Device and method

Abstract

Provided are a device and method capable of accurately estimating the motivation that led a user to purchase a product.　A device 10 comprises: a determination unit 12 that, on the basis of information regarding the actions of the user, determines action information, which is information indicating a temporal change in the state of a user when the user intends to perform an action; and an estimation unit 13 that, on the basis of the action information, estimates motivation information, which is information regarding the motivation that led the user to an action when the user intended to perform the action.

Description

Apparatus and method

[0001] The present invention relates to an apparatus and a method.

[0002] Patent document 1 describes a method of dividing multiple customers into groups based on information indicating the customers and the products they have purchased, and information indicating the purchase reasons given for each product, and determining the products to be recommended to the customers for each group.

[0003] Japanese Patent Application Laid-Open No. 2015-201090

[0004] However, in the device described in Patent Document 1, the reason for purchase is predetermined for each product, so it is not possible to estimate the reason why each user purchased a product for each user, and therefore it is not possible to accurately estimate the motive that led the user to purchase the product.

[0005] The present invention has been made in view of the above, and has as its object to provide an apparatus and method that can accurately estimate the motivation that led a user to take an action.

[0006] In order to achieve the above-mentioned object, the device of the present invention comprises a determination unit that determines behavioral information, which is information indicating changes in the user's state over time when the user is about to take action, based on information about the user's behavior, and an estimation unit that estimates motivation information, which is information about the user's motivation for taking action when the user is about to take action, based on the behavioral information.

[0007] According to the present invention, it is possible to accurately estimate the motive that led a user to take an action.

[0008] FIG. 1 is a diagram for explaining an example of processing in an apparatus and method according to the present embodiment. FIG. 2 is a block diagram showing the functional configuration of an apparatus according to the present embodiment. FIG. 3 is a diagram showing an example of purchase behavior information. FIG. 4 is a diagram for explaining a method for generating purchase behavior information. FIG. 5 is a diagram for explaining processing for generating vector information based on purchase behavior information. FIG. 6 is a flowchart showing an example of processing for estimating purchase motivation information. FIG. 7 is a diagram showing an example of the hardware configuration of an apparatus according to an embodiment of the present disclosure.

[0009] Hereinafter, an embodiment of the device and method according to the present invention will be described in detail with reference to the drawings. In the description of the drawings, the same elements are designated by the same reference numerals, and duplicated explanations will be omitted.

[0010] 1 is a diagram illustrating an example of processing in the device and method according to the present embodiment. The device determines behavioral information, which is information indicating a temporal change in the user's state when the user is about to perform the behavior, based on information about the user's behavior. The device estimates motivation information, which is information about the user's motivation for performing the behavior when the user is about to perform the behavior, based on the behavioral information.

[0011] A user's behavior is one of various behaviors performed by a user. For example, a user's behavior is the user purchasing a purchase item. The behavior information is purchase behavior information that indicates changes in the user's state over time during purchase behavior, which is the user's behavior when attempting to purchase a purchase item. The motivation information is purchase motivation information related to the motivation that led the user to purchase the purchase item during purchase behavior. A user's behavior may be behavior other than the user purchasing a purchase item, such as the user visiting a specified location, or other behavior other than those described above.

[0012] Purchasing behavior refers to a user's purchasing behavior. For example, purchasing behavior refers to the user's behavior when attempting to purchase a product during a period from the time the user becomes aware of the product to the time the user recommends it. Specifically, purchasing behavior refers to the user's behavior from the time the user becomes aware of, appeals to, or researches the product to the time the user takes action or recommends it. As an example, purchasing behavior in the 5A customer journey will be described. First, the 5A customer journey is composed of awareness, appeal, research, action, and recommendation. "Awareness" means that the user becomes aware of the product. "Appeal" means that the user is attracted to the product. "Research" means that the user researches the product. "Action" means that the user purchases the product. "Recommendation" means that the user repurchases the product, recommends it to other users, or a predetermined period (e.g., one to two weeks) has passed since the user purchased the product. In the 5A customer journey, the start of the purchasing behavior is at any of the points of awareness, appeal, and research, and the end of the purchasing behavior is at the point of action or recommendation.

