Information processing device

Abstract

In the present invention, a nudge management device includes: a storage unit for storing information regarding nudge, which is a mechanism for urging a user to voluntarily take desirable action; an acquisition unit for acquiring nudge intervention information related to intervention of nudge; and a wear derivation unit for deriving and outputting nudge wear information indicating the degree of decrease in the effect of nudge related to the nudge intervention information.

Description

[Technical field]

[0001] One aspect of the present invention relates to an information processing device. [Background technology]

[0002] Patent Document 1 describes a system that encourages users to change their behavior by utilizing nudges that encourage users to voluntarily take actions that are desirable for individuals and society, based on cognitive bias. [Prior art documents] [Patent documents]

[0003] [Patent Document 1] JP 2020-140596 A Summary of the Invention [Problem to be solved by the invention]

[0004] In behavioral economics, the above-mentioned nudges are considered to wear out. Here, nudge wear out refers to the fact that the behavior change effect of a nudge decreases as a result of repeated interventions (recommendations to users). Until now, this type of nudge wear has not been properly taken into consideration.

[0005] The present invention has been made in consideration of the above-mentioned circumstances, and has an object to appropriately quantify the wear of a nudge. [Means for solving the problem]

[0006] An information processing device according to one embodiment of the present invention includes a memory unit that stores information about a nudge, which is a mechanism for encouraging a user to voluntarily take desirable behavior, an acquisition unit that acquires nudge intervention information, which is information related to nudge intervention, and a wear derivation unit that derives and outputs nudge wear information indicating the degree to which the effect of a nudge related to the nudge intervention information is decreasing based on the nudge intervention information.

[0007] In an information processing device according to one aspect of the present invention, nudge intervention information, which is information related to nudge intervention (information related to user intervention regarding a nudge), is acquired, and nudge wear-out information indicating the degree of decrease in the effect of a nudge is derived and output based on the nudge intervention information. In this way, by estimating (deriving) nudge wear-out information from information related to user nudge intervention (e.g., frequency of nudge intervention, etc.), it is possible to appropriately (highly accurately) quantify the wear-out of a nudge, for example, in cases where a nudge is wearing down (the behavior change effect of the nudge is decreasing) due to repeated nudge intervention. As described above, the information processing device according to one aspect of the present invention can appropriately quantify the wear-out of a nudge. Effect of the Invention

[0008] According to one aspect of the present invention, the wear of the nudge can be appropriately quantified. [Brief description of the drawings]

[0009] [Figure 1] FIG. 1 is a diagram explaining the process of encouraging users to change their behavior through nudges. [Diagram 2] FIG. 2 is a diagram illustrating the wear of the nudge. [Diagram 3] FIG. 3 is a functional block diagram of the nudge management device according to the first embodiment. [Figure 4] FIG. 4 is a diagram illustrating the wear calculation of a nudge. [Diagram 5] FIG. 5 is a diagram illustrating the wear calculation of a nudge. [Figure 6] FIG. 6 is a diagram for explaining the nudge recovery calculation. [Figure 7] FIG. 7 is a sequence diagram showing a wear update process for a nudge. [Figure 8] FIG. 8 is a functional block diagram of the nudge management device according to the second embodiment. [Figure 9] FIG. 9 is a diagram for explaining generation of wear features. [Figure 10]FIG. 10 is a diagram for explaining behavioral change estimation. [Figure 11] FIG. 11 is a diagram illustrating nudge selection. [Figure 12] FIG. 12 is a sequence diagram showing a nudge recommendation process. [Figure 13] FIG. 13 is a diagram illustrating a hardware configuration of the nudge management device according to the embodiment. DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS

[0010] Hereinafter, an embodiment of the present invention will be described in detail with reference to the accompanying drawings. In the description of the drawings, the same or equivalent elements are designated by the same reference numerals, and duplicated explanations will be omitted.

[0011] [First embodiment] First, the nudge described in this embodiment and the promotion of behavioral change in users using the nudge will be described with reference to Fig. 1 and Fig. 2. Fig. 1 is a diagram explaining a series of steps for promoting behavioral change in users by using a nudge. Fig. 2 is a diagram explaining the wear of a nudge.

[0012] A nudge is a mechanism or device based on cognitive bias that encourages a user to voluntarily take actions that are desirable for individuals and society. In this embodiment, an example will be described in which a nudge is a display such as a message displayed on a communication terminal such as a smartphone. In FIG. 1, a scene is assumed in which a user Y is heading to a bus stop 300 to board a bus. As shown in FIG. 1, it is assumed that the bus (next bus) that the user Y is expected to board is now highly crowded. In this case, for example, a push notification is sent to the communication terminal 100 such as a smartphone of the user Y through a predetermined application (for example, a bus app that assists with boarding a bus). The push notification is a notification related to a nudge that encourages a user to change his / her behavior, and specifically, a notification related to a nudge that encourages a user to board a bus (recommended bus) other than the next crowded bus.

[0013] As shown in FIG. 1, when user Y transitions from the push notification notified to the communication terminal 100 to the nudge screen, messages such as "Wait for an available following bus for a comfortable ride" and "10 points will be added to those who help see the bus off" are displayed along with information indicating that the next bus is crowded, and information indicating the scheduled departure time and congestion status of the recommended bus. This state of transition to the nudge screen is a state in which the user has "nudged." User Y checks the nudge screen and selects whether or not to change his or her originally planned action and take the action of "boarding the recommended bus."

[0014] In order to effectively encourage user Y to change his / her behavior (in the above example, to "take the recommended bus"), it is important to intervene with user Y with the most effective nudge at an appropriate timing. The appropriate timing for performing nudge intervention may be determined based on, for example, information acquired through an application of the communication terminal 100 ("bus app" in the above example) and location information of user Y. In this embodiment, detailed explanation of the timing for performing nudge intervention is omitted. For an effective nudge, for example, a nudge that has the highest behavior change effect in the current scene may be selected based on information acquired through an application of the communication terminal 100 ("bus app" in the above example). For example, in the above example where the bus to be boarded is crowded, when there are nudges that encourage a change in transportation means, nudges that encourage the user to forgo boarding, and nudges that encourage the user to make a detour, it is possible to select a nudge that encourages the user to forgo boarding, which is generally considered to be the most likely to be selected by the user.

