Notification control device, notification control method, and notification control system

Abstract

To notify a user of messages at an appropriate frequency.SOLUTION: A notification control device comprises: a notification control unit that controls the notification of a message to a user on the basis of message notification control data relating to the execution frequency of the notification of the message to the user; an analysis unit that analyzes the frequency at which the notification of the message to the user has been executed; and an update unit that updates the message notification control data on the basis of an analysis result from the analysis unit and target data representing a target value of the frequency of the notification of the message to the user.SELECTED DRAWING: Figure 1

Description

Technical Field

[0001] The present invention relates to a notification control device, a notification control method, and a notification control system.

Background Art

[0002] In recent years, as a means of promoting changes in user behavior such as health behavior and purchasing behavior, there is a method of notifying a message to a terminal carried by a user or a terminal provided in a facility. However, when the user is working or in a situation where message viewing is not prioritized, the user may find the message notification annoying.

[0003] Therefore, Patent Document 1 discloses a method of notifying a user of a message based on a specific behavior of the user (for example, transition from walking to stationary, transition from sitting to standing, sending an email, operating an electronic device, etc.).

Prior Art Documents

Patent Documents

[0004]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0005] However, the above specific behavior may occur frequently in a specific time period. For example, in the morning time period, the repetition of walking and stationary, which are specific behaviors, frequently occurs due to walking, and if the occurrence time of the specific behavior is set as the message notification timing, a large number of messages will be notified in the same time period. As a result, there is a possibility that the user may find the message notification annoying.

[0006] Furthermore, there may be a limit on the maximum number of messages notified per day. In this case, if message notifications concentrate in a specific time period, messages may not be notified after that specific time period, and the effect of message notifications may be diminished.

[0007] Therefore, the present invention has been made in view of the above problems, and an object of the present invention is to provide a novel and improved technology capable of notifying a user of messages at an appropriate frequency.

Means for Solving the Problems

[0008] In order to solve the above problems, according to an aspect of the present invention, there is provided a notification control device including: a notification control unit that controls the notification of the message to the user based on message notification control data regarding the execution frequency of the notification of the message to the user; an analysis unit that analyzes the frequency at which the notification of the message to the user has been executed; and an update unit that updates the message notification control data based on the analysis result by the analysis unit and target data representing a target value of the frequency of the notification of the message to the user.

[0009] The notification control unit may control the notification of the message to the user based on the message notification control data updated by the update unit.

[0010] The update unit may update the message notification control data so that the frequency of the notification of the message executed by the notification control unit based on the updated message notification control data approaches the target data.

[0011] When the frequency analyzed by the analysis unit is greater than the target value of the notification frequency, the update unit updates the message notification control data so that the execution frequency of the notification decreases from before the update to after the update of the message notification control data. When the frequency analyzed by the analysis unit is less than the target value of the notification frequency, the update unit may update the message notification control data so that the execution frequency of the notification increases from before the update to after the update of the message notification control data.

[0012] The update unit may control the time interval for updating the message notification control data based on the difference between the frequency analyzed by the analysis unit and the target value of the notification frequency.

[0013] The message notification control data is data for controlling the execution frequency of the message notification for each of a plurality of time frames obtained by dividing a predetermined period. The analysis unit analyzes the frequency using the number of times the message has been notified to the user for each time frame. The target data may represent the target value of the message notification for each time frame.

[0014] The message notification control data is data for determining the notification frequency of the message when a predetermined condition is satisfied. The notification control unit may determine whether to notify the message when the predetermined condition is satisfied based on the message notification control data.

[0015] The predetermined condition may include a condition related to the behavior of the user or the environment in which the user is located.

[0016] The predetermined condition may include that the determination of whether to notify the message in the time frame to which the current time belongs has not been made.

[0017] The message notification control data may be data representing the probability of executing the message notification when the predetermined condition is satisfied.

[0018] The analysis unit may analyze the frequency by statistically counting the number of messages notified in each time frame within a plurality of predetermined periods for each corresponding time frame within the plurality of predetermined periods.

[0019] The update unit may update the target data based on the response of the user to the notification of the message.

[0020] When the response rate at which the user responds to the message is higher than a predetermined value, the update unit may update the target data so that the target value increases from before the update to after the update of the target data. When the response rate at which the user responds to the message is lower than a predetermined value, the update unit may update the target data so that the target value decreases from before the update to after the update of the target data.

[0021] The notification control device may further include a setting unit that sets the target data, and the setting unit may set the message notification control data according to the target data.

[0022] The setting unit classifies each of the plurality of users into a plurality of groups, sets the target data prepared for each group, and the update unit may update the message notification control data for each group respectively.

[0023] The setting unit sets the target data prepared for each attribute corresponding to the message, and the update unit may update the message notification control data for each attribute respectively.

[0024] The message is a message for prompting a change in the behavior of the user, and the attribute may be set for each message according to the content of the type of the behavior.

[0025] The message is classified into any of the following types: a message that recommends a specific action to the user, a message that presents information regarding a specific action, or a message regarding the execution result of a specific action of the user, and the attribute may be the type.

[0026] Also, according to another aspect of the present invention for solving the above problems, based on message notification control data regarding the execution frequency of notification of a message to a user, controlling the notification of the message to the user, analyzing the frequency at which the notification of the message to the user has been executed, and updating the message notification control data based on the analysis result of the frequency and target data representing a target value of the frequency of notification of the message to the user, there is provided a notification control method executed by a computer, including these steps.

[0027] Also, according to another aspect of the present invention for solving the above problems, a notification control unit that controls the notification of the message to the user based on message notification control data regarding the execution frequency of notification of a message to a user, an analysis unit that analyzes the frequency at which the notification of the message to the user has been executed, and an update unit that updates the message notification control data based on the analysis result by the analysis unit and target data representing a target value of the frequency of notification of the message to the user, there is provided a notification control system including these components.

Advantages of the Invention

[0028] As described above, according to the present invention, it is possible to notify a user of a message at an appropriate frequency.

Brief Description of the Drawings

[0029]

Figure 1

Figure 2

Figure 3

Figure 4

Figure 5

Figure 6

Figure 7

Embodiments for Carrying Out the Invention

[0030] Hereinafter, preferred embodiments of the present invention will be described in detail with reference to the accompanying drawings. In the present specification and drawings, components having substantially the same functional configuration are denoted by the same reference numerals, and redundant description is omitted.

[0031] <<0. Overview>> Embodiments of the present invention relate to a notification control system that executes control to notify a message for prompting a change in a user's behavior at an appropriate frequency. The behavior prompted by the notification control system is not particularly limited, such as a health behavior (e.g., a user's walking, sleeping, eating, exercising, etc.) that contributes to the user's health improvement, a user's purchasing behavior, an environmentally considerate behavior that contributes to environmental protection, and other behaviors related to the solution of social issues. In the embodiments of the present invention, an example in which the behavior prompted by the notification control system is a behavior that contributes to the user's health improvement, particularly the use of stairs (stair walking), will be mainly described.

