Information processing apparatus, information processing method, and information processing system

Abstract

To provide a mechanism configured to send messages at more appropriate timing.SOLUTION: An information processing apparatus includes: a notification condition setting unit which divides a notification period into time blocks including one or more time slots, on the basis of the upper limit of notifications in the notification period and target notification probability for each of the time slots which are obtained by dividing the notification period; and a notification determination unit which determines whether to notify a target person. The notification determination unit is configured to: determine whether to execute a notification based on the target notification probability of a time slot including the time at which status data of the target person matches a notification criterion when the notification has not been executed, in the time block including the time; and determine not to execute the notification when the notification has been already executed.SELECTED DRAWING: Figure 1

Description

[Technical Field]

[0001] The present invention relates to an information processing device, an information processing method, and an information processing system. [Background technology]

[0002] In recent years, technologies have been developed that encourage users to change their awareness or behavior by notifying them of messages related to health behavior or purchasing behavior. However, there may be situations in which it is difficult for users to view the messages, such as when they are concentrating on a task. If a message is notified in a situation in which it is difficult for users to view the messages, it may be annoying for the users, and they may view the messages less frequently.

[0003] Therefore, Patent Document 1 below proposes a technique for determining a situation in which a message is likely to be viewed, and notifying a user of the message in a situation in which the message is likely to be viewed. [Prior art documents] [Patent documents]

[0004] [Patent Document 1] Japanese Patent Application Publication No. 2018-129004 Summary of the Invention [Problem to be solved by the invention]

[0005] However, with the technology disclosed in Patent Document 1, there is a risk that a message may be notified at an inappropriate time.

[0006] Therefore, the present invention has been made in consideration of the above problems, and an object of the present invention is to provide a mechanism that can more appropriately time a message notification. [Means for solving the problem]

[0007] In order to solve the above problem, according to one aspect of the present invention, an information processing device is provided, which includes a notification condition setting unit that divides a notification target period into time blocks including one or more time slots based on an upper limit number of notifications during the notification target period and a target notification probability for each time slot into which the notification target period is divided, and a notification determination unit that determines whether to execute a notification to a target person, wherein the notification determination unit determines whether to execute the notification based on the target notification probability for the time slot to which the time belongs if the notification has not yet been executed in the time block to which the target person's status data matches the notification implementation criteria, and determines not to execute the notification if the notification has already been executed.

[0008] The notification determination unit determines whether to execute the notification based on a control notification probability calculated by multiplying the target notification probability by a control coefficient set for each time slot, and the control coefficient may be set to a larger value for the later time slot within the time block.

[0009] The control coefficient may be set to satisfy Equation (1), where N is the number of time slots included in the time block, i is the order of the time slots within the time block, Ki is the control coefficient for the i-th time slot within the time block, and Pi is the target notification probability for the i-th time slot within the time block.

[0010] The notification condition setting unit may select the time slots in a predetermined order until the cumulative sum of the upper limit notification probabilities becomes 1 or greater, and set a set of one or more selected time slots as one time block, and the upper limit notification probability may be calculated by multiplying the target notification probability by a value obtained by dividing the number of upper limit notifications by the sum of the target notification probabilities during the notification target period.

[0011] The notification condition setting unit may set a set of one or more consecutive time slots as one time block.

[0012] The notification determination unit may determine whether or not to execute the notification up to once per time slot.

[0013] The notification condition setting unit may correct the target notification probability by dividing it by the number of times the target person's situation data matches the notification implementation criteria, and the notification determination unit may make a determination as to whether or not to execute the notification for each time slot without any upper limit.

[0014] When an actual value of the notification probability for each time slot is smaller than the target notification probability for that time slot, the notification condition setting unit may correct the target notification probability for that time slot to a larger value.

[0015] The notification condition setting unit may correct the target notification probabilities of all the time slots to a larger value when the maximum value of the actual value of the number of notifications for each notification target period is smaller than the sum of the target notification probabilities.

[0016] The notification condition setting unit may correct the target notification probability to a larger value when a frequency at which it is determined whether or not to perform the notification for each time slot is lower than a predetermined threshold value.

[0017] The notification condition setting unit may correct the upper limit number of notifications to a larger value when the maximum value of the actual number of notifications for each notification period is smaller than the upper limit number of notifications.

[0018] Furthermore, in order to solve the above-mentioned problem, according to another aspect of the present invention, there is provided an information processing method executed by a computer, which includes dividing a notification target period into time blocks including one or more time slots based on an upper limit number of notifications in the notification target period and a target notification probability for each time slot into which the notification target period is divided, and determining whether to execute a notification to the target person, wherein determining whether to execute a notification to the target person includes determining whether to execute the notification based on the target notification probability for the time slot to which the time belongs if the notification has not been executed in the time block to which the time when the target person's status data matches the notification implementation criterion belongs, and determining not to execute the notification if the notification has already been executed.

[0019] Furthermore, in order to solve the above problem, according to another aspect of the present invention, there is provided an information processing system comprising an information processing device and a terminal device, wherein the information processing device has a notification condition setting unit that divides a notification target period into time blocks including one or more time slots based on an upper limit number of notifications in the notification target period and a target notification probability for each time slot into which the notification target period is divided, and a notification determination unit that determines whether to execute a notification to a target person, wherein the notification determination unit determines whether to execute the notification based on the target notification probability for the time slot to which the time belongs if the notification has not yet been executed in the time block to which the time when the target person's status data matches the notification implementation criteria belongs, and determines not to execute the notification if the notification has already been executed, and the terminal device outputs a message when the notification determination unit determines to execute the notification. [Effects of the Invention]

[0020] As described above, according to the present invention, a mechanism is provided that can more appropriately time a message notification. [Brief explanation of the drawings]

[0021] [Figure 1]1 is a diagram illustrating an example of the configuration of a system 1 according to an embodiment of the present invention. [Figure 2] FIG. 10 is a diagram for explaining a specific example of setting a time block according to the embodiment. [Figure 3] 10A and 10B are diagrams for explaining specific examples of calculation of control notification probability according to the present embodiment. [Figure 4] 10A and 10B are diagrams for explaining the effect of the control notification probability according to the present embodiment. [Figure 5] 10A and 10B are diagrams for explaining a specific example of determining whether or not a notification can be executed according to the present embodiment. [Figure 6] 10 is a flowchart showing an example of the flow of a message notification process executed by the system 1 according to the present embodiment. [Figure 7] 10 is a flowchart showing an example of the flow of a notification condition setting process executed by the system 1 according to the present embodiment. [Figure 8] FIG. 10 is a diagram for explaining a message notification timing in a comparative example. [Figure 9] FIG. 10 is a diagram for explaining a message notification timing in a comparative example. [Figure 10] FIG. 10 is a diagram for explaining a message notification timing in a comparative example. [Figure 11] FIG. 2 is a diagram for explaining the timing of message notification by the system 1 according to the present embodiment. [Figure 12] FIG. 2 is a block diagram showing an example of a hardware configuration of the information processing device according to the present embodiment. DETAILED DESCRIPTION OF THE INVENTION

[0022] Hereinafter, preferred embodiments of the present invention will be described in detail with reference to the accompanying drawings. In this specification and drawings, components having substantially the same functional configurations are designated by the same reference numerals, and redundant explanations will be omitted.

