Method of providing event and electronic device performing the method

Abstract

A method for providing an event according to various embodiments and an electronic device for performing said method are disclosed. In one embodiment of the present invention, the electronic device includes a processor and a memory electrically connected to said processor and storing instructions executed by said processor. When said instructions are executed, said processor may cause said electronic device to receive data regarding user activity from a server connected via communication, determine said user’s spending tendency based on said data, determine an event to be provided to said user based on said spending tendency, and provide said event to said server.

Description

Technology Field

[0001] The invention relates to a method for providing an event according to various embodiments and an electronic device for performing said method. Background Technology

[0002] Companies providing goods and services conduct various marketing and promotions to increase sales.

[0003] Companies providing numerous mobile applications offer advertising, marketing, and promotions, but the conversion rate of mobile app users to paid subscriptions remains very low.

[0004] The conversion rate of mobile app users to paid payments is very low, at less than 2%. If discount promotions are offered to mobile app users, users can be encouraged to make paid payments, thereby increasing revenue.

[0005] However, providing indiscriminate discount promotions to users may actually lead to a decrease in sales. For example, if discount promotions are offered to users who already have a purchase or payment intention, even without the promotion itself, sales will ultimately decline.

[0006] To increase overall sales, it is necessary to differentiate between users with and without purchasing intent and provide discount promotions to those without purchasing intent.

[0007] The background technology described above is possessed or acquired by the inventor in the process of deriving the content of the disclosure of the present application, and cannot necessarily be considered as prior art disclosed to the general public prior to the filing of this application. The problem to be solved

[0008] According to various embodiments, an electronic device and a method for providing events that can determine or predict a user's payment intention, purchase intention, or spending propensity can be provided.

[0009] According to various embodiments, an electronic device and a method for providing events can be provided to improve sales revenue by providing events (e.g., discount promotions) to users according to their spending habits.

[0010] According to various embodiments, by comparing the average expenditure of a management group and an average expenditure per user of a non-management group, an electronic device and a method for providing events that can improve sales revenue can be provided.

[0011] However, technical challenges are not limited to the technical challenges described above, and other technical challenges may exist. means of solving the problem

[0012] An electronic device according to various embodiments includes a processor and a memory electrically connected to the processor and storing instructions executed by the processor, and when the instructions are executed, the processor may cause the electronic device to receive data regarding user activity from a server connected via communication, determine the user's spending tendency based on the data, determine an event to be provided to the user based on the spending tendency, and provide the event to the server.

[0013] The above user may be included in the management group among all users classified into management groups and non-management groups.

[0014] The above processor can calculate the average expenditure of the management group and the non-management group or the average expenditure per user.

[0015] The above processor can determine the charge amount based on the difference in expenditure between the management group and the non-management group.

[0016] The above processor can determine the event to increase the user's spending amount according to the user's spending propensity.

[0017] The above processor can determine the spending propensity by using a model trained to input the above data and output the spending propensity.

[0018] The processor can receive total data regarding the activities of all users, use the total data to identify changes in the activity patterns of all users, and retrain the model based on the changes in the activity patterns.

[0019] The processor can receive all events from the server and determine the event among the all events.

[0020] A method for providing an event according to various embodiments may include receiving data regarding a user's activity from a server connected via communication, determining the user's spending tendency based on the data, determining an event to be provided to the user based on the spending tendency, and providing the event to the server.

[0021] The above user may be included in the management group among all users classified into management groups and non-management groups.

[0022] The above event provision method may further include an operation to calculate the average expenditure of the management group and the non-management group or the expenditure per user.

[0023] The above event provision method may further include an operation to determine a charge amount based on the difference in expenditure between the management group and the non-management group.

[0024] The operation of determining the above event may include the operation of determining the event to increase the user's expenditure amount according to the user's spending propensity.

[0025] The operation of determining the expenditure propensity may include the operation of determining the expenditure propensity by using a model trained to input the data and output the expenditure propensity.

