Distribution device, distribution method, and distribution program

Abstract

To solve a problem that, when an upper limit is set on the number of times advertisement mails and notifications are distributed, a plurality of services is in a first-come, first-served situation, and a service provider is unable to send information such as mails and notifications that the service provider would like to distribute to users.SOLUTION: A distribution device according to the present application includes: a determination unit that determines, in response to a request for distribution of information to users, whether or not the number of times the information has been distributed to the users within a predetermined period has reached an upper limit, and when it is determined that the number of times the information has been distributed has not reached the upper limit, determines, on the basis of interest of the users, whether or not to distribute the information; and a distribution unit that, when it is determined that the information should be distributed, distributes the information to the users via user terminals. This allows a service provider to distribute more important information such as mails and notifications to the users, while limiting the number of times mails and notifications can be distributed.SELECTED DRAWING: Figure 3

Description

[Technical field]

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

[0002] Users can receive various advertising (promotional) emails and notifications through emails and SNS (Social Networking Services). Some of these advertising emails and notifications are based on user preferences, and contain information that is useful to users. However, because a large number of advertising emails and notifications are delivered from various services, many users treat them as spam or do not even open (view) them.

[0003] On the other hand, service providers, such as companies that distribute advertising e-mails and notifications, check, for example, how many advertising e-mails and notifications have been opened (viewed), and currently distribute a large number of advertising e-mails and notifications. In addition, many service providers provide multiple services, and advertising e-mails and notifications are distributed from each service, resulting in a huge number of them.

[0004] Therefore, service providers attempt to improve the rate at which advertising emails and notifications are opened (viewed) by users, for example, by limiting the number of advertising emails and notifications sent to each user to a certain number, such as 10 emails per month. [Prior art documents] [Patent documents]

[0005] [Patent Document 1] JP 2010-176468 A Summary of the Invention [Problem to be solved by the invention]

[0006] However, setting an upper limit on the number of times advertising emails, notifications, etc. can be sent results in a first-come, first-served situation across multiple services, which can lead to a problem for service providers, as they may not be able to deliver emails, notifications, and other information that they would like to send to users.

[0007] The present application has been made in consideration of the above, and aims to enable a service provider to deliver to users information such as emails and notifications that should be delivered more frequently, given that there is an upper limit on the number of times that emails, notifications, etc. can be delivered. [Means for solving the problem]

[0008] The distribution device of the present application is characterized by having a determination unit that, in response to a request for information distribution to a user, determines whether the number of distributions to the user within a specified period has reached an upper limit, and if it is determined that the number of distributions has not reached the upper limit, determines whether to distribute information based on the user's interests, and if it is determined that the information should be distributed, distributes the information to the user via a user terminal used by the user. Effect of the Invention

[0009] According to one aspect of this embodiment, it is possible for a service provider to deliver to a user information such as emails or notifications that should be delivered more frequently, even if there is an upper limit on the number of times emails or notifications can be delivered. [Brief description of the drawings]

[0010] [Figure 1] FIG. 1 is a diagram showing an example of the configuration of an information processing system 1 according to the present embodiment. [Diagram 2] FIG. 2 is a diagram showing an example of the configuration of the distribution device 100 according to the present embodiment. [Diagram 3] FIG. 3 is a flowchart showing an example of a procedure of a distribution process according to the present embodiment. [Figure 4] FIG. 4 is a flowchart showing an example of a procedure of a threshold update process according to the present embodiment. [Diagram 5]FIG. 5 is a flowchart showing an example of a procedure of the training process according to this embodiment. [Figure 6] FIG. 6 is a hardware configuration diagram showing an example of a computer that realizes the functions of the distribution device 100. DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS

[0011] Hereinafter, a detailed description will be given of a form for implementing a distribution device, a distribution method, and a distribution program according to the present application (hereinafter, referred to as an "embodiment") with reference to the drawings. Note that the distribution device, the distribution method, and the distribution program according to the present application are not limited to the embodiment. In addition, the same parts in each of the following embodiments are given the same reference numerals, and duplicated descriptions are omitted.