[0023] <1. Overview> 1 is a diagram showing an example of the configuration of a system 1 according to an embodiment of the present invention. As shown in FIG.

[0024] The server 10 is an information processing device that controls the process of notifying a user of a message. The server 10 extracts a message according to the user's situation and determines whether to notify the user of the message. If the server 10 determines that a message should be notified, the server 10 transmits the message according to the user's situation to the user terminal 20.

[0025] The user terminal 20 is a terminal device that outputs a message to a user. The user terminal 20 may be any terminal device carried by a user, such as a smartphone, a tablet terminal, or a smartwatch. The user of the user terminal 20 is an example of a target person to whom the message is notified. The user terminal 20 outputs a message received from the server 10.

[0026] The server 10 and the user terminal 20 are connected via an arbitrary network such as the Internet.

[0027] The system 1 executes a process of notifying the user of a message according to the user's situation in each of a plurality of time slots obtained by dividing the notification period.

[0028] The notification period is a period during which a message can be sent to the user. For example, the notification period may be from 9:00 to 19:00 every day.

[0029] A time slot is a unit period that constitutes a notification period. For example, a time slot may be a time period obtained by dividing the notification period from 9:00 to 19:00 into one-hour segments.

[0030] However, an upper limit on the number of notifications during a notification period is set in the system 1. The upper limit on the number of notifications is the upper limit on the number of messages that can be notified during a notification period.

[0031] In addition, a target notification probability list is set in the system 1. The target notification probability list is a list of target notification probabilities for each time slot in the notification target period. The target notification probability is a target value for the message notification probability set for each time slot. It is expected that the probability of a message being notified for each time slot will match the target notification probability. The target notification probability is set high for time slots where messages are likely to be viewed, and low for time slots where they are not.

[0032] The sum of the target notification probabilities during the notification period is also referred to as the target number of notifications. The target number of notifications is a target value for the number of messages to be notified during the notification period.

[0033] System 1 determines whether to notify a user of a message based on the upper notification limit number and the target notification probability list. In particular, system 1 determines whether to notify a user of a message so that the timing of message notifications is distributed throughout the notification target period. This configuration prevents messages from being notified in a concentrated manner during certain time periods during the notification target period, reducing the burden on the user and, as a result, is expected to improve the probability that the message will be viewed.

[0034] <2.Technical issues> Hereinafter, the technical problems of the system 1 according to this embodiment will be described with reference to Figures 8 to 10. Figures 8 to 10 are diagrams for explaining the timing of message notification in a comparative example.

[0035] As shown in FIG. 8, a first comparative example can be considered in which a message is notified at a timing when a user's behavior changes, such as when the user switches between walking and standing still. Such timings of behavioral changes are likely to be times when a user is likely to view a message. However, the first comparative example may be annoying to the user, and may reduce the frequency with which the user views messages. That is, if a specific behavior (e.g., repeated walking and standing still while taking a walk) occurs frequently during a specific time period (e.g., morning time), and a message is notified every time the specific behavior occurs, a large number of messages may be notified in a short period of time.

[0036] Therefore, as shown in Figure 9, a second comparative example can be considered in which a notification probability is set for each time period, and when a candidate for a message notification timing occurs, whether or not to notify the message is determined based on the notification probability. However, in the second comparative example, there is a risk that more messages than the number of scheduled notifications per day calculated from the notification probability will be notified. This case, too, may be annoying to the user, and the frequency of viewing messages may decrease.

[0037] Furthermore, as shown in FIG. 10, a third comparative example can be considered in which an upper limit is set on the number of messages that can be notified per day, and when the number of message notifications per day reaches the upper limit, message notifications are prohibited for subsequent time periods. However, in the third comparative example, messages are no longer notified after a certain time period. In this case, it may be difficult to notify messages in accordance with the intentions of the notification organizer (e.g., a service provider of sales promotion or health promotion). In other words, there is a risk that message notifications may be biased toward time periods not intended by the notification organizer, and messages may not be notified during the time periods intended by the notification organizer.

[0038] In order to solve the problems in the comparative example described above, the system 1 according to this embodiment was created.

[0039] In the system 1 according to this embodiment, as in the comparative example, the notification conditions are set as an upper limit on the number of messages that can be notified in one day (i.e., the notification target period) (i.e., the upper limit on the number of notifications) and a target notification probability for each time period (i.e., time slot) (i.e., the target notification probability). These notification conditions can be specified by the notification organizer.

[0040] Based on these notification conditions, the system 1 according to this embodiment divides the notification period into time blocks each including one or more time slots, and sends a maximum of one message notification per time block. Furthermore, the system 1 sets a notification probability (a control notification probability, described later) that is actually used to determine whether or not to send a notification, based on the target notification probability for each time slot and the time block settings. The system 1 then determines whether or not to send a message based on the set control notification probability.

[0041] 11 is a diagram illustrating the timing of message notification by the system 1 according to this embodiment. As shown in FIG. 11, according to the system 1 according to this embodiment, messages up to the upper notification limit number are notified to the user in a distributed manner during the time period intended by the notification organizer. In other words, according to the system 1 according to this embodiment, it is possible to notify the user of messages in a distributed manner during the time period intended by the notification organizer without causing the user to feel annoyed.

[0042] <3. Technical features related to message notification processing> <3.1.Configuration example> Hereinafter, referring again to FIG. 1, an example of the configuration of the system 1 relating to message notification processing will be described.

[0043] (1) User terminal 20 The user terminal 20 transmits behavioral environment data to the server 10. The behavioral environment data is information that indicates the behavioral environment of the user. The user terminal 20 may include various sensors such as a walking sensor or a barometric pressure sensor, various communication interfaces such as a beacon, and an operation interface that outputs questions and receives input of responses. The user terminal 20 then transmits the information acquired by these to the server 10 as behavioral environment data. The user terminal 20 may transmit behavioral environment data to the server 10 only when there is a change in the user's behavioral environment.