[0013] The purchasing behavior may be a purchasing behavior in a known customer journey other than the above. As an example, in the AIDA customer journey, the start point of the purchasing behavior is any one of the points of attention, interest, and desire, and the end point of the purchasing behavior is the point of behavior. As another example, in the AIDA customer journey, the start point of the purchasing behavior is any one of the points of attention, interest, desire, and memory, and the end point of the purchasing behavior is the point of behavior.

[0014] The process of extracting a period during which a user performed a purchasing behavior will be described. The device extracts the start and end points of the purchasing behavior. For example, the device acquires the user's web browsing information and determines whether the user is aware of the purchase target. If the device determines that the user is aware of the purchase target, it determines that the start point of the purchasing behavior is the time when the user became aware of the purchase target (for example, the time when the user viewed a web page listing the purchase target). Note that the device may also determine that the start point of the purchasing behavior is one to two weeks before the time when the user purchased the purchase target.

[0015] The device determines that the purchase behavior ends one to two weeks after the user purchases the purchase item. The device may also determine that the purchase behavior ends when the user repurchases the purchase item or when the user recommends the purchase item to other users.

[0016] In the example shown in FIG. 1 , the device determines purchase behavior information (space-time graph G) based on information P about user purchases. Then, based on the purchase behavior information, the device estimates purchase motivation information, which is information about the motivation that led the user to purchase the purchase item in the purchase behavior, using, for example, an estimation model M. Finally, based on the purchase motivation information, the device estimates the motivation that led the user to purchase the purchase item in the purchase behavior. Thereafter, the device may implement marketing measures for the user according to the estimated motivation.

[0017] Next, the process of estimating purchase motivation information will be described in detail. Fig. 2 is a block diagram showing the functional configuration of the device according to this embodiment. As shown in Fig. 2, the device 10 includes an input unit 11, a determination unit 12, an estimation unit 13, and an output unit 14. Note that the device 10 may be one element of a motivation estimation system that includes a terminal held by a user and a server.

[0018] The input unit 11 inputs information about user behavior to the determination unit 12 and the estimation unit 13. Specifically, the input unit 11 inputs information about user purchases to the determination unit 12 and the estimation unit 13. As an example, the input unit 11 inputs information about purchases by multiple users during a period from the start to the end of a purchasing behavior to the determination unit 12. Note that the input unit 11 may acquire information about user behavior from a terminal held by the user. The input unit 11 may acquire information about user behavior from a server that stores information about user behavior.

[0019] Information about user behavior is information about user purchases. Information about user purchases is information related to the user in terms of purchasing behavior. Information about user purchases includes not only information directly related to purchasing behavior, but also information indirectly related to purchasing behavior. Specifically, information about user purchases is information about user attributes, information about user psychology, or information about user behavior (e.g., what service they viewed, what places they visited).

[0020] In the example shown in Figure 1, attribute information P1, contract information P2, billing information P3, usage amount information P4, usage status information P5, browsing information P6, store order information P7, location information P8, psychological information P9, and community information P10 are shown as examples of information related to user purchases. Attribute information P1 is an example of information related to user attributes. Contract information P2, billing information P3, usage amount information P4, usage status information P5, browsing information P6, store order information P7, location information P8, and community information P10 are examples of information related to user behavior. Psychological information P9 is an example of information related to the user's psychology.

[0021] Attribute information P1 is information indicating the user's attributes. Contract information P2 is information indicating the content of the contract concluded by the user. Billing information P3 is information indicating the content of the bill to the user. Usage amount information P4 is information indicating the amount of communication and phone calls used by the user. Usage status information P5 is information indicating the usage status of the user's services (for example, services used to pay for product purchases). Browsing information P6 is information indicating the web pages viewed by the user. Store order information P7 is information indicating the contents of the order the user made at an actual store. Location information P8 is information regarding the user's location. Psychological information P9 is information indicating the user's psychology (for example, the results of a survey conducted on the user). Community information P10 is information regarding the community to which the user belongs.

[0022] The information about user purchases includes information about the user and information about the time. Specifically, the information about user purchases includes information about multiple users and information about multiple times. The information about multiple users is information about users for each time. For example, attribute information P1 includes information about user attributes for each time. Contract information P2, billing information P3, usage amount information P4, usage status information P5, browsing information P6, store order information P7, location information P8, psychological information P9, and community information P10 also include information for each time.