[0015] Here, in behavioral economics, it is assumed that the behavior change effect of a nudge is not constant but changes. Specifically, as shown in FIG. 2, it is considered that the behavior change effect of a nudge that is administered to a user on a daily basis (continuously and long-term) gradually decreases. Hereinafter, such a decrease in the behavior change effect of a nudge administered to a user through an intervention may be referred to as "nudge wear." When the nudge is worn out, the user does not want to see the nudge (information), and it becomes difficult to encourage the user to change his / her behavior. On the other hand, when the nudge is not worn out, the user is likely to show interest in the nudge (information), and it is possible to effectively encourage the user to change his / her behavior. In this way, it is important to derive nudge wear information because it is possible to select a nudge that truly has a high behavior change effect by deriving nudge wear information. Below, the contents related to the derivation of nudge wear information will be explained in detail.

[0016] FIG. 3 is a functional block diagram of a nudge management device 10 (information processing device) included in the nudge recommendation system 1 according to the first embodiment. As shown in FIG. 3, the nudge recommendation system 1 includes an application 101 of a communication terminal 100 and the nudge management device 10. Note that the nudge recommendation system 1 actually includes applications 101 of a plurality of communication terminals 100 of different users, but for convenience of explanation, only the application 101 of one communication terminal 100 will be described here. The communication terminal 100 may be a terminal capable of wireless communication, such as a smartphone, a tablet terminal, or a PC terminal. The application 101 may be an application that can be activated in the communication terminal 100, such as the bus app that assists with bus boarding described above.

[0017] The nudge management device 10 is a device that manages information on multiple types of nudges and updates the nudge information based on information from an application 101. The nudge management device 10 includes an acquisition unit 11, a storage unit 12, a wear derivation unit 13, a recovery derivation unit 14, and an update unit 15.

[0018] The acquisition unit 11 acquires various information from the application 101. For example, the acquisition unit 11 acquires nudge intervention information, which is information related to the intervention of a nudge (information related to an intervention to a user regarding a nudge), for each of a plurality of types of nudges. The nudge intervention information may include, for example, the presence or absence of a push notification on the previous day, the presence or absence of a nudge intervention on the previous day, and the behavior change result on the previous day. Note that, in the following description, "the previous day" refers to the previous day as an example of a predetermined period, and may refer to a predetermined period other than the previous day (for example, the most recent three days, etc.). The presence or absence of a push notification here is information indicating whether or not a push notification has been made on the user's communication terminal 100 via the application 101. The presence or absence of a nudge intervention is information indicating whether or not a nudge has been viewed by the user on a nudge screen in response to a push notification. The behavior change result is information indicating whether or not the user has taken the behavior encouraged by the nudge.

[0019] The acquisition unit 11 further acquires user information related to the attributes of the user that affects the reduction in the effect of the nudge. The information related to the attributes of the user is information unique to the user according to the unique characteristics of the user. The user information may include, for example, the usage time of the communication terminal 100 (smartphone) on the previous day, whether or not the user has been vaccinated against the corona vaccine, and the corona infection status on the previous day. From the usage time of the communication terminal 100, it is possible to estimate how the user uses the communication terminal 100, so it is possible to estimate, for example, whether or not the user is a user who does not check the screen in detail, or whether or not the user is a user who sees through the psychological effects of a nudge. From the vaccination against the corona vaccine, it is possible to estimate the user's thoughts on risk. From the corona infection status, it is possible to estimate the current mental and physical health status of the user. The acquisition unit 11 may acquire other user information such as whether or not the user has visited a racecourse, whether or not the user has visited each tourist spot, and the number of points acquired related to the application 101. From the visit to a racecourse, it is possible to estimate the degree of the user's risk preference. The strength of conformity bias and the need for approval can be inferred from the visit to each tourist spot. The level of participation in the campaign can be inferred from the number of points acquired, and loss aversion and bias regarding gains can be inferred. All of the above user information can affect the reduction of the effectiveness of the nudge.

[0020] The acquisition unit 11 further acquires environmental information indicating the state of the user's external environment during a predetermined period. The user's external environment refers to elements that surround the user and may affect the user's behavior, and are elements that are not related to the user's attributes. The acquisition unit 11 may acquire, as environmental information, the weather of the previous day, the temperature of the previous day, the day of the previous day (whether it was a weekday or weekend), the number of coronavirus infections of the previous day, etc. These pieces of information are information that can be used to estimate whether or not the user will go out or take actions that may lead to crowding. In addition to the above-mentioned pieces of information, the acquisition unit 11 may acquire factors that may affect the user's behavior. The acquisition unit 11 stores the acquired pieces of information in the storage unit 12.

[0021] The storage unit 12 is a database that stores information on multiple types of nudges and stores information stored from the acquisition unit 11. The storage unit 12 stores, as information on multiple types of nudges, information that uniquely identifies the nudge (nudge ID), an intervention condition, the content of the action to be encouraged, a behavior change effect, an incentive, a behavior change means, and a nudge content, in association with each other. The intervention condition is information indicating what kind of case is a candidate for a nudge to be intervened in, and is defined, for example, as "when the bus to be boarded is crowded." The content of the action to be encouraged is the specific content of the action that the nudge encourages the user to take, and is defined, for example, as "take a subsequent bus that is not crowded." The behavior change effect is information indicating the degree (probability) that the user will take the action encouraged by the nudge when the nudge intervention is performed, and is defined, for example, as "10%." The incentive is an incentive that the user receives when the user performs the action encouraged by the nudge, and is defined, for example, as "10 points." The means of behavior change is information that indicates the means by which behavior change will be carried out, such as a message, image, or sound. The nudge content is information that indicates the specific content of the nudge (for example, the message content (the wording of the nudge) if it is a message). For example, several wordings are specified, such as "There is a rare open bus after this one!" and "Avoiding crowds is a contribution to society."

[0022] As the information stored in the memory unit 12 from the acquisition unit 11, for example, as shown in FIG. 4, a feature f_a1 indicating the presence or absence of a push notification on the previous day by 0 or 1, a feature f_a2 indicating the presence or absence of a nudge intervention on the previous day by 0 or 1, a feature f_a3 indicating the result of behavioral change on the previous day by 0 or 1, a feature f_a4 indicating whether the weather on the previous day was rainy by 0 or 1, a feature f_a5 indicating whether the weather on the previous day was sunny by 0 or 1, a feature f_a6 indicating whether the weather on the previous day was cloudy by 0 or 1, and a feature f_a7 indicating whether the weather on the previous day was snowy by 0 or 1. The storage device may store a feature f_a7 indicating the temperature of the previous day, a feature f_a8 indicating the temperature of the previous day, a feature f_a9 indicating whether the previous day was a weekday with 0 or 1, a feature f_a10 indicating whether the previous day was a weekend with 0 or 1, a feature f_a11 indicating the time spent using a smartphone on the previous day, a feature f_a12 indicating whether the user has been vaccinated with a corona vaccine with 0 or 1, a feature f_a13 indicating the corona infection status on the previous day with 0 or 1, a feature f_a14 indicating the number of corona infections on the previous day, and a feature f_an indicating factors that may affect the behavior of other users. FIG. 4 shows the features of Examples 1 to 3 acquired by the acquisition unit 11 at different times.