[0044] The user terminal 20 receives message data from the server 10. The message data is data indicating a message to be notified to the user. The user terminal 20 outputs a message based on the received message data as information that is any one or a combination of two or more of visual information, auditory information, and tactile information.

[0045] The behavioral environment data described above is an example, and any data may be adopted as the behavioral environment data.

[0046] (2) Server 10 As shown in FIG. 1, the server 10 includes a status collection unit 11, a message notification unit 12, a notification condition setting unit 13, a control notification probability calculation unit 14, and a notification determination unit 15.

[0047] (Status Collection Unit 11) The situation collection unit 11 has a function of collecting situation data of the user.

[0048] The situation collection unit 11 accumulates environmental behavior data input from the user terminal 20 in time series, analyzes it every predetermined time (for example, every minute), and generates situation data. The situation data is information that indicates the user's situation. For example, the situation collection unit 11 detects the user's situation, such as "has been sitting for more than one hour," "started walking 10 seconds ago," or "has climbed an average of five or more flights of stairs per day," based on the time series data of the sensor values ​​of the walking sensor and the atmospheric pressure sensor included in the behavioral environment data, and generates these detection results as situation data. The situation collection unit 11 sequentially outputs the generated situation data to the message notification unit 12.

[0049] The situation data described above is an example, and any data may be adopted as the situation data.

[0050] (Message notification unit 12) The message notification unit 12 has a function of notifying the user of a message.

[0051] The message notification unit 12 determines whether the user's situation data matches the notification implementation criteria. The notification implementation criteria are criteria set in association with one or more message candidates. The message candidates are candidates for messages to be notified to the user. If the notification implementation criteria are met, the message candidate associated with the notification implementation criteria may be notified to the user. For example, the notification implementation criteria may be "detecting a beacon in the office around 3 p.m. and having been sitting for more than an hour." The message candidate corresponding to the notification implementation criteria may be "Why not take a bathroom break to refresh your brain?"

[0052] When the message notification unit 12 determines that the user's situation data matches the notification implementation criteria, it requests the notification determination unit 15 to determine whether or not to notify the user of the message candidate. In detail, the message notification unit 12 outputs determination request data to the notification determination unit 15 and obtains determination result data from the notification determination unit 15. The determination request data is information requesting a determination of whether or not to notify the user of the message candidate. The determination result data is data indicating the determination result of whether or not to notify the user of the message candidate.

[0053] Here, it is assumed that the message notification unit 12 can output the determination request data to the notification determination unit 15 a maximum of once in one time slot.

[0054] The message notification unit 12 transmits message data to the user terminal 20 based on the determination result data input from the notification determination unit 15. In particular, when determination result data indicating that notification is possible is input, the message notification unit 12 transmits message data of the message candidate to the user terminal 20. On the other hand, when determination result data indicating that notification is not possible is input, the message notification unit 12 does not transmit the message data.

[0055] (Notification condition setting unit 13) The notification condition setting unit 13 has a function of setting notification conditions for a message. The notification condition setting unit 13 outputs an upper limit number of notifications, a target notification probability list, and a time block list as notification conditions for a message to the control notification probability calculation unit 14.

[0056] The upper notification limit and the target notification probability list may be specified by an operator of the system 1 (ie, a notification organizer) or an external party such as a user.

[0057] The time block list is a list of time blocks included in the notification period (more precisely, a list of identification information of the time blocks and identification information of the time slots included in the time blocks). A time block is a set of one or more time slots.

[0058] The notification condition setting unit 13 divides the notification target period into time blocks each including one or more time slots. A message can be notified at most once in one time block. This configuration makes it possible to prevent messages from being notified intensively in one time block.

[0059] The notification condition setting unit 13 may set a set of one or more consecutive time slots as one time block, which makes it possible to distribute the timings at which messages are notified throughout the entire notification period.

[0060] A specific example of setting time blocks will be described below with reference to FIG.

[0061] Fig. 2 is a diagram for explaining a specific example of setting time blocks according to this embodiment. As shown in Fig. 2, the time slot from 9:00 to 19:00 in one day is the notification target period, and time slots TS1 to TS10, each having a length of one hour, are set. Furthermore, (0.2, ..., 0.25) are set as the target notification probability list for time slots TS1 to TS10.

[0062] The notification condition setting unit 13 sets an upper limit notification probability list based on the upper limit notification number and the target notification probability list. The upper limit notification probability list is a list of upper limit notification probabilities. The upper limit notification probability is a notification probability for achieving the upper limit notification number, which is set for each time slot. When messages are notified according to the upper limit notification probability, it is expected that the number of messages notified during the notification target period will match the upper limit notification number.

[0063] Specifically, the notification condition setting unit 13 calculates the upper limit notification probability by multiplying the target notification probability by a value obtained by dividing the upper limit number of notifications by the sum of the target notification probabilities. That is, the notification condition setting unit 13 calculates the upper limit notification probability by multiplying the target notification probability by a value obtained by dividing the upper limit number of notifications by the target notification number. With this configuration, the sum of the upper limit notification probabilities during the notification target period matches the upper limit number of notifications.

[0064] In the example shown in FIG. 2, the sum of the target notification probabilities in the notification target period is 2. Therefore, the target number of notifications in the notification target period is 2. If the upper limit number of notifications is, for example, 4, the notification condition setting unit 13 calculates the upper limit notification probability by multiplying the target notification probability by 2 obtained by dividing the upper limit number of notifications, 4, by the target number of notifications, 2. For example, in time slot TS1, the target notification probability is 0.2, so 0.4 is calculated as the upper limit notification probability. As a result, an upper limit notification probability list (0.4, ..., 0.50) is obtained.

[0065] The notification condition setting unit 13 selects time slots in a predetermined order until the cumulative sum of the upper limit notification probabilities becomes equal to or greater than 1, and sets a set of one or more selected time slots as one time block. An example of the predetermined order is the order from earliest to latest time slot.

[0066] In the example shown in FIG. 2, first, the cumulative sum of the upper limit notification probabilities of time slots TS1 to TS3 is 1.2 (≧1), so the notification condition setting unit 13 sets time slots TS1 to TS3 to time block TB1. Next, the cumulative sum of the upper limit notification probabilities of time slots TS4 to TS7 is 1.3 (≧1), so the notification condition setting unit 13 sets time slots TS4 to TS7 to time block TB2. Next, the cumulative sum of the upper limit notification probabilities of time slots TS8 to TS9 is 1.0 (≧1), so the notification condition setting unit 13 sets time slots T8 to T9 to time block TB3. The remaining time slot TS10 has an upper limit notification probability of 0.5 (<1), but because it is the last time slot of the notification period, the notification condition setting unit 13 sets time slot TS10 to time block TB4.