[0026] The above-described event providing method may include the operation of receiving all data regarding the activities of all users, the operation of identifying a change in the activity pattern of all users using the all-data, and the operation of retraining the model based on the change in the activity pattern.

[0027] The operation of determining the above event may include the operation of receiving all events from the server and the operation of determining the event among the all events. Effects of the invention

[0028] An electronic device and an event providing method according to various embodiments can improve total sales by predicting a user's spending propensity (or intention to pay) and providing an event according to the predicted spending propensity.

[0029] The electronic device and event provision method according to various embodiments can provide information on sales fluctuations resulting from event provision by providing information on expenditures of a management group and a non-management group. Brief explanation of the drawing

[0030] FIG. 1 is a schematic block diagram of an electronic device according to various embodiments. FIG. 2 is a diagram showing the operation of a model according to various embodiments. FIG. 3 is a flowchart of the operation of an event providing method performed by an electronic device according to various embodiments. FIG. 4 is a diagram showing the operation of an electronic device according to various embodiments for determining whether to relearn a model. FIG. 5 is a diagram illustrating the operation of an electronic device according to various embodiments determining an event based on spending propensity. FIG. 6 is a diagram showing the operation of an electronic device according to various embodiments determining a billing amount. FIG. 7 is a diagram illustrating the operation of an electronic device according to various embodiments for determining the ratio of a management group. Specific details for implementing the invention

[0031] Hereinafter, embodiments are described in detail with reference to the attached drawings. However, various modifications may be made to the embodiments, and thus the scope of the patent application is not limited or restricted by these embodiments. It should be understood that all modifications, equivalents, and substitutions to the embodiments are included within the scope of the rights.

[0032] The terms used in the embodiments are for illustrative purposes only and should not be interpreted as intended to be limiting. Singular expressions include plural expressions unless the context clearly indicates otherwise. In this specification, terms such as "comprising" or "having" are intended to indicate the existence of the features, numbers, steps, actions, components, parts, or combinations thereof described in the specification, and should be understood as not precluding the existence or addition of one or more other features, numbers, steps, actions, components, parts, or combinations thereof.

[0034] Unless otherwise defined, all terms used herein, including technical or scientific terms, have the same meaning as generally understood by those skilled in the art to which the embodiments pertain. Terms such as those defined in commonly used dictionaries should be interpreted as having a meaning consistent with their meaning in the context of the relevant technology, and should not be interpreted in an ideal or overly formal sense unless explicitly defined in this application.

[0035] In addition, when describing with reference to the attached drawings, identical components are assigned the same reference numeral regardless of drawing symbols, and redundant descriptions thereof are omitted. In describing the embodiments, if it is determined that a detailed description of related prior art could unnecessarily obscure the essence of the embodiments, such detailed description is omitted.

[0037] 1. Electronic device

[0038] 1.1 Components of the Electronic Device

[0039] FIG. 1 is a schematic block diagram of an electronic device (100) according to various embodiments.

[0040] Referring to FIG. 1, an electronic device (100) according to various embodiments may include a processor (110), memory (120), a model (130), and a communication circuit (140).

[0041] The processor (110) can, for example, execute software (e.g., a program) to control at least one other component (e.g., a hardware or software component) of the electronic device (100) connected to the processor (110) and perform various data processing or operations. According to one embodiment, as at least part of the data processing or operations, the processor (110) can store commands or data received from other components (e.g., a sensor module or a communication module) in volatile memory, process the commands or data stored in volatile memory, and store the resulting data in non-volatile memory. According to one embodiment, the processor (110) may include a main processor (e.g., a central processing unit or an application processor) or an auxiliary processor (e.g., a graphics processing unit, a neural processing unit (NPU), an image signal processor, a sensor hub processor, or a communication processor) that can operate independently or together with it. For example, if the electronic device (100) includes a main processor and an auxiliary processor, the auxiliary processor may be configured to use less power than the main processor or to be specialized for a designated function. The auxiliary processor can be implemented separately from the main processor or as part of it.

