Approach proposal device

The approach proposal device addresses the challenge of marketing to users with dissimilar inner values by estimating internal states, extracting positive example surfaces, and clustering users for personalized behavior change strategies, enhancing marketing effectiveness and user engagement.

WO2024241735A1PCT designated stage expired Publication Date: 2024-11-28NTT DOCOMO INC
View PDF 4 Cites 0 Cited by

Patent Information

Application Number
PCT/JP2024/014311
Authority / Receiving Office
WO · WO
Patent Type
Applications
Current Assignee / Owner
Priority Date
2023-05-19
Filing Date
2024-04-08
Publication Date
2024-11-28

AI Technical Summary

Technical Problem

Conventional marketing technologies are unable to effectively approach users with dissimilar inner values, limiting their ability to tailor marketing strategies to diverse customer groups.

Method used

An approach proposal device that estimates internal states of users using behavior data, extracts positive example inner surfaces, identifies clusters, and estimates behavior change approaches for each cluster, allowing for personalized marketing strategies even among users with dissimilar inner surfaces.

Benefits of technology

Enables targeted marketing approaches for users with different inner values by identifying clusters and tailoring behavior change strategies based on estimated internal states, improving marketing effectiveness and user engagement.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure JP2024014311_28112024_PF_FP_ABST
    Figure JP2024014311_28112024_PF_FP_ABST
Patent Text Reader

Abstract

An approach proposal device 10 is provided with: an inner aspect estimation unit 12 that obtains estimated inner aspects, which are results of estimating a plurality of inner aspects of users in a target user group, which is a set of users serving as targets, using behavioral data of the users; an inner aspect feature extraction unit 13 that uses the estimated inner aspects to extract positive example inner aspects, which are a plurality of inner aspects characteristic of a positive example user group, which is a set of users in the target user group who have a prescribed behavior; a cluster identification unit 15 that identifies a plurality of clusters for the target user group using at least some of the positive example inner aspects; and a behavioral change estimation unit 18 that estimates and outputs an approach for encouraging a behavioral change for each of the plurality of clusters on the basis of the estimated inner aspects.
Need to check novelty before this filing date? Find Prior Art

Description

Approach proposal device

[0001] The present invention relates to an approach suggestion device.

[0002] Marketing technologies have been proposed. Patent Document 1 discloses a technology for visualizing customer values ​​and conducting marketing tailored to customer needs. The technology described in Patent Document 1 calculates similarities corresponding to customer behavior and estimates the customer's financial values.

[0003] Patent Document 2 discloses a technology for improving the accuracy of appeals. The technology described in Patent Document 2 classifies consumer values ​​using all or part of the consumer's purchasing behavior or consciousness.

[0004] Patent Literature 3 discloses a technology that proposes an approach tailored to each user. The technology described in Patent Literature 3 takes the behavioral history of a user to be estimated as input and outputs estimated values ​​of characteristics related to consumption behavior.

[0005] JP 2019-46493 A JP 2021-43899 A JP 2022-96488 A

[0006] Conventional techniques have been able to approach users who share similar personalities, such as values, to the user, but have not been able to approach users who do not share similar personalities.

[0007] The present disclosure aims to provide a technology that can approach users who are not similar in personality.

[0008] An approach suggestion device according to one aspect of the present disclosure includes an inner state estimation unit that obtains estimated inner states, which are the results of estimating multiple inner states of users, for a target user group, which is a group of target users, using user behavioral data; an inner state feature extraction unit that uses the estimated inner states to extract positive example inner states, which are multiple inner states that are characteristic of a positive example user group, which is a group of users from the target user group who are engaging in predetermined behavior; a cluster identification unit that identifies multiple clusters for the target user group using at least a portion of the positive example inner states; and a behavior change estimation unit that estimates and outputs an approach to encourage behavior change for each of the multiple clusters, based on the estimated inner states.

[0009] An approach suggestion device according to one aspect of the present disclosure outputs, for each user in a target user group, an estimated inner state, which is the result of estimating multiple inner states from behavioral data. From the estimated inner state, positive inner states, which are multiple inner states characteristic of a positive example user group among the target user group, are extracted. A cluster is identified for each user using at least a portion of the positive example inner states. Then, for each cluster, an approach to encourage behavioral change is estimated based on the estimated inner state. With this configuration, inner states characteristic of a positive example user group are treated as positive example inner states, and an approach to encourage behavioral change is estimated for each cluster according to the estimated inner state. As a result, different approaches can be estimated for clusters with dissimilar inner states, for example. As a result, users with dissimilar inner states can also be approached via the clusters.

[0010] According to the present disclosure, it is possible to provide a technology that can approach users who do not have similar personalities.

[0011] FIG. 1 is a schematic diagram showing an example of a user. FIG. 2 is a block diagram showing an example of the functional configuration of an approach proposal system. FIG. 3 is a diagram showing an example of data used to create an inner self estimation model. FIG. 4 is a flowchart showing an example of the operation of the approach proposal device. FIG. 5 is a diagram showing an example of data acquired by an input unit. FIG. 6 is a diagram showing an example of data used in an inner self feature extraction unit. FIG. 7 is a diagram showing an example of an axis inner surface. FIG. 8 is a diagram showing an example of cluster classification. FIG. 9 is an example of a graph. FIG. 10 is a diagram showing an example of feature values. FIG. 11 is a diagram showing an example of data stored in a behavior change database. FIG. 12 is a diagram showing an example of the hardware configuration of an approach proposal system according to an embodiment of the present disclosure.

[0012] The present disclosure will be described with reference to the accompanying drawings. Whenever possible, the same parts are designated by the same reference numerals and redundant description will be omitted.