[0012] [1. Configuration of information processing system] With reference to FIG. 1, information processing realized by the distribution device 100 and the like of the present embodiment will be described. FIG. 1 is a diagram showing a configuration example of an information processing system 1 according to the present embodiment. In the example shown in FIG. 1, the information processing system 1 has a user terminal 10 and a distribution device 100. As shown in FIG. 1, the user terminal 10 and the distribution device 100 are connected to each other via a network N, for example, in a wired or wireless manner so as to be able to communicate with each other. 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 landline telephone network), a regional IP (Internet Protocol) network, or the Internet. The network N may include a wired network or a wireless network. The information processing system 1 shown in FIG. 1 may include a plurality of user terminals 10 and a plurality of distribution devices 100.

[0013] The user terminal 10 shown in Fig. 1 is an information processing terminal used by a user who receives various types of information such as advertising emails and notifications via email, SNS, etc. For example, the user terminal 10 is a desktop PC (Personal Computer), a notebook PC, a tablet terminal, a mobile phone, a PDA (Personal Digital Assistant), etc. In the example shown in Fig. 1, the user terminal 10 is a smart device such as a smartphone or tablet used by a user.

[0014] 1 receives information such as advertising e-mails and notifications distributed from the distribution device 100, and displays it on a display unit or a display communicably connected to the user terminal 10. For convenience, the following description may use either advertising e-mails or notifications, but these are merely examples and are not limited to either one, and the information received and displayed by the user terminal 10 includes various information distributed from the distribution device 100 via e-mails, notifications, etc.

[0015] 1 is an information processing device such as a server computer managed by a service provider that distributes information such as advertising emails and notifications to users. Alternatively, the distribution device 100 may be a cloud computer device managed by a cloud service provider that provides cloud computing services.

[0016] In addition, the distribution device 100 determines whether the number of distributions to the user within a predetermined period has reached an upper limit in response to a distribution request for information from each service to the user. The upper limit of the number of distributions within a predetermined period may be, for example, 10 per month, which may be common to each service and specific to each user. In addition, when the distribution device 100 determines that the number of distributions has not reached the upper limit, the distribution device 100 determines whether to distribute information based on the interest of the user. Then, when the distribution device 100 determines that the information is to be distributed, the distribution device 100 distributes the information for which a distribution request has occurred to the user via the user terminal 10 used by the user. On the other hand, when the distribution device 100 determines that the number of distributions has reached the upper limit, the distribution device 100 controls not to distribute information to the target user until a predetermined period has elapsed and the number of distributions is reset. In addition, for example, the determination of whether the number of distributions has reached the upper limit, the determination of whether to distribute or not, and the information distribution to the user, which are executed by the distribution device 100, are performed for each user.

[0017] 2. Configuration of the distribution device Next, the configuration of the distribution device 100 will be described with reference to Fig. 2. Fig. 2 is a diagram showing an example of the configuration of the distribution device 100 according to the present embodiment. As shown in Fig. 2, the distribution device 100 includes a communication unit 110, a storage unit 120, and a control unit 130.

[0018] (Regarding communication unit 110) The communication unit 110 is realized by, for example, a network interface card (NIC) etc. The communication unit 110 is connected to a network N by wire or wirelessly, and transmits and receives information to and from other devices such as the user terminal 10.

[0019] (Regarding the 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. As shown in Fig. 2, the storage unit 120 has a delivery data storage unit 121, a user data storage unit 122, a delivery performance data storage unit 123, and a model data storage unit 124.

[0020] (Regarding distribution data storage unit 121) The distribution data storage unit 121 stores information about distribution data of each service that is distributed to a user via e-mail, notification, etc. in response to a request for information distribution to the user, for example.

[0021] (Regarding the user data storage unit 122) The user data storage unit 122 stores information about users who receive various types of advertising mail, notifications, and other information via email, SNS, and the like.

[0022] The user data storage unit 122 may store, for example, an upper limit on the number of deliveries of emails or notifications, such as 10 per month, and the remaining number of deliveries, for each user. Note that, for example, in cases where the upper limit on the number of deliveries is uniform for all users, the user data storage unit 122 may store only the remaining number of deliveries, without storing the upper limit on the number of deliveries. The number of deliveries is decremented, for example, each time information is delivered. Alternatively, instead of the remaining number of deliveries, the number of deliveries may be stored in the user data storage unit 122, and the number of deliveries may be incremented each time information is delivered. Also, the remaining number of deliveries and the number of deliveries stored in the user data storage unit 122 are reset at a preset date and time, such as the beginning of the month.

