grouping, the providing device 100 provides the provider X with statistical information on each user grouped into the same set (hereinafter referred to as the "same cluster") (step S5).

[0030] The providing device 100 individually collects data characterizing each cluster (e.g., number of users ≧10) into which users belonging to a predetermined category are grouped. Then, the providing device 100 generates statistical information based on the data individually collected for each cluster, and provides the statistical information to the business operator X. Note that the providing device 100 may set not only a lower limit but also an upper limit (e.g., number of users ≦20) for the number of users belonging to each grouped cluster.

[0031] For example, the providing device 100 refers to search histories associated with each user belonging to the same cluster, tallying up search words entered by each user for each cluster individually, and identifies the most frequently searched search word. Then, the providing device 100 can provide information on the search words identified for each cluster as statistical information to the business entity X. Fig. 2 is a diagram illustrating an example of statistical information based on search histories according to an embodiment.

[0032] As shown in Fig. 2, the providing device 100 can provide the business operator X with statistical information configured in a list format by associating information on the search word most frequently searched by users in each cluster with information on the corresponding category, for example. The example shown in Fig. 2 shows "ballroom dancing," which is the most frequently searched search word in one cluster grouped from users belonging to category CT-A, "immigration," which is the most frequently searched search word in one cluster grouped from users belonging to category CT-A, and "world heritage," which is the most frequently searched search word in one cluster grouped from users belonging to category CT-A.

[0033] Also, for example, the providing device 100 refers to the purchase history associated with each user belonging to the same cluster, individually counts the number of purchases of products purchased by each user for each cluster, and identifies the most purchased product. Then, the providing device 100 can provide information on the products identified for each cluster as statistical information to the business entity X. FIG. 3 is a diagram illustrating an example of statistical information based on the purchase history according to the embodiment.

[0034] As shown in Fig. 3, the providing device 100 can provide the business operator X with statistical information configured in a list format by associating information on the product that was purchased most frequently by users in each cluster with information on the corresponding category, for example. The example shown in Fig. 3 shows "camera", which is the product that was purchased most frequently in one cluster grouped from users belonging to category CT-A, "vacuum cleaner", which is the product that was purchased most frequently in one cluster grouped from users belonging to category CT-A, and "bedding", which is the product that was purchased most frequently in one cluster grouped from users belonging to category CT-A.

[0035] Furthermore, the providing device 100 is not limited to providing statistical information in a list format. Fig. 4 is a diagram showing another example of statistical information based on a search history according to an embodiment. As shown in Fig. 4, the providing device 100 may provide the business operator X with statistical information configured in a keyword map format by associating information on the search word that was most frequently searched by users in each cluster with the corresponding classification model MA.

[0036] In addition, the providing device 100 can provide information based on the scores of each user output from the classification model as statistical information. In the example shown in FIG. 2 and FIG. 4, the average value VA1-1 of the output scores output from the classification model MA for each user belonging to a set (cluster) linked to the search word: "ballroom dance" is provided in association with the search word: "ballroom dance". Similarly, the average value VA1-2 of the output scores output from the classification model MA for each user belonging to a set (cluster) linked to the search word: "migration" is provided in association with the search word: "migration". Similarly, the average value VA1-3 of the output scores output from the classification model MA for each user belonging to a set (cluster) linked to the search word: "world heritage" is provided in association with the search word: "world heritage". As a result, the business entity X who has received the statistical information can identify search words that are more strongly correlated with users belonging to the category CT-A.

[0037] In this way, the providing device 100 can provide the business entity X with useful information on users belonging to a predetermined category. That is, the providing device 100 can provide the business entity X with useful information on users targeted by the business entity X. Note that the providing device 100 can provide the business entity X with statistical information on user attributes and the like, in addition to search history and purchase history.

[0038] In addition, the providing device 100 provides statistical information about users belonging to the same cluster on the condition that the number of users grouped in the same cluster is equal to or greater than a predetermined threshold. This makes it possible to provide statistical information with anonymity guaranteed.

[0039] Furthermore, when the number of users grouped into the same set is less than a predetermined threshold, the providing device 100 may relax the threshold condition for classifying whether the user belongs to a predetermined category (for example, category CT-A: "resident in Chuo Ward" + "50s" + "male") so that the number of users is equal to or greater than the predetermined threshold. That is, the providing device 100 may relax the threshold for determining the score for classifying the user into a predetermined category among the scores output from the classification model. This allows the number of users belonging to a predetermined category to be expanded, and the number of grouped users to be adjusted to satisfy the predetermined condition. Note that the providing device 100 may relax the condition for determining similar users when clustering.