[0067] With this configuration, even if messages are sent in all time blocks, the number of message notifications is expected to be equal to or less than the upper limit. As a result, it is possible to prevent imbalances in the timing of message notifications, such as a concentration of message notifications in the morning and no message notifications in the afternoon or later.

[0068] (Control notification probability calculation unit 14) The control notification probability calculation unit 14 has a function of calculating the control notification probability and generating a control notification probability list. The control notification probability calculation unit 14 outputs the upper limit notification number and the time block list input from the notification condition setting unit 13, as well as the generated control notification probability list, to the notification determination unit 15.

[0069] The control notification probability list is a list of control notification probabilities for each time slot. The control notification probability is a message notification probability set for each time slot, and is a value actually used when the notification determination unit 15 determines whether or not to notify a message.

[0070] The control notification probability calculation unit 14 calculates the control notification probability by multiplying the target notification probability by a control coefficient set for each time slot. The control coefficient is a coefficient for realizing the target notification probability. The control coefficient is set to a larger value the later the time slot in the time block (i.e., the longer the time that has elapsed since the start of the time block). With this configuration, the later the time slot in the time block, the larger the control notification probability calculated compared to the target notification probability. As a result, the more time passes within the time block, the more likely it is that a message will be notified, making it possible to prevent a situation in which no message is not notified at all within a time block.

[0071] It is desirable that the control notification probability calculation unit 14 sets the control coefficient so as to satisfy the following equation.

[0072]

number

[0073] N is the number of time slots contained in the time block. i is the order of the time slot within the time block. K i is the control factor for the ith time slot in the time block. P i is the target notification probability for the ith time slot in the time block.

[0074] A specific example of calculation of the control notification probability will be described below with reference to FIG.

[0075] Fig. 3 is a diagram for explaining a specific example of calculation of the control notification probability according to the present embodiment. Fig. 3 shows a specific example of calculation of the control notification probability in the specific example described above with reference to Fig. 2.

[0076] 3, the control notification probability calculation unit 14 sets the control coefficients of the time slots TS1, TS4, TS8, and TS10, which are the first time slots of the time block, to 1 in accordance with the above formula (1). As a result, the control notification probability calculation unit 14 sets the target notification probabilities of these time slots as the control notification probabilities as they are.

[0077] 3, the control notification probability calculation unit 14 sets the control coefficients of the time slots TS2, TS3, TS5, TS6, TS7, and TS9, which are the second and subsequent time slots in the time block, to larger values ​​the later the time slot is in the time block, according to the above formula (1).As a result, the control notification probability calculation unit 14 sets the control notification probability to a value obtained by increasing the target notification probability of these time slots the later the time slot is in the time block.

[0078] By calculating the control notification probability using the control coefficient calculated using the above formula (1), it is possible to realize a notification frequency in accordance with the target notification probability list. This point will be described in detail with reference to FIG.

[0079] FIG. 4 is a diagram for explaining the effect of the control notification probability according to this embodiment. The horizontal axis of the graph shown in FIG. 4 is the time slot number in an arbitrary time block. The vertical axis of the graph shown in FIG. 4 is the probability that a message will be notified. It is assumed that a time block includes N time slots. In FIG. 4, in each time slot, the probability that a message will be notified is indicated by a thick solid line, and the probability that a message will not be notified is indicated by a dashed line.

[0080] Here, in the i-th time slot, the target notification probability P i The message will be notified in accordance with the

[0081] The probability that it is determined that a message is to be notified in time slot TS1 is equal to the target notification probability P1. On the other hand, the probability that it is determined that a message is not to be notified in time slot TS1 is (1-P1).

[0082] Only when a message is not notified in time slot TS1 is it determined whether a message is notified in time slot TS2. This is because the maximum number of messages that can be notified in one time block is 1. Therefore, the probability that a message is determined to be notified in time slot TS2 is (1-P1)P2. On the other hand, the probability that a message is determined not to be notified in time slot TS2 is (1-P1)(1-P2).

[0083] Only when no message is notified in time slots TS1 and TS2 is it determined whether or not a message is notified in time slot TS3. Therefore, the probability that a message is determined to be notified in time slot TS3 is (1-P1)(1-P2)P3. On the other hand, the probability that a message is not determined to be notified in time slot TS3 is (1-P1)(1-P2)(1-P3).

[0084] That is, the probability that a message is actually sent in the i-th time slot in any time block is P' i is expressed by the following equation:

[0085]

number

[0086] Referring to the above formula (2), the probability that it is determined that the message is actually notified is P' iis the target notification probability P i The difference becomes larger in the later time slots within the time block.

[0087] Correcting for this difference, the probability P' that the message will actually be notified is calculated. i The target notification probability P i To match the target notification probability P i The control coefficient K is expressed by the following equation: i Whether or not to notify the message may be determined based on the value obtained by multiplying the value by the number of messages.

[0088]

number

[0089] By modifying the above formula (3), the above formula (1) is obtained. Therefore, by calculating the control coefficient using the above formula (1) and determining whether to notify a message based on the control notification probability obtained by multiplying the target notification probability by the control coefficient, it is possible to realize a notification frequency in accordance with the target notification probability list.

[0090] (Notification determination unit 15) The notification determination unit 15 has a function of determining whether or not to notify the user of a message. When determination request data is input from the message notification unit 12, the notification determination unit 15 determines whether or not to notify the user of a message, and outputs determination result data including information indicating the determination result to the message notification unit 12.

[0091] When a message notification has not yet been performed in a time block containing a time when the user's status data matches the notification implementation criteria, the notification determination unit 15 determines whether to perform a message notification based on the target notification probability for the time slot containing that time. On the other hand, when a message notification has already been performed in a time block containing a time when the user's status data matches the notification implementation criteria, the notification determination unit 15 determines not to perform a message notification. With this configuration, whether to perform a message notification is determined only when no message notification has been performed within the time block. This prevents multiple message notifications in one time block and enables the timing of message notifications to be distributed throughout the entire notification target period.

[0092] In particular, the notification determination unit 15 determines whether to execute a message notification based on a control notification probability calculated by multiplying a target notification probability by a control coefficient set for each time slot. That is, when a message notification has not been executed in a time block including a time when the user's situation data matches the notification execution criteria, the notification determination unit 15 determines whether to execute a message notification based on the control notification probability of the time slot including that time. With this configuration, it is possible to achieve a notification frequency in accordance with the target notification probability list, as described above.