[0023] Information about time is associated with information about the user. Specifically, information about time is associated with information about the user corresponding to the time. For example, information indicating time T is associated with information indicating the user's attributes at time T, which is included in attribute information P1, and information indicating the contract details concluded at time T, which is included in contract information P2. Information indicating time T is similarly associated with information corresponding to time T, which is included in billing information P3, usage amount information P4, usage status information P5, browsing information P6, store order information P7, location information P8, psychological information P9, and community information P10.

[0024] The input unit 11 inputs information indicating a motivation for purchasing a purchase item in a purchasing behavior to the estimation unit 13. In the example shown in Fig. 1 , the information indicating a motivation for purchasing a purchase item in a purchasing behavior is information indicating the results of a questionnaire given to the user, which is included in the psychological information P9. As an example, the information indicating a motivation for purchasing a purchase item in a purchasing behavior is a label associated with the purchasing behavior.

[0025] The determination unit 12 determines, based on information about the user's behavior, behavioral information indicating changes in the user's state over time when the user is about to perform the behavior. Specifically, the determination unit 12 determines, based on information about the user's purchase, purchase behavior information indicating changes in the user's state over time during purchase behavior, which is the behavior the user performs when purchasing an item to be purchased. For example, based on the information about the user's purchase, the determination unit 12 determines, as the purchase behavior information, a graph in which information about time is represented as a first node, information about the user is represented as a second node, and a correspondence relationship between the information about the user and the information about time is represented as an edge between the first node and the second node. The first node and the second node each have a feature expressed by a vector. The first node and the second node are located at positions in the vector space corresponding to the feature. For example, the graph is constructed from information about the user during a period in which the user is performing behavior corresponding to the 5A of the customer journey, and one example is a space-time graph.

[0026] FIG. 3 is a diagram showing an example of a space-time graph. In the example shown in FIG. 3, the state of a user in a 5A customer journey is shown as a space-time graph G. The space-time graph G is information indicating the state of a user at each time. Specifically, in the space-time graph G, information relating to multiple times is expressed as multiple first nodes N11 to N13. The first node N11 is a node indicating time T-1, the first node N12 is a node indicating time T, and the first node N13 is a node indicating time T+1. The multiple first nodes are arranged at positions in the vector space corresponding to the respective feature amounts. An edge E1 is established between two adjacent first nodes.

[0027] In the space-time graph G, information about multiple users is represented as multiple second nodes N201 to N205, second nodes N301 to N305, and second nodes N401 to N405. The multiple second nodes are arranged at positions in the vector space corresponding to their respective feature quantities. The five second nodes N201 to N205 have an edge E2 with the first node N11. For example, the five second nodes N201 to N205 are nodes that represent the user's behavior, the user's location, the relationship between the user and the purchase object, the user's attributes, and the user's psychology, respectively. Similarly, the five second nodes N301 to N305 have an edge E2 with the first node N12. The five second nodes N401 to N405 have an edge E2 with the first node N13. Note that the number of first nodes and the number of second nodes in the space-time graph G are not limited to those described above.

[0028] A method for generating the space-time graph G will be described in detail. FIG. 4 is a diagram illustrating the method for generating the space-time graph G. In the example shown in FIG. 4, the determination unit 12 acquires information indicating a user's order at time T, which is included in store order information P7. The information indicating the user's order at time T includes information such as the type, number, and frequency of the order. The determination unit 12 converts the information indicating the user's order at time T into vector information to create a second node N307. The determination unit 12 also performs similar processing on the attribute information P1, contract information P2, billing information P3, usage amount information P4, usage status information P5, browsing information P6, location information P8, psychological information P9, and community information P10. As a result, the determination unit 12 determines second nodes N301 to N306 and N308 to N310. The determination unit 12 establishes an edge E2 between the second nodes N301 to N306 and N308 to N310 and the first node N12.

[0029] In this way, a graph is generated for the first node N12, which is the node indicating time T. The determination unit 12 performs similar processing for the first nodes N11 and N13. The determination unit 12 then generates a space-time graph G by attaching an edge E1 between the first nodes N11 to N13. As described above, the determination unit 12 generates a space-time graph G of purchasing behavior by creating multiple graphs for each of the nodes indicating multiple times from the start point to the end point of the purchasing behavior.