[0040] [2. Configuration of the provided device] The configuration of the providing device 100 according to the embodiment will be described with reference to Fig. 5. Fig. 5 is a diagram illustrating an example of the configuration of the providing device according to the embodiment.

[0041] As shown in Fig. 5, the providing device 100 includes a communication unit 110, a storage unit 120, and a control unit 130. Note that Fig. 5 shows an example of the configuration of the providing device 100, and is not limited to the form shown in Fig. 5, and may include other functional units than those shown in Fig. 5.

[0042] (Communication unit 110) The communication unit 110 is connected to a network N, for example, by wire or wirelessly, and transmits and receives information to and from other devices such as the operator terminal 10 via the network N. The communication unit 110 is realized by, for example, a network interface card (NIC) or an antenna. The network N is a communication network such as a local area network (LAN), a wide area network (WAN), a telephone network (such as a mobile phone network or a landline telephone network), a regional Internet Protocol (IP) network, or the Internet. The network N may include a wired network or a wireless network.

[0043] The communication unit 110 receives label information of customers (users) belonging to a predetermined category for each predetermined category from the business operator terminal 10. In addition, the communication unit 110 transmits statistical information generated by the control unit 130 to the business operator terminal 10.

[0044] (Storage unit 120) The storage unit 120 is realized by, for example, a semiconductor memory element such as a random access memory (RAM) or a flash memory, or a storage device such as a hard disk or an optical disk. The storage unit 120 stores programs and data for realizing information processing executed by each part of the control unit 130.

[0045] As shown in FIG. 5, the storage unit 120 has a service user information storage unit 121 and a model storage unit 122. The service user information storage unit 121 stores service user information related to the service user in association with identification information (e.g., a user ID) for identifying the service user. The service user information includes the service user's search history (search log), user attributes based on the service user's operation, browsing, etc. in various services (e.g., demographic attributes such as age, sex, and region, and psychographic attributes estimated based on the usage history of online content in various services), and the service user's behavior history in various services. The model storage unit 122 stores the data of the model generated by the control unit 130 for each predetermined category.

[0046] (Control unit 130) The control unit 130 is a controller that controls the providing device 100. The control unit 130 is realized by a CPU (Central Processing Unit), an MPU (Micro Processing Unit), or the like executing various programs (e.g., information processing programs) stored in a storage device inside the providing device 100 using a RAM as a working area. The control unit 130 may also be realized by an integrated circuit such as an ASIC (Application Specific Integrated Circuit) or an FPGA (Field Programmable Gate Array).

[0047] As shown in Fig. 5, the control unit 130 has a receiving unit 131, a generating unit 132, a classifying unit 133, a grouping unit 134, and a providing unit 135. The control unit 130 realizes or executes the functions and actions of information processing described below by using these units. The internal configuration of the control unit 130 is not limited to the configuration shown in Fig. 4, and may be other configurations as long as they perform information processing described below. Furthermore, the connection relationship of the units in the control unit 130 is not limited to the connection relationship shown in Fig. 4, and may be other connection relationships.

[0048] (Reception Department 131) The reception unit 131 receives label information (e.g., “purchase of refrigerator” or “annual income of 10 million yen or more”) of a user belonging to a predetermined category (e.g., “resident of Chuo-ku” + “50s” + “male”) from a first business (e.g., “business X”) through the communication unit 110. The reception unit 131 sends the received label information to the generation unit 132.

[0049] (Generation unit 132) The generation unit 132 generates a classification model for each predetermined category that classifies users having the label information acquired from the reception unit 131 into the same category. The generation unit 132 stores data of the generated classification model in the model storage unit 122.

[0050] (Classification Department 133) The classification unit 133 classifies users belonging to a predetermined category from among the service users included in the service user information stored in the service user information storage unit 121, using the classification model stored in the model storage unit 122. The classification unit 133 sends to the grouping unit 134 identification information (e.g., a user ID) for identifying each classified user.

[0051] (Grouping part 134) As described above, the grouping unit 134 uses an arbitrary grouping method to group the users classified by the classification unit 133. The grouping unit 134 sends to the providing unit 135 identification information (for example, a user ID) for identifying each of the grouped users.