[0013] The approach suggestion system of the present disclosure estimates and outputs an approach that encourages a user to change their behavior. A user is, for example, a person who is a target of marketing. Behavioral change refers to a change in a user's behavior. An approach refers to an action or proposal method that influences behavior change. An approach is, for example, an activity or a text, or an advertisement or recommendation through an activity or a text, but is not limited to these. In the present disclosure, a group of target users is referred to as a "target user group." A group of users from the target user group who are engaging in a predetermined behavior is referred to as a "positive example user group." The predetermined behavior is, for example, an expected behavior. Examples of expected behavior include, but are not limited to, purchasing or traveling to a specific location.

[0014] FIG. 1 is a schematic diagram showing an example of a user. FIG. 1 shows a target user group T and a positive example user group P. In one example, the target user group T is a group of fans of an idol. The positive example user group P is a group of fans who attended an idol event. The predetermined behavior is attending an idol event. Examples of the event include a concert or a handshake event. The target user group T may include fans who attended the idol event and fans who did not attend the idol event.

[0015] 2 is a block diagram showing an example of the functional configuration of the approach proposal system 1. The approach proposal system 1 includes an approach proposal device 10 and a terminal 100. The approach proposal device 10 is communicably connected to the terminal 100 via a network or the like.

[0016] The terminal 100 is, for example, a computer used by a person using the approach proposal system 1. The type of the terminal 100 is not limited. For example, the terminal 100 may be a personal computer. The terminal 100 may also be a high-function mobile phone (smartphone), a tablet terminal, a wearable terminal, or the like.

[0017] The approach proposal device 10 includes, as functional elements, a model management unit 20, an input unit 11, an inner self estimation unit 12, an inner self feature extraction unit 13, an axis determination unit 14, a cluster identification unit 15, a graph drawing unit 16, an inner self feature calculation unit 17, and a behavior change estimation unit 18. The approach proposal device 10 also includes a behavior change database 30.

[0018] The model management unit 20 manages a machine learning model (hereinafter referred to as an "inner self estimation model") that estimates the user's inner self. The inner self is a concept that includes at least one of values, consciousness, personality, cognitive bias, and behavioral characteristics, for example. Examples of inner self include, but are not limited to, desire for recognition, extroversion, and assertiveness. The number of inner self is not limited, and may be, for example, 100. The model management unit 20 includes an inner self database 21, a behavior database 22, and a model creation unit 23. The model management unit 20 may be provided in a computer system separate from the approach proposal device 10.

[0019] The internal data database 21 is a non-transitory storage medium or storage device that stores internal data of some users. The some users may be part of the target user group T, or may be users other than the target user group T. The internal data is electronic data that indicates values ​​or parameters corresponding to each internal state. The internal data is acquired in advance, for example, by answering a questionnaire. In the questionnaire, question items and answer items are created based on, for example, a psychological scale. The internal data database 21 stores the internal data of users in association with a user ID. The user ID is an identifier that uniquely identifies a user.

[0020] The behavior database 22 is a non-transitory storage medium or storage device that stores behavior data of some users. The behavior data is electronic data that vectorizes the user's behavior. The behavior data can also be considered as behavior features. The behavior data is acquired in advance from some users' terminals, etc. Examples of behavior data include, but are not limited to, semantic vectors of app usage information, payment information, and location information. The behavior database 22 stores the behavior data in association with a user ID.

[0021] The model creation unit 23 creates an internal state estimation model using the internal state data and the behavioral data. For example, the model creation unit 23 associates the internal state data and the behavioral data by a user ID. FIG. 3 is a diagram showing an example of data used to create the internal state estimation model. FIG. 3 shows an example in which the internal state data and the behavioral data are associated by a user ID. In one example, a user ID "0001" is associated with a first vector "-0.7" and a second vector "2.3", which are behavioral data, and a need for recognition "0", which is internal state data. The first vector and the second vector are values ​​obtained by vectorizing different behaviors.

[0022] The model creation unit 23 creates an inner self estimation model by performing machine learning using behavioral data as an explanatory variable and inner self data as a target variable. The model creation unit 23 creates an inner self estimation model for each piece of inner self data. The learning method for the inner self estimation model is not limited. The model creation unit 23 may store the created inner self estimation model in a predetermined storage medium or storage device. The inner self estimation model outputs estimation results obtained by inputting behavioral data of the user and estimating multiple inner self aspects of the user. The estimation results can be represented by values ​​or parameters corresponding to each inner self.

[0023] Returning to FIG. 2 , the input unit 11 acquires various information of the target user group T. For example, the input unit 11 acquires a user ID, behavioral data, and information indicating a positive user. The information indicating a positive user is, for example, a flag indicating whether or not the user corresponds to the positive user group P (hereinafter referred to as a "positive user flag"). The input unit 11 may accept input of various information of the target user group T from, for example, the terminal 100. The input unit 11 may read out various information of the target user group T stored in advance in a predetermined storage unit or storage device.

[0024] The inner surface estimation unit 12 obtains an estimated inner surface, which is a result of estimating multiple inner surfaces of a user for a target user group T, using behavioral data of the user. For example, the inner surface estimation unit 12 estimates the user's inner surface by performing an extended estimation using an inner surface estimation model. The inner surface estimation unit 12 obtains an estimated inner surface of the user by inputting the user's behavioral data into the inner surface estimation model. The inner surface estimation unit 12 obtains an estimated inner surface of each user in the target user group T.

[0025] The inner surface feature extraction unit 13 uses the estimated inner surface to extract positive inner surfaces, which are multiple inner surfaces characteristic of the positive example user group P among the target user group T. For example, the inner surface feature extraction unit 13 compares the inner surfaces of the positive example user group P with the inner surfaces of the target user group T to extract positive inner surfaces. The positive inner surfaces are part of the estimated inner surfaces. An example of the extraction process of positive inner surfaces will be described later.