[0032] Specifically, the notification control system according to the embodiment of the present invention controls the notification of messages to the user based on message notification control data regarding the execution frequency of message notification to the user. Then, the notification control system according to the embodiment of the present invention analyzes the frequency at which the message is notified to the user, and updates the message notification control data based on the analysis result and target data representing the target value of the message notification frequency. Each process will be described in detail later. By executing each process, the notification control system according to the embodiment of the present invention realizes notifying the user of messages at an appropriate frequency.

[0033] <<1. First Embodiment>> Subsequently, the details of the first embodiment of the present invention will be described.

[0034] <1-1. Description of Configuration> First, a configuration example of the notification control system according to the first embodiment of the present invention will be described. FIG. 1 is a diagram showing a configuration example of the notification control system 1 according to the first embodiment of the present invention. As shown in FIG. 1, the notification control system 1 according to the first embodiment of the present invention includes a user terminal 10 and a server 20. The user terminal 10 and the server 20 are connected to a network, and the user terminal 10 and the server 20 are configured to be able to communicate with each other via the network.

[0035] (User Terminal 10) The user terminal 10 is a terminal used by the user of the notification control system 1. The user is a person who is urged to change their behavior by the message notification service provided by the notification control system 1. The user terminal 10 may be a portable terminal such as a smartphone, a tablet terminal, or a wearable terminal. The user terminal 10 may be a portable terminal owned by the user, or may be a signage terminal, a smart speaker, a communication robot, or a portable terminal installed in a facility such as a commercial facility or an office building and installed so as to be portable within the facility.

[0036] The user terminal 10 has a function of receiving data such as message data representing a message for prompting a change in behavior from the server 20 to the user who uses the user terminal 10. The data may include character information, image information, or voice information.

[0037] In addition, the user terminal 10 has a function of outputting a message represented by the message data received from the server 20. For example, the user terminal 10 may cause a display unit to output a screen including the message. Also, the user terminal 10 may output the content of the message as voice.

[0038] The user terminal 10 may have various sensors for detecting the user's state such as the user's activity level and location. The sensor may detect, for example, the number of steps the user has taken on the day and the number of floors the user has climbed up and down the stairs. The detection result detected by the user terminal 10 may be transmitted to the server 20.

[0039] (Server 20) The server 20 is a notification control device according to the first embodiment of the present invention, which can be realized by a computer. The server 20 includes a control unit (not shown) and a storage unit (not shown). The control unit (not shown) includes a target distribution setting unit 210, a control distribution setting unit 220, a message notification unit 230, and an actual situation distribution analysis unit 240.

[0040] Note that the control unit (not shown) is realized by a program being executed by a processor. Such a program is recorded on a recording medium and can be read and executed by the processor from the recording medium. Alternatively, these blocks may be configured by dedicated hardware.

[0041] The storage unit (not shown) may be configured by a memory. For example, the memory may be a memory such as a RAM (Random Access Memory), a hard disk drive, or a flash memory.

[0042] (Target Distribution Setting Unit 210) The target distribution setting unit 210 functions as a setting unit that sets target data representing the target value of the message notification frequency. The target data may be data representing the target value for each of a plurality of time frames obtained by dividing a predetermined period, that is, data representing the distribution of the target values for each time frame (hereinafter, also simply referred to as the "target distribution"). Hereinafter, the target data representing the distribution of the target values for each time frame is also referred to as "target distribution data".

[0043] The target value may be, for example, the number of messages that the notifier, who is the administrator of the message notification service, expects to be notified to the user in each time frame. In the present embodiment, an example in the case where the target data is the target distribution data representing the distribution of the target values, which is the number of messages that the notifier expects to be notified to the user in each time frame, will be mainly described. However, the target value is not limited to this, and may be, for example, a value representing the distribution of the notification frequency in each time frame.

[0044] The predetermined period composed of a plurality of time frames may be arbitrarily set. For example, it may be one day or one hour. Here, an upper limit number of messages to be notified to the user in the above-mentioned predetermined period may be set. Therefore, by designing the above-mentioned predetermined period in combination with the setting of the upper limit number of messages, it is possible to execute message notifications at a frequency more in line with the intention of the notifier. In the present embodiment, an example in which the above-mentioned predetermined period is one day will be mainly described.

[0045] Also, the length of the time frame constituting the predetermined period may be arbitrarily set. For example, the time frame may be a frame in which one day, which is the predetermined period, is divided every hour, or a frame in which one hour, which is the predetermined period, is divided every minute. Also, the length of the time frame does not have to be uniform (that is, the predetermined period does not have to be evenly divided). For example, at night (e.g., from 0:00 to 6:00 and from 22:00 to 24:00), it may be divided every two hours, and in other time zones, it may be divided every hour, as long as it is set flexibly. Also, an upper limit number may be set for the messages notified in each time frame. Therefore, the time frame may be arbitrarily designed in combination with the setting of the upper limit number of messages. In this embodiment, an example in which the time frame is a frame in which one day is divided every hour (0:00 to 1:00, 1:00 to 2:00 ···) will be mainly described.

[0046] The target distribution setting unit 210 outputs target distribution data to the control distribution setting unit 220.

[0047] (Control distribution setting unit 220) The control distribution setting unit 220 functions as a setting unit that sets message notification control data regarding the execution frequency of message notifications to the user. The message notification control data may be data for controlling the execution frequency of message notifications for each of the above time frames. That is, the message notification control data may be data representing the distribution of the control of the execution frequency of message notifications for each time frame (hereinafter, also simply referred to as "control distribution"). Hereinafter, the message notification control data representing the distribution of the control of the execution frequency of message notifications for each time frame is also referred to as "control distribution data". In this embodiment, an example in which the message notification control data is control distribution data will be mainly described. The details of the control distribution data will be described later.

[0048] The control distribution setting unit 220 outputs the set control distribution data to the message notification unit 230.

[0049] (Message notification unit 230) The message notification unit 230 functions as a notification control unit that controls the notification of messages to the user based on the control distribution data. The message notification unit 230 executes control to notify the user of a message by outputting message data indicating the message to the user terminal 10.

[0050] (Live distribution analysis unit 240) The live distribution analysis unit 240 functions as an analysis unit that analyzes the frequency of message notifications to the user by the message notification unit 230. The live distribution analysis unit 240 generates notification execution analysis data, which is the analysis result of analyzing the frequency using the number of times of message notifications to the user for each of the above time frames.

[0051] More specifically, the live distribution analysis unit 240 may generate notification execution analysis data by statistically counting the number of notifications of messages notified by the message notification unit 230 for each time frame in a plurality of predetermined periods for each corresponding time frame within the plurality of predetermined periods. That is, the notification execution analysis data may be data representing the distribution (hereinafter, also simply referred to as "live distribution") of the execution frequency of messages notified for each time frame. Hereinafter, the notification execution analysis data representing the distribution of the execution frequency of messages notified for each time frame is also referred to as "live distribution data". Also, hereinafter, the target distribution data, the control distribution data, and the live distribution data may be collectively referred to as "distribution data" in some cases. In this embodiment, an example in which the notification execution analysis data is the live distribution data will be mainly described. The details of the live distribution data will be described later.