[0023] The wear derivation unit 13 is configured to derive and output nudge wear information indicating the degree of decrease in the effect of the nudge related to the nudge intervention information based on the nudge intervention information. As described above, the nudge intervention information is information including, for example, the presence or absence of a push notification on the previous day, the presence or absence of a nudge intervention on the previous day, and the behavior change effect on the previous day. The wear derivation unit 13 may derive nudge wear information for each of a plurality of types of nudges. The wear derivation unit 13 identifies each feature amount related to the nudge intervention information by referring to the information stored in the storage unit 12, and derives nudge wear information based on the value of each identified feature amount. In the example shown in FIG. 4, the feature amount f_a1 indicating the presence or absence of a push notification on the previous day is set to 1 when there is a notification and 0 when there is no notification. In addition, the feature amount f_a2 indicating the presence or absence of a nudge intervention on the previous day is set to 1 when there is an intervention and 0 when there is no intervention. In addition, feature f_a3, which indicates the behavioral change results for the previous day, is set to 1 if there was a behavioral change (if the user took the behavior encouraged by the nudge) and 0 if there was no behavioral change (if the user did not take the behavior encouraged by the nudge).

[0024] When there is no push notification on the previous day (f_a1=0) or when there is no nudge intervention on the previous day (f_a2=0), the wear derivation unit 13 derives nudge wear information indicating that wear has not occurred, with abrasion(date)=0, which indicates wear. This is because it can be determined that the nudge has not worn out because there is no nudge intervention. For example, in the cases of Example 1 and Example 2 in FIG. 4, nudge wear information indicating that wear has not occurred is derived.

[0025] On the other hand, when there was a push notification on the previous day (f_a1=1) and a nudge intervention on the previous day (f_a2=1), the wear derivation unit 13 further considers the user information and the environmental information to derive the nudge wear information. As described above, the user information is information including, for example, the smartphone usage time on the previous day, whether or not the user has been vaccinated with the corona vaccine, and the corona infection status on the previous day. In the example shown in FIG. 4, the feature f_a11 indicating the smartphone usage time on the previous day is set to a value between 0 and 24 hours. In addition, the feature f_a12 indicating the presence or absence of the corona vaccine is set to 1 if the user has been vaccinated and 0 if the user has not been vaccinated. In addition, the feature f_a13 indicating the corona infection status on the previous day is set to 1 if the user is infected and 0 if the user is not infected.

[0026] As described above, the environmental information is information including, for example, the weather of the previous day, the temperature of the previous day, the day of the week of the previous day (whether it was a weekday or a weekend), and the number of coronavirus infections of the previous day. In the example shown in FIG. 4, the feature value f_a4 indicating whether the weather of the previous day was rainy or not is set to 1 if it was rainy and 0 if it was not rainy. The feature value f_a5 indicating whether the weather of the previous day was sunny or not is set to 1 if it was sunny and 0 if it was not sunny. The feature value f_a6 indicating whether the weather of the previous day was cloudy or not is set to 1 if it was cloudy and 0 if it was not cloudy. The feature value f_a7 indicating whether the weather of the previous day was snowy or not is set to 1 if it was snowy and 0 if it was not snowy. The feature value f_a8 indicating the temperature of the previous day is set to a value indicating the temperature. The feature value f_a9 indicating whether the previous day was a weekday or not is set to 1 if it was a weekday and 0 if it was not a weekday. In addition, the feature f_a10 indicating whether the previous day was a Saturday or Sunday is set to 1 if it was a Saturday or Sunday, and 0 if it was not a Saturday or Sunday. In addition, the feature f_a14 indicating the number of COVID-19 infected people on the previous day is set to a value indicating the number of infected people.

[0027] When there was a push notification on the previous day (f_a1=1) and a nudge intervention on the previous day (f_a2=1), the wear derivation unit 13 takes into account user information and environmental information and derives abrasion(date), which indicates wear, using the following formula (1). In the formula below, wα is a weight and takes different values ​​depending on the model case. The abrasion(date), which indicates wear, is adjusted to take a value in the range of 0 to 1.

number

[0028] The weight wα may be derived, for example, by finding a regression equation using the least squares method or the like. The weight wα may also be derived, for example, from a correlation coefficient between each feature amount (column) and the behavior change result, which is the objective variable. The weight wα may also be derived, for example, by creating a machine learning model that predicts the behavior change result, which is the objective variable, and using the contribution rate of each feature amount (column).

[0029] By deriving the nudge wear information by the above formula (1), for example, a machine learning model predicting the behavior change result, which is the objective variable, may be used to derive a behavior change result that takes the nudge wear information into consideration for each of the examples (Examples 1 to 3) as shown in Fig. 5. In the example shown in Fig. 5, the behavior change result is set to 1 when it is predicted that there is a behavior change (when it is predicted that the user will take the behavior encouraged by the nudge), and 0 when it is predicted that there is no behavior change (when it is predicted that the user will not take the behavior encouraged by the nudge).

[0030] In addition, the wear derivation unit 13 has been described as deriving abrasion(date) indicating wear using the above formula (1) when there was a push notification on the previous day (f_a1=1) and a nudge intervention on the previous day (f_a2=1), but this is not limited to this, and wear information may be derived as follows. Now, an example will be described in which wear information is derived from the presence or absence of a push notification on the previous day (f1), the presence or absence of a nudge intervention on the previous day (f2), and the behavior change effect on the previous day (f3), which are nudge intervention information, and the number of visits to a certain tourist spot (f4), which is user information. For example, if the number of visits f4 exceeds 10, it is set to 10, and a value obtained by dividing by 10 is set. The weights of f1 to f4 in deriving wear information are 0.1, 0.2, 0.6, and 0.1, respectively. In this case, if f1=1, f2=1, f3=1, and f4=0.2, taking into account the weights, the wear is 0.1×1+0.2×1+0.6×1+0.1×0.2=0.92. If f1=1, f2=1, f3=0, and f4=0.2, the wear is 0.1×1+0.2×1+0.6×0+0.1×0.2=0.32.