[0026] The axis determination unit 14 determines inner axis surfaces, which are multiple axes serving as references, based on the positive example inner surfaces. The inner axis surfaces are part of the positive example inner surfaces. The number of inner axis surfaces is not limited, and may be, for example, two or three. The inner axis surfaces can be used as axes of a graph. The graph is drawn by the graph drawing unit 16, which will be described later.

[0027] The cluster identification unit 15 identifies multiple clusters for a target user group using at least a portion of the positive example inner surfaces. For example, the cluster identification unit 15 identifies multiple clusters using an axis inner surface. The cluster identification unit 15 identifies multiple clusters by comparing the value of the axis inner surface of each user with a predetermined threshold. The predetermined threshold may be different for each axis inner surface or may be a common value. An example of the cluster identification process will be described later.

[0028] The graph drawing unit 16 draws a graph for each of the multiple clusters using the inner axis surfaces. For example, the graph drawing unit 16 draws a graph using the inner axis surfaces as axes. In one example, when there are two inner axis surfaces, the graph drawing unit 16 draws a two-axis graph.

[0029] The inner surface characteristic calculation unit 17 calculates a characteristic value for each estimated inner surface for each of the plurality of clusters. For example, the inner surface characteristic calculation unit 17 calculates the average value of each estimated inner surface for each cluster as the characteristic value.

[0030] The behavioral change estimation unit 18 estimates and outputs an approach to encourage behavioral change for each of the multiple clusters based on the estimated internal self. For example, the behavioral change estimation unit 18 estimates and outputs an approach to encourage behavioral change for each of the multiple clusters using internal self corresponding to a high value among the feature values. The behavioral change estimation unit 18 acquires various information from the behavioral change database 30 described below using internal self with a high feature value as an extraction condition. It can also be said that internal self with a high feature value indicates internal self with a low feature value. For example, it can also be said that a user with a high value of cooperativeness is a user with a low value of assertiveness. The behavioral change estimation unit 18 outputs the estimated approach.

[0031] The behavior change database 30 is a non-transitory storage medium or storage device that stores effective phrases or recommended actions for each internal state. It can also be said that the behavior change database 30 stores approaches that encourage behavior change according to internal states. The behavior change database 30 may be constructed as a single database or a collection of multiple databases. The location of the behavior change database 30 is not limited. For example, the behavior change database 30 may be provided in a computer system separate from the approach suggestion device 10.

[0032] An example of the operation method of the approach proposal device 10 will be described with reference to Figures 4 to 11. Figure 4 is a flowchart showing an example of the operation of the approach proposal device 10. In the flow of Figure 4, the explanation will be given assuming that an inner surface estimation model has already been created by the model management unit 20.

[0033] In step S1, the approach proposing device 10 acquires behavioral data of the target user group T. For example, the input unit 11 acquires the user IDs, behavioral data, and positive example user flags of the target user group T.

[0034] 5 is a diagram illustrating an example of data acquired by the input unit 11. For example, the input unit 11 acquires a user ID, a first vector and a second vector that are behavioral data, and a positive user flag. The first vector and the second vector indicate examples of behavioral data of the target user group T. The positive user flag is, for example, "0" if the user does not correspond to a positive user, and is "1" if the user corresponds to a positive user.

[0035] In one example, the input unit 11 acquires a first vector "-0.7" of a user corresponding to a user ID "0001," a second vector "2.3" of the user, and a positive example user flag "0" of the user. The input unit 11 acquires a first vector "1.2" of a user ID "0002," a second vector "-0.1" of the user, and a positive example user flag "1" of the user. The input unit 11 acquires a first vector "-0.5" of a user corresponding to a user ID "0003," a second vector "3" of the user, and a positive example user flag "0" of the user. The input unit 11 acquires a first vector "0.1" of a user corresponding to a user ID "0004," a second vector "1" of the user, and a positive example user flag "1" of the user.

[0036] Returning to FIG. 4 , in step S2, the approach proposal device 10 estimates multiple inner faces for each user in the target user group T. For example, the inner face estimation unit 12 estimates multiple inner faces using data such as that illustrated in FIG. 5 . The inner face estimation unit 12 obtains an estimated inner face, which is a result of estimating multiple inner faces of a user for the target user group T, using the user's behavioral data. The inner face estimation unit 12 obtains the estimated inner face of the user by inputting the user's behavioral data into an inner face estimation model. The inner face estimation unit 12 obtains the estimated inner face of each user in the target user group T.

[0037] In step S3, the approach proposal device 10 extracts a plurality of positive example inner surfaces. For example, the inner surface feature extraction unit 13 uses the estimated inner surface to extract positive example inner surfaces, which are a plurality of inner surfaces characteristic of the positive example user group P among the target user group T. The inner surface feature extraction unit 13 compares the inner surfaces of the positive example user group P with the inner surfaces of the target user group T to extract the positive example inner surfaces.

[0038] An example of the extraction process of positive example inner faces will be described with reference to Fig. 6. Fig. 6 is a diagram showing an example of data used by the inner face feature extraction unit 13. The inner face feature extraction unit 13 acquires data indicating the estimated inner faces of the target user group T and which users are positive example users. For example, the inner face feature extraction unit 13 acquires the estimated inner faces and positive example user flags associated with the user IDs.

[0039] The inner surface feature extraction unit 13 creates a machine learning model using the acquired data. For example, the inner surface feature extraction unit 13 performs machine learning using the estimated inner surface as a feature and the positive example user flag as training data. In the machine learning process, the inner surface feature extraction unit 13 extracts features that are strongly present in the positive example user group P. The inner surface feature extraction unit 13 may extract the strengths of the inner surface features of multiple positive examples.