[0052] The live distribution analysis unit 240 outputs the generated live distribution data to the control distribution setting unit 220. Here, the control distribution setting unit 220 functions as an update unit that updates the control distribution data based on the live distribution data generated by the live distribution analysis unit 240 and the target distribution data set by the target distribution setting unit 210. The control distribution setting unit 220 outputs the updated control distribution data to the message notification unit 230. Then, the message notification unit 230 controls the notification of messages to the user based on the updated control distribution data by the live distribution analysis unit 240. Furthermore, the live distribution analysis unit 240 newly generates live distribution data based on the notification of the message executed based on the updated control distribution data.

[0053] Here, the control distribution setting unit 220 updates the control distribution data so that the frequency of message notification executed based on the updated control distribution data by the message notification unit 230 approaches the target distribution data. By repeating the control distribution data update process by the control distribution setting unit 220, the message notification control process by the message notification unit 230, and the live distribution data generation process by the live distribution analysis unit 240, the server 20 realizes notifying the user of messages at a more appropriate frequency.

[0054] The configuration example of the notification control system 1 according to the first embodiment of the present invention has been described above.

[0055] <1-2. Operation example> Next, an operation example of the notification control system 1 according to the first embodiment of the present invention will be described.

[0056] FIG. 2 is a diagram for explaining the operation of the notification control system 1 according to the first embodiment of the present invention. As shown in FIG. 2, the operation of the notification control system 1 according to the first embodiment of the present invention is divided into the following steps: (S1) setting of target distribution data and control distribution data, (S2) notification of messages and generation of live distribution data, (S3) update of control distribution data, and (S4) determination of whether to end the operation.

[0057] Hereinafter, each of these steps will be described with reference to FIG. 3. FIG. 3 is a diagram for explaining the generation of each distribution data according to the first embodiment of the present invention.

[0058] (S1) Setting of target distribution data and control distribution data First, the target distribution setting unit 210 of the server 20 sets target distribution data including the target value of the notification frequency of messages for each time frame. Note that the target distribution data may be prepared in advance by the notification organizer. Also, updated control distribution data such as control distribution data generated in the test environment of the message notification service provided by the notification control system 1 may be used as the target distribution data.

[0059] In FIG. 3, an example of the target distribution a(t) is shown as an example of the target distribution represented by the target distribution data set by the target distribution setting unit 210. In the target distribution a(t), it is defined as the goal to notify messages equally to each of the four time frames T1 to T4 from 9:00 to 13:00 and the four time frames T5 to T8 from 15:00 to 19:00. For example, when the notification organizer expects 4 messages to be notified per day, for each of the time frames T1 to T8, "0.5" calculated by dividing 4 by 8 is set as the target value.

[0060] Here, an example where the target values are evenly distributed in the time frames T1 to T8 is shown, but the target values may not be evenly distributed. For example, if the notification organizer is the person in charge of a fresh food retail store and the message to be notified is a message for promoting the purchase of goods by users, the target value in the afternoon time frame may be set to be larger than the target value in the morning time frame. This is because it is expected that food waste on the same day can be suppressed by increasing the message notification frequency in the afternoon.

[0061] Also, in the target distribution a(t), "0" is set as the target value for time frames other than the time frames T1 to T8. This represents that the notification organizer does not want messages to be notified to users in time frames other than the time frames T1 to T8.

[0062] The target distribution setting unit 210 outputs target distribution data representing the target distribution a(t) to the control distribution setting unit 220.

[0063] The control distribution setting unit 220 sets control distribution data according to the target distribution data acquired from the target distribution setting unit 210. For example, as shown in FIG. 3, the control distribution setting unit 220 may set the target value of each time frame of the target distribution a(t) indicated by the target distribution data acquired from the target distribution setting unit 210 as the control value of the execution frequency of the corresponding notification in the control distribution b1(t) indicated by the control distribution data. That is, the control distribution setting unit 220 may copy the target distribution data representing the target distribution a(t) acquired from the target distribution setting unit 210 and set it as the control distribution data representing the control distribution b1(t).

[0064] However, it is not always necessary to use a copy of the target distribution data as the control distribution data set here. For example, the control value of the execution frequency of each time frame may be set to the number obtained by dividing the number of messages that the notification organizer expects to be notified in one day by the number of time frames. However, in this case, the speed at which the actual situation distribution data approaches (converges to) the target distribution data in the steps described later becomes slow, so it is more preferable to use a copy of the target distribution data as the control distribution data here.

[0065] The control distribution setting unit 220 outputs the control distribution data representing the control distribution b1(t) to the message notification unit 230, and the operation proceeds to step S2.

[0066] (S2) Notification of Messages and Generation of Actual Situation Distribution Data The message notification unit 230 uses the control distribution data acquired from the control distribution setting unit 220 to determine the notification frequency of messages when a predetermined condition is satisfied. More specifically, when a predetermined condition is satisfied, the message notification unit 230 extracts the timing when the predetermined condition is satisfied as a notification timing candidate. Hereinafter, the predetermined condition used for extracting the notification timing candidate is also referred to as the "candidate extraction condition".

[0067] The candidate extraction conditions include either one or both of the conditions related to the user's behavior and the conditions related to the environment in which the user is placed (hereinafter, also referred to as "user conditions"). The user conditions may be set according to the content of the message to be notified. For example, when the message to be notified is a message for promoting stair walking, the user conditions may include that the user is near the stairs or that physical activities such as a stationary state continuing are not sufficiently performed.

[0068] The message notification unit 230 may determine whether either one or both of the user's behavior and the environment in which the user is placed satisfy the user conditions based on the detection results detected by the sensors included in the user terminal 10. Note that the message notification unit 230 may also determine whether either one or both of the user's behavior and the environment in which the user is placed satisfy the user conditions based on the detection results by sensors other than the sensors included in the user terminal 10. For example, the message notification unit 230 may determine whether either one or both of the user's behavior and the environment in which the user is placed satisfy the user conditions based on the detection results by an external camera or an environmental sensor that detects the flow of people.

[0069] Note that the method for extracting the notification timing candidates is not limited to the above method, and a conventionally known method may be used.

[0070] When the message notification unit 230 extracts the notification timing candidates, it determines whether to notify the user of the message based on the control distribution data.

[0071] The message notification unit 230 determines whether to notify the user of the message by referring to the control value of the execution frequency of the time frame to which the time (i.e., the current time) at which the notification timing candidate is extracted belongs in the control distribution data.

[0072] The control value of the execution frequency may be, for example, a value representing the probability of executing a message notification at a notification timing candidate. More specifically, in determining whether to notify the user of a message, the message notification unit 230 may generate a random number value between 0 and 1.0. Then, when the generated random number value is smaller than the value of the control distribution b1(t) of the time frame to which the current time belongs (that is, the control value of the execution frequency in the time frame to which the current time belongs), the message notification unit 230 may determine the notification timing candidate as the notification timing.

[0073] Note that the method for determining whether to use the notification timing candidate as the notification timing based on the control distribution data is not limited to the above method, and any conventionally known method may be used.