[0031] The recovery derivation unit 14 is configured to derive and output nudge recovery information indicating the degree of recovery of the effect of the nudge related to the nudge intervention information based on the nudge intervention information. The nudge recovery information is information indicating the degree of recovery of a nudge that has once worn out. As described above, the nudge intervention information is information including, for example, the presence or absence of a push notification on the previous day, the presence or absence of a nudge intervention on the previous day, and the behavior change effect on the previous day. The recovery derivation unit 14 may derive nudge recovery information for each of a plurality of types of nudges. The recovery derivation unit 14 specifies each feature amount related to the nudge intervention information by referring to the information stored in the storage unit 12, and derives nudge recovery information based on the value of each specified feature amount. In the example shown in FIG. 6, the feature amount f_r1 indicating the presence or absence of a push notification on the previous day is set to 1 if there is a notification and 0 if there is no notification. In addition, the feature amount f_r2 indicating the presence or absence of a nudge intervention on the previous day is set to 1 if there is an intervention and 0 if there is no intervention. In addition, the feature f_r3, which indicates the behavioral change results for the previous day, is set to 1 if there was a behavioral change (if the user took the behavior encouraged by the nudge) and 0 if there was no behavioral change (if the user did not take the behavior encouraged by the nudge).

[0032] If there was a behavioral change on the previous day (f_r3=1), the recovery derivation unit 14 derives nudge recovery information indicating that the nudge has not recovered, with recovery(date)=0 indicating recovery. This is because if the user has recently changed their behavior due to the nudge, it is highly likely that the nudge has worn out and it can be determined that the nudge has not recovered. For example, in the case of Example 3 in FIG. 6, nudge recovery information indicating that the nudge has not recovered is derived.

[0033] On the other hand, when there was no behavioral change on the previous day (f_r3=0), the recovery derivation unit 14 derives nudge recovery information by further considering other information. In the example shown in Fig. 6, the other information includes the smartphone usage time on the previous day, the number of days since the last push notification, the number of days since the last nudge intervention, the number of days since the last behavioral change, and other factors that may affect the behavior.

[0034] When there was no behavioral change on the previous day (f_r3=0), the recovery derivation unit 14 takes into consideration the other information described above and derives recovery(date), which indicates recovery, using the following formula (2). In the formula below, wr is a weight and takes different values ​​depending on the model case. wr can be calculated, for example, in the same way as wα, which indicates a weight related to wear derivation. Recovery(date), which indicates recovery, is adjusted to take a value in the range of 0 to 1.

number

[0035] The update unit 15 is configured to update the information of the nudge stored in the memory unit 12 based on the nudge wear information and nudge recovery information. The update unit 15 acquires nudge wear information of each nudge from the wear derivation unit 13. The update unit 15 acquires nudge recovery information of each nudge from the recovery derivation unit 14. The update unit 15 acquires current wear information of each nudge from the nudge information stored in the memory unit 12. For each nudge, the update unit 15 derives the latest wear information based on the nudge wear information, nudge recovery information, and current wear information, and updates the information of each nudge stored in the memory unit 12 based on the derived wear information.

[0036] The update unit 15 may update the information of the one nudge by taking into consideration both the nudge wear information of the one nudge included in the multiple types of nudges and the nudge wear information of nudges similar to the one nudge.

[0037] For example, the wear of a nudge can be expressed by the recurrence equations (3) and (4) below.

number

number

[0038] Equation (3) indicates that when N=0, the nudge is not worn out. Equation (4) indicates that when deriving the wear-out F(N)I of a nudge, for each nudge, the recovery(date) indicating recovery is subtracted from the abrasion(date) indicating wear-out, and then the current wear information F(N-1)I is added together and a value is derived by multiplying it by the weight WI_J, and the values ​​of each nudge are added together to derive the wear-out FNI of the nudge. For nudges that are not similar to the nudge, the weight WI_J is set to 0. In this way, the wear-out of the nudge is derived by taking into account only the information of nudges that are similar to each other.

[0039] For example, suppose that the multiple types of nudges include Nudge A, Nudge B, and Nudge C, which are similar to each other. In this case, the wear F(N)A of Nudge A is derived from the following equation (5). In the following equation (5), WA_A is the weight when calculating the wear of Nudge A itself, WA_B is the weight used to calculate the wear of Nudge B when calculating the wear of Nudge A, and WA_C is the weight used to calculate the wear of Nudge C when calculating the wear of Nudge A. WA_B (or WA_C) is set based on the degree of similarity between Nudge A and Nudge B (or Nudge C).

number

[0040] The weight WI_J will be explained in detail. When deriving the wear of one nudge from the wear of multiple types of nudges, the wear weight of that one nudge (target nudge) is the largest. The higher the similarity of a nudge to the target nudge, the larger the wear weight is. A high similarity means that the overlap of cognitive biases (psychological biases) associated with the nudge is high. For example, suppose that biases a, b, and c are associated with nudge A, biases b, c, and d are associated with nudge B, and bias d is associated with nudge C. In this case, for example, the similarity according to the overlap of biases may be derived based on [number of biases in common with the target nudge / unique number of biases of the two nudges].

[0041] In the above example, let us say that nudge A is the target nudge. In this case, WA_A has three biases in common with the target nudge (itself), and the unique number of biases in the two nudges is three, so the result is 3 / 3 = 1.0. WA_B has two biases in common with the target nudge, b and c, and the unique number of biases in the two nudges is four, a, b, c, and d, so the result is 2 / 4 = 0.5. WA_C has zero biases in common with the target nudge, and the unique number of biases in the two nudges is four, a, b, c, and d, so the result is 0 / 4 = 0. Having zero common biases indicates that the two nudges are not similar.

[0042] Similarly, suppose nudge B is the target nudge. In this case, the weight WB_A used to derive the wear of nudge A when calculating the wear of nudge B is 2 / 4=0.5, since the two common biases b and c are used with the target nudge, and the unique number of biases for the two nudges is a, b, c, and d, which is four. WB_B is also 1.0. The weight WB_C used to derive the wear of nudge C when calculating the wear of nudge B is 1 / 3=0.333..., since the one common bias d is used with the target nudge, and the unique number of biases for the two nudges is b, c, and d, which is three.

[0043] Next, the wear update process of the nudge will be described with reference to Fig. 7. Fig. 7 is a sequence diagram showing the wear update process of the nudge.

[0044] As shown in FIG. 7, various information including nudge intervention information is acquired from the application 101 by the acquisition unit 11 and stored in the storage unit 12 (step S11).