[0040] For example, the internal feature extraction unit 13 extracts important features, which are features that contribute to the prediction of positive example users. For example, the internal feature extraction unit 13 extracts important features using SHAP (Shapely Additive exPlanations). The important features indicate the ranking of the strength of the internal features. The internal feature extraction unit 13 extracts the internal features that rank highest (for example, two or three) of the important features. The internal features that rank highest can be said to be features that appear strongly in the positive example user group P. The internal feature extraction unit 13 may output the internal features that rank highest as positive example internal features.

[0041] 4, if a positive inner surface is extracted in step S3 (YES in step S4), the process proceeds to step S5. If a positive inner surface is not extracted in step S3 (NO in step S4), the process ends.

[0042] In step S5, the approach proposing device 10 determines inner axis surfaces. For example, the axis determining unit 14 determines inner axis surfaces, which are multiple reference axes, based on the positive example inner surfaces. The axis determining unit 14 determines, from among the multiple positive example inner surfaces, a positive example inner surface having a strong characteristic as the inner axis surface. In one example, the axis determining unit 14 determines, from among the multiple positive example inner surfaces, two positive example inner surfaces as two inner axis surfaces.

[0043] The axis determination unit 14 may determine the inner axis surfaces based on the ranking of the strength of the features of the positive example inner surfaces. For example, the axis determination unit 14 may determine the top two inner positive example surfaces in terms of the strength of the features of the positive example inner surfaces as the two inner axis surfaces. The axis determination unit 14 may determine the inner positive example surfaces extracted by the inner surface feature extraction unit 13 according to the ranking of the strength as the inner axis surfaces.

[0044] 7 is a diagram showing an example of an inner axis. Fig. 7 shows "need for recognition" and "extroversion" as two inner axes. In this case, it can be said that "need for recognition" and "extroversion" are characteristics that are strongly present in the positive sample user group P.

[0045] Returning to FIG. 4 , in step S6, the approach proposal device 10 identifies a cluster for each user. For example, the cluster identification unit 15 identifies multiple clusters for the target user group using at least a portion of the positive example inner surfaces. The cluster identification unit 15 identifies multiple clusters using the axis inner surfaces. The cluster identification unit 15 identifies multiple clusters by comparing the value of the axis inner surface for each user with a predetermined threshold. In one example, the cluster identification unit 15 classifies users into clusters by comparing the value of the axis inner surface "desire for recognition" and the value of the axis inner surface "extroversion" with a predetermined threshold.

[0046] An example of the cluster identification process will be described with reference to Fig. 8. Fig. 8 is a diagram showing an example of cluster classification. Fig. 8 shows division into four quadrants based on the combination of the level of "desire for recognition" and the level of "extroversion." The classification of clusters is not limited to four.

[0047] The cluster identification unit 15 compares the value of the inner axis with a predetermined threshold and determines which of the clusters divided according to the combination of the inner axis the value belongs to, thereby identifying multiple clusters. For example, the cluster identification unit 15 determines whether the value of each inner axis is high or low based on a predetermined threshold. The cluster identification unit 15 may identify a user with a high "need for recognition" and high "extroversion" as cluster C1. The cluster identification unit 15 may identify a user with a low "need for recognition" and high "extroversion" as cluster C2. The cluster identification unit 15 may identify a user with a high "need for recognition" and low "extroversion" as cluster C3. The cluster identification unit 15 may identify a user with a low "need for recognition" and low "extroversion" as cluster C4.

[0048] Returning to FIG. 4 , in step S7, the approach proposal device 10 draws a graph. For example, the graph drawing unit 16 draws a graph using the inner axis surfaces for each of the multiple clusters. For example, the graph drawing unit 16 draws a graph using the inner axis surfaces as axes. In one example, when there are two inner axis surfaces, the graph drawing unit 16 draws a two-axis graph. The graph drawing unit 16 may display the drawn graph on a display device, or may display it on a display device of the terminal 100. The graph drawing unit 16 may display the values ​​of the inner axis surfaces for each cluster on the display device, or may transmit them to the terminal 100.

[0049] FIG. 9 is an example of a graph. In graph G shown in FIG. 9, the vertical axis is "need for recognition" and the horizontal axis is "extroversion." Graph G shows clusters C1 to C4. For example, cluster C1 is a cluster with a high value for "need for recognition" and a high value for "extroversion." Cluster C1 is a cluster to which positive case users and users whose inner selves are highly similar to those of the positive case users (need for recognition and extroversion) belong. Cluster C2 is a cluster to which users whose values ​​for "need for recognition" are low and whose values ​​for "extroversion" belong. Cluster C2 may include clusters C21 and C22. Cluster C3 is a cluster to which users whose values ​​for "need for recognition" are high and whose values ​​for "extroversion" belong. Cluster C3 may include clusters C31 and C32. Cluster C4 is a cluster to which users whose values ​​for "need for recognition" are low and whose values ​​for "extroversion" belong.

[0050] 4, in step S8, the approach proposing device 10 calculates feature values ​​related to the estimated inner surfaces. For example, the inner surface feature calculation unit 17 calculates feature values ​​related to each of the estimated inner surfaces for each of the multiple clusters.

[0051] 10 is a diagram showing an example of feature values. For example, the inner surface feature calculation unit 17 calculates the average value of each estimated inner surface for each cluster as the feature value. The inner surface feature calculation unit 17 may normalize the calculated feature value. FIG. 10 shows feature values ​​associated with cluster identification numbers.