[0030] The estimation unit 13 estimates motivation information, which is information about the motivation that led the user to take action when the user is about to take action, based on the behavior information. Specifically, the estimation unit 13 estimates purchase motivation information, which is information about the motivation that led the user to purchase the purchase target in the purchase behavior, based on the purchase behavior information. For example, the estimation unit 13 estimates the purchase motivation information based on the purchase behavior information using an estimation model M trained using machine learning. As an example, the estimation unit 13 inputs vector information based on the purchase behavior information into the estimation model M to estimate the purchase motivation information.

[0031] The purchase motivation information includes information indicating the type of motivation for purchasing a purchase item in a purchasing behavior and information indicating an evaluation value for each type of motivation. The estimation unit 13 estimates that the motivation corresponding to the highest evaluation value is the motivation that led the user to make a purchase in the purchasing behavior. In the example shown in FIG. 1 , the purchase motivation information is information indicating the evaluation values ​​for "price," "variety," "benefits," "quality," and "convenience." Since the evaluation value for "quality" is the highest, the estimation unit 13 estimates that the "quality" of the purchase item is the motivation that led the user to make a purchase in the purchasing behavior. Note that the purchase motivation information may include information indicating a type of motivation other than the above five types of motivation. When multiple types of motivations correspond to the highest evaluation value, the estimation unit 13 randomly selects one of the multiple types of motivation and estimates that the selected motive is the motive that led the user to make a purchase in the purchasing behavior.

[0032] The estimation model M is trained using vector information as an explanatory variable and purchase motivation information as a target variable. For example, the estimation model M is a graph neural network (GNN). The estimation unit 13 constructs the estimation model M using information about the user's purchase and information indicating the motivation for purchasing the purchase item in the purchasing behavior as training data. As an example, a case will be described in which the motivation corresponding to the information indicating the motivation for purchasing the purchase item in the purchasing behavior is "price." The estimation unit 13 generates a space-time graph based on the information about the user's purchase. The estimation unit 13 constructs the estimation model M so that it receives vector information based on the space-time graph as input and outputs purchase motivation information in which the evaluation values ​​of "price," "diversity," "benefits," "quality," and "convenience" are "1.0," "0," "0," and "0," respectively.

[0033] The process of generating vector information based on purchase behavior information will be described in detail. The estimation unit 13 converts the space-time graph G into vector information. Specifically, for each first node, the estimation unit 13 first calculates a feature vector for each time by adding vector information obtained by multiplying vector information indicated by multiple second nodes by weights to the vector information indicated by the first node. Here, the weight is set for each second node in consideration of information about the user corresponding to the second node. This makes it possible to convolute the space-time graph G for each first node in consideration of information about the user corresponding to the second node.

[0034] FIG. 5 is a diagram illustrating a process for generating vector information based on purchase behavior information. In the example shown in FIG. 5, the estimation unit 13 acquires a feature vector B301, which is vector information indicating the second node N301, for the first node N12 in the space-time graph G. Similarly, the estimation unit 13 acquires multiple feature vectors, which are multiple pieces of vector information indicating the second nodes N302 to N305. The estimation unit 13 adds the vector information calculated by multiplying the multiple feature vectors by multiple weights to the vector information indicating the first node N12 to generate a feature vector T12 for time T. The estimation unit 13 performs similar processing for the first nodes N11 and N13 in the space-time graph G to generate a feature vector T11 for time T−1 and a feature vector (not shown) for time T+1. The multiple weights are values ​​that are updated during the learning process of the GNN (estimation model M). The initial values ​​of the multiple weights may be random values ​​or may be values ​​set using functions present in an open-source GNN library.

[0035] The estimation unit 13 generates vector information based on the spatio-temporal graph G by convolving the feature vectors for each time in the time direction. In the example shown in FIG. 5 , the estimation unit 13 adds vector information obtained by multiplying a weighted feature vector T11 for time T−1 to a feature vector T12 for time T to generate a new feature vector T12. Then, the estimation unit 13 adds vector information obtained by multiplying the new feature vector T12 by a weight to a feature vector for time T+1 to generate a new feature vector. The estimation unit 13 performs the above calculation for the feature vectors for all times. The estimation unit 13 regards the last calculated feature vector TN as vector information based on the spatio-temporal graph G. In this way, the estimation unit 13 generates vector information based on purchase behavior information. Note that the weights are values ​​that are updated during the learning process of the GNN (estimation model M). The initial values ​​of the weights may be random values ​​or may be values ​​set using functions present in an open-source GNN library.