[0045] Then, the wear derivation unit 13 acquires information (including nudge intervention information) stored in the memory unit 12 (step S12). Then, the wear derivation unit 13 derives nudge wear information for each nudge based on the nudge intervention information, etc. (step S13).

[0046] Furthermore, the recovery derivation unit 14 acquires information (including nudge intervention information) stored in the storage unit 12 (step S14). Then, the recovery derivation unit 14 derives nudge recovery information for each nudge based on the nudge intervention information and the like (step S15).

[0047] Next, the derivation result of the nudge wear information by the wear derivation unit 13 is acquired by the update unit 15 (step S16), and the derivation result of the nudge recovery information by the recovery derivation unit 14 is acquired by the update unit 15 (step S17). In addition, the current wear information of each nudge is acquired by the update unit 15 from the storage unit 12 (step S18).

[0048] Then, the update unit 15 performs wear update processing based on the acquired information (step S19), and the wear update results are reflected in the information on each nudge stored in the storage unit 12 (step S20).

[0049] Next, the effects of the nudge management device 10 according to the first embodiment will be described.

[0050] The nudge management device 10 of this embodiment includes a memory unit 12 that stores information about nudges, which are mechanisms for encouraging a user to voluntarily take desirable behavior, an acquisition unit 11 that acquires nudge intervention information, which is information related to nudge intervention (information related to intervention in the user regarding nudges), and a wear derivation unit 13 that derives and outputs nudge wear information indicating the degree to which the effect of the nudge related to the nudge intervention information is decreasing based on the nudge intervention information.

[0051] In the nudge management device 10 according to this embodiment, nudge intervention information, which is information related to nudge intervention (information related to user intervention regarding a nudge), is acquired, and nudge wear-out information indicating the degree of decrease in the effect of a nudge is derived and output based on the nudge intervention information. In this way, by estimating (deriving) nudge wear-out information from information related to user nudge intervention (e.g., frequency of nudge intervention, etc.), it is possible to appropriately (highly accurately) quantify the wear-out of a nudge, for example, in cases where a nudge is wearing out (the behavior change effect of a nudge is decreasing) due to repeated nudge intervention. As described above, the nudge management device 10 according to this embodiment can appropriately quantify the wear-out of a nudge.

[0052] By appropriately quantifying the wear of a nudge, for example, there are the following advantages. First, when recommending a nudge to a user, it becomes possible to make a recommendation that takes into account the wear of the nudge. Recommendations can be made based on the magnitude relationship of the numerical values, or the quantified wear can be used as a feature of machine learning related to the recommendation. Recommendations that take wear into account will be described in detail in the second embodiment. Second, it becomes possible to identify nudges that are generally prone to wear. By calculating the average wear of each nudge at the time when a certain amount of data has been collected, it is possible to identify nudges that are prone to wear and those that are difficult to wear, and to use this information in considering new nudges based on the cognitive bias associated with them. Third, it is possible to identify the upper limit of wear. The upper limit of wear here refers to a value that does not wear out any more, or a value that does not change the effect even if the apparent wear number increases. By identifying the upper limit of wear in a usage scenario, it becomes possible to determine whether it is meaningless to apply a nudge continuously any more. Fourth, the accuracy of verifying the recovery of the nudge and collecting data is improved. When verifying the recovery of a nudge or collecting data under specific conditions, it is possible to intentionally wear down the nudge and then perform a nudge intervention under the same conditions. In this case, because the wear is quantified, it is possible to verify the recovery of the nudge and collect data after appropriately adjusting the conditions.

[0053] Returning to the explanation of the action and effect, the nudge intervention information may include at least information indicating whether the nudge was viewed by the user within a predetermined period of time and information indicating whether the user took the action encouraged by the nudge. With such a configuration, it is possible to specify whether the nudge was an intervention for the user (viewed by the user) and whether the user actually changed their behavior due to the nudge, and therefore it is possible to more appropriately derive the wear of the nudge based on information closely related to the wear of the nudge.

[0054] The acquisition unit 11 may further acquire user information related to the attributes of the user and affecting the reduction in the effect of the nudge, and the wear derivation unit 13 may derive the nudge wear information by further considering the user information. According to such a configuration, the nudge wear information is derived by further considering information related to the attributes of the user, such as the time spent using a smartphone or whether or not the user has visited a specific place, which may affect the reduction in the effect of the nudge, so that the wear of the nudge can be more suitably derived.

[0055] The acquisition unit 11 may further acquire environmental information indicating the state of the user's external environment during a predetermined period, and the wear derivation unit 13 may derive the nudge wear information by further taking into account the environmental information. According to this configuration, the nudge wear information is derived by further taking into account environmental information indicating the state of the user's external environment, such as the weather and the number of people infected with COVID-19, so that the wear of the nudge can be more suitably derived.

[0056] The nudge management device 10 may further include an update unit 15 that updates, based on the nudge wear information, the nudge information related to the nudge intervention information stored in the storage unit 12. In this way, the quantified and derived nudge wear information is used to update the nudge information in the storage unit 12, so that the nudge wear information can be reflected in the original nudge information.

[0057] The storage unit 12 stores information on a plurality of types of nudges, the wear deriving unit 13 derives nudge wear information for each of the plurality of types of nudges, and the update unit 15 may update the information on a single nudge by considering both the nudge wear information of a single nudge included in the plurality of types of nudges and the nudge wear information of a nudge similar to the single nudge. For example, if a nudge similar to a single nudge is repeatedly intervened by a user, it is considered that the single nudge will also wear out due to the influence. In this regard, when updating the information on a single nudge, by considering not only the wear information of the single nudge but also the nudge wear information of a nudge similar to the single nudge, the information on the single nudge can be updated based on a wear state that is more in line with the actual state of the single nudge.

[0058] The nudge management device 10 further includes a recovery derivation unit 14 that derives nudge recovery information indicating the degree of recovery of the effect of the nudge related to the nudge intervention information based on the nudge intervention information, and the update unit 15 may update the nudge information related to the nudge intervention information by further taking the nudge recovery information into consideration. For example, even if a nudge has worn out once due to repeated intervention by a user, it is considered that the effect of the nudge will recover if no intervention is performed for a predetermined period of time. For this reason, the nudge recovery information is derived based on the nudge intervention information, and the nudge information is updated taking the nudge recovery information into consideration, so that the nudge information can be updated with information that is more in line with the actual situation.

[0059] [Second embodiment] Next, a nudge management device 10A (information processing device) included in a nudge recommendation system 1A according to a second embodiment will be described with reference to Fig. 8 to Fig. 12. In the second embodiment, descriptions common to the first embodiment will be omitted, and differences from the first embodiment will be mainly described.