[0052] For example, for the cluster with identification number "1", the internal characteristic calculation unit 17 calculates an average value of "0.0002" for the need for recognition and an average value of "0.3" for the extroversion. For the cluster with identification number "2", the internal characteristic calculation unit 17 calculates an average value of "0.5" for the need for recognition and an average value of "0.0004". For the cluster with identification number "3", the internal characteristic calculation unit 17 calculates an average value of "0.8" for the need for recognition and an average value of "0.9" for the extroversion.

[0053] The internal personality characteristic calculation unit 17 may determine a positive example user group P and a similar cluster that is a cluster similar to the positive example user group P by comparing the values ​​of the internal axis among the feature values ​​between multiple clusters. For example, assume that the internal axis determined by the axis determination unit 14 is "need for recognition" and "extroversion." In this case, the internal personality characteristic calculation unit 17 compares the value of the need for recognition and the value of extroversion for each cluster. In the example shown in FIG. 10 , the estimated internal personality value of the cluster with identification number "3" is the highest or has the greatest difference compared to the values ​​of the other clusters. In this case, the internal personality characteristic calculation unit 17 determines the cluster with identification number "3" as a similar cluster. The internal personality characteristic calculation unit 17 may output information such as a flag indicating whether the determined similar cluster is a similar cluster.

[0054] The inner surface feature calculation unit 17 may calculate other types of inner surfaces, which are inner surfaces with high feature values, for each of the dissimilar clusters other than the similar clusters. In the example shown in Figure 10, the inner surface feature calculation unit 17 determines the clusters other than the cluster with identification number "3" as dissimilar clusters. The inner surface feature calculation unit 17 may output information such as a flag indicating whether the determined dissimilar clusters are similar clusters.

[0055] In one example, the internal characteristics calculation unit 17 calculates the other-type internal characteristics for each of the clusters with identification numbers "1" and "2", which are dissimilar clusters. For example, the other-type internal characteristics of the cluster with identification number "1" may be, for example, "extroversion" and "agreeableness". The other-type internal characteristics of the cluster with identification number "2" may be, for example, "desire for recognition" and "proactiveness". The other-type internal characteristics may overlap with the axis internal characteristics.

[0056] In step S9, the approach suggestion device 10 estimates and outputs an approach to encourage behavioral change. For example, the behavior change estimation unit 18 estimates and outputs an approach to encourage behavioral change for each of a plurality of clusters using an inner surface corresponding to a high value among the feature values. The behavior change estimation unit 18 may estimate an approach to encourage behavioral change for a similar cluster using an inner surface of an axis. The behavior change estimation unit 18 may estimate an approach to encourage behavioral change for a dissimilar cluster using a different type of inner surface. The behavior change estimation unit 18 may display the estimated approach on a display device or transmit it to the terminal 100. For example, the behavior change estimation unit 18 may transmit an approach in the form of a message or the like to the terminal of a user belonging to the cluster.

[0057] For example, the behavior change estimation unit 18 acquires various information from the behavior change database 30 using an internal state with a high feature value as an extraction condition. FIG. 11 is a diagram showing an example of data stored in the behavior change database 30. The behavior change database 30 stores recommended approaches and reliability levels in association with internal states. Internal states can be uniquely identified. For example, the behavior change database 30 stores recommended actions, recommended spaces, and recommended words, as well as reliability levels of recommended actions and reliability levels of recommended wording in association with internal states. The information stored in the behavior change database 30 is not limited to these.

[0058] The recommended actions, recommended spaces, and recommended words are the recommended actions, recommended spaces (places, etc.), and recommended words, respectively. The reliability of the recommended actions and the reliability of the recommended wording are the reliability of the recommended actions, recommended spaces, and recommended words. The reliability is determined and revised based on research or implementation results. The reliability can be expressed, for example, by three levels, A to C.

[0059] For example, the behavioral change database 30 stores various information in association with the internal state of "desire for recognition." The behavioral change database 30 stores various information in association with the internal state of "proactivity." The behavioral change database 30 stores various information in association with the internal state of "cooperativeness." The behavioral change database 30 stores various information in association with the internal state of "extroversion."

[0060] For example, the behavioral change estimation unit 18 may estimate and output a different approach for each of multiple clusters. For cluster C2 shown in Fig. 9, the behavioral change estimation unit 18 may estimate and output the approach of "creating a place where fans can interact with each other on-site." For cluster C3 shown in Fig. 9, the behavioral change estimation unit 18 may estimate and output the approach of "creating an event that can be participated in in a remote space."

[0061] Next, the effects of the approach suggestion device 10 according to one aspect of the present disclosure will be described.

[0062] An approach suggestion device 10 according to one aspect of the present disclosure includes an inner state estimation unit 12 that obtains estimated inner states, which are the results of estimating multiple inner states of users, for a target user group T, which is a group of target users, using user behavior data; an inner state feature extraction unit 13 that uses the estimated inner states to extract positive example inner states, which are multiple inner states that are characteristic of a positive example user group P, which is a group of users among the target user group T who are engaging in predetermined behavior; a cluster identification unit 15 that identifies multiple clusters for the target user group using at least a portion of the positive example inner states; and a behavior change estimation unit 18 that estimates and outputs an approach to encourage behavior change for each of the multiple clusters based on the estimated inner states.

[0063] An approach suggestion device 10 according to one aspect of the present disclosure outputs, for each user in a target user group T, an estimated inner state, which is the result of estimating multiple inner states from behavioral data. From the estimated inner states, positive example inner states, which are multiple inner states characteristic of a positive example user group P among the target user group T, are extracted. A cluster is identified for each user using at least a portion of the positive example inner states. Then, for each cluster, an approach to encourage behavioral change is estimated based on the estimated inner state. With this configuration, inner states characteristic of the positive example user group P are treated as positive example inner states, and an approach to encourage behavioral change is estimated for each cluster according to the estimated inner state. As a result, different approaches can be estimated for clusters whose inner states are dissimilar, for example. As a result, users whose inner states are dissimilar can also be approached via the clusters.