[0042] An auxiliary processor can control at least some of the functions or states associated with at least one component (e.g., a display module, a sensor module, or a communication module) of the electronic device (100), for example, on behalf of the main processor while the main processor is in an inactive (e.g., sleep) state, or together with the main processor while the main processor is in an active (e.g., application execution) state. According to one embodiment, the auxiliary processor (e.g., an image signal processor or a communication processor) may be implemented as part of another functionally related component (e.g., a camera module or a communication module). According to one embodiment, the auxiliary processor (e.g., a neural network processing unit) may include a hardware structure specialized for processing an artificial intelligence model. The artificial intelligence model may be generated through machine learning. Such learning may be performed, for example, on the electronic device (100) itself where the artificial intelligence model is executed, or through a separate server.

[0043] The memory (120) can store various data used by at least one component of the electronic device (100) (e.g., processor (110) or model (130)). The data may include, for example, software (e.g., a program) and input data or output data for related instructions. The memory (120) may include volatile memory or non-volatile memory.

[0044] For example, the communication circuit (140) can establish a direct communication channel or a wireless communication channel between the electronic device (100) and the server (10), and support wired / wireless communication through the established communication channel.

[0045] An electronic device (100) and a server (10), or a server (10) and a user terminal (20) may be connected via a network. Examples of networks include, but are not limited to, a 3GPP (3rd Generation Partnership Project) network (3G network, 4G or LTE (Long Term Evolution) network, 5G or NR (New Radio) network, or 6G network, etc.), a WIMAX (World Interoperability for Microwave Access) network, the Internet, a LAN (Local Area Network), a Wireless LAN (Wireless Local Area Network), a WAN (Wide Area Network), a PAN (Personal Area Network), a Bluetooth network, a satellite broadcasting network, an analog broadcasting network, a DMB (Digital Multimedia Broadcasting) network, etc.

[0047] 1.2 Operation of the electronic device (100)

[0048] 1.2.1 Reception of data regarding user activity

[0049] For example, the electronic device (100) may receive data regarding user activities from the server (10). For example, the data may include information regarding activities performed by the user using the user terminal (20).

[0050] According to one embodiment, the server (10) may store data regarding activities performed by a user through an application, a web browser, etc. For example, activities may include all sessions, from signing up and onboarding through an application, a web browser, etc.

[0051] For example, data may include information such as login, logout, product views, post views, product / service purchase status, number of product / service purchases, expenditure amount, time spent on a page, usage time, etc. Additionally, data may include information directly entered by the user, such as age, gender, occupation, etc.

[0052] For example, the data may include event logs and log data that can be received or generated from a terminal at the server (10).

[0053] The information that may be included in the data is not limited to the examples described above and may include various information that can be collected or recognized from the user terminal (20).

[0055] 1.2.2 Determining User Spending Propensity

[0056] For example, the electronic device (100) can determine the user's spending propensity based on data. For example, the spending propensity may indicate the probability that the user will purchase goods / services. Additionally, the spending propensity may indicate the degree of the user's willingness to make a paid payment.

[0058] 1.2.2.1 Learning of the model (130)

[0059] For example, the electronic device (100) can determine the user's spending propensity by inputting user data into a learned model (130). In FIG. 1, for convenience of explanation, the model (130) is described as being a component of the electronic device (100), but is not limited thereto. For example, the model (130) may be software, stored in memory (120), and executed by the processor (110) of the electronic device (100).

[0060] The data used for training the model (130) may include at least one of login, logout, product viewing, post viewing, whether a product / service was purchased, the number of product / service purchases, expenditure amount, page dwell time, and usage time, or a combination thereof. According to one embodiment, the model (130) may be trained to output a spending tendency by inputting data and / or user information.

[0061] For example, the model (130) can be trained using data. For example, the model (130) can be trained to input data and output spending tendencies. The model (130) can be trained by an electronic device (100) or an external electronic device.