[0060] 8 is a functional block diagram of a nudge management device 10A included in a nudge recommendation system 1A according to the second embodiment. The nudge management device 10A has a function of recommending to a user a nudge with a high probability of behavioral change, which is the probability that the user will take the behavior encouraged by the nudge, taking into account the wear of the nudge.

[0061] As shown in FIG. 8, the nudge management device 10A includes an acquisition unit 11, a storage unit 12, a wear feature amount generation unit 16 (wear derivation unit), a behavior change estimation unit 17, and a nudge selection unit 18.

[0062] The acquisition unit 11 acquires various pieces of information linked to each other from the application 101 when a specific condition is satisfied. The specific condition is a specific condition that may recommend a nudge to the user, and specifically, for example, checking in to a specific spot (such as a store). The acquisition unit 11 acquires, for example, nudge intervention information. In this case, the nudge intervention information may include, for example, the presence or absence of a push notification on the previous day, a planned intervention nudge, the presence or absence of a nudge intervention on the previous day, and the behavior change result on the previous day. The planned intervention nudge is a nudge that was scheduled to be intervened in (or was actually intervened in) by the user when the user opened the push notification.

[0063] The acquisition unit 11 may also acquire user information, which is information related to the attributes of the user, as information included in the various information. The user information is, for example, a user ID that uniquely identifies the user, gender, age, family structure, etc. The acquisition unit 11 may also acquire information such as weather, temperature, day of the week, the user's smartphone usage time, whether the user has been vaccinated against COVID-19, the user's COVID-19 infection status, the number of COVID-19 infected people on the previous day, and the user's close contact flag as other information included in the various information (feature amounts that are likely to contribute to behavior). The acquisition unit 11 stores the acquired information in the memory unit 12.

[0064] The wear feature generator 16 generates wear features expressing nudge wear information for each of a plurality of types of nudges based on the nudge intervention information. FIG. 9 is a diagram for explaining wear feature generation. FIG. 9(a) shows information (log) including nudge intervention information acquired by the acquisition unit 11 and stored in the storage unit 12. Such a log is record-generated each time a nudge is pushed. The wear feature generator 16 converts the log into wear features shown in FIG. 9(b).

[0065] In the example shown in FIG. 9(b), the wear features are exemplified as follows: a feature f_1 indicating a user ID; a feature f_2 indicating the number of days since the last push notification; a feature f_3 indicating the number of days since the push notification before last; a feature f_4 indicating the number of days since the last Nudge A intervention; a feature f_5 indicating the number of days since the Nudge A intervention before last; a feature f_6 indicating the number of days since the behavior change caused by the last Nudge A; a feature f_7 indicating the number of days since the behavior change caused by the Nudge A before last; a feature f_8 indicating the number of days since the last Nudge B intervention; ..., a feature f_16 indicating the number of days since the behavior change caused by the last Nudge D. Although omitted in FIG. 9(b), the same feature as Nudge A is defined for each nudge. Also, as shown in FIG. 9(b), the cumulative number of times each nudge has been used may be defined as a feature.

[0066] The behavior change estimation unit 17 estimates a behavior change probability, which is the probability that the user will take the behavior encouraged by the nudge. The behavior change estimation unit 17 estimates the behavior change probability for each of the multiple types of nudges based on the wear features related to the multiple types of nudges.

[0067] The behavior change estimation unit 17 generates an estimation model (machine learning model) that estimates the behavior change probability for each of multiple types of nudges based on the wear feature and user information. FIG. 10 is a diagram for explaining behavior change estimation, and in detail, a diagram for explaining the generation of an estimation model that estimates the behavior change probability. In the example shown in FIG. 10, the behavior change estimation unit 17 generates an estimation model that estimates the behavior change probability of nudge A using the wear feature, the user information such as user ID, gender, age, and family structure, and other information (features that are likely to contribute to behavior) such as weather, temperature, day of the week, user's smartphone usage time, whether the user has been vaccinated against the corona vaccine, the user's corona infection status, the number of corona infections on the previous day, and the user's close contact flag, and the behavior change result (objective variable) as learning data. Note that, as there are multiple records of learning data for examples 1 to 3 in FIG. 10, even for the same user, multiple learning data for the same nudge may exist depending on the difference in the timing of information acquisition (difference in nudge intervention scene).

[0068] The behavior change estimation unit 17 estimates a behavior change probability for each of the multiple types of nudges based on the estimation model. The behavior change estimation unit 17 inputs data similar to the learning data into each estimation model for each nudge, thereby estimating a behavior change probability for each nudge for the target user.

[0069] The nudge selection unit 18 selects a nudge to be recommended to the target user based on the behavior change probability. Specifically, the nudge selection unit 18 selects the nudge with the highest behavior change probability as the nudge to be recommended to the user. FIG. 11 is a diagram for explaining nudge selection. Consider an example of selecting the optimal nudge from Nudge A to Nudge C. Assume that estimated models (Nudge A model, Nudge B model, and Nudge C model) for each of Nudge A to Nudge C are generated for a certain target user (male, 25 years old). As shown in FIG. 11(a), in the first nudge intervention, the behavior change probability estimated from the Nudge A model is 0.6, the behavior change probability estimated from the Nudge B model is 0.5, and the behavior change probability estimated from the Nudge C model is 0.4. In this case, the nudge selection unit 18 selects the Nudge A with the highest behavior change probability as the nudge to be recommended. When Nudge A is most recently recommended, the behavior change probability of Nudge A is lowered in the Nudge A model, so that in the second nudge intervention, as shown in Figure 11(b), the behavior change probability estimated from the Nudge A model is 0.4, the behavior change probability estimated from the Nudge B model is 0.5, and the behavior change probability estimated from the Nudge C model is 0.4. In this case, the nudge selection unit 18 selects Nudge B, which has the highest behavior change probability, as the nudge to be recommended. In this way, the behavior change probability is updated based on the nudge intervention information, and the optimal nudge is selected.

[0070] Next, the nudge recommendation process will be described with reference to Fig. 12. Fig. 12 is a sequence diagram showing the nudge recommendation process.

[0071] As shown in FIG. 12, when a specific condition is satisfied, various information including nudge intervention information is acquired from the application 101 by the acquisition unit 11 and stored in the storage unit 12 (step S101).

[0072] Then, the wear feature generator 16 acquires log data including nudge intervention information stored in the memory 12 (step S102), and generates wear features of each nudge based on the log data (step S103).