[0074] The candidate extraction conditions may further include conditions different from the user conditions. For example, the candidate extraction conditions may include that the determination of the candidate extraction conditions has not been performed in the time frame to which the current time belongs. That is, when the message notification unit 230 performs the determination of the candidate extraction conditions, regardless of the result, the determination of the candidate extraction conditions may not be performed in the time frame in which the determination was executed.

[0075] Including the above conditions in the candidate extraction conditions prevents the extraction of notification timing candidates from being performed multiple times within the same time frame. As a result, when the user conditions are satisfied at least once in each time frame, the probability of executing a message notification with the notification timing candidate will match the probability of executing a message notification in the time frame. Therefore, when the user conditions are satisfied at least once in each time frame, it is assumed that the actual situation distribution analyzed for the frequency of notifications executed based on the control distribution b1(t) set according to the target distribution a(t) will approach the target distribution a(t).

[0076] In addition, since the above conditions are included in the candidate extraction conditions, it is possible to prevent a plurality of messages from being notified to the user within the same time frame, so that it is possible to execute the message notification so that the user does not feel bothered by the notification. However, since there is a possibility that messages may be continuously notified in consecutive time frames, it is desirable to set the length of each time frame so that the user does not feel bothered by the messages being notified in consecutive time frames.

[0077] Furthermore, the candidate extraction conditions may include that the notification of the messages executed in one day does not exceed the upper limit number of the messages notified to the user within a predetermined period (here, one day).

[0078] When the message notification unit 230 determines the notification timing candidate as the notification timing, it executes the notification of the message to the user. When the message notification unit 230 executes the notification of the message to the user, it outputs the actual situation data, which actualizes that the message has been notified, to the message notification unit 230.

[0079] On the other hand, when the message notification unit 230 does not determine the notification timing candidate as the notification timing, it does not notify the user of the message. Also, in such a case, the message notification unit 230 does not output the actual situation data to the message notification unit 230.

[0080] The actual situation distribution analysis unit 240 aggregates the actual situation data acquired from the message notification unit 230 and analyzes the actual situation distribution. More specifically, the actual situation distribution analysis unit 240 first aggregates the number of actual situation data received in each time frame within a predetermined period (here, one day) to aggregate the number of messages notified based on the same control distribution data in each time frame.

[0081] Then, the actual situation distribution analysis unit 240 analyzes the frequency of the message notification by statistically processing the number of messages notified in each time frame in a plurality of predetermined periods for each corresponding time frame within the plurality of predetermined periods.

[0082] Here, the number of predetermined periods included in the plurality of predetermined periods may be set to be a period in which a sufficient number of actual situation data can be obtained for analyzing the notification frequency. For example, the number of predetermined periods may be set to a period in which the number of messages expected to be notified to the notification organizer in the plurality of predetermined periods is 100 or more. However, the number of predetermined periods is not limited to this, and it may be arbitrarily set according to the wish of the update frequency of the control distribution data by the notification organizer.

[0083] Here, an example in which the number of predetermined periods is 7, that is, the actual situation distribution analysis unit 240 mainly counts the number of messages notified in each time frame in one week for each corresponding time frame in one week will be mainly described. For example, the actual situation distribution analysis unit 240 obtains the statistical data obtained by dividing the number of actual situation data obtained in the time frame from 0:00 to 1:00 in one week by 7 as the execution frequency of the message notified in the time frame from 0 to 1:00. The actual situation distribution analysis unit 240 generates actual situation distribution data by executing such processing for each time frame.

[0084] The actual situation distribution analysis unit 240 may generate actual situation distribution data based on the actual situation data for one week, for example, by starting to collect the actual situation data at 0:00 on Monday and ending at 24:00 on Sunday. As a result, since the processing of step S4 to be performed subsequently will be performed after 24:00 on Sunday, the control distribution setting unit 220 can execute the update process of the control distribution data in a time zone where it is unlikely that the user will check the notified messages. Note that the start time and the end time are not limited to this example, and may be arbitrarily set according to the type of message and the like.

[0085] In addition, the actual situation distribution analysis unit 240 may generate actual situation distribution data by statistically processing the actual situation data for each of a plurality of users. When the actual situation distribution data is generated by statistically processing the actual situation data for each of the plurality of users, the update process of the control distribution data described later is also executed for each of the plurality of users. As a result, since the control distribution data is updated to suit each of the plurality of users, notifications can be executed at an optimal frequency for each user.

[0086] Alternatively, the actual situation distribution analysis unit 240 may generate actual situation distribution data by collectively statistically processing the actual situation data for a plurality of users. When the actual situation distribution data is generated by collectively statistically processing the actual situation data for a plurality of users, the number of samples of the actual situation data collected in the same period is larger than when the actual situation data is statistically processed for each of the plurality of users. For example, when it is assumed that the lifestyles of a plurality of users are similar, it is assumed that the actual situation distributions of the plurality of users are similar. Therefore, in such a case, by collectively statistically processing the actual situation data for a plurality of users, it is expected that the actual situation distribution data will approach the target distribution data faster.

[0087] FIG. 3 shows an actual situation distribution c1(t) represented by the actual situation distribution data generated by the above method. Here, since the notification timing candidates are extracted according to the user conditions, the user conditions are not necessarily satisfied at least once in each time frame. Therefore, as shown in FIG. 3, it is assumed that the actual situation distribution c1(t) will be a distribution different from the control distribution b1(t).

[0088] The actual situation distribution analysis unit 240 outputs the actual situation distribution data representing the generated actual situation distribution c1(t) to the control distribution setting unit 220, and the operation proceeds to step S3.

[0089] (S3) Update of control distribution data Subsequently, the control distribution setting unit 220 updates the control distribution data. More specifically, the control distribution setting unit 220 updates the control distribution data so that the notification frequency of the messages executed by the message notification unit 230 approaches the target distribution data based on the updated control distribution data.

[0090] More specifically, for each time frame, the control distribution setting unit 220 updates the control value of the execution frequency represented by the control distribution data based on the execution frequency at which the messages represented by the actual situation distribution data are notified and the target value of the notification frequency represented by the target distribution data.

[0091] For each time frame, when the execution frequency at which the message is notified is greater than the target value of the notification frequency, the control distribution setting unit 220 may update the control value of the execution frequency so that the control value of the execution frequency decreases from before the update to after the update.

[0092] Also, for each time frame, when the execution frequency at which the message is notified is less than the target value of the notification frequency, the control distribution setting unit 220 may update the control value of the execution frequency so that the control value of the execution frequency increases from before the update to after the update.

[0093] For example, in the example shown in FIG. 3, the control distribution setting unit 220 may update the control distribution b1(t) to the control distribution b2(t) by using the following formula (1) for each time frame.