[0062] The processor (110) may include at least one processor (110) for processing various data, for example, a plurality of processors (110). The processor (110) may include, for example, a learning processor (110) for machine learning, and may train a model (130) composed of an artificial neural network using training data. The trained artificial neural network may be referred to as a training model (130).

[0063] The learned model (130) can be used to infer a result value for new input data that is not the learning data, and the inferred value can be used as a basis for judgment to perform some action.

[0064] A processor (110) according to one embodiment can train a learning model (130) through a deep learning algorithm. A deep learning algorithm is a machine learning algorithm and refers to a modeling technique (130) developed from an artificial neural network modeled after a human neural network. An artificial neural network can be composed of a multi-layered hierarchical structure.

[0065] An artificial neural network (ANN) may be composed of a hierarchical structure including an input layer, an output layer, and at least one intermediate layer (or hidden layer) (e.g., a kernel) between the input layer and the output layer.

[0066] Deep learning algorithms can produce highly reliable results by optimizing the weights of the activation functions between layers based on such a multi-layer structure.

[0067] The learning algorithm for training the model (130) may include, for example, supervised learning, unsupervised learning, semi-supervised learning, or reinforcement learning, but is not limited to the examples described above. The artificial intelligence model (130) may include a plurality of artificial neural network layers. The artificial neural network may be a deep neural network (DNN), a convolutional neural network (CNN), a recurrent neural network (RNN), a restricted Boltzmann machine (RBM), a deep belief network (DBN), a bidirectional recurrent deep neural network (BRDNN), deep Q-networks, or a combination of two or more of the above, but is not limited to the examples described above. In addition to the hardware structure, the artificial intelligence model (130) may include a software structure, either additionally or substantially.

[0068] Deep learning algorithms applicable to a processor (110) according to one embodiment of the present disclosure may include, for example, a Convolutional Neural Network (CNN) or a Recurrent Neural Network (RNN), but are not limited thereto. It can be understood that other deep learning algorithms may be applied depending on the embodiment.

[0070] 1.2.2.2 Learning of the model (130) for identifying changes in activity patterns

[0071] For example, the electronic device (100) can determine whether there is a change in the activity patterns of all users. For example, the electronic device (100) can determine whether there is a change in the activity patterns of users by analyzing all data (or a part of all data) regarding the activities of all users.

[0072] For example, the electronic device (100) can determine whether there is a change in activity patterns by using changes in total sales, changes in average expenditure per user, changes in payment frequency per user, etc. The electronic device (100) can determine whether there is a change in the activity patterns of users by analyzing the entire data (or a part of the entire data) at set intervals.

[0073] According to one embodiment, the model (130) may be trained to identify whether there is a change in the activity pattern. For example, the model (130) may be trained to output whether there is a change in the activity pattern by inputting all data (or part of all data) regarding the activity of all users.

[0074] The electronic device (100) can identify or determine whether there is a change in the activity patterns of all users by using a learned model (130). If the activity patterns have changed, the electronic device (100) can cause the model (130) to be relearned.

[0075] For example, the electronic device (100) can identify whether there is a change in the activity pattern at set intervals. The electronic device (100) can identify whether there is a change in the activity pattern by inputting the entire data or a part of the entire data into a learned model (130) at set intervals.

[0076] For example, the model (130) can be retrained by the electronic device (100) or an external electronic device. If the activity pattern changes, the model (130) can be retrained to output the user's spending tendency using all data from the time the activity pattern changed for a set period (e.g., 3 days before and after the time the activity pattern changed).

[0077] As the model (130) is retrained according to changes in the user's activity pattern, the model (130) can be trained to output an accurate user's spending tendency.

[0079] 1.2.3 Event Decision

[0080] For example, the electronic device (100) can determine the events to be provided to the user based on spending habits.