[0073] Then, the behavior change estimation unit 17 acquires various features such as user information stored in the memory unit 12 (step S104), and acquires wear features of each nudge from the wear feature generation unit 16 (step S105).Based on the wear features and the user information, etc., the behavior change probability (ease of behavior change) of each nudge is estimated (step S106).

[0074] Next, the nudge selection unit 18 acquires the behavior change probability (effectiveness estimate) of each nudge, and selects a nudge to be recommended to the target user from among the multiple nudges based on the behavior change probability (step S108). The selected nudge is then recommended to the target user via the application 101 (step S109). Nudge intervention information about the recommended nudge is stored in the memory unit 12 via the acquisition unit 11 (step S110), and is used as log data for subsequent wear feature generation.

[0075] Next, the effects of the nudge management device 10A according to the second embodiment will be described.

[0076] The nudge management device 10A of this embodiment further includes a behavior change estimation unit 17 that estimates a behavior change probability, which is the probability that the user will take the action encouraged by the nudge, and a nudge selection unit 18 that selects a nudge to recommend to the user based on the behavior change probability, and the memory unit 12 stores information on multiple types of nudges, and the wear derivation unit has a wear feature generation unit 16 that generates wear features representing nudge wear information for each of the multiple types of nudges based on nudge intervention information, the behavior change estimation unit 17 estimates a behavior change probability for each of the multiple types of nudges based on the wear features related to the multiple types of nudges, and the nudge selection unit 18 selects the nudge with the highest behavior change probability as the nudge to recommend to the user.

[0077] In this way, based on the wear features that represent the nudge wear information, the probability of behavior change is estimated for each of multiple types of nudges, and the nudge with a high probability of behavior change is selected as the nudge to be recommended.By taking into account the nudge wear information, the probability of behavior change can be estimated with greater accuracy, and a nudge that can encourage the user to change their behavior can be suitably selected.

[0078] The behavior change estimation unit 17 may generate an estimation model that estimates the behavior change probability for each of the multiple types of nudges based on the wear feature and user information, which is information related to the user's attributes, and estimate the behavior change probability for each of the multiple types of nudges based on the estimation model. In this way, an estimation model is generated for each nudge taking into account the wear feature and user information, and the behavior change probability of each nudge is estimated based on the estimation model, making it possible to estimate the behavior change probability of each nudge more simply and accurately.

[0079] Next, the hardware configuration of the above-mentioned nudge management device 10, 10A will be described with reference to Fig. 13. The nudge management device 10, 10A may be physically configured as a computer device including a processor 1001, a memory 1002, a storage 1003, a communication device 1004, an input device 1005, an output device 1006, a bus 1007, and the like.

[0080] In the following description, the term "apparatus" may be interpreted as a circuit, a device, a unit, etc. The hardware configuration of the nudge management apparatus 10, 10A may be configured to include one or more of the apparatuses shown in the drawings, or may be configured to exclude some of the apparatuses.

[0081] Each function of the nudge management device 10, 10A is realized by loading a specific software (program) onto hardware such as a processor 1001 and a memory 1002, so that the processor 1001 performs calculations and controls communication via a communication device 1004 and the reading and / or writing of data in the memory 1002 and storage 1003.

[0082] The processor 1001, for example, operates an operating system to control the entire computer. The processor 1001 may be configured as a central processing unit (CPU) including an interface with peripheral devices, a control device, an arithmetic unit, a register, etc. For example, the control function of the acquisition unit 11, etc. may be realized by the processor 1001.

[0083] Moreover, the processor 1001 reads out programs (program codes), software modules, and data from the storage 1003 and / or the communication device 1004 into the memory 1002, and executes various processes according to the programs. As the programs, those that cause a computer to execute at least a part of the operations described in the above-mentioned embodiments are used.

[0084] For example, the control functions of the acquisition unit 11 and the like may be realized by a control program stored in the memory 1002 and running on the processor 1001, and the other functional blocks may be realized in a similar manner. Although the above-mentioned various processes have been described as being executed by one processor 1001, they may be executed simultaneously or sequentially by two or more processors 1001. The processor 1001 may be implemented in one or more chips. The program may be transmitted from a network via a telecommunication line.

[0085] The memory 1002 is a computer-readable recording medium, and may be composed of at least one of, for example, a Read Only Memory (ROM), an Erasable Programmable ROM (EPROM), an Electrically Erasable Programmable ROM (EEPROM), a Random Access Memory (RAM), etc. The memory 1002 may also be called a register, a cache, a main memory (primary storage device), etc. The memory 1002 can store a program (program code), software modules, etc. that are executable to implement a wireless communication method according to one embodiment of the present invention.

[0086] Storage 1003 is a computer-readable recording medium, and may be composed of at least one of, for example, an optical disk such as a CDROM (Compact Disc ROM), a hard disk drive, a flexible disk, a magneto-optical disk (e.g., a compact disk, a digital versatile disk, a Blu-ray® disk), a smart card, a flash memory (e.g., a card, a stick, a key drive), a floppy disk, a magnetic strip, and the like. Storage 1003 may be referred to as an auxiliary storage device. The above-mentioned storage medium may be, for example, a database, a server, or other suitable medium including memory 1002 and / or storage 1003.

[0087] The communication device 1004 is hardware (transmission / reception device) for communicating between computers via a wired and / or wireless network, and is also called, for example, a network device, a network controller, a network card, or a communication module.

[0088] The input device 1005 is an input device (e.g., a keyboard, a mouse, a microphone, a switch, a button, a sensor, etc.) that accepts input from the outside. The output device 1006 is an output device (e.g., a display, a speaker, an LED lamp, etc.) that performs output to the outside. The input device 1005 and the output device 1006 may be integrated into one device (e.g., a touch panel).

[0089] Furthermore, each device such as the processor 1001 and the memory 1002 is connected by a bus 1007 for communicating information. The bus 1007 may be configured as a single bus, or may be configured as different buses between the devices.

[0090] Furthermore, the nudge management device 10, 10A may be configured to include hardware such as a microprocessor, a digital signal processor (DSP), an application specific integrated circuit (ASIC), a programmable logic device (PLD), a field programmable gate array (FPGA), etc., and some or all of the functional blocks may be realized by the hardware. For example, the processor 1001 may be implemented by at least one of these pieces of hardware.

[0091] Although the present embodiment has been described in detail above, it is clear to those skilled in the art that the present embodiment is not limited to the embodiment described in this specification. The present embodiment can be implemented as a modified or altered form without departing from the spirit and scope of the present invention defined by the description of the claims. Therefore, the description in this specification is intended to be illustrative and does not have any limiting meaning on the present embodiment.