[0052] (Provider 135) As described above, the providing unit 135 provides the business entity X with statistical information on each user grouped into the same cluster. Specifically, the providing unit 135 individually collects data (such as search words, purchased products, and user attributes) that characterize users belonging to each cluster for each cluster in which the number of users grouped into the same cluster is 10 or more. Then, the providing unit 135 generates statistical information based on the data identified for each cluster, and provides the statistical information to the business entity X via the communication unit 110.

[0053] 6 is a diagram showing an example of statistical information regarding search history for each category according to the embodiment. For example, as shown in FIG. 6, the providing unit 135 can provide the business entity X with statistical information in a list format in which information on search words most frequently searched by each user grouped into the same cluster is associated with the corresponding category.

[0054] [3. Processing Procedure] Hereinafter, a processing procedure by the providing device 100 according to the embodiment will be described with reference to Fig. 7. Fig. 7 is a flowchart showing an example of a processing procedure by the providing device according to the embodiment. The processing procedure shown in Fig. 7 is executed by the control unit 130 of the providing device 100. The processing procedure shown in Fig. 7 is repeatedly executed while the providing device 100 is in operation.

[0055] As shown in FIG. 7, the receiving unit 131 receives information on the labels of users who belong to a predetermined category from the business terminal 10 via the communication unit 110 (step S101).

[0056] Furthermore, the generating unit 132 generates, for each predetermined category, a classification model for classifying users having the label information acquired from the receiving unit 131 into the same category (step S102).

[0057] In addition, the classification unit 133 uses the classification model stored in the model storage unit 122 to classify users belonging to a predetermined category from among the service users included in the service user information stored in the service user information storage unit 121 (step S103).

[0058] Furthermore, the grouping unit 134, as described above, uses an arbitrary grouping method to classify the users classified by the classification unit 133 into groups (step S104).

[0059] Furthermore, the providing unit 135 provides the statistical information on the users grouped into the same cluster by the grouping unit 134 to the provider X through the communication unit 110 (step S105), and the processing procedure shown in FIG. 7 ends.

[0060] [4. Modifications] (4-1. Providing statistical information based on multiple classification models) In the above-described embodiment, the providing device 100 may provide a combination of statistical information of users classified into each category. Fig. 8 is a diagram showing an example of a method for providing statistical information according to a modified example. Fig. 8 shows an example of a case where statistical information on users belonging to the category of "resident in Chuo Ward" + "50s" is provided.

[0061] As shown in FIG. 8, when providing statistical information on users belonging to the category of "resident in Chuo Ward" + "50s", the providing device 100 classifies the users using classification models corresponding to each of a plurality of categories with more limited conditions, and divides the classified users into groups. For example, the providing device 100 uses classification model MA to classify users belonging to the category of "resident in Chuo Ward" + "50s" + "male". In addition, the providing device 100 uses classification model MX to classify users belonging to the category of "resident in Chuo Ward" + "50s" + "female".

[0062] Next, the providing device 100 generates statistical information on users grouped into the same cluster by grouping users classified into the categories of "resident in Chuo Ward" + "age 50" + "male." The providing device 100 also generates statistical information on users grouped into the same cluster by grouping users classified into the categories of "resident in Chuo Ward" + "age 50" + "female."

[0063] The providing device 100 then provides a combination of statistical information on users belonging to the categories of "resident in Chuo Ward" + "age 50" + "male" and statistical information on users belonging to the categories of "resident in Chuo Ward" + "age 50" + "female." This allows the providing device 100 to provide statistical information on users belonging to a desired category without reducing the classification accuracy of users belonging to a predetermined category.

[0064] (4-2. Use of classification models) In the above-described embodiment, the providing device 100 may use the classification model stored in the model storage unit 122 when providing statistical information to other companies that are in a competitive relationship with the business run by the business operator X.

[0065] [5. Hardware configuration] The providing device 100 according to the embodiment or the modification is realized by, for example, a computer 1000 having a configuration as shown in Fig. 9. Fig. 9 is a hardware configuration diagram showing an example of a computer that realizes the functions of the providing device according to the embodiment or the modification.

[0066] The computer 1000 has a CPU 1100, a RAM 1200, a ROM 1300, a HDD 1400, a communication interface (I / F) 1500, an input / output interface (I / F) 1600, and a media interface (I / F) 1700.