[0081] For example, the spending propensity represents the probability that a user will purchase a product / service and can be expressed as a value between 0 and 1. The electronic device (100) can determine whether to provide an event to the user by comparing the spending propensity with a set threshold. If the spending propensity is below the set threshold, the electronic device (100) can decide to provide an event to the user.

[0082] For example, spending propensity can be classified into multiple propensities, such as high, normal, low, etc. The electronic device (100) may decide to provide an event to a user corresponding to a low spending propensity.

[0083] For example, the electronic device (100) can determine which event to provide to the user among multiple events based on spending habits. For example, if the event is a discount promotion, the electronic device (100) can determine which discount promotion to provide to the user among multiple discount promotions with different discount rates.

[0084] For example, the electronic device (100) can determine a discount promotion that can induce a user to make a paid payment and increase sales among a plurality of discount promotions.

[0085] For example, multiple discount promotions may include a discount promotion with a high discount rate and a discount promotion with a low discount rate. For example, if the user's spending propensity is 0 or higher and 0.3 or lower, the electronic device (100) may provide the user with a discount promotion with a high discount rate. If the user's spending propensity is greater than 0.3 and 0.7 or lower, the electronic device (100) may provide the user with a discount promotion with a low discount rate.

[0086] According to one embodiment, the electronic device (100) can determine the discount rate of a discount promotion to be provided to the user. For example, the electronic device (100) can determine or calculate the user's spending propensity according to the discount rate. The electronic device (100) can determine the discount rate of a discount promotion to be provided to the user among the discount rates where the user's spending propensity according to the discount rate exceeds a set threshold.

[0087] For example, if the set threshold is 0.7, the electronic device (100) can calculate or determine the user's spending propensity according to the discount rate. For example, the electronic device (100) can calculate or determine the user's spending propensity as 0.6 when the discount rate is 30%, the user's spending propensity as 0.75 when the discount rate is 50%, and the user's spending propensity as 0.85 when the discount rate is 70%. The electronic device (100) can determine the discount rate to be provided to the user among the discount rates (e.g., 50%, 70%) where the user's spending propensity is calculated to be higher than the set threshold of 0.7. For example, the electronic device (100) can determine a discount promotion with a discount rate of 50% as the discount promotion (or event) to be provided to the user.

[0088] In the above examples, the number of multiple discount promotions, discount rates, and the range of the user's spending propensity are exemplary and are not limited to the examples described above.

[0090] 1.2.3.1 Event Determination Based on User Information

[0091] According to one embodiment, the electronic device (100) can determine an event based on user information and / or spending habits. For example, user information may include products of interest, categories of interest, etc. set by the user. Based on the user information, the electronic device (100) can determine a discount promotion for products of interest or categories of interest as an event.

[0092] The electronic device (100) can provide discount promotions on products of interest, etc., that are likely to be purchased by the user, thereby inducing the user to make a purchase and increasing overall sales.

[0094] 1.2.3.2 Event determination based on previously provided events

[0095] According to one embodiment, the electronic device (100) can determine an event based on at least one of an event previously provided to the user, user information, and spending habits.

[0096] For example, if a user was previously provided with a 30% discount promotion and the user made a payment using the discount promotion, the electronic device (100) can determine the same 30% discount promotion as the previously provided event as the event.

[0097] Additionally, according to an embodiment, the electronic device (100) may determine a discount promotion different from a previously provided event (e.g., a 40% discount promotion, a 20% discount promotion, etc.) as an event. The electronic device (100) may determine an event that is the same as or different from a previously provided event according to a set policy.

[0098] For example, if a user was previously offered a 30% discount promotion and the user did not make a payment using the discount promotion, the electronic device (100) may determine a discount promotion with a higher discount rate than the previously offered discount promotion (e.g., a 40% discount promotion) as an event.

[0100] 1.2.3.3 Event Determination for Management Groups

[0101] For example, all users may be divided into a management group and a non-management group. For example, the electronic device (100) can determine the spending tendency of users included in the management group. The electronic device (100) can provide events to users included in the management group according to the spending tendency.