[0023] In addition, the user data storage unit 122 may store, for example, a behavior history, preferences, etc., for each user. The behavior history of a user may be, for example, a user's browsing history of information, or a purchasing history of products, services, etc. In addition, the preferences of a user may be, for example, a category of information that the user is likely to like (for example, sports, pets, travel, etc.), selected by the user or estimated from the user's browsing history of information, etc.

[0024] (Regarding the distribution record data storage unit 123) The distribution history data storage unit 123 stores, for example, information related to distribution data previously distributed to each user. Note that the information stored in the distribution history data storage unit 123 does not have to be the distribution data itself, but may be the category of the distribution data (for example, sports, pets, travel, etc.).

[0025] (Regarding the model data storage unit 124) The model data storage unit 124 stores, for example, information on a machine learning model for estimating the first information for which a delivery request is generated for a user within a predetermined period based on past delivery records to the user and a first interest score indicating the degree of interest of the user in the first information, and model parameters for constructing the machine learning model. The machine learning model is generated by machine learning using, for example, information on the date when a second delivery request was generated for second information that was a delivery candidate in the past as a feature, and information on the content of the second information and a second interest score indicating the degree of interest of the second user in the second information as a correct answer label. The second user is, for example, a user to whom the second information is to be delivered.

[0026] (Regarding the control unit 130) The control unit 130 is a controller, and is realized, for example, by a central processing unit (CPU) or a micro processing unit (MPU) executing various programs stored in a storage device inside the distribution device 100 using a RAM as a working area. The control unit 130 is also a controller, and is realized, for example, by an integrated circuit such as an application specific integrated circuit (ASIC), a field programmable gate array (FPGA), or a general purpose graphic processing unit (GPGPU). As shown in FIG. 2, the control unit 130 according to the present embodiment has a determination unit 131, a calculation unit 132, a distribution unit 133, an update unit 134, an estimation unit 135, and a generation unit 136, and realizes or executes the functions and actions of information processing described below.

[0027] (Regarding the determination unit 131) For example, in response to a request for information delivery to a user, the determination unit 131 determines whether the number of deliveries to the user within a predetermined period has reached an upper limit. Here, for example, the number of deliveries within a predetermined period is 10 per month, and the upper limit and the remaining number of deliveries are stored in the user data storage unit 122 for each user.

[0028] Furthermore, for example, when it is determined that the number of deliveries within a predetermined period of time of the user has not reached an upper limit, the determination unit 131 determines whether or not to deliver the information for which a delivery request has occurred, based on the interest of the user. The process of determining whether or not to deliver the information for which a delivery request has occurred, based on the interest of the user, may include, for example, a process of determining whether or not to deliver the information, based on whether or not an interest score indicating the degree of interest of the user in the information for which a delivery request has occurred, exceeds a predetermined threshold. The interest score is an evaluation value expressed by various names such as interest level, attention score, interest level, interest score, etc., and is calculated by the calculation unit 132 using an existing formula.

[0029] (Regarding the calculation unit 132) The calculation unit 132 calculates an interest score indicating the degree of interest of the user in the information for which a delivery request has occurred, based on at least one of the user's behavioral history and preferences, for example. Here, for example, the user's behavioral history is the user's browsing history of information and step mails, and the purchase history of products and services, etc., which are collected for each user and stored in the user data storage unit 122. In addition, for example, the user's preferences are, for example, categories of information that the user is likely to like (for example, sports, pets, travel, etc.) selected by the user or estimated from the user's browsing history of information, etc., which are stored in the user data storage unit 122.

[0030] (About distribution unit 133) For example, when the determination unit 131 determines that the information for which a distribution request has occurred is to be distributed, the distribution unit 133 distributes the information to the user via the user terminal 10 used by the user.

[0031] Furthermore, the delivery unit 133 delivers, for example, a summary of information that has not been delivered to the user among information for which a delivery request has occurred within a predetermined period of time, to the user via the user terminal 10. The summary is generated, for example, by the generation unit 136. Note that the timing for generating and delivering the summary may be, for example, after the predetermined period has elapsed, or may be one week before the predetermined period has elapsed, as a step mail if the number of deliveries within the predetermined period has not reached the upper limit, or the like.