[0067] The CPU 1100 operates and controls each unit based on a program stored in the ROM 1300 or the HDD 1400. The ROM 1300 stores a boot program executed by the CPU 1100 when the computer 1000 is started up, programs that depend on the hardware of the computer 1000, and the like.

[0068] The HDD 1400 stores programs executed by the CPU 1100, data used by such programs, etc. The communication interface 1500 receives data from other devices via a network (communication network) N and sends it to the CPU 1100, and transmits data generated by the CPU 1100 to other devices via the network (communication network) N.

[0069] 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 acquires data from the input devices via the input / output interface 1600. The CPU 1100 also outputs generated data to the output devices via the input / output interface 1600.

[0070] The media interface 1700 reads a program or data stored in the recording medium 1800 and provides it to the CPU 1100 via the RAM 1200. The CPU 1100 loads 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 a PD (Phase change rewritable Disc), a magneto-optical recording medium such as an MO (Magneto-Optical disk), a tape medium, a magnetic recording medium, or a semiconductor memory.

[0071] For example, when the computer 1000 functions as the providing device 100 according to the embodiment, the CPU 1100 of the computer 1000 executes a program loaded onto the RAM 1200 to realize the function of the control unit 130. In addition, the HDD 1400 stores data in the storage unit 120. The CPU 1100 of the computer 1000 reads and executes these programs from the recording medium 1800, but as another example, the CPU 1100 may obtain these programs from another device via a network (communication network) N.

[0072] [6.Other] Of the processes described in the above embodiments or modifications, all or part of the processes described as being performed automatically can be performed manually, or all or part of the processes described as being performed manually can be performed automatically by a known method. In addition, the information including the process procedures, specific names, various data and parameters shown in the above documents and drawings can be changed arbitrarily unless otherwise specified.

[0073] In the above-described embodiment, in order to realize the provision method by the providing device 100 (for example, see FIG. 7), the processing functions corresponding to each part (reception unit 131, generation unit 132, classification unit 133, grouping unit 134, and provision unit 135) of the control unit 130 possessed by the providing device 100 may be realized as an add-on to a provision program pre-installed in the providing device 100, or may be realized by flexibly writing it as a dedicated provision program using a lightweight programming language, etc.

[0074] In addition, in the above-described embodiment and modified examples, the providing device 100 may be configured as a device that provides various services to service users and a device that provides statistical information to businesses, which are physically separated from each other.

[0075] In addition, each component of each device shown in the figure is a functional concept, and does not necessarily have to be physically configured as shown in the figure. In other words, the specific form of distribution and integration of each device is not limited to that shown in the figure, and all or part of them can be functionally or physically distributed and integrated in any unit according to various loads, usage conditions, etc. For example, the reception unit 131 and the generation unit 132 of the control unit 130 may be functionally integrated.

[0076] Furthermore, the above-described embodiments and modifications can be appropriately combined as long as the processing contents are not contradictory.

[0077] [7. Effects] The providing device 100 according to the above-described embodiment or modification includes a receiving unit 131, a generating unit 132, a classifying unit 133, a grouping unit 134, and a providing unit 135. The receiving unit 131 receives label information (an example of "attribute information") of users belonging to a predetermined category from, for example, a business operator X (an example of a "first business operator"). The generating unit 132 generates a classification model that classifies users included in the service user information, using service user information (an example of "user information") that is accumulated in advance by, for example, a business operator Y (an example of a "second business operator"), and classifies users having label information received by the receiving unit 131 into the same category. The classifying unit 133 classifies users belonging to a predetermined category from among users included in the service user information, using the classification model generated by the generating unit 132. The grouping unit 134 groups the users classified by the classifying unit 133. The providing unit 135 provides the business operator X with statistical information on users grouped into the same set by the grouping unit 134.

[0078] In this way, the providing device 100 according to the embodiment or the modified example can provide useful information on users belonging to a predetermined category to, for example, the business entity X. That is, the providing device 100 can provide useful information on target users to the business entity X, in other words, a wide variety of information that cannot be known within the scope of the business entity X.

[0079] Furthermore, in the providing device 100 according to the embodiment or the modification, the providing unit 135 provides statistical information on users belonging to the same set on condition that the number of users grouped into the same set by the grouping unit 134 is equal to or greater than a predetermined threshold. This allows the providing device 100 according to the embodiment or the modification to provide users with guaranteed anonymity.