[0094] b2(t)=b1(t)×a(t) / c1(t)···(1)

[0095] In addition, for time frames where the actual situation distribution c1(t) is 0, it is assumed that message notifications are not expected, that is, when the target distribution a(t) is 0 (for example, time frames other than time frames T1 to T8 in the actual situation distribution c1(t)). Also, for time frames where the actual situation distribution c1(t) is 0, it is also assumed that there is not enough actual situation data to analyze the notification frequency (for example, time frame T7 in the actual situation distribution c1(t)). In such cases, the control distribution setting unit 220 may interpolate the control distribution b2(t) for the time frame with a value interpolated or extrapolated from the values of the time frames in the vicinity of the time frame. Also, in such cases, especially when the target distribution a(t) is 0, the control distribution setting unit 220 may set the control distribution b2(t) for the time frame to 0.

[0096] The message notification unit 230 controls the notification of messages to the user based on the control distribution data representing the updated control distribution b2(t) by the control distribution setting unit 220. Then, the actual situation analysis unit 240 generates actual situation distribution data representing an actual situation distribution c2(t) indicating the execution frequency at which messages are notified based on the updated control distribution data by the message notification unit 230.

[0097] As shown in FIG. 3, the actual situation distribution c2(t) approaches the target distribution a(t) more than the actual situation distribution c1(t). That is, as described so far, by updating the control distribution data, the message is notified at a frequency close to the notification frequency determined by the preset target distribution data, that is, the frequency intended by the notification organizer. As a result, messages can be notified to the user at an appropriate frequency, so it is possible to prevent the utilization rate of the message notification service provided by the notification control system 1 from decreasing due to the user feeling bothered by the notifications. Also, according to such a configuration, by setting the target distribution data so as not to be biased towards a specific time zone in advance, it is possible to prevent notifications from being biased towards a specific time zone.

[0098] Note that the mathematical formula used for updating the control distribution data is not limited to Formula (1), and other mathematical formulas may be used as long as they have the property that the actual situation distribution data converges to the target distribution data. As an example of other mathematical formulas, the following Formula (2) may be used.

[0099] b2(t)=b1(t)+w(t)×(a(t)-c1(t))···(2)

[0100] Here, w(t) is a weighting coefficient set for each time frame. According to Formula (2), when w(t) is set to a positive number greater than 1, the change amount of the updated control distribution b2(t) becomes larger. Thereby, it can be expected to increase the speed at which the execution frequency of the notified message converges to the target value in the time frame where w(t) is set to a positive number greater than 1. Therefore, it is effective to set w(t) to a positive number greater than 1 in the time frame where the notification organizer wants to ensure the execution frequency of message notification from the beginning of the update.

[0101] On the other hand, when w(t) is set to a positive number smaller than 1, the change amount of the updated control distribution b2(t) becomes smaller. Thereby, it can be expected to slow down the speed at which the execution frequency of the notified message converges to the target value in the time frame where w(t) is set to a positive number smaller than 1. Therefore, it is effective to set w(t) to a positive number smaller than 1 in the time frame where the notification organizer does not need to ensure the execution frequency of message notification from the beginning of the update.

[0102] The above describes the update of the control distribution data. In the examples described so far, the actual situation distribution data is generated based on the actual situation data for one week, and the control distribution data is updated every week. However, the update interval of the control distribution data is not limited to this example. For example, the control distribution setting unit 220 may control the update time interval of the control distribution data (that is, the length of time for collecting the actual situation data) based on the difference between the execution frequency of the notified message in each time frame analyzed by the actual situation distribution analysis unit 240 and the target value of the notification frequency.

[0103] For example, the control distribution setting unit 220 calculates the mean squared error of the difference between the execution frequency at which messages are notified in each time frame and the target value of the notification frequency. If the calculation result is smaller than the threshold value, the update may be stopped. Alternatively, in such a case, the control distribution setting unit 220 may control to extend the update period from the current update period. More specifically, the control distribution setting unit 220 may extend the update period set for one week to one month. Note that how much to extend the update period may be determined according to the calculation result of the mean squared error.

[0104] When the control distribution setting unit 220 updates the control distribution data or determines to stop the update, the operation proceeds to step S4.

[0105] (S4) Determination of whether to end the operation When the notification organizer inputs an instruction to end the operation by operating an operation unit (not shown) of the server 20 or the like, the operation of the notification control system 1 ends. Otherwise, the operation proceeds to step S2. Note that when the execution period of step S2 is determined in advance, step S2 may be executed after it is determined that the next execution timing of step S2 has arrived based on the execution period.

[0106] The operation example of the notification control system 1 according to the first embodiment of the present invention has been described above.

[0107] <<2. Second Embodiment>> Subsequently, details of the second embodiment of the present invention will be described. In the first embodiment of the present invention, an example in the case where the distribution data to be updated is control distribution data has been described. In the second embodiment of the present invention, an example in which, in addition to the control distribution data being updated, the target distribution data is also updated will be described. Hereinafter, among the configurations of the notification control system according to the second embodiment of the present invention, the configurations different from those of the notification control system 1 according to the first embodiment of the present invention will be mainly described, and detailed descriptions of the same configurations as those of the notification control system 1 according to the first embodiment of the present invention will be omitted.

[0108] <2-1. Description of the Configuration> A configuration example of the notification control system according to the second embodiment of the present invention will be described. FIG. 4 is a diagram showing a configuration example of the notification control system 2 according to the second embodiment of the present invention. As shown in FIG. 4, the notification control system 2 according to the second embodiment of the present invention includes a user terminal 11 and a server 21. The user terminal 11 and the server 21 are connected to a network, and the user terminal 11 and the server 21 are configured to be able to communicate with each other via the network.

[0109] (User Terminal 11) In addition to the functions provided by the user terminal 10 according to the first embodiment, the user terminal 11 has a function of transmitting response data to the server 21 when there is a response to the message notification by the user.

[0110] When the message is viewed by the user, the user terminal 11 may transmit response data to the server 21. Whether the message has been viewed by the user may be determined by whether the user has performed an operation of opening the message. Further, when there is an operation by the user to respond to the message, the user terminal 11 may transmit response data to the server 21. The operation of responding to the message may be, for example, pressing a button required for the user to press when viewing the message.

[0111] Note that the user terminal 11 may transmit response data only when the time from the time when the message data is received until there is a response by the user is within a predetermined time.

[0112] (Server 21) The server 21 is a notification control device according to the second embodiment of the present invention that can be realized by a computer. The server 21 includes a control unit (not shown) and a storage unit (not shown). The control unit (not shown) includes a target distribution setting unit 211, a control distribution setting unit 221, a message notification unit 231, and an actual situation distribution analysis unit 241.

[0113] (Message notification unit 231) The message notification unit 231 has a function of acquiring response data from the user terminal 11 in addition to the functions of the message notification unit 230 according to the first embodiment. When the message notification unit 231 acquires response data from the user terminal 11, it outputs the response data to the actual situation distribution analysis unit 241.

[0114] (Actual situation distribution analysis unit 241) The actual situation distribution analysis unit 241 has a function of analyzing the frequency of responses to message notifications by the user in addition to the functions of the actual situation distribution analysis unit 240 according to the first embodiment. The actual situation distribution analysis unit 241 generates response distribution data, which is the analysis result of analyzing the frequency using the number of times the user has responded to a message, that is, the number of times response data has been acquired, for each time frame.