[0064] For example, the approach suggestion device 10 outputs an estimated inner self for each fan of an idol. From a group of fans of the idol, positive inner self examples relating to a group of fans who attended an event for the idol are extracted. Using at least a portion of the positive inner self examples, a cluster is identified for each fan. Then, an approach to encourage behavioral change is estimated for each cluster. For example, for cluster C2 shown in FIG. 9 , an approach of "creating a space where fans can interact with each other on-site" may be estimated and output. For cluster C3 shown in FIG. 9 , an approach of "creating an event that can be participated in remotely" may be estimated and output. Furthermore, compared to when approaches are proposed manually, human workload can be reduced. Furthermore, since approaches based on inner self are applied to users belonging to a cluster, a pleasant user experience is expected.

[0065] The approach suggestion device 10 includes an axis determination unit 14 that determines inner axis surfaces, which are multiple axes that serve as references, based on the inner surface of the positive example. The cluster identification unit 15 identifies multiple clusters using the inner axis surfaces. In this case, the inner axis surfaces are determined from the inner surface of the positive example, and clusters are identified based on the inner axis surfaces. This makes it possible to identify clusters that place more emphasis on inner surfaces that are characteristic of the positive example user group.

[0066] The cluster identification unit 15 identifies multiple clusters by comparing the values ​​of the inner axis surfaces with a predetermined threshold and determining which of the clusters divided according to the combination of the inner axis surfaces the value belongs to. This simple determination method can suppress an increase in calculation costs.

[0067] The approach suggestion device 10 includes an inner-life feature calculation unit | that calculates feature values ​​for each estimated inner life for each of a plurality of clusters. The behavioral change estimation unit | estimates an approach for each of a plurality of clusters using the inner life corresponding to the highest feature value. In this case, an approach that encourages behavioral change is estimated for each cluster depending on which inner life feature value is high. This allows for the estimation of a more appropriate approach.

[0068] The interior feature extraction unit 13 extracts the strength of the features of the positive example interior surfaces. The axis determination unit 14 determines the interior axis surface based on the ranking of the strength of the features of the positive example interior surfaces. In this case, the ranking of the strength of the features of the positive example interior surfaces is reflected in the determination of the interior axis surface, making it possible to determine a more appropriate interior axis surface.

[0069] The inner surface feature calculation unit 17 compares the values ​​of the inner surface of the axis among the feature values ​​between multiple clusters to determine the positive example user group P and similar clusters that are clusters similar to the positive example user group P. The behavioral change estimation unit 18 estimates approaches for similar clusters using the inner surface of the axis. In this case, it is highly likely that users of the positive example user group P and users who have an inner surface similar to that of the positive example user group P belong to the similar clusters. By estimating approaches according to the inner surface of the axis for similar clusters, it is possible to estimate more appropriate approaches.

[0070] The inner face feature calculation unit 17 calculates other inner faces, which are inner faces with high feature values, for each dissimilar cluster, which is a cluster other than the similar cluster. The behavioral change estimation unit 18 estimates an approach for each dissimilar cluster using the other inner faces. In this case, other inner faces corresponding to each dissimilar cluster are calculated. By estimating an approach according to the other inner faces for each dissimilar cluster, a more appropriate approach can be estimated.

[0071] The approach proposal device 10 includes a graph drawing unit 16 that draws a graph using the inner axis lines for each of a plurality of clusters. In this case, how each cluster is represented relative to the inner axis lines is visually provided. This allows the similarity between clusters to be easily grasped based on the inner axis lines. Furthermore, because the axes are set by the system when visualizing the clusters, no human subjectivity or bias is introduced. This allows the visualized graph to provide suggestions that are free from human bias.

[0072] The approach proposal device of the present disclosure has the following configuration.

[0073] [1] An approach proposal device comprising: an inner state estimation unit that, for a target user group, which is a group of target users, uses behavioral data of the users to obtain estimated inner states, which are the result of estimating multiple inner states of the users; an inner state feature extraction unit that, using the estimated inner states, extracts positive example inner states, which are multiple inner states characteristic of a positive example user group, which is a group of users from the target user group who are engaging in a predetermined behavior; a cluster identification unit that identifies multiple clusters for the target user group using at least a portion of the positive example inner states; and a behavior change estimation unit that estimates and outputs an approach to encourage behavior change for each of the multiple clusters based on the estimated inner states. [2] The approach proposal device described in [1], which includes an axis determination unit that determines inner axis states, which are multiple axes that serve as references, based on the positive example inner states, and the cluster identification unit identifies the multiple clusters using the inner axis states. [3] The approach proposal device described in [2], which includes: an axis determination unit that determines inner axis states, which are multiple axes that serve as references, based on the positive example inner states, and the cluster identification unit identifies the multiple clusters using the inner axis states. [4] The approach suggestion device according to [2] or [3], further comprising an inner surface feature calculation unit that calculates feature values ​​for each of the estimated inner surfaces for each of the plurality of clusters, and the behavior change estimation unit estimates the approach for each of the plurality of clusters using an inner surface corresponding to a higher value of the feature values. [5] The approach suggestion device according to [4], further comprising: an inner surface feature extraction unit that extracts strengths of features of the positive example inner surfaces, and the axis determination unit determines the inner axis surface based on a ranking of the strengths of the features of the positive example inner surfaces. [6] The approach suggestion device according to [4] or [5], further comprising: an inner surface feature calculation unit that compares values ​​of the inner axis surface among the feature values ​​between the plurality of clusters to determine the positive example user group and similar clusters that are clusters similar to the positive example user group, and the behavior change estimation unit estimates the approach for the similar clusters using the inner axis surface.[7] The approach suggestion device of [6], wherein the inner face feature calculation unit calculates, for each of the dissimilar clusters other than the similar clusters, a different inner face that is an inner face with a high value among the feature values, and the behavioral change estimation unit estimates the approach for the dissimilar clusters using the different inner faces. [8] The approach suggestion device of any of [4] to [7], further comprising a graph drawing unit that draws a graph using the axis inner faces for each of the plurality of clusters.