[0080] Furthermore, in the providing device 100 according to the embodiment or the modified example, when the number of users grouped into the same set by the grouping unit 134 is less than a predetermined threshold, the providing unit 135 relaxes the threshold condition for classifying whether the users belong to a predetermined category or not so that the number of users becomes equal to or greater than the predetermined threshold. This makes it possible to actively provide statistical information.

[0081] Furthermore, in the providing device 100 according to the embodiment or the modified example, the providing unit 135 may provide information based on the scores output from the classification model as statistical information (for example, the average score of the users belonging to each cluster). This makes it possible to provide an objective index for easily identifying information correlated with a predetermined category (for example, "resident in Chuo Ward" + "age 50" + "male") in the statistical information.

[0082] Furthermore, in the providing device 100 according to the embodiment or the modified example, the providing unit 135 provides a combination of statistical information on users classified into each category. This makes it possible to provide statistical information on users belonging to a desired category without reducing the classification accuracy of users belonging to a predetermined category.

[0083] The above describes the embodiments of the present application in detail with reference to several drawings. However, these are merely examples, and the present invention can be embodied in other forms that incorporate various modifications and improvements based on the knowledge of those skilled in the art, including the aspects described in the Disclosure of the Invention section.

[0084] Moreover, the above-mentioned "section, module, unit" can be read as "means" or "circuit", etc. For example, a control section can be read as control means or a control circuit. [Explanation of symbols]

[0085] 10. Operator terminal 100 Providing equipment 110 Communications Department 120 Storage section 121 Service user information storage unit 122 Model Memory Section 130 Control section 131 Reception 132 Generation part 133 Classification Department 134 Grouping Section 135 Provision Department

Claims

1. a receiving unit that receives, for each predetermined category, a label of a user belonging to the predetermined category from a first business operator; a generation unit that generates a classification model that uses user information previously accumulated by a second business operator to classify users included in the user information, the classification model classifying users having the label accepted by the acceptance unit into the same category; and a classification unit that classifies users included in the user information into users belonging to the predetermined category by using the classification model generated by the generation unit; a grouping unit that uses data associated with each user classified into the predetermined category by the classification unit to compare feature information calculated for each user with each other, and classifies each user into one of the groups based on a similarity of the feature information; a providing unit that provides the first carrier with statistical information regarding each of the users grouped into the same set by the grouping unit; A providing device comprising:

2. The providing unit is On condition that the number of the users grouped into the same set by the grouping unit is equal to or greater than a predetermined threshold, statistical information regarding the users belonging to the same set is provided. The providing device according to claim 1 .

3. The providing unit is When the number of the users grouped into the same set by the grouping unit is less than a predetermined threshold, a threshold condition for classifying whether the users belong to the predetermined category is relaxed so that the number of the users becomes equal to or greater than the predetermined threshold.

3. The providing device according to claim 1 or 2.

4. The providing unit is As the statistical information, information based on the scores output from the classification model is provided.

4. The providing device according to claim 1, wherein the providing device is a device for providing a plurality of information.

5. The providing unit is Provide a combination of user statistics for each category 5. The providing device according to claim 1, wherein the providing device is a device for providing a plurality of information.

6. 1. A computer-implemented method for providing a method comprising: a receiving step of receiving, from the first business entity, labels of users belonging to each predetermined category; a generation step of generating a classification model that uses user information previously accumulated by a second business operator to classify users included in the user information, the classification model classifying users having the label accepted by the acceptance step into the same category; a classification step of classifying users included in the user information into users belonging to the predetermined category by using the classification model generated by the generation step; a grouping step of comparing feature information calculated for each user using data associated with the users classified into the predetermined category by the classification step, and classifying the users into any one of the groups based on a similarity of the feature information; a providing step of providing statistical information regarding each of the users grouped into the same set by the grouping step to the first carrier; A method of providing comprising:

7. On the computer, a receiving step of receiving, from a first business entity, labels of users belonging to each predetermined category; a generation step of generating a classification model that uses user information previously accumulated by a second business operator to classify users included in the user information, the classification model classifying users having the label accepted by the acceptance step into the same category; a classification step of classifying users included in the user information into users belonging to the predetermined category by using the classification model generated by the generation step; a grouping step of comparing feature information calculated for each user using data associated with the users classified into the predetermined category by the classification step, and grouping the users into any one of the sets based on a similarity of the feature information; a providing step of providing statistical information on each of the users grouped into the same set by the grouping step to the first carrier; A program for providing the above-mentioned features.

Images