[0115] More specifically, the actual situation distribution analysis unit 241 aggregates the response data acquired from the message notification unit 231 and analyzes the response distribution representing the distribution of the response data. Since the method of aggregating the response data is the same as the method of aggregating the actual situation data, the description is omitted.

[0116] The actual situation distribution analysis unit 241 outputs the response distribution data and the actual situation distribution data representing the analyzed response distribution to the target distribution setting unit 211.

[0117] (Target distribution setting unit 211) The target distribution setting unit 211 has the function of an update unit that updates the target distribution data based on the response distribution data acquired from the actual situation distribution analysis unit 241. More specifically, the target distribution setting unit 211 calculates the response rate at which the user responds to a message for each time frame. Then, the target distribution setting unit 211 updates the target distribution data so that the target value for the time frame with a relatively high response rate becomes higher than the target value before the update, and the target value for the time frame with a relatively low response rate becomes lower than the target value before the update. The method of updating the target distribution data will be described in detail later.

[0118] The target distribution setting unit 211 outputs the updated target distribution data to the control distribution setting unit 221.

[0119] (Control distribution setting unit 221) Similar to the control distribution setting unit 220 according to the first embodiment, the control distribution setting unit 221 updates the control distribution data. The control distribution setting unit 220 according to the first embodiment used the same target distribution data in each update, but the control distribution setting unit 221 updates the control distribution data based on the updated target distribution data acquired from the target distribution setting unit 211. And, similar to the first embodiment, the message notification unit 231 controls the notification of messages to the user based on the updated control distribution data by the control distribution setting unit 221.

[0120] Thus, according to the server 21 according to the second embodiment, the update process of the target distribution data by the target distribution setting unit 211, the update process of the control distribution data by the control distribution setting unit 221, the message notification control process by the message notification unit 231, and the generation process of the response distribution data and the actual situation distribution data by the actual situation distribution analysis unit 241 are repeated. As a result, in addition to the server 21 notifying the user of messages at a more appropriate frequency, it is realized that the server 21 notifies the user of messages during a time period when the user is highly likely to respond.

[0121] The configuration example of the notification control system 2 according to the second embodiment of the present invention has been described above.

[0122] <2-2. Operation example> Subsequently, an operation example of the notification control system 2 according to the second embodiment of the present invention will be described.

[0123] FIG. 5 is a diagram for explaining the operation of the notification control system 2 according to the second embodiment of the present invention. As shown in FIG. 5, the operation of the notification control system 2 according to the second embodiment of the present invention includes (S11) setting of target distribution data and control distribution data, (S12) notification of a message and generation of actual situation distribution data and response distribution data, (S13) update of the target distribution data and the control distribution data, and (S14) determination as to whether to end the operation.

[0124] Hereinafter, each of these steps will be described with reference to FIG. 6. FIG. 6 is a diagram for explaining the generation of each distribution data according to the second embodiment of the present invention.

[0125] (S11) Setting of target distribution data and control distribution data The step of S11 is substantially the same as the operation of the step of S1 in the notification control system 1 according to the first embodiment described with reference to FIG. 2, and thus a detailed description thereof will be omitted. In the step of S11, the target distribution a1(t) shown in FIG. 6 is the same as the target distribution a(t) shown in FIG. 3. When the target distribution data representing the target distribution a1(t) and the control distribution data representing the control distribution b1(t) are set, the operation proceeds to the step of S12.

[0126] (S12) Notification of a message and generation of actual situation distribution data and response distribution data In the step of S12, in addition to the operation of the step of S2 in the notification control system 1 according to the first embodiment described with reference to FIG. 2, a generation process of response distribution data is executed. The actual situation distribution analysis unit 241 generates response distribution data, which is an analysis result obtained by analyzing the frequency using the number of times a user has responded to a message (that is, the number of times response data has been acquired) for each time frame. In the present embodiment, the actual situation distribution analysis unit 241 generates response distribution data by statistically counting the number of times a user has responded to a message in each time frame within one week for each corresponding time frame within one week.

[0127] FIG. 6 shows a response distribution d1(t) represented by the response distribution data generated by the above method. As shown by the response distribution d1(t), it is assumed that there is a bias in the time zone when the user responds to the message. More specifically, in the response distribution d1(t), it is shown that the response rates in time frames T1 to T4 are relatively low, and the response rates in time frames T5 to T8 are relatively high.

[0128] When the actual situation distribution analysis unit 241 outputs the response distribution data representing the analyzed response distribution d1(t) and the actual situation distribution data representing the actual situation distribution c1(t) to the target distribution setting unit 211, and outputs the actual situation distribution data representing the actual situation distribution c1(t) to the control distribution setting unit 221, the operation proceeds to step S13.

[0129] (S13) Update of target distribution data and control distribution data The target distribution setting unit 211 updates the target distribution data based on the response distribution data. First, the target distribution setting unit 211 calculates, for each time frame, a response rate indicating the ratio of the messages to which the user has responded among the messages notified to the user.

[0130] The target distribution setting unit 211 may calculate the response rate for each time frame using the following formula (3).

[0131] d1(t) / c1(t) ···(3)

[0132] Then, the target distribution setting unit 211 updates the target distribution data according to the calculated response rate. More specifically, the target distribution setting unit 211 updates the target distribution data such that the target value of the time frame with a relatively high response rate becomes higher than the target value before the update, and the target value of the time frame with a relatively low response rate becomes lower than the target value before the update.

[0133] For example, when the response rate is higher than a first predetermined value, the target distribution setting unit 211 may update the target value so that the target value increases from before the update to after the update of the target value for the time frame corresponding to the response rate. Since the response rate of the user is high for the time frame, it is assumed that by increasing the frequency of message notifications, the possibility that the user takes an action prompted by the message can be increased. The first predetermined value may be, for example, 0.1.

[0134] Further, when the response rate is lower than a second predetermined value, the target distribution setting unit 211 may update the target value so that the target value decreases from before the update to after the update of the target value for the time frame corresponding to the response rate. Since the response rate of the user is low for the time frame, even when a message is notified, it is because the possibility that the user takes an action prompted by the message is low. The second predetermined value may be, for example, 0.05.

[0135] Here, when the response rate is greater than or equal to the second predetermined value and less than or equal to the first predetermined value, the target distribution setting unit 211 may not update the target value. However, the first predetermined value and the second predetermined value may be the same value. In this case, the target distribution setting unit 211 updates the target values for all time frames.

[0136] FIG. 6 shows a target distribution a2(t) represented by updated target distribution data including the target values for each time frame generated by the above method. Thus, in the target distribution a2(t), the target values for time frames T1 to T4 are set smaller than before the update, and the target values for time frames T5 to T8 are set larger than before the update.

[0137] The target distribution setting unit 211 outputs target distribution data representing the updated target distribution a2(t) to the control distribution setting unit 221.

[0138] The control distribution setting unit 221 updates the control distribution data in the same manner as the operation of step S3 of the notification control system 1 according to the first embodiment described with reference to FIG. 2. However, for the update of the control distribution data, the updated target distribution data by the target distribution setting unit 211 is used. The control distribution setting unit 221 outputs the updated control distribution data to the message notification unit 231.