[0102] For example, the electronic device (100) can determine or calculate the average expenditure of the management group and the non-management group and / or the average expenditure per user. The electronic device (100) can determine the increase in sales resulting from the provision of events by comparing the average expenditure of the management group and the non-management group and / or the average expenditure per user.

[0103] For example, if the average expenditure per user of the management group is higher than the average expenditure per user of the non-management group, it can be understood that the total expenditure of the management group has increased due to the influence of the provided event. The electronic device (100) can evaluate the increase in sales revenue by providing events according to the spending propensity by calculating the average expenditure or expenditure per user of the management group and the non-management group.

[0104] For example, the electronic device (100) can determine the charge amount based on the difference in expenditure between the management group and the non-management group. For example, the electronic device (100) can determine the charge amount as a certain percentage of the increased sales revenue by providing an event based on the expenditure tendency.

[0105] The user of the electronic device (100) may charge the administrator (or service provider) of the server (10) a determined amount. The difference between the expenditure of the management group (or the average expenditure per user) and the expenditure of the non-management group (or the average expenditure per user) may occur depending on the event provided by the electronic device (100). The user of the electronic device (100) may charge the administrator of the server (10) a certain percentage of the increase in sales revenue generated depending on the provision of the event.

[0106] As a result, the manager of the server (10) can increase the overall sales and increase the profit. In addition, since the manager of the server (10) pays costs in proportion to the increase in sales, the billing amount can be set reasonably.

[0108] 1.2.4 Event Provision

[0109] For example, the electronic device (100) can provide an event to the server (10). The server (10) can provide the received event to the user terminal (20).

[0110] For example, an electronic device (100) may provide a Software Development Kit (SDK) to a server (10). An administrator (or user) of the server (10) may use the SDK to enable the server (10) to provide events to the user. Additionally, an administrator (or user) of the server (10) may use the SDK to configure the necessary details for providing events to the user. For example, the details required for providing events may include the ratio of the managed group to the unmanaged group, the event (or promotion) to be provided, and the time for providing the event. An administrator of the server (10) may change the details required for providing events.

[0111] A user terminal (20) according to one embodiment may include all types of wired and wireless communication devices capable of input and output, such as, for example, PCS (Personal Communication System), GSM (Global System for Mobile communication), PDC (Personal Digital Cellular), PHS (Personal Handyphone System), PDA (Personal Digital Assistant), IMT (International Mobile Telecommunication)-2000, CDMA (Code Division Multiple Access)-2000, W-CDMA (WCode Division Multiple Access), Wibro (Wireless Broadband Internet) terminal, smartphone, smartpad, tablet PC, laptop, wearable device, digital signage, etc., but is not limited thereto.

[0112] For example, the electronic device (100) can provide statistical information to the server (10), such as the amount spent by the management group and / or non-management group, the average amount spent per user, the sales revenue increased by the provision of events, and the amount charged.

[0113] The above description of FIG. 1 is a description of an example in which an electronic device (100) includes a model (130) and determines an event to be provided to a user (or user terminal (20)) based on data received from a server (10).

[0114] In an embodiment other than the embodiment shown in FIG. 1, a user terminal (20) according to one embodiment may include a model (e.g., model (130)) or store it in the memory of the user terminal (20).

[0115] The model included in the user terminal (20) can operate substantially the same as the aforementioned model (130). For example, the model included in the user terminal (20) can output the user's spending tendency when data regarding the user's activity is input. The user terminal (20) can input data regarding the user's activity into the model to determine or output the user's spending tendency. The user terminal (20) can determine or generate data based on input received from the user at the user terminal.

[0116] The user terminal (20) can transmit spending trends to the server (20). The server (20) can determine an event to transmit to the user terminal (20) in response to the received spending trends. The server (20) can provide the determined event to the user terminal (20).