[0093] The notification determination unit 15 determines whether or not to notify a message up to once per time slot. This can be achieved by allowing the message notification unit 12 to output determination request data to the notification determination unit 15 a maximum of once per time slot. The more times the determination of whether or not to notify a message is made, the higher the probability that the message will be notified. Therefore, if such an upper limit is not imposed, the probability that the message will be notified will increase in the first time slot within the time block (i.e., the time slot with the shortest elapsed time since the start of the time block). In other words, the timing of message notification will be concentrated at the timing immediately after the time block changes. In this regard, by imposing the above upper limit, it is possible to distribute the timing of message notification throughout the entire time block.

[0094] Hereinafter, a specific example of determining whether or not a notification can be executed will be described with reference to FIG.

[0095] Fig. 5 is a diagram for explaining a specific example of the determination of whether or not a notification can be executed according to the present embodiment. Fig. 5 shows a specific example of the determination of whether or not a notification can be executed in the specific example described above with reference to Figs. 2 and 3.

[0096] 5, situation data C1 to C10 are collected in time slots TS1 to TS10. Then, in time slots other than time slots TS3 and TS6, the collected situation data matches the notification implementation criteria, and message candidates M1, M2, M4, M5, M7, M8, M9, and M10 are extracted.

[0097] Since message candidate M1 exists in time slot TS1, message notification unit 12 outputs determination request data to notification determination unit 15. When the determination request data is input, notification determination unit 15 determines whether or not to notify the message based on the control notification probability, and outputs determination result data to message notification unit 12. Here, notification determination unit 15 outputs determination result data including notification not possible (NG-B: indicating that it has been determined that notification is not possible based on the control notification probability). Since determination result data including notification not possible (NG-B) is input, message notification unit 12 does not transmit the message data.

[0098] Since message candidate M2 exists in time slot TS2, message notification unit 12 outputs determination request data to notification determination unit 15. When the determination request data is input, notification determination unit 15 determines whether or not to notify the message based on the control notification probability, and outputs determination result data to message notification unit 12. Here, notification determination unit 15 outputs determination result data including notification possible (OK). Since determination result data including notification possible (OK) is input to message notification unit 12, message notification unit 12 transmits message data including message candidate M2 to user terminal 20.

[0099] In time slot TS3, since there are no message candidates, the message notification unit 12 does not output judgment request data and does not transmit message data.

[0100] The operations in time slots TS4 and TS5 are the same as the operation in time slot TS1. That is, the message notification unit 12 outputs determination request data, receives determination result data including notification not possible (NG-B), and does not transmit message data.

[0101] The operation in time slot TS6 is the same as the operation in time slot TS3, that is, the message notification unit 12 does not output judgment request data and does not transmit message data.

[0102] The operation in time slot TS7 is the same as the operation in time slot TS1. That is, the message notification unit 12 outputs determination request data, receives determination result data including notification not possible (NG-B), and does not transmit message data.

[0103] The operation in time slot TS8 is the same as the operation in time slot TS2. That is, the message notification unit 12 outputs determination request data, receives determination result data including notification OK (OK), and transmits message data including message candidate M8 to the user terminal 20.

[0104] Since message candidate M9 exists in time slot TS9, message notification unit 12 outputs determination request data to notification determination unit 15. However, since a determination that notification is possible has already been made in time slot TS8, which belongs to the same time block TB3 as current time slot TS9, notification determination unit 15 determines that notification is not possible. Then, notification determination unit 15 outputs determination result data including notification is not possible (NG-A: indicating that notification is not possible because notification has already been made in the same time block). Since determination result data including notification is not possible (NG-A) is input to message notification unit 12, it does not transmit the message data.

[0105] The operation in time slot TS10 is the same as the operation in time slot TS1. That is, the message notification unit 12 outputs determination request data, receives determination result data including notification not possible (NG-B), and does not transmit message data.

[0106] <3.2. Operational processing example> FIG. 6 is a flowchart showing an example of the flow of a message notification process executed by the system 1 according to this embodiment.

[0107] 6, first, the situation collecting unit 11 collects situation data (step S102). More specifically, the situation collecting unit 11 generates situation data based on the environmental behavior data received from the user terminal 20.

[0108] Next, the message notification unit 12 extracts message candidates (step S104). Specifically, the message notification unit 12 extracts message candidates corresponding to the notification implementation criteria that the situation data collected by the situation collection unit 11 matches.

[0109] Next, the message notification unit 12 determines whether or not the notification of the message has been determined within the current time slot by the notification determination unit 15 (step S106). If the notification of the message has been determined within the current time slot (step S106: YES), the process proceeds to step S112.

[0110] If it has not yet been determined whether or not to notify the message within the current time slot (step S106: NO), the message notification unit 12 outputs determination request data to the notification determination unit 15. Then, the notification determination unit 15 determines whether or not to notify the message based on the input determination request data (step S108). In detail, the notification determination unit 15 determines whether or not the message has already been notified in the same time block, i.e., in another time slot belonging to the same time block as the current time slot. Then, if the message has already been notified in the same time block, the notification determination unit 15 determines that the message cannot be notified. On the other hand, if the message has not already been notified in the same time block, the notification determination unit 15 determines whether or not to notify the message based on the control notification probability of the time slot to which the current time belongs in the control notification probability list generated by the control notification probability calculation unit 14.

[0111] If it is determined that the message should be notified (step S108: YES), the notification determination unit 15 outputs determination result data including notification possible (OK) to the message notification unit 12. Then, the message notification unit 12 performs processing to notify the user of the message based on the input of the determination result data indicating notification possible (OK) (step S110). That is, the message notification unit 12 transmits message data of the message candidate extracted in step S104 to the user terminal 20. The user terminal 20 outputs a message based on the received message data to the user.

[0112] On the other hand, if it is determined that the message should not be notified (step S108: NO), the notification determination unit 15 outputs determination result data including notification not possible (NG-A or NG-B) to the message notification unit 12. Then, the message notification unit 12 waits based on the input of the determination result data indicating notification not possible (NG-A or NG-B).

[0113] Thereafter, the server 10 (for example, the message notification unit 12) determines whether or not to end the process (step S112). For example, the server 10 determines whether or not to end the process based on whether or not there is an end instruction from the operator of the system 1.

[0114] If it is determined that the process should not be ended (step S112: NO), the process returns to step S102 again.

[0115] On the other hand, if it is determined that the process is to be ended (step S112: YES), the process ends.

[0116] <4. Technical features related to setting notification conditions> As described above, the notification conditions can be externally specified by an operator or a user of the system 1. Furthermore, the server 10 may update the notification conditions as appropriate.

[0117] <4.1.Configuration example> Hereinafter, referring again to FIG. 1, an example of the configuration of the system 1 regarding the setting of notification conditions will be described.