[0139] The message notification unit 231 controls the notification of messages to the user based on the control distribution data representing the updated control distribution b2’(t) by the control distribution setting unit 221. Then, the actual situation distribution analysis unit 241 generates actual situation distribution data representing the actual situation distribution c2’(t) indicating the execution frequency at which messages are notified based on the updated control distribution data by the message notification unit 231. Further, the actual situation distribution analysis unit 241 generates response distribution data representing the response distribution d2(t) indicating the number of times the user has responded to the messages notified based on the updated control distribution data by the message notification unit 231.

[0140] As shown in FIG. 6, the actual situation distribution c2’(t) approaches the updated target distribution a2(t). Also, as shown in the response distribution d1(t) and the response distribution d2(t), the total number of times the user has responded to the messages in one day increases with the update of the control distribution data. As described so far, by updating the control distribution data using the updated target distribution data, in addition to notifying the user of messages at an appropriate frequency during the time period intended by the notification organizer, it is realized to notify the user of messages during the time period when the user is highly likely to respond. Thereby, it is expected that the response rate of the user to the messages in one day will be improved, and the utilization rate of the message notification service provided by the notification control system 1 will be improved.

[0141] When the control distribution setting unit 221 updates the control distribution data or determines to stop the update, the operation proceeds to step S14.

[0142] (S14) Determination of whether to end the operation When the organizer inputs an instruction to end the operation through an operation on an operation unit (not shown) of the server 21 or the like, the operation of the notification control system 2 ends. Otherwise, the operation proceeds to step S12. Note that, similar to S2 of the notification control system 1 according to the first embodiment described with reference to FIG. 2, when the execution cycle of the steps of step S12 is determined in advance, the steps of S12 may be executed after it is determined that the next execution timing of the steps of S12 has arrived based on the execution cycle.

[0143] The operation example of the notification control system 2 according to the second embodiment of the present invention has been described above.

[0144] <<3. Hardware Configuration Example>> Subsequently, the hardware configuration of the information processing apparatus 900 as an example of the hardware configurations of the server 20 according to the first embodiment of the present invention and the server 21 according to the second embodiment of the present invention will be described. FIG. 7 is a diagram showing the hardware configuration of the information processing apparatus 900 as an example of the hardware configurations of the server 20 according to the first embodiment of the present invention and the server 21 according to the second embodiment of the present invention. Note that the hardware configurations of the user terminal 10 and the user terminal 11 may also be realized in the same manner as the hardware configuration of the information processing apparatus 900 shown in FIG. 7.

[0145] As shown in FIG. 7, the information processing apparatus 900 includes a CPU (Central Processing Unit) 901, a ROM (Read Only Memory) 902, a RAM (Random Access Memory) 903, a host bus 904, a bridge 905, an external bus 906, an interface 907, an input device 908, an output device 909, a storage device 910, and a communication device 911.

[0146] The CPU 901 functions as an arithmetic processing unit and a control unit, and controls the overall operations within the information processing device 900 according to various programs. Also, the CPU 901 may be a microprocessor. The ROM 902 stores programs, arithmetic parameters, etc. used by the CPU 901. The RAM 903 temporarily stores programs used in the execution of the CPU 901 and parameters that change as appropriate during the execution. These are interconnected by a host bus 904 composed of a CPU bus, etc.

[0147] The host bus 904 is connected to an external bus 906 such as a PCI (Peripheral Component Interconnect / Interface) bus via a bridge 905. Note that it is not necessarily required to separately configure the host bus 904, the bridge 905, and the external bus 906, and these functions may be implemented on a single bus.

[0148] The input device 908 is composed of input means such as a mouse, keyboard, touch panel, button, microphone, switch, and lever for the user to input information, and an input control circuit that generates an input signal based on the input by the user and outputs it to the CPU 901. The user who operates the information processing device 900 can input various data to the information processing device 900 or instruct processing operations by operating this input device 908.

[0149] The output device 909 includes, for example, display devices such as a CRT (Cathode Ray Tube) display device, a liquid crystal display (LCD) device, an OLED (Organic Light Emitting Diode) device, a lamp, and audio output devices such as a speaker.

[0150] The storage device 910 is a device for storing data. The storage device 910 may include a storage medium, a recording device for recording data on the storage medium, a reading device for reading data from the storage medium, a deleting device for deleting data recorded on the storage medium, and the like. The storage device 910 is composed of, for example, an HDD (Hard Disk Drive). This storage device 910 drives a hard disk and stores programs executed by the CPU 901 and various data.

[0151] The communication device 911 is, for example, a communication interface composed of a communication device or the like for connecting to a network. Also, the communication device 911 may support either wireless communication or wired communication.

[0152] As described above, the hardware configuration example of the information processing device 900 as an example of the hardware configuration of the server 20 according to the first embodiment of the present invention and the server 21 according to the second embodiment of the present invention has been described.

[0153] <<4. Modifications>> As described above, the preferred embodiments of the present invention have been described in detail with reference to the accompanying drawings, but the present invention is not limited to such examples. It is obvious that those having ordinary knowledge in the technical field to which the present invention pertains can conceive of various modification examples or correction examples within the scope of the technical idea described in the claims, and it is naturally understood that these also belong to the technical scope of the present invention.

[0154] <4-1. Modifications Regarding System Configuration> In the above, the case where the server includes a target distribution setting unit, a control distribution setting unit, a message notification unit, and an actual situation distribution analysis unit has been described, but the configuration of the notification control system is not limited to this. For example, at least a part of the configuration of the target distribution setting unit, the control distribution setting unit, the message notification unit, and the actual situation distribution analysis unit may be provided in the user terminal.

[0155] <4-2. Modifications Regarding Each Distribution Data> In the above, an example in which a set of distribution data (target distribution data, control distribution data, actual situation distribution data, and response distribution data) is generated and updated has been described. However, two or more sets of distribution data may be prepared. That is, a plurality of target distribution data, each belonging to a different set, are preset. Based on each target distribution data, control distribution data belonging to the same set is set. The results of controlling the execution of notifications based on each control distribution data are analyzed, and actual situation distribution data and response distribution data belonging to the same set may be generated.

[0156] For example, the target distribution setting unit 210 (or the target distribution setting unit 211, the same applies in the following examples) may set the target distribution data for each day of the week. It is assumed that the behavior of the user varies for each day of the week. That is, it is assumed that the actual situation distribution and the response distribution will be different distributions for each day of the week. Therefore, the target distribution data is set by the target distribution setting unit 210 for each day of the week, and the control distribution data is updated by the control distribution setting unit 220 (or the control distribution setting unit 221, the same applies in the following examples) for each day of the week, so that messages are notified at an appropriate frequency for each day of the week, and it can be expected that the user will be less likely to feel annoyed by the notifications.

[0157] Similarly, the target distribution setting unit 210 may set the target distribution data as each distribution data for weekdays and each distribution data for holidays. This is because it is assumed that the behavior of the user may vary depending on whether it is a weekday or a holiday.