[0036] In this way, the estimation unit 13 weights the features of multiple second nodes that have edges to the first node and adds them to the node features of the first node to update the features of the first node. The updated features of the multiple first nodes are then aggregated to obtain one piece of embedded vector information for one space-time graph. In other words, the estimation unit 13 performs convolution on the features of the first and second nodes, taking into account the type of information on which each second node is based and the time to which each first node corresponds.

[0037] The output unit 14 outputs the purchase motivation information to the outside of the device 10. The output unit 14 outputs the purchase motivation information to a terminal held by the user or a server. The output unit 14 may output the estimation result by the estimation unit 13 to the outside of the device 10, or may implement marketing measures for the user based on the estimation result by the estimation unit 13. For example, when the estimation unit 13 estimates that the motivation that led the user to purchase the purchase item is the quality of the purchase item, the output unit 14 selects a high-quality purchase item. The output unit 14 may output a coupon that can be used to purchase the selected purchase item or a list of the selected purchase items to the user's terminal or a server.

[0038] Next, a process executed by the device 10 according to this embodiment will be described with reference to the flowchart of FIG. 6. FIG. 6 is a flowchart showing an example of a process for estimating purchase motivation information. First, the device 10 inputs information related to user behavior (Step S01: input step). Specifically, the information related to user behavior is information related to user purchases. The information related to user purchases includes information related to the user and information related to the time associated with the information related to the user.

[0039] The device 10 determines, based on information about the user's behavior, behavior information that indicates changes in the user's state over time when the user is about to perform the behavior (step S02: determination step). Specifically, based on information about the user's purchase, the device 10 determines purchase behavior information that indicates changes in the user's state over time in purchase behavior, which is the behavior the user performs when purchasing an item to be purchased. For example, based on the information about the user's purchase, the device 10 determines, as the purchase behavior information, a graph in which information about time is represented as a first node, information about the user is represented as a second node, and the correspondence between the information about the user and the information about time is represented as an edge attached between the first node and the second node.

[0040] The device 10 estimates, based on the behavioral information, motivation information, which is information regarding the motivation that led the user to take action when the user is about to take action (step S03: estimation step). Specifically, the device 10 estimates, based on the purchase behavior information, purchase motivation information, which is information regarding the motivation that led the user to make a purchase in the purchase behavior. For example, the device 10 inputs vector information based on the purchase behavior information into an estimation model M to estimate the purchase motivation information. The purchase motivation information is information regarding the evaluation value for each type of motivation for purchasing a purchase item in the purchase behavior. Then, the device 10 estimates that the type of motivation with the largest evaluation value is the motivation that led the user to make a purchase in the purchase behavior.

[0041] Finally, the device 10 outputs the purchase motivation information to the outside (step S04). In this case, the device 10 may output the result of estimating the user's motivation for making a purchase to the outside of the device 10, or may execute a marketing measure for the user based on the result of estimating the user's motivation for making a purchase.

[0042] Next, the effects of the device 10 and method according to this embodiment will be described. With the device 10 and method according to this embodiment, information regarding the motivation that led the user to take an action is estimated for each user action based on information indicating a temporal change in the user's state when the user is about to take the action. This makes it possible to accurately estimate information regarding the motivation that led the user to take the action when the user is about to take the action.

[0043] Furthermore, in the device 10 according to this embodiment, the information on user behavior may be information on user purchases, and the behavior information may be purchase behavior information indicating temporal changes in the user's state during purchase behavior, which is the behavior of the user when attempting to purchase an item, and the motivation information may be purchase motivation information regarding the motivation that led the user to purchase the item during purchase behavior. In this case, information on the motivation that led the user to purchase the item during purchase behavior is estimated for each purchase behavior based on information indicating temporal changes in the user's state during purchase behavior. For example, information on the motivation that led the user to purchase the item during purchase behavior is estimated taking into account changes in the user's psychological state from the time the user becomes aware of the existence of a product until the time the user purchases the product. This allows for accurate estimation of information on the motivation that led the user to purchase the item during purchase behavior. As a result, it becomes possible to optimize marketing measures for each user based on the motivation that led the user to purchase the item during purchase behavior.