[0118] (Notification determination unit 15) 1, the notification determination unit 15 outputs the determination result data to the notification condition setting unit 13. The notification determination unit 15 may output the determination result data to the notification condition setting unit 13 at predetermined intervals (for example, one week intervals).

[0119] The determination result data is information indicating the results of determination by the notification determination unit 15. The determination result data includes, for example, the input frequency of determination request data for each time slot in a past predetermined period (e.g., one month), the output frequency of determination result data of whether notification is possible / not possible for each time slot, and the number of message notifications in a notification target period (e.g., one day).

[0120] (Notification condition setting unit 13) As described above, the notification condition setting unit 13 may set notification conditions externally specified by an operator or a user of the system 1. Furthermore, the notification condition setting unit 13 may correct the notification conditions based on the determination result data input from the notification determination unit 15.

[0121] As an example, the notification condition setting unit 13 may correct the target notification probability list based on the judgment result data. When the target notification probability list is corrected, the control notification probability calculation unit 14 generates a control notification probability list based on the corrected target notification probability list. With this configuration, it is possible to adjust the notification probability of a message for each time slot to match the target notification probability at the time of initial setup specified by an external party such as an operator or user of the system 1.

[0122] As another example, the notification condition setting unit 13 may correct the upper limit number of notifications based on the judgment result data. When the upper limit number of notifications is corrected, the control notification probability calculation unit 14 generates a control notification probability list based on the corrected upper limit number of notifications. With this configuration, it is possible to adjust the number of message notifications during the notification target period to match the upper limit number of notifications at the time of initial setup specified by an external party such as the operator or user of the system 1.

[0123] Note that, when the target notification probability is corrected, the setting of the time block may or may not be updated based on the corrected target notification probability. The same applies to the upper limit number of notifications.

[0124] A detailed correction example will be described below.

[0125] If the actual value of the notification probability for each time slot is lower than the target notification probability for that time slot, the notification condition setting unit 13 may correct the target notification probability for that time slot to a larger value. Specifically, the notification condition setting unit 13 may define a correction coefficient greater than 1 and multiply the target notification probability by the correction coefficient. The actual value of the notification probability for each time slot may be calculated based on the frequency with which notification-enabled determination result data for that time slot is obtained. For example, if the target notification probability for a certain time slot is 0.2 but the actual value of the notification probability for the past month was 0.1, the target notification probability for that time slot may be corrected to 0.4. By calculating the control notification probability based on the corrected target notification probability, it is expected that the notification probability for that time slot will be 0.2 in the next month. In this way, with this configuration, it is possible to bring the notification probability for each time slot closer to the target notification probability at the time of initial setting.

[0126] If the maximum actual value of the number of notifications for each notification target period is less than the sum of the target notification probabilities (i.e., the target number of notifications), the notification condition setting unit 13 may correct the target notification probabilities for all time slots to a larger value. Specifically, the notification condition setting unit 13 may define a correction coefficient greater than 1 and multiply the target notification probabilities for all time slots by this correction coefficient. For example, if the target number of notifications is two but a maximum of one message has been notified per day over the past month, the target notification probabilities for all time slots may be corrected to double. With this configuration, it is possible to bring the notification probability for each time slot closer to the target notification probability at the time of initial setting throughout the entire notification target period.

[0127] The notification condition setting unit 13 may correct the target notification probability to a larger value if the frequency at which it is determined whether or not to execute notification for each time slot is lower than a predetermined threshold. Specifically, the notification condition setting unit 13 may define a correction coefficient greater than 1 and multiply the target notification probability by the correction coefficient. The frequency at which it is determined whether or not to execute notification for each time slot is synonymous with the input frequency of determination request data for each time slot. The predetermined threshold may be set based on at least one of the upper limit number of notifications or the target notification probability. With this configuration, it is possible to bring the notification probability for each time slot closer to the target notification probability at the time of initial setting.

[0128] If the maximum actual value of the number of notifications per notification period is less than the upper limit number of notifications, the notification condition setting unit 13 may correct the upper limit number of notifications to a larger value. Specifically, the notification condition setting unit 13 may define a correction coefficient greater than 1 and multiply the upper limit number of notifications by the correction coefficient. For example, if the upper limit number of notifications is 4 but a maximum of two messages have been notified per day in the past month, the upper limit number of notifications may be corrected to 8. By calculating the control notification probability according to the corrected upper limit number of notifications, it is expected that a maximum of four messages will be notified per day in the next month. In this way, with this configuration, it is possible to bring the number of notifications per notification period closer to the initial setting upper limit number of notifications.

[0129] <4.2. Operational processing example> FIG. 7 is a flowchart showing an example of the flow of the notification condition setting process executed by the system 1 according to this embodiment.

[0130] 7, first, the notification condition setting unit 13 sets a notification condition (step S202). When this step is executed for the first time, the notification condition setting unit 13 sets an upper limit number of notifications and a target notification probability list specified externally by the operator or user of the system 1, and sets a time block accordingly. On the other hand, when this step is executed for the second or subsequent time and a correction coefficient is calculated in step S208 (described later), the notification condition setting unit 13 corrects at least one of the upper limit number of notifications or the target notification probability based on the correction coefficient.

[0131] Next, the control notification probability calculation unit 14 generates a control notification probability list based on the notification conditions set by the notification condition setting unit 13 (step S204). In detail, the control notification probability calculation unit 14 calculates a control coefficient for each time slot using the above formula (1), and then multiplies the control coefficient by the target notification probability to calculate the control notification probability for each time slot.

[0132] Next, the notification condition setting unit 13 determines whether to update the notification conditions (step S206). As an example, the notification condition setting unit 13 determines to update the notification conditions when a predetermined time (for example, one week) has passed since the notification conditions were last updated. As another example, the notification condition setting unit 13 determines to update the notification conditions when the difference between the upper limit number of notifications and the target notification probability and the corresponding actual values ​​is equal to or greater than a predetermined threshold.

[0133] If it is determined that the notification condition is to be updated (step S206: YES), the notification condition setting unit 13 calculates at least one of a correction coefficient for the upper limit number of notifications or a correction coefficient for the target notification probability (step S208). After that, the process returns to step S202.

[0134] If it is determined that the notification condition is not to be updated (step S206: NO), the process returns to step S202.

[0135] <5. Effects> The technical features of the system 1 according to this embodiment have been described above. Below, the effects of the system 1 will be described while explaining a comparative example.