[0074] The block diagrams used to explain the above embodiments show functional blocks. These functional blocks (components) are realized by any combination of hardware and / or software. Furthermore, the method for realizing each functional block is not particularly limited. That is, each functional block may be realized using a single device that is physically or logically coupled, or may be realized using two or more physically or logically separated devices that are directly or indirectly connected (e.g., wired, wireless, etc.) and these multiple devices. The functional block may also be realized by combining software with the single device or multiple devices.

[0075] Functions include, but are not limited to, judgment, determination, assessment, calculation, computation, processing, derivation, investigation, search, confirmation, reception, transmission, output, access, resolution, selection, selection, establishment, comparison, assumption, expectation, consideration, broadcasting, notifying, communicating, forwarding, configuring, reconfiguring, allocating, mapping, and assignment. For example, a functional block (component) that performs transmission is called a transmitting unit or transmitter. As mentioned above, there are no particular limitations on how these functions are implemented.

[0076] For example, the approach proposal system 1 according to an embodiment of the present disclosure may function as a computer that performs information processing according to the present disclosure. Fig. 12 is a diagram illustrating an example of the hardware configuration of the approach proposal system 1 according to an embodiment of the present disclosure. The approach proposal system 1 described above 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. The hardware configuration of the terminal 100 may also be as described herein.

[0077] In the following description, the term "apparatus" can be interpreted as a circuit, a device, a unit, etc. The hardware configuration of the approach proposal system 1 may be configured to include one or more of the apparatuses shown in the figure, or may be configured to exclude some of the apparatuses.

[0078] Each function in the approach proposal system 1 is realized by loading specified software (programs) onto hardware such as a processor 1001 and memory 1002, causing the processor 1001 to perform calculations, control communication via a communication device 1004, and control at least one of reading and writing data in the memory 1002 and storage 1003.

[0079] The processor 1001, for example, runs 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, each function in the approach proposal system 1 described above may be realized by the processor 1001.

[0080] The processor 1001 also reads programs (program codes), software modules, data, etc. from at least one of the storage 1003 and the communication device 1004 into the memory 1002 and executes various processes in accordance with these. The programs used are those that cause a computer to execute at least some of the operations described in the above-described embodiments. For example, each function of the approach proposal system 1 may be implemented by a control program stored in the memory 1002 and running on the processor 1001. While the above-described various processes have been described as being executed by one processor 1001, they may also be executed simultaneously or sequentially by two or more processors 1001. The processor 1001 may be implemented by one or more chips. The programs may also be transmitted from a network via a telecommunications line.

[0081] The memory 1002 is a computer-readable recording medium and may be configured, for example, by at least one of 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 executable programs (program codes), software modules, etc. for performing information processing according to an embodiment of the present disclosure.

[0082] 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 CD-ROM (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 (registered trademark) disk), a smart card, a flash memory (e.g., a card, a stick, a key drive), a floppy (registered trademark) disk, a magnetic strip, etc. Storage 1003 may also be called an auxiliary storage device. The storage medium provided in approach proposal system 1 may be, for example, a database, a server, or other appropriate medium including at least one of memory 1002 and storage 1003.

[0083] The communication device 1004 is hardware (transmission / reception device) for communicating between computers via at least one of a wired network and a wireless network, and is also called, for example, a network device, a network controller, a network card, or a communication module.

[0084] The input device 1005 is an input device (e.g., a keyboard, a mouse, a microphone, a switch, a button, a sensor, etc.) that receives input from the outside. The output device 1006 is an output device (e.g., a display, a speaker, an LED lamp, etc.) that outputs to the outside. The input device 1005 and the output device 1006 may be integrated into one device (e.g., a touch panel).

[0085] 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 using a single bus, or may be configured using different buses between each device.

[0086] The approach proposal system 1 may also 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), or a field programmable gate array (FPGA), and some or all of the functional blocks may be realized by the hardware. For example, the processor 1001 may be implemented using at least one of these pieces of hardware.

[0087] The order of the procedures, sequences, flowcharts, etc. of each aspect / embodiment described in this disclosure may be changed unless it is consistent. For example, the methods described in this disclosure present elements of various steps using an example order, and are not limited to the particular order presented.

[0088] Input and output information may be stored in a specific location (for example, memory) or may be managed using a management table. Input and output information may be overwritten, updated, or added to. Output information may be deleted. Input information may be transmitted to another device.

[0089] The determination may be made based on a value represented by one bit (0 or 1), a Boolean value (true or false), or a numerical comparison (e.g., comparison with a predetermined value).

[0090] The aspects / embodiments described in this disclosure may be used alone, in combination, or switched depending on the implementation. Notification of predetermined information (e.g., notification that "X is true") is not limited to explicit notification, but may be implicit (e.g., not notifying the predetermined information).

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

[0092] 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.

[0093] Software, instructions, information, etc. may also be transmitted or received over a transmission medium. For example, if software is transmitted from a website, server, or other remote source using wired technologies (such as coaxial cable, fiber optic cable, twisted pair, Digital Subscriber Line (DSL)), and / or wireless technologies (such as infrared, microwave), then these wired and / or wireless technologies are included within the definition of transmission media.