[0044] In the past, it was desirable to consider what kind of marketing measures would be effective for customers who are likely to purchase a specific purchase item. In response to this, the device 10 according to the present embodiment estimates the motives and reasons why a user purchased a purchase item based on their purchasing behavior. This makes it possible to optimize marketing measures according to the motives and reasons.

[0045] Furthermore, in the device 10 according to the present embodiment, the purchasing behavior may be the behavior of the user when he or she attempts to purchase an item during a period from the time the user becomes aware of the item to the time the user recommends it. In this case, the motive that led the user to purchase the item is estimated taking into account the change in the user's state over time from the time the user becomes aware of the item to the time the user recommends it. This allows for more accurate estimation of information regarding the motive that led the user to purchase the item in the purchasing behavior.

[0046] Furthermore, in the device 10 according to the present embodiment, the information about user purchases may include information about the user and information about time associated with the information about the user. Based on the information about the user purchases, the determination unit 12 may determine, as the purchasing behavior information, a graph in which information about time is represented as a first node, information about the user is represented as a second node, and the correspondence between the information about the user and the information about time is represented as edges established between the first node and the second node. In this case, in the purchasing behavior information, the state of the user at a given time is represented as a plurality of second nodes with edges established between the first node and the second node. This allows the purchasing behavior information to accurately represent changes in the user's purchasing behavior over time. This allows for more accurate estimation of information about the user's motivation for making a purchase in the purchasing behavior.

[0047] In the device 10 according to the present embodiment, the information about the user may be at least one of information about the user's attributes, information about the user's psychology, and information about the user's behavior. In this case, the purchase motivation information can be estimated with even greater accuracy based on the purchase behavior information based on the information about the user's purchases.

[0048] Furthermore, in the device 10 according to the present embodiment, the estimation unit 13 may estimate purchase motivation information based on purchase behavior information using an estimation model M trained using machine learning. For example, the purchase motivation information is estimated by applying a graph neural network to a space-time graph generated for each purchase behavior. In this case, the estimation model M can be used to more accurately estimate information about the motivation that led the user to make a purchase in the purchase behavior.

[0049] Furthermore, in the device 10 according to the present embodiment, the estimation unit 13 may estimate purchase motivation information by inputting vector information based on purchase behavior information into the estimation model M, and the estimation model M may be trained using the vector information as an explanatory variable and the purchase motivation information as a target variable. In this case, the estimation model M can be used to more accurately estimate information about the motivation that led a user to make a purchase in purchase behavior.

[0050] Furthermore, in the device 10 according to the present embodiment, the purchase motivation information may include information indicating the type of motivation for purchasing the purchase item in the purchasing behavior and information indicating the evaluation value for each type of motivation, and the estimation unit 13 may estimate that the motivation corresponding to the largest evaluation value is the motivation that led the user to make the purchase in the purchasing behavior. In this case, the motive that led the user to make the purchase in the purchasing behavior can be estimated more accurately.

[0051] [About the Present Disclosure] The device 10 of the present disclosure has the following configuration.

[0052] [1] A device comprising: a determination unit that determines behavioral information, which is information indicating a temporal change in a user's state when the user is about to take an action, based on information about the user's behavior; and an estimation unit that estimates motivation information, which is information about the user's motivation for taking an action when the user is about to take an action, based on the behavioral information.

[0053] [2] The device described in [1], wherein the information regarding the user's behavior is information regarding the user's purchases, the behavior information is purchase behavior information indicating changes in the user's state over time in purchase behavior, which is the behavior of the user when attempting to purchase an item to be purchased, and the motivation information is purchase motivation information regarding the motivation that led the user to purchase the item to be purchased in the purchase behavior.

[0054] [3] The device according to [2], wherein the purchase behavior is the behavior of the user when attempting to purchase the purchase item during a period that includes the time when the user becomes aware of the purchase item and the time when the user recommends the purchase item.