[0032] Furthermore, the distribution unit 133 may distribute paid information to the user via the user terminal 10, regardless of the upper limit of the number of distributions. Here, paid information to the user is, for example, information that the user receives by paying a fee, such as a monthly fee, to the service provider. Since such information is information that the service provider should distribute to the user, it may be distributed regardless of the upper limit of the number of distributions.

[0033] (Regarding update part 134) The update unit 134 updates the threshold for the interest score based on at least one of the number of days or time elapsed within a predetermined period and the delivery record for the user. This is to avoid a state in which, for example, information is delivered to the maximum number of deliveries at the beginning of the predetermined period, and new delivery requests that arise before the predetermined period has elapsed cannot be met at all. For this reason, for example, the initial value of the threshold for the interest score is set high, and as the number of days elapsed within the predetermined period increases (the number of days passes), the update unit 134 updates the threshold so as to gradually lower it. Alternatively, the update unit 134 increases or decreases the threshold for the interest score according to the delivery record for the user, for example, the remaining number of deliverables within the predetermined period, and controls so that information is delivered in a balanced manner within the predetermined period.

[0034] Furthermore, the update unit 134 updates the threshold for the interest score based on the first information for which a delivery request will be generated for the user within a predetermined period, which is estimated by the estimation unit 135 in consideration of future advertising emails, notifications, etc., and the first interest score indicating the degree of interest of the user in the first information. Thereby, for example, when the first interest score of the first information for which a delivery request will be generated in the future is higher than a predetermined value, the update unit 134 increases the threshold for the interest score, thereby preventing a situation in which too much information with an interest score lower than the first interest score is delivered and the first information cannot be delivered. The estimation of the first information and the first interest score will be described later.

[0035] Furthermore, the update unit 134 updates the threshold for the interest score based on a cluster of the third information generated by the generation unit 136 based on the similarity of the third information previously distributed to the user, for example. As a result, for example, the update unit 134 can raise the threshold for the interest score of information similar to previously distributed information, thereby controlling so that similar information is not distributed. Conversely, for example, the update unit 134 can lower the threshold for the interest score of information similar to previously distributed information, thereby controlling so that information similar to the previously distributed information that is of interest to the user is distributed.

[0036] Furthermore, for example, when the information for which a distribution request has been generated is paid information for a user, the update unit 134 updates the threshold for the interest score based on at least one of the price of the paid information and the number of times the paid information should be distributed within a predetermined period. As described above, paid information can be distributed regardless of the upper limit on the number of times it is distributed, but in order to avoid a situation in which the user does not even open (view) the information due to excessive distribution of the information, for example, the update unit 134 adjusts the threshold for the interest score based on the price of the paid information and the number of times it should be distributed (for example, the number of contracted distributions, etc.), and can distribute carefully selected information that should be distributed to the user.

[0037] The above describes the process of updating the thresholds for the interest scores based on various information by the update unit 134. Each update process may be executed independently, or at least two of the update processes may be executed and the highest threshold among the multiple derived thresholds or the average of the thresholds may be adopted.

[0038] (Regarding the estimation unit 135) The estimation unit 135 estimates the first information for which a delivery request is generated for the user within a predetermined period and the first interest score indicating the degree of interest of the user in the first information, based on the past delivery record to the user, taking into consideration, for example, advertising mails and notifications that will occur in the future. The process of estimating the first information and the first interest score may include, for example, a process of estimating the first information and the first interest score using a machine learning model generated by machine learning using information on the date when a second delivery request was generated for the second information that was a delivery candidate in the past as a feature, and information on the content of the second information and the second interest score indicating the degree of interest of the second user in the second information as a correct answer label.

[0039] (Regarding the generation unit 136) The generating unit 136 uses, for example, an existing technique, to perform clustering of the third information based on the similarity of the third information previously distributed to the user, and generates clusters of the third information.

[0040] Furthermore, the generating unit 136 generates a summary of information that has not been distributed to the user among information for which a distribution request has occurred within a predetermined period. Note that the summary may include, for example, all information that has not been distributed to the user among information for which a distribution request has occurred within a predetermined period, or may include information that is likely to be of interest to the user by calculating an interest score for each piece of information.