[0118] FIG. 2 is a diagram showing the operation of a model (130) according to various embodiments.

[0119] In FIG. 2, the data (131) may include data (131) regarding the activity of a specific user, or overall data (131) regarding the activity of all users.

[0120] For example, data (131) may represent a log generated by collecting events, activities, and events that occurred from a user terminal (20) connected to the server (10). For example, activities may include all activities that can be performed from the user terminal (20). Activities may include actions performed through the user terminal (20), such as signing up, logging in, viewing, purchasing products, making payments, searching, etc.

[0121] Referring to FIG. 2, a model (130) according to one embodiment can be trained to output a spending tendency (133) using input data (131).

[0122] Spending propensity (133) can indicate, for example, the probability of a user making a payment or the extent to which a payment is made.

[0123] Referring to FIG. 2, a model (130) according to one embodiment can be trained to output whether there is a change in the activity pattern (135) using input data (131) (or the entire data (131), a part of the entire data (131)).

[0124] For example, the electronic device (100) can determine whether there is a change in the activity pattern (135) by using the model (130) at set intervals. If the activity pattern has changed, the electronic device (100) can cause the model (130) to be relearned.

[0126] FIG. 3 is a flowchart of the operation of an event providing method performed by an electronic device (100) according to various embodiments.

[0127] The operations (310) to (340) illustrated in FIG. 3 can be performed substantially identically by the processor (110) of the electronic device (100).

[0128] The operations (310) to (340) illustrated in FIG. 3 may be performed sequentially, but are not necessarily performed sequentially. For example, the order of the operations may be changed, and at least two operations may be performed in parallel.

[0129] For example, the electronic device (100) can receive data regarding user activities from a server (10) connected via communication in operation (310). For example, the data may be regarding user activities and may include information regarding all activities performed through a user terminal (20) connected via communication to the server (10).

[0130] For example, the electronic device (100) can determine the user's spending propensity based on data in operation (320). The user's spending propensity can indicate the probability and degree to which the user makes a payment.

[0131] For example, an electronic device (100) can determine a user's spending propensity using a learned model (130). The model (130) can be trained to output a spending propensity using input data.

[0132] For example, the electronic device (100) can determine the event to be provided to the user based on spending habits in operation (330).

[0133] The electronic device (100) can determine an event by comparing the spending propensity with a threshold value.

[0134] For example, if the spending propensity is above a threshold, the electronic device (100) may not provide an event to the user. A spending propensity exceeding the threshold may indicate that the user is highly likely to make a payment even without providing an event. Therefore, in order to improve overall sales, the electronic device (100) may not provide an event to users who are highly likely to make a payment.

[0135] For example, if the spending propensity is below a threshold, the electronic device (100) can determine an event to provide to the user. A spending propensity below the threshold may indicate that the user is unlikely to make a payment if no event is provided. Therefore, in order to improve overall sales, the electronic device (100) can determine an event to provide to the user.

[0136] For example, the electronic device (100) can determine which event to provide to the user among a plurality of events based on spending propensity. For example, the electronic device (100) can determine a discount promotion with a lower discount rate as an event when the spending propensity is high. The electronic device (100) can determine a discount promotion with a higher discount rate as an event when the spending propensity is low.

[0137] According to one embodiment, the electronic device (100) may determine an accumulation promotion as an event for a user whose spending propensity is lower (than a threshold). The accumulation promotion may represent a promotion that provides a portion of the user's spending amount as points. By providing the accumulation promotion to a user with a low spending propensity, the electronic device (100) may induce the user to make a repurchase to utilize the points.

[0138] As described above, the electronic device (100) can determine an event suitable for providing to the user among a plurality of events according to the spending tendency. For example, the plurality of events may include a plurality of promotions with different values ​​and types, such as discount promotions with various discount rates, accumulation promotions with various accumulation rates, free shipping promotions, etc.

[0139] For example, the electronic device (100) can provide an event to the server (10) in operation (340). The server (10) can provide the received event to the user terminal (20).