[0055] [4] The device described in [2] or [3], wherein the information regarding the user's purchases includes information regarding the user and information regarding a time associated with the information regarding the user, and the determination unit determines, based on the information regarding the user's purchases, a graph in which the information regarding the time is represented as a first node, the information regarding the user is represented as a second node, and the correspondence between the information regarding the user and the information regarding the time is represented as an edge attached between the first node and the second node, as the purchase behavior information.

[0056] [5] The device according to [4], wherein the information about the user is at least one of information about the attributes of the user, information about the psychology of the user, and information about the behavior of the user.

[0057] [6] The device according to any one of [2] to [5], wherein the estimation unit estimates the purchase motivation information based on the purchase behavior information using an estimation model trained using machine learning.

[0058] [7] The device described in [6], wherein the estimation unit inputs vector information based on the purchase behavior information into the estimation model to estimate the purchase motivation information, and the estimation model is trained using the vector information as an explanatory variable and the purchase motivation information as a target variable.

[0059] [8] The device described in any one of [2] to [7], wherein the purchase motivation information includes information indicating the type of motivation for purchasing the purchase item in the purchasing behavior and information indicating an evaluation value related to the motivation for each type, and the estimation unit estimates that the motivation corresponding to the largest evaluation value is the motivation that led the user to make the purchase in the purchasing behavior.

[0060] [9] A method comprising: a determination step of determining behavioral information, which is information indicating a temporal change in a user's state when the user is about to take an action, based on information about the user's behavior; and an estimation step of estimating motivation information, which is information about the user's motivation for taking an action when the user is about to take an action, based on the behavioral information.

[0061] [Definition of Terms, etc.] 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 connected directly or indirectly (e.g., via wire, wirelessly, etc.) and these multiple devices. The functional block may also be realized by combining the single device or multiple devices with software.

[0062] 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.

[0063] For example, the device 10 according to an embodiment of the present disclosure may function as a computer that performs the processing of the present disclosure. Fig. 7 is a diagram illustrating an example of the hardware configuration of the device 10 according to an embodiment of the present disclosure. The device 10 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, etc.

[0064] In the following description, the term "apparatus" can be interpreted as a circuit, a device, a unit, etc. The hardware configuration of apparatus 10 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.

[0065] Each function of the device 10 is realized by loading specified software (programs) onto hardware such as the processor 1001 and memory 1002, causing the processor 1001 to perform calculations, control communication via the communication device 1004, and control at least one of reading and writing data in the memory 1002 and storage 1003.

[0066] The processor 1001 controls the entire computer by running, for example, an operating system. The processor 1001 may be configured by a central processing unit (CPU) including an interface with peripheral devices, a control device, an arithmetic unit, a register, etc. For example, the above-mentioned estimation unit 13 and the like may be realized by the processor 1001.

[0067] 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, the estimation unit 13 and the like may be implemented by a control program stored in the memory 1002 and running on the processor 1001, and similar implementations may also be made for other functional blocks. 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.

[0068] 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 processing according to an embodiment of the present disclosure.

[0069] 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 referred to as an auxiliary storage device. The above-mentioned storage medium may be, for example, a database, a server, or other appropriate medium including at least one of memory 1002 and storage 1003.

[0070] 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 referred to as, for example, a network device, a network controller, a network card, or a communication module. The communication device 1004 may be configured to include a high-frequency switch, a duplexer, a filter, a frequency synthesizer, etc. to realize at least one of frequency division duplex (FDD) and time division duplex (TDD). For example, the input unit 11 described above may be realized by the communication device 1004. The communication device 1004 may be implemented with a transmitter and a receiver that are physically or logically separated from each other.

[0071] 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. Note that the input device 1005 and the output device 1006 may be integrated into one device (e.g., a touch panel).

[0072] 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.

[0073] The device 10 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.

[0074] The notification of information is not limited to the aspects / embodiments described in the present disclosure and may be performed using other methods. For example, the notification of information may be performed by physical layer signaling (e.g., Downlink Control Information (DCI) and Uplink Control Information (UCI)), higher layer signaling (e.g., Radio Resource Control (RRC) signaling, Medium Access Control (MAC) signaling, broadcast information (Master Information Block (MIB) and System Information Block (SIB))), other signals, or a combination thereof. Furthermore, the RRC signaling may be referred to as an RRC message, and may be, for example, an RRC Connection Setup message, an RRC Connection Reconfiguration message, or the like.