[0041] In addition, the control unit 130 may further include a training unit, for example, when the machine learning model used in the estimation unit 135 described above is trained in the distribution device 100. The machine learning model is, for example, a machine learning model for estimating first information for which a distribution request is generated for a user within a predetermined period and a first interest score for the first information. The training unit trains and generates the machine learning model using, for example, information on the date when a second distribution request was generated for second information that was a distribution candidate in the past as a feature, and information on the content of the second information and a second interest score indicating the degree of interest of the second user in the second information as a correct answer label.

[0042] [3. Distribution process flow] The procedure of a delivery process for an advertising email, a notification, etc. according to this embodiment will be described with reference to Fig. 3. Fig. 3 is a flowchart showing an example of the procedure of the delivery process according to this embodiment. The delivery process shown in Fig. 3 may be executed, for example, for each user, when a delivery request for information is made to the user.

[0043] First, as shown in Fig. 3, the distribution device 100 determines whether the number of distributions to the user within a predetermined period has reached an upper limit in response to a request for distribution of information to the user (step S101). If it is determined that the number of distributions to the user within a predetermined period has reached an upper limit (step S101: Yes), the distribution process shown in Fig. 3 ends.

[0044] On the other hand, if it is determined that the number of deliveries to the user within the specified period has not reached the upper limit (step S101: No), the distribution device 100 determines whether or not to deliver the information for which a delivery request has occurred, for example, based on the user's interest (step S102). For example, if the interest score for the information for which a delivery request has occurred exceeds a specified threshold and it is determined that the user is interested in the information, the distribution device 100 determines to deliver the information. On the other hand, for example, if the interest score for the information for which a delivery request has occurred is equal to or less than a specified threshold and it is determined that the user is not interested in the information, the distribution device 100 determines not to deliver the information. If it is determined that the information is not to be delivered (step S103: No), the distribution process shown in FIG. 3 ends.

[0045] On the other hand, if it is determined that the information is to be distributed (step S103: Yes), the distribution device 100 distributes the information to the user via the user terminal 10 used by the user to whom the information is to be distributed (step S104).

[0046] Next, the distribution device 100, for example, increments the number of distributions to update it (step S105). After executing step S105, the distribution process shown in Fig. 3 ends, but the distribution device 100 repeats the distribution process shown in Fig. 3 every time an information distribution request occurs, for example, and resets the number of distributions when a predetermined period has elapsed to prepare for the distribution process of the next period.

[0047] [4. Training process flow] A procedure of updating a threshold for an interest score by the distribution device 100 according to the present embodiment will be described with reference to Fig. 4. Fig. 4 is a flowchart showing an example of the procedure of updating a threshold according to the present embodiment. The update process shown in Fig. 4 may be executed, for example, in the process of determining whether or not to perform distribution in the distribution process shown in Fig. 3 (step S102).

[0048] First, as shown in FIG. 4, the distribution device 100 calculates an interest score indicating the degree of interest of the user in the information for which a distribution request has been generated, based on, for example, at least one of the behavioral history and preferences of the user to be distributed (step S201).

[0049] Next, the distribution device 100 performs clustering of the information previously distributed to the user based on the similarity of the information by using, for example, an existing technique, to generate a cluster of the information (step S202). Note that, if the cluster is not used in updating the threshold in the next step S203, step S202 may be skipped.

[0050] Next, the distribution device 100 updates, for example, the threshold for the interest score (step S203). As described above, the threshold may be updated based on at least one of the number of days or time elapsed within a predetermined period and the delivery record to the user. Alternatively, the threshold may be updated based on the first information for which a delivery request is generated to the user within a predetermined period, which is estimated by the estimation unit 135 in consideration of advertising mails and notifications that will occur in the future, and the first interest score indicating the degree of interest of the user in the first information. Alternatively, the threshold may be updated based on the cluster generated in step S202. Furthermore, if the information for which a delivery request is generated is paid information for the user, the threshold may be updated based on at least one of the price of the paid information and the number of times the paid information should be delivered within a predetermined period. Alternatively, the distribution device 100 may derive a threshold based on at least two of these, and update the threshold using the highest threshold among the derived thresholds or the average value of the thresholds. After execution of step S203, the update process shown in FIG. 4 ends.