[0092] Each aspect / embodiment described herein may be applied to systems utilizing LTE (Long Term Evolution), LTE-Advanced (LTE-A), SUPER 3G, IMT-Advanced, 4G, 5G, FRA (Future Radio Access), W-CDMA (registered trademark), GSM (registered trademark), CDMA2000, UMB (Ultra Mobile Broadband), IEEE 802.11 (Wi-Fi), IEEE 802.16 (WiMAX), IEEE 802.20, UWB (Ultra-Wide Band), Bluetooth (registered trademark), or other suitable systems and / or next generation systems enhanced based thereon.

[0093] The steps, sequences, flow charts, etc. of each aspect / embodiment described herein may be reordered unless inconsistent, For example, the methods described herein present elements of various steps in an example order, and are not limited to the particular order presented.

[0094] The input and output information may be stored in a specific location (e.g., memory) or may be managed in a management table. The input and output information may be overwritten, updated, or added to. The output information may be deleted. The input information may be transmitted to another device.

[0095] The determination may be based on a value represented by a single bit (0 or 1), a Boolean value (true or false), or a numerical comparison (e.g., comparison with a predetermined value).

[0096] Each aspect / embodiment described in this specification may be used alone, in combination, or switched according to execution. In addition, notification of specific information (e.g., notification that "X is the case") is not limited to being done explicitly, but may be done implicitly (e.g., not notifying the specific information).

[0097] Software shall be construed broadly to mean instructions, instruction sets, code, code segments, program code, programs, subprograms, software modules, applications, software applications, software packages, routines, subroutines, objects, executable files, threads of execution, procedures, functions, etc., whether referred to as software, firmware, middleware, microcode, hardware description language, or otherwise.

[0098] Additionally, software, instructions, etc. may be transmitted or received over a transmission medium. For example, if the software is transmitted from a website, server, or other remote source using wired technologies, such as coaxial cable, fiber optic cable, twisted pair, and Digital Subscriber Line (DSL), and / or wireless technologies, such as infrared, radio, and microwave, these wired and / or wireless technologies are included within the definition of transmission media.

[0099] The information, signals, etc. described herein may be represented using any one of a variety of different technologies. For example, data, instructions, commands, information, signals, bits, symbols, chips, etc. that may be referred to throughout the above description may be represented by voltages, currents, electromagnetic waves, magnetic fields or magnetic particles, optical fields or photons, or any combination thereof.

[0100] In addition, terms explained in this specification and / or terms necessary for understanding this specification may be replaced with terms having the same or similar meanings.

[0101] Furthermore, the information, parameters, etc. described in this specification may be expressed as absolute values, may be expressed as relative values ​​from a predetermined value, or may be expressed as other corresponding information.

[0102] A communications terminal may also be referred to by those skilled in the art as a mobile communications terminal, subscriber station, mobile unit, subscriber unit, wireless unit, remote unit, mobile device, wireless device, wireless communications device, remote device, mobile subscriber station, access terminal, mobile terminal, wireless terminal, remote terminal, handset, user agent, mobile client, client, or some other suitable terminology.

[0103] As used herein, the phrase "based on" does not mean "based only on," unless expressly stated otherwise. In other words, the phrase "based on" means both "based only on" and "based at least on."

[0104] When designations such as "first," "second," etc. are used herein, any reference to an element is not intended to generally limit the quantity or order of those elements. These designations may be used herein as a convenient method of distinguishing between two or more elements. Thus, a reference to a first and a second element does not imply that only two elements may be employed therein or that the first element must precede the second element in some way.

[0105] To the extent that the terms "include," "including," and variations thereof are used herein in the specification or claims, these terms are intended to be inclusive, similar to the term "comprising." Further, the term "or" as used herein is not intended to be an exclusive or.

[0106] In this specification, a plurality of devices is also included unless the context or the technical basis clearly indicates that only one device is present.

[0107] Throughout this disclosure, the plural is intended to be included unless the context clearly indicates the singular. [Explanation of symbols]

[0108] 10, 10A... nudge management device (information processing device), 11... acquisition unit, 12... memory unit, 13... wear derivation unit, 14... recovery derivation unit, 15... update unit, 16... wear feature generation unit, 17... behavior change estimation unit, 18... nudge selection unit.

Claims

1. A storage unit that stores nudge information, which is a mechanism for encouraging a user to voluntarily take a desired action; An acquisition unit that acquires nudge intervention information, which is information related to the nudge intervention, from an application of one or more communication terminals; An information processing device comprising: a wear derivation unit that derives and outputs nudge wear information indicating the degree of reduction in the effect of the nudge related to the nudge intervention information based on the nudge intervention information, deriving the nudge wear information indicating that no wear has occurred for the nudge that has not been intervened in the nudge intervention information, and deriving the nudge wear information indicating that wear has occurred for the nudge that has been intervened in the nudge intervention information.

2. The information processing device of claim 1 , wherein the nudge intervention information includes at least information indicating whether the nudge was viewed by the user within a predetermined period of time and information indicating whether the nudge caused the user to take the action encouraged by the nudge.

3. 3. An information processing device as described in claim 1 or 2, further comprising an update unit that acquires current wear information of the nudge from the nudge information stored in the memory unit, derives latest wear information based on the nudge wear information and the current wear information, and updates the nudge information stored in the memory unit based on the derived latest wear information.

4. The storage unit stores information on a plurality of types of the nudges, The acquisition unit acquires the nudge intervention information for each of the plurality of types of nudges, The wear derivation unit derives the nudge wear information for each of the plurality of types of nudges based on the respective nudge intervention information; The information processing device of claim 3, wherein the update unit acquires current wear information of a nudge and current wear information of a nudge similar to the one nudge from the information of the multiple types of nudges stored in the memory unit, derives latest wear information based on the nudge wear information of the one nudge and the nudge similar to the one nudge and the current wear information of the one nudge and the nudge similar to the one nudge, and updates the information of the one nudge stored in the memory unit based on the derived latest wear information.

5. A recovery derivation unit derives nudge recovery information indicating a degree of recovery of the effect of the nudge related to the nudge intervention information based on the nudge intervention information, and further comprises a recovery derivation unit deriving the nudge recovery information indicating that the nudge in which the user has changed their behavior has not been recovered in the nudge intervention information, The information processing device of claim 3, wherein the update unit further acquires the nudge recovery information, derives latest wear information based on the nudge wear information, the nudge recovery information, and the current wear information, and updates the nudge information stored in the memory unit based on the derived latest wear information.

Images