[0136] As explained above, the number of times a message can be notified in one time block is limited to a maximum of one. This makes it possible to avoid the situation that occurred in the comparative example, where message notifications are distributed to time periods not intended by the notification organizer. As a result, users are less likely to find message notifications annoying, and it is possible to prevent a decrease in the rate at which messages are viewed.

[0137] As explained above, the controlled notification probability is set taking into consideration that the number of times a message is notified in one time block is limited to a maximum of one. This satisfies the upper limit on the number of notifications and realizes message notifications in distributed time periods that are substantially in line with the target notification probability list. This makes it possible to notify messages in accordance with the user's lifestyle or the intentions of the notification organizer.

[0138] As described above, the notification conditions are updated based on the judgment performance data. As a result, for example, if a change in the user's behavioral characteristics makes it difficult for the user to receive a message in a specific time slot, the target notification probability for that time slot can be increased to make it easier for the user to receive the message. Alternatively, by increasing the overall target notification probability or upper limit number of notifications, including other time slots, the decrease in the message notification probability for that specific time slot can be compensated for by increasing the overall message notification probability. In this way, stable message notification can be achieved in accordance with the target notification probability and upper limit number of notifications initially set.

[0139] <5. Hardware configuration example> Next, the hardware configuration of an information processing device according to this embodiment will be described with reference to Fig. 12. Fig. 12 is a block diagram showing an example of the hardware configuration of an information processing device according to this embodiment. Note that the information processing device 900 shown in Fig. 12 may realize, for example, the server 10 or the user terminal 20 shown in Fig. 1. Information processing by the server 10 or the user terminal 20 according to this embodiment is realized by cooperation between software and hardware described below.

[0140] As shown in FIG. 12, the information processing device 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.

[0141] The CPU 901 functions as an arithmetic processing unit and control unit, and controls the overall operation of the information processing device 900 in accordance with various programs. The CPU 901 may also be a microprocessor. The ROM 902 stores programs used by the CPU 901, calculation parameters, etc. 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 that is composed of a CPU bus, etc. The CPU 901 may form, for example, a status collection unit 11, a message notification unit 12, a notification condition setting unit 13, a control notification probability calculation unit 14, and a notification determination unit 15 shown in FIG. 1 .

[0142] The host bus 904 is connected to an external bus 906, such as a PCI (Peripheral Component Interconnect / Interface) bus, via a bridge 905. It is not necessary to configure the host bus 904, bridge 905, and external bus 906 separately, and these functions may be implemented on a single bus.

[0143] The input device 908 is composed of input means for a user to input information, such as a mouse, keyboard, touch panel, button, microphone, switch, or lever, and an input control circuit that generates an input signal based on the user's input and outputs it to the CPU 901. A user operating the information processing device 900 can input various data and instruct the information processing device 900 to perform processing operations by operating the input device 908. The input device 908 may also be formed by a device that detects information about the user. For example, the input device 908 may include various sensors such as an image sensor (e.g., a camera), a depth sensor (e.g., a stereo camera), an acceleration sensor, a gyro sensor, a geomagnetic sensor, a light sensor, a sound sensor, a distance sensor, and a force sensor. The input device 908 may also acquire information about the state of the information processing device 900 itself, such as the attitude and movement speed of the information processing device 900, or information about the surrounding environment of the information processing device 900, such as the brightness or noise around the information processing device 900. The input device 908 may also include a GNSS module that receives GNSS signals from GNSS (Global Navigation Satellite System) satellites (e.g., GPS signals from GPS (Global Positioning System) satellites) to measure location information including latitude, longitude, and altitude of the device. The input device 908 may acquire environmental behavior data, for example, at the user terminal 20.

[0144] The output device 909 may include, for example, a display device that outputs visual information, such as a liquid crystal display (LCD) device, an OLED (Organic Light Emitting Diode) device, or a lamp. The output device 909 may include an audio output device that outputs auditory information, such as a speaker. The output device 909 may include a haptic presentation device that outputs haptic information, such as an eccentric motor. The output device 909 may output a message as visual information, auditory information, or haptic information to the user terminal 20, for example.

[0145] 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, and a deleting device for deleting data recorded on the storage medium. The storage device 910 is configured, for example, with an HDD (Hard Disk Drive). This storage device 910 drives a hard disk and stores programs executed by the CPU 901 and various data. The storage device 910 may store environmental behavior data and judgment performance data in the server 10, for example.

[0146] The communication device 911 is, for example, a communication interface configured with a communication device for connecting to a network. The communication device 911 may support either wireless communication or wired communication. The communication device 911 may perform communication between the server 10 and the user terminal 20, for example.

[0147] The above describes an example of a hardware configuration capable of realizing the functions of the information processing device 900 according to this embodiment. Each of the above components may be realized using general-purpose components, or may be realized by hardware specialized for the function of each component. Therefore, the hardware configuration used can be changed as appropriate depending on the technical level at the time of implementing this embodiment.

[0148] <6. Supplementary Information> Although the preferred embodiments of the present invention have been described in detail above with reference to the accompanying drawings, the present invention is not limited to these examples. It is clear that a person skilled in the art to which the present invention pertains can conceive of various modifications and alterations within the scope of the technical ideas set forth in the claims, and it is understood that these also naturally fall within the technical scope of the present invention.

[0149] (1) First Modification In the above embodiment, an example has been described in which the notification determination unit 15 determines whether or not to perform message notification up to once per time slot, but the present invention is not limited to this example.

[0150] The notification determination unit 15 may determine whether or not to execute a message notification for each time slot without an upper limit. In other words, the message notification unit 12 may output determination request data to the notification determination unit 15 multiple times in one time slot.

[0151] In this case, however, the notification condition setting unit 13 corrects the target notification probability by dividing it by the number of times that the user's situation data matches the notification implementation criteria. For example, if the number of times that determination request data is input in a certain time slot is N, the notification condition setting unit 13 corrects the target notification probability for that time slot to 1 / N. As a result, when N times of determination request data are input to the notification determination unit 15 in that time slot, it is expected that the probability that notification is determined to be possible in that time slot will match the target notification probability before correction.

[0152] Note that a predicted value or a past actual value may be used as the number of times (i.e., N) that the user's situation data used to correct the target notification probability matches the notification implementation criteria. Also, a common value for all time slots may be used as the number of times that the user's situation data used to correct the target notification probability matches the notification implementation criteria, or a different value may be used for each time slot. Note that the target notification probability before being corrected to 1 / N is used to set the time block.

[0153] (2) Other Although the above description is of an example in which the notification period is from 9:00 to 19:00 every day, the present invention is not limited to such an example. Also, although the description is of an example in which the time slot has a length of one hour, the present invention is not limited to such an example. These may be set arbitrarily. For example, in the case of an application for health management of shift workers, the notification period (1 week x 24 hours) and time slot (e.g., 10 minutes) may be set according to the weekly shift work schedule (i.e., shift roster).