[0158] In addition, the target distribution setting unit 210 may set target distribution data for each group to which the user belongs for each set of distribution data. Each user may be classified into one of a plurality of groups based on the user's age, gender, living area, workplace, or type of work. This is because it is assumed that the time frame in which the notification organizer expects to send the message and the time frame in which the user views the message may differ depending on the user's age, gender, living area, workplace, or type of work. By setting target distribution data for each group by the target distribution setting unit 210 and updating control distribution data for each group by the control distribution setting unit 220, messages are notified at an appropriate frequency for each group, so it can be expected that users will be less likely to find the notifications bothersome.

[0159] In addition, the target distribution setting unit 210 may set target distribution data prepared for each attribute corresponding to the message for each set of distribution data. For example, the attribute corresponding to the message may be the type of action prompted by the message. The type of action may include, for example, health actions such as walking, sleeping, eating, and exercising, environmentally conscious actions, or purchasing actions. This is because it is assumed that the time frame in which the notification organizer expects to send the message and the time frame in which the user views the message may differ depending on the type of action. Also, this is because it is assumed that the candidate extraction conditions differ depending on the type of action.

[0160] Also, the attribute corresponding to the message may be the type of the message. Here, as an action modification process for changing the user's awareness and behavior, techniques such as providing a trigger for a specific action, providing knowledge related to a specific action, and providing a reward for the action performance of a specific action are known. Therefore, the type of the message may be, for example, a message recommending a specific action for providing a trigger for a specific action to the user, a message presenting information related to a specific action (for example, the physical effect that the user can obtain when a specific action is executed by the user, etc.) for providing knowledge related to a specific action, or a message including the execution result of a specific action for providing a reward for the action performance of a specific action by the user. For example, the message recommending a specific action may be a message such as "Let's use the stairs". Also, the message presenting information related to a specific action may be a message such as "Using the stairs has the effect of lowering blood sugar levels". The execution result of a specific action may be, for example, a notification of the performance record of the number of floors used (for example, a message such as "The record of using the stairs was updated just now") or a notification related to the reward (monetary incentive, etc.) obtained by walking on the stairs (for example, a message such as "200 points were awarded for using the stairs today"). Depending on the type of the message, it is assumed that the time frame in which the notification organizer expects the message to be notified or the time frame in which the user views the message may differ. Also, it is assumed that the candidate extraction conditions differ depending on the type of the message.

[0161] By setting the target distribution data for each attribute by the target distribution setting unit 210 and updating the control distribution data for each attribute by the control distribution setting unit 220 as described above, the message is notified at an appropriate frequency for each group, so it can be expected that the user will be less likely to feel bothered by the notification.

Explanation of Signs

[0162] 1, 2 Notification control system 10, 11 User terminal Servers 20 and 21 Target distribution setting units 210 and 211 Control distribution setting units 220 and 221 Message notification units 230 and 231 Live distribution analysis units 240 and 241

Claims

1. A notification control unit that controls the notification of the message to the user based on message notification control data related to a frequency of execution of the notification of the message to the user; an analysis unit that analyzes the frequency with which the notification of the message to the user is executed; an update unit that updates the message notification control data based on an analysis result by the analysis unit and target data that indicates a target value for the frequency of notifying the user of the message; A notification control device comprising:

2. The notification control device according to claim 1 , wherein the notification control unit controls the notification of the message to the user based on the message notification control data updated by the update unit.

3. The notification control device according to claim 2 , wherein the update unit updates the message notification control data so that a frequency of the message notification executed by the notification control unit based on the updated message notification control data approaches the target data.

4. When the frequency analyzed by the analysis unit is greater than a target value of the frequency of the notification, the update unit updates the message notification control data so that the frequency of execution of the notification decreases from before the update of the message notification control data to after the update, When the frequency analyzed by the analysis unit is smaller than the target value of the frequency of the notification, the message notification control data is updated so that the frequency of execution of the notification increases from before the update of the message notification control data to after the update. The notification control device according to claim 3 .

5. The notification control device according to claim 2 , wherein the update unit controls a time interval for updating the message notification control data based on a difference between the frequency analyzed by the analysis unit and a target value of the notification frequency.

6. The message notification control data is data for controlling a frequency of execution of the message notification for each of a plurality of time slots obtained by dividing a predetermined period, The analysis unit analyzes the frequency using the number of times that the notification of the message to the user was executed for each time frame; The target data represents a target value of notification of the message for each time slot. The notification control device according to claim 1 .

7. The message notification control data is data for determining a frequency of message notifications when a predetermined condition is satisfied, The notification control unit determines whether to notify a message when the predetermined condition is satisfied based on the message notification control data. The notification control device according to claim 6 .

8. The notification control device according to claim 7 , wherein the predetermined condition includes a condition related to an action of the user or an environment in which the user is placed.

9. The notification control device according to claim 7 , wherein the predetermined condition includes a condition that a determination as to whether or not to notify the message has not been made in the time frame to which the present belongs.

10. The notification control device according to claim 7 , wherein the message notification control data is data representing a probability of executing notification of the message when the predetermined condition is satisfied.

11. The notification control device according to claim 7 , wherein the analysis unit analyzes the frequency by taking statistics on the number of notifications of messages notified in each time frame in a plurality of predetermined periods, for each corresponding time frame in the plurality of predetermined periods.

12. The notification control device according to claim 1 , wherein the update unit updates the goal data based on a response by the user to the notification of the message.

13. the update unit updates the target data so that the target value increases from before the update of the target data to after the update when a response rate at which the user responded to the message is higher than a predetermined value; When a response rate at which the user responds to the message is lower than a predetermined value, the target data is updated so that the target value becomes smaller from before the update of the target data to after the update. The notification control device according to claim 12.

14. The notification control device includes: A setting unit for setting the target data is further provided, The setting unit sets the message notification control data according to the target data. The notification control device according to claim 1 .

15. The setting unit classifies each of the plurality of users into a plurality of groups, and sets the target data prepared for each of the groups; The update unit updates the message notification control data for each of the groups. The notification control device according to claim 14.

16. The setting unit sets the target data prepared for each attribute corresponding to the message, The update unit updates the message notification control data for each of the attributes. The notification control device according to claim 14.

17. the message is a message for encouraging a change in the user's behavior, The attribute is a type of the action. The notification control device according to claim 16.

18. The message is classified into one of a message recommending a specific action to the user, a message presenting information about a specific action, and a message about a result of the execution of a specific action by the user; The attribute is the type. The notification control device according to claim 16.

19. Controlling notification of the message to the user based on message notification control data relating to a frequency of execution of notification of the message to the user; Analyzing the frequency with which notifications of the messages to the users are performed; updating the message notification control data based on the frequency analysis result and target data representing a target value of the frequency of notification of the message to the user; A notification control method implemented by a computer.

20. A notification control unit that controls the notification of the message to the user based on message notification control data related to a frequency of execution of the notification of the message to the user; an analysis unit that analyzes the frequency with which the notification of the message to the user is executed; an update unit that updates the message notification control data based on an analysis result by the analysis unit and target data that indicates a target value for the frequency of notifying the user of the message; A notification control system comprising:

Images