[0051] [5. Training process flow] A procedure of a training process of a machine learning model used in the estimation unit 135 by the distribution device 100 according to the present embodiment will be described with reference to Fig. 5. The machine learning model is, for example, a machine learning model for estimating information for which a distribution request is generated for a user within a predetermined period of time and an interest score for the information. Fig. 5 is a flowchart showing an example of a procedure of the training process according to the present embodiment. The training process shown in Fig. 5 may be executed, for example, at any timing.

[0052] First, as shown in FIG. 5, the distribution device 100 acquires, for example, information on the date on which a distribution request was made for information that was previously a distribution candidate, information on the content of the information that was previously a distribution candidate, and an interest score for the information that was previously a distribution candidate, as past distribution records, from the distribution record data storage unit 123 or the like (step S301).

[0053] Next, the distribution device 100 generates training data based on the past distribution record acquired in step S301 (step S302). More specifically, the distribution device 100 generates training data using, as a feature, information on the date on which a distribution request for information that was a candidate for distribution in the past acquired in step S301 was made, and information on the content of the information that was a candidate for distribution in the past and an interest score for the information that was a candidate for distribution in the past as a correct answer label.

[0054] Next, the distribution device 100 trains and generates a machine learning model using, for example, the training data generated in step S302 (step S303). After execution of step S303, the training process illustrated in FIG. 5 ends.

[0055] 6. Effects As described above, the distribution device 100 of this embodiment has a determination unit 131 that, in response to a request for information distribution to a user, determines whether the number of distributions to the user within a specified period has reached an upper limit, and if it is determined that the number of distributions has not reached the upper limit, determines whether or not to distribute the information based on the user's interest, and if it is determined that the information should be distributed, a distribution unit 133 that distributes the information to the user via the user terminal 10 used by the user.

[0056] As a result, the distribution device 100 according to the present embodiment can distribute information such as e-mails and notifications that should be distributed more frequently to a user, even if there is an upper limit on the number of times that e-mails and notifications can be distributed.

[0057] In addition, the distribution device 100 according to this embodiment has a calculation unit 132 that calculates an interest score indicating the degree of the user's interest in the information based on at least one of the user's behavioral history and preferences, and the process executed by the distribution device 100 to determine whether or not to distribute the information based on the interest includes a process of determining whether or not to distribute the information based on whether the interest score exceeds a predetermined threshold.

[0058] As a result, the distribution device 100 according to the present embodiment can distribute information such as e-mails and notifications that should be distributed more frequently to a user, even if there is an upper limit on the number of times that e-mails and notifications can be distributed.

[0059] Moreover, the distribution device 100 according to the present embodiment includes an update unit 134 that updates the threshold value based on at least one of the number of days or time that has elapsed within a predetermined period and the distribution record for the user.

[0060] As a result, the distribution device 100 according to the present embodiment can distribute information such as e-mails and notifications that should be distributed more frequently to a user, even if there is an upper limit on the number of times that e-mails and notifications can be distributed.

[0061] Moreover, the distribution device 100 according to the present embodiment includes an estimation unit 135 that estimates the first information for which a distribution request will be generated for the user within a predetermined period of time, based on the past distribution record for the user.

[0062] As a result, the distribution device 100 according to the present embodiment can distribute information such as e-mails and notifications that should be distributed more frequently to a user, even if there is an upper limit on the number of times that e-mails and notifications can be distributed.

[0063] In addition, the distribution device 100 according to this embodiment has an estimation unit 135 that estimates, based on past distribution records to a user, first information for which a distribution request will be generated to the user within a specified period and a first interest score indicating the user's degree of interest in the first information, and an update unit 134 that updates a threshold value based on the first information and the first interest score.

[0064] As a result, the distribution device 100 according to the present embodiment can distribute information such as e-mails and notifications that should be distributed more frequently to a user, even if there is an upper limit on the number of times that e-mails and notifications can be distributed.