[0094] As used in this disclosure, the terms "system" and "network" are used interchangeably.

[0095] Furthermore, the information, parameters, etc. described in this disclosure may be expressed using absolute values, may be expressed using relative values ​​from a predetermined value, or may be expressed using other corresponding information.

[0096] As used in this disclosure, the terms "determining" and "determining" may encompass a wide variety of actions. "Determining" and "determining" may include, for example, judging, calculating, computing, processing, deriving, investigating, looking up, searching, inquiring (e.g., searching in a table, database, or other data structure), ascertaining, and the like. "Determining" and "determining" may also include receiving (e.g., receiving information), transmitting (e.g., sending information), input, output, accessing (e.g., accessing data in memory), and the like. Furthermore, "judgment" and "decision" can include regarding resolving, selecting, choosing, establishing, comparing, etc. as having been "judged" or "decided." In other words, "judgment" and "decision" can include regarding some action as having been "judged" or "decided." Furthermore, "judgment (decision)" can be interpreted as "assuming," "expecting," "considering," etc.

[0097] The terms "connected," "coupled," or any variation thereof, refer to any direct or indirect connection or coupling between two or more elements, and may include the presence of one or more intermediate elements between two elements that are "connected" or "coupled" to each other. The coupling or connection between elements may be physical, logical, or a combination thereof. For example, "connected" may be read as "access." As used in this disclosure, two elements may be considered to be "connected" or "coupled" to each other using one or more wires, cables, and / or printed electrical connections, as well as electromagnetic energy having wavelengths in the radio frequency range, microwave range, and optical (both visible and invisible) range, as some non-limiting and non-exhaustive examples.

[0098] As used in this disclosure, 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."

[0099] As used in this disclosure, any reference to an element using a designation such as "first," "second," etc. does not generally limit the quantity or order of those elements. These designations may be used in this disclosure 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 or that the first element must in some way precede the second element.

[0100] When the terms "include," "including," and variations thereof are used in this disclosure, these terms are intended to be inclusive, similar to the term "comprising." Furthermore, when the term "or" is used in this disclosure, it is not intended to be an exclusive or.

[0101] In this disclosure, where articles are added by translation, such as a, an, and the in English, the disclosure may include that the nouns following these articles are in the plural form.

[0102] In the present disclosure, the term "A and B are different" may mean "A and B are different from each other." The term may also mean "A and B are each different from C." Terms such as "separate" and "coupled" may also be interpreted in the same way as "different."

[0103] 1...Approach proposal system, 10...Approach proposal device, 11...Input unit, 12...Inner self estimation unit, 13...Inner self feature extraction unit, 14...Axis determination unit, 15...Cluster identification unit, 16...Graph drawing unit, 17...Inner self feature calculation unit, 18...Behavioral change estimation unit, 30...Behavioral change database, 20...Model management unit, 21...Inner self database, 22...Behavioral database, 23...Model creation unit, 100...Terminal.

Claims

1. An approach suggestion device comprising: an inner self estimation unit that obtains an estimated inner self, which is a result of estimating multiple inner self of a target user group, which is a group of target users, using behavioral data of the users; an inner self feature extraction unit that uses the estimated inner self to extract positive example inner self, which is a multiple inner self characteristic of a positive example user group, which is a group of users among the target user group who are engaging in a predetermined behavior; a cluster identification unit that identifies multiple clusters for the target user group using at least a portion of the positive example inner self; and a behavior change estimation unit that estimates and outputs an approach to encourage behavior change for each of the multiple clusters based on the estimated inner self.

2. The approach proposal device according to claim 1, further comprising an axis determination unit that determines axis inner faces, which are multiple reference axes, based on the positive example inner faces, and the cluster identification unit identifies the multiple clusters using the axis inner faces.

3. The approach proposal device according to claim 2, wherein the cluster identification unit identifies the plurality of clusters by comparing the value of the inner axis surface with a predetermined threshold value and determining which of the clusters divided according to the combination of the inner axis surfaces the value corresponds to.

4. The approach suggestion device of claim 2, further comprising an inner face feature calculation unit that calculates feature values ​​for each of the estimated inner faces for each of the plurality of clusters, and the behavior change estimation unit estimates the approach for each of the plurality of clusters using an inner face corresponding to a higher value among the feature values.

5. The approach proposal device according to claim 4, wherein the inner surface feature extraction unit extracts the strength of the features of the positive example inner surfaces, and the axis determination unit determines the axis inner surface based on a ranking of the strength of the features of the positive example inner surfaces.

6. The approach suggestion device described in claim 4, wherein the inner surface feature calculation unit determines the positive example user group and similar clusters which are clusters similar to the positive example user group by comparing the values ​​of the inner surface of the axis among the feature values ​​between the multiple clusters, and the behavioral change estimation unit estimates the approach for the similar cluster using the inner surface of the axis.

7. The approach suggestion device of claim 6, wherein the inner feature calculation unit calculates a different type of inner feature, which is an inner feature having a high value among the feature values, for each of dissimilar clusters that are clusters other than the similar clusters, and the behavior change estimation unit estimates the approach for the dissimilar clusters using the different type of inner features.

8. The approach proposal device according to claim 4, further comprising a graph drawing unit that draws a graph using the inner axis surface for each of the plurality of clusters.

Citation Information

Patent Citations

  • Information terminal and program

    JP2017033167A

  • Characteristic estimation device, characteristic estimation method, and characteristic estimation program or the like

    JP2020035409A

  • Device, system, program, and method

    JP2023066133A

  • Information processing device, information processing method, and program

    WO2015016094A1