[0154] Although the above describes an example in which the notification target period is a continuous period, the present invention is not limited to such an example. For example, in the case of a service in which messages are sent to a user group including multiple users in sequence at regular intervals, a notification target period including multiple time slots that are not necessarily consecutive may be set for each user.

[0155] Although the above describes an example in which a set of one or more consecutive time slots is set as one time block, the present invention is not limited to such an example. A set of multiple time slots that are not necessarily consecutive may be set as one time block.

[0156] Although the example in which the notification condition setting unit 13 updates the notification conditions based on the determination result data has been described above, the present invention is not limited to this example. The notification condition setting unit 13 does not have to update the notification conditions.

[0157] Although the above describes an example in which the control coefficient is calculated based on Equation (1), the present invention is not limited to such an example. The control coefficient may be set to a larger value the later the time slot in the time block (i.e., the longer the time that has elapsed since the start of the time block), and the calculation method may be any method.

[0158] In the above, the user terminal 20 carried by the user is given as an example of a terminal device that outputs a message to the user, but the present invention is not limited to this example. The terminal device may be a device installed in the environment, such as a personal computer (PC) or digital signage. Alternatively, the terminal device may be a robot, such as a communication robot.

[0159] Each device described in this specification may be realized as a single device, or some or all of them may be realized as separate devices. For example, at least one of the components included in the server 10 shown in FIG. 1 may be included in the user terminal 20.

[0160] The series of processes performed by each device described herein may be implemented using software, hardware, or a combination of software and hardware. The software programs may be stored in advance, for example, on a recording medium (more specifically, a non-transitory computer-readable storage medium) internal or external to each device. Each program is loaded into a random access memory (RAM) and executed by a processing circuit such as a central processing unit (CPU). The recording medium may be, for example, a magnetic disk, an optical disk, a magneto-optical disk, or a flash memory. The computer program may be distributed, for example, via a network without using a recording medium. The computer may be an application-specific integrated circuit (ASIC), a general-purpose processor that executes functions by loading a software program, or a computer on a server used in cloud computing. The series of processes performed by each device described herein may be centrally processed by a single computer or distributed across multiple computers. Furthermore, in each of the above embodiments, two or more communication means present in one device may be physically implemented on a single medium.

[0161] Furthermore, the processes described herein using flowcharts or sequence diagrams do not necessarily have to be performed in the order shown. Some process steps may be performed in parallel. Furthermore, additional process steps may be employed, and some process steps may be omitted. [Explanation of symbols]

[0162] 1 System 10 Servers 11 Situation Collection Department 12 Message notification section 13 Notification condition setting section 14 Control notification probability calculation unit 15 Notification judgment section 20 User terminal

Claims

1. a notification condition setting unit that divides the notification period into time blocks including one or more time slots based on an upper limit number of notifications in the notification period and a target notification probability for each time slot into which the notification period is divided; a notification determination unit that determines whether or not to notify a target person; Equipped with the notification determination unit determines whether to execute the notification based on the target notification probability of the time slot to which the time belongs, when the notification has not been executed in the time block to which the time when the situation data of the subject person matches a notification execution criterion belongs, and determines not to execute the notification when the notification has already been executed. Information processing device.

2. the notification determination unit determines whether to execute the notification based on a control notification probability calculated by multiplying the target notification probability by a control coefficient set for each of the time slots; the control coefficient is set to a larger value for the later time slot in the time block; The information processing device according to claim 1 .

3. The control coefficient is set to satisfy the following equation: N is the number of time slots included in the time block, i is the order of the time slot within the time block; K ｉ is the control factor for the i-th time slot in the time block, P ｉ is the target notification probability for the i-th time slot within the time block; The information processing device according to claim 2 . [Equation 1]

4. the notification condition setting unit selects the time slots in a predetermined order until a cumulative sum of upper limit notification probabilities becomes 1 or greater, and sets a set of the selected one or more time slots as one time block; The upper limit notification probability is calculated by dividing the upper limit notification number by the sum of the target notification probabilities during the notification target period and multiplying the result by the target notification probability. The information processing device according to claim 1 .

5. the notification condition setting unit sets a set of one or more consecutive time slots as one time block. The information processing device according to claim 1 .

6. the notification determination unit determines whether or not to execute the notification up to once per time slot; The information processing device according to claim 1 .

7. the notification condition setting unit corrects the target notification probability by dividing it by the number of times that the situation data of the subject person matches the notification implementation criterion; the notification determination unit determines whether or not to execute the notification for each time slot without an upper limit. The information processing device according to claim 1 .

8. When an actual value of the notification probability for each time slot is smaller than the target notification probability for the time slot, the notification condition setting unit corrects the target notification probability for the time slot to a larger value. The information processing device according to claim 1 .

9. When a maximum value of the actual value of the number of notifications for each notification target period is smaller than the sum of the target notification probabilities, the notification condition setting unit corrects the target notification probabilities of all the time slots to a larger value. The information processing device according to claim 1 .

10. the notification condition setting unit corrects the target notification probability to a larger value when a frequency at which it is determined whether or not to perform the notification for each time slot is lower than a predetermined threshold value; The information processing device according to claim 1 .

11. When the maximum value of the actual number of notifications for each notification period is smaller than the upper limit number of notifications, the notification condition setting unit corrects the upper limit number of notifications to a larger value. The information processing device according to claim 1 .

12. Dividing the notification target period into time blocks including one or more of the time slots based on an upper limit number of notifications in the notification target period and a target notification probability for each time slot into which the notification target period is divided; determining whether to notify the target person; Including, Determining whether to execute the notification to the target person includes: determining whether to execute the notification based on the target notification probability of the time slot to which the time belongs when the notification has not been executed in the time block to which the time when the status data of the target person matches a notification execution criterion belongs, and determining not to execute the notification when the notification has already been executed. A computer-implemented information processing method.

13. an information processing device and a terminal device; Equipped with The information processing device includes: a notification condition setting unit that divides the notification period into time blocks including one or more time slots based on an upper limit number of notifications in the notification period and a target notification probability for each time slot into which the notification period is divided; a notification determination unit that determines whether or not to notify a target person; and the notification determination unit determines whether to execute the notification based on the target notification probability of the time slot to which the time belongs, when the notification has not yet been executed in the time block to which the time when the situation data of the subject person matches a notification execution criterion belongs; and determines not to execute the notification when the notification has already been executed; the terminal device outputs a message when the notification determination unit determines that the notification should be executed. Information processing system.

Images