[0065] In addition, the process of estimating the first information and the first interest score based on past distribution records, which is executed by the distribution device 100 in this embodiment, includes a process of estimating the first information and the first interest score using a machine learning model generated by machine learning using information regarding the date when a second distribution request was made for the second information that was a distribution candidate in the past as a feature, and information regarding the content of the second information and the second interest score indicating the degree of interest of the second user in the second information as a correct answer label.

[0066] As a result, the distribution device 100 according to the present embodiment can distribute information such as e-mails and notifications that should be distributed more frequently to a user, even if there is an upper limit on the number of times that e-mails and notifications can be distributed.

[0067] In addition, the distribution device 100 according to this embodiment has a generation unit 136 that performs clustering of the third information based on the similarity of the third information previously distributed to the user to generate clusters of the third information, and an update unit 134 that updates the threshold based on the clusters.

[0068] As a result, the distribution device 100 according to the present embodiment can distribute information such as e-mails and notifications that should be distributed more frequently to a user, even if there is an upper limit on the number of times that e-mails and notifications can be distributed.

[0069] In addition, the distribution device 100 according to this embodiment has a generation unit 136 that generates a summary of information that has not been distributed to a user among information for which a distribution request has occurred within a specified period of time, and the distribution unit 133 included in the distribution device 100 distributes the summary to the user via the user terminal 10.

[0070] As a result, the distribution device 100 according to the present embodiment can distribute information such as e-mails and notifications that should be distributed more frequently to a user, even if there is an upper limit on the number of times that e-mails and notifications can be distributed.

[0071] Moreover, the distribution unit 133 included in the distribution device 100 according to the present embodiment distributes paid information to the user via the user terminal 10, regardless of the upper limit.

[0072] As a result, the distribution device 100 according to the present embodiment can distribute information such as e-mails and notifications that should be distributed more frequently to a user, even if there is an upper limit on the number of times that e-mails and notifications can be distributed.

[0073] In addition, the distribution device 100 according to this embodiment has an update unit 134 that updates the threshold based on at least one of the price of the paid information and the number of times the paid information should be distributed within a specified period when the information is paid information for a user.

[0074] As a result, the distribution device 100 according to the present embodiment can distribute information such as e-mails and notifications that should be distributed more frequently to a user, even if there is an upper limit on the number of times that e-mails and notifications can be distributed.

[0075] [7. Hardware Configuration] The distribution device 100 and the user terminal 10 according to the embodiment described above are realized, for example, by a computer 1000 having a configuration as shown in Fig. 6. The distribution device 100 will be described below as an example with reference to Fig. 6. Fig. 6 is a hardware configuration diagram showing an example of a computer that realizes the functions of the distribution device 100. The computer 1000 has a CPU 1100, a ROM 1200, a RAM 1300, a HDD 1400, a communication interface (I / F) 1500, an input / output interface (I / F) 1600, and a media interface (I / F) 1700.

[0076] The CPU 1100 operates and controls each unit based on a program stored in the ROM 1200 or the HDD 1400. The ROM 1200 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.

[0077] HDD 1400 stores programs executed by CPU 1100, data used by such programs, etc. Communication interface 1500 receives data from other devices via communication network 500 (e.g., corresponding to network N shown in FIG. 1) and sends the data to CPU 1100, and also transmits data generated by CPU 1100 to other devices via communication network 500.

[0078] 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 data generated via the input / output interface 1600 to the output devices.

[0079] Media interface 1700 reads a program or data stored in recording medium 1800 and provides it to CPU 1100 via RAM 1300. CPU 1100 loads the program from recording medium 1800 onto RAM 1300 via media interface 1700 and executes the loaded program. 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.

[0080] For example, when the computer 1000 functions as the distribution device 100, the CPU 1100 of the computer 1000 executes a program loaded onto the RAM 1300 to realize the function of the control unit 130. In addition, the HDD 1400 stores each piece of data in the storage device of the distribution device 100. The CPU 1100 of the computer 1000 reads and executes these programs from the recording medium 1800, but as another example, the CPU 1100 of the computer 1000 may obtain these programs from another device via a predetermined communication network.

[0081] [8. Other] Although some of the present embodiments have been described in detail above with reference to the drawings, 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 forms described in the Disclosure of the Invention section.