[0075] 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.

[0076] 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 sent to another device.

[0077] 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).

[0078] 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).

[0079] Although the present disclosure has been described in detail above, it is clear to those skilled in the art that the present invention is not limited to the embodiments described in the present disclosure. 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.

[0080] 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.

[0081] 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.

[0082] The information, signals, etc. described in this disclosure may be represented using any 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.

[0083] Note that terms described in this disclosure and terms necessary for understanding this disclosure may be replaced with terms having the same or similar meanings. For example, at least one of a channel and a symbol may be a signal (signaling). Furthermore, a signal may be a message. Furthermore, a component carrier (CC) may be called a carrier frequency, a cell, a frequency carrier, etc.

[0084] Furthermore, the information, parameters, etc. described in the present 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. For example, a radio resource may be indicated by an index.

[0085] The names used for the above-described parameters are not intended to be limiting in any way. Furthermore, the mathematical expressions using these parameters may differ from those explicitly disclosed in this disclosure. The various channels (e.g., PUCCH, PDCCH, etc.) and information elements may be identified by any suitable names, and therefore the various names assigned to these various channels and information elements are not intended to be limiting in any way.

[0086] In this disclosure, the terms "Mobile Station (MS)," "user terminal," "User Equipment (UE)," "terminal," and the like may be used interchangeably.

[0087] A mobile station may also be referred to by those skilled in the art as a subscriber station, mobile unit, subscriber unit, wireless unit, remote unit, mobile device, wireless device, wireless communication 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.

[0088] 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.

[0089] 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.

[0090] 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."

[0091] 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.

[0092] 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.

[0093] 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.

[0094] 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."

[0095] 10...device, 11...input unit, 12...determination unit, 13...estimation unit, 1001...processor, 1002...memory, 1003...storage, 1004...communication device, 1005...input device, 1006...output device.

Claims

1. A determination unit that determines action information, which is information indicating a temporal change in the state of the user when the user is about to act, based on information regarding the user's actions; and an estimation unit that estimates motivation information, which is information regarding the motivation for which the user has come to act when the user is about to act, based on the action information. An apparatus comprising the above.

2. The information regarding the user's actions is information regarding the user's purchases. The action information is purchase action information indicating a temporal change in the state of the user in a purchase action, which is an action when the user is about to purchase a purchase target. The motivation information is purchase motivation information regarding the motivation for which the user has come to purchase the purchase target in the purchase action. The apparatus according to claim 1.

3. The purchase action is an action when the user is about to purchase a purchase target during a period from the time when the user has recognized the purchase target to the time when the user has recommended the purchase target. The apparatus according to claim 2.

4. The information regarding the user's purchases includes information regarding the user and information regarding the time associated with the information regarding the user. The determination unit determines, as the purchase action information, a graph in which the information regarding the time is represented as a first node, the information regarding the user is represented as a second node, and the correspondence between the information regarding the user and the information regarding the time is represented as an edge attached between the first node and the second node, based on the information regarding the user's purchases. The apparatus according to claim 2.

5. The information regarding the user is at least any one of information regarding the attributes of the user, information regarding the psychology of the user, and information regarding the actions of the user. The apparatus according to claim 4.

6. The estimation unit estimates the purchase motivation information based on the purchase action information, using an estimation model learned using machine learning. The apparatus according to claim 2.

7. The estimation unit inputs vector information based on the purchase action information into the estimation model to estimate the purchase motivation information. The estimation model is learned with the vector information as an explanatory variable and the purchase motivation information as an objective variable. The apparatus according to claim 6.

8. The purchase motivation information includes information indicating the type of motivation for purchasing a purchase target in the purchase behavior and information indicating the evaluation value for each type of the motivation. The estimation unit estimates that the motivation corresponding to the largest evaluation value is the motivation for which the user has made a purchase in the purchase behavior. The apparatus according to claim 2.

9. A method comprising: a determination step of determining action information, which is information indicating a temporal change in the state of a user when the user is about to take an action, based on information regarding the user's action; and an estimation step of estimating motivation information, which is information regarding the motivation for which the user has taken an action when the user is about to take an action, based on the action information.