[0082] Further, the configuration of the distribution device 100 described above can be flexibly changed, for example, by calling an external platform or the like using an API (Application Programming Interface) or network computing to realize some functions.

[0083] Furthermore, the term "unit" in the claims may be read as "means" or "circuit," etc. For example, a determination unit may be read as a determination means or a determination circuit. [Explanation of symbols]

[0084] 10 User terminal 100 Distribution Device 110 Communications Department 120 Storage section 121 Distribution data storage unit 122 User data storage unit 123 Delivery performance data storage unit 124 Model data storage unit 130 Control section 131 Judgment section 132 Calculation section 133 Distribution Department 134 Update Department 135 Estimation part 136 Generation part 1000 Computers 1100 CPU 1200 ROM 1300 RAM 1400 HDD 1500 Communication Interface 1600 Input / Output Interface 1700 Media Interface 1800 Recording media

Claims

1. In response to a request for information distribution to a user, it is determined whether or not the number of times the information has been distributed to the user within a predetermined period of time has reached an upper limit; a determination unit that, when it is determined that the number of times of distribution has not reached the upper limit, determines whether or not to distribute the information based on the interest of the user; a distribution unit that distributes the information to the user via a user terminal used by the user when it is determined that the information is to be distributed; A distribution device comprising:

2. a calculation unit that calculates an interest score indicating a degree of interest of the user in the information based on at least one of a behavioral history and a preference of the user; The process of determining whether or not to distribute the information based on the interest includes: Whether or not to deliver the information is determined based on whether or not the interest score exceeds a predetermined threshold.

2. The distribution device according to claim 1, further comprising a process.

3. 3. The delivery device according to claim 2, further comprising an update unit that updates the threshold value based on at least one of the number of days or time that has elapsed within the predetermined period and delivery records for the user.

4. 2. The delivery device according to claim 1, further comprising an estimation unit that estimates the first information for which the delivery request will be generated to the user within the predetermined period, based on a past delivery record to the user.

5. an estimation unit that estimates, based on a past delivery record to the user, first information for which the delivery request will be generated to the user within the predetermined period and a first interest score indicating a degree of interest of the user in the first information; an update unit that updates the threshold based on the first information and the first interest score; 3. The delivery device according to claim 2, further comprising:

6. The process of estimating the first information and the first interest score based on the past delivery performance includes: The first information and the first interest score are estimated using a machine learning model generated by machine learning using information on a date when a second distribution request for second information that was a distribution candidate in the past was generated as a feature, and information on the content of the second information and a second interest score indicating the degree of interest of the second user in the second information as a correct answer label.

6. The distribution device according to claim 5, further comprising a process.

7. a generation unit that performs clustering of the third information based on a similarity of the third information previously distributed to the user to generate a cluster of the third information; The distribution device according to claim 2 , further comprising an update unit that updates the threshold value based on the cluster.

8. a generation unit that generates a summary of the information that has not been distributed to the user among the information for which the distribution request has occurred within the predetermined period, 8. The distribution device according to claim 1, wherein the distribution unit distributes the summary to the user via the user terminal.

9. 8. The distribution device according to claim 1, wherein the distribution unit distributes paid information to the user via the user terminal, regardless of the upper limit.

10. The distribution device according to claim 2, further comprising an update unit that updates the threshold value based on at least one of the price of the paid information and the number of times the paid information should be distributed within the specified period when the information is paid information for the user.

11. A distribution method executed by a distribution device, comprising: In response to a request for information distribution to a user, it is determined whether or not the number of times the information has been distributed to the user within a predetermined period of time has reached an upper limit; a determination step of determining whether or not to distribute the information based on the interest of the user when it is determined that the number of times the information has been distributed has not reached the upper limit; a delivery step of delivering the information to the user via a user terminal used by the user when it is determined that the information should be delivered; A distribution method comprising:

12. In response to a request for information distribution to a user, it is determined whether or not the number of times the information has been distributed to the user within a predetermined period of time has reached an upper limit; a determination step of determining whether or not to distribute the information based on the interest of the user when it is determined that the number of times the information has been distributed has not reached the upper limit; a delivery procedure for delivering the information to the user via a user terminal used by the user when it is determined that the information is to be delivered; A distribution program that causes a distribution device to execute the above.

Images