[0140] If events such as discount promotions are provided to all users regardless of the user's spending propensity, the total sales may actually decrease. The electronic device (100) can identify users who are unlikely to make a payment based on their spending propensity. The electronic device (100) can increase the total sales by providing events only to users with low spending propensity.

[0142] FIG. 4 is a diagram showing the operation of an electronic device (100) according to various embodiments to determine whether to relearn a model (130).

[0143] The operations (410) to (430) illustrated in FIG. 4 can be performed substantially identically by the processor (110) of the electronic device (100).

[0144] The operations (410) to (430) illustrated in FIG. 4 may be performed sequentially, but are not necessarily performed sequentially. For example, the order of the operations may be changed, and at least two operations may be performed in parallel.

[0145] For example, the electronic device (100) can receive all data regarding the activity of all users in operation (410).

[0146] For example, the electronic device (100) may receive the entire data at set intervals. Alternatively, the electronic device (100) may receive the entire data when the possibility of a change in the activity pattern is identified. For example, the electronic device (100) may identify the possibility of change when the amount of change in total sales is greater than a set threshold, or when the change in the sales ratio of a product or product category is greater than a set threshold. The criteria for determining the possibility of change are not limited to the examples described above and may be set in various ways.

[0147] For example, the electronic device (100) can identify changes in the activity patterns of all users by using the entire data in operation (420).

[0148] The electronic device (100) can identify changes in the activity patterns of all users by analyzing the entire data (or a part of the entire data). For example, the electronic device (100) can determine whether there is a change in the activity pattern by using changes in total sales, changes in the average expenditure per user, changes in the frequency of payments per user, changes in the sales ratio of products or product categories, etc. The electronic device (100) can determine whether there is a change in the activity patterns of users by analyzing the entire data (or a part of the entire data) at set intervals.

[0149] The electronic device (100) can identify or determine whether there is a change in the activity patterns of all users by using a learned model (130). According to one embodiment, the model (130) can be learned to identify whether there is a change in the activity patterns. For example, the model (130) can be learned to input all data (or part of the all data) regarding the activities of all users and output whether there is a change in the activity patterns.

[0150] For example, the electronic device (100) can cause the model (130) to be retrained based on a change in the activity pattern in operation (430). For example, the electronic device (100) can cause the model (130) to be retrained using all data for a set period from the time when the activity pattern changed.

[0152] FIG. 5 is a diagram showing the operation of an electronic device (100) according to various embodiments determining an event based on spending tendencies.

[0153] The operations (510) to (530) illustrated in FIG. 5 can be performed substantially identically by the processor (110) of the electronic device (100).

[0154] The operations (510) to (530) illustrated in FIG. 5 may be performed sequentially, but are not necessarily performed sequentially. For example, the order of the operations may be changed, and at least two operations may be performed in parallel.

[0155] For example, the electronic device (100) can compare the spending propensity with a first threshold value in the operation (510) following the operation (320) of FIG. 3.

[0156] In operation (510), if it is determined that the spending propensity is greater than the first threshold, the electronic device (100) may determine in operation (520) that the second event is an event to be provided to the user.

[0157] In operation (510), if it is determined that the spending propensity is below the first threshold, the electronic device (100) may determine in operation (530) that the first event is an event to be provided to the user.

[0158] As with operations (520) and (530), the electronic device (100) can determine an event to increase the total sales amount or an event to increase the user's spending amount according to the spending tendency.

[0159] For example, the first event may be a discount promotion with a low discount rate, and the second event may be a discount promotion with a high discount rate. If the spending propensity is greater than the first threshold, the electronic device (100) may determine the first event of the discount promotion with a low discount rate as the event to be provided to the user because the probability of the user making a payment is high when the spending propensity is greater than the first threshold. If the spending propensity is less than or equal to the first threshold, the electronic device (100) may determine the second event of the discount promotion with a high discount rate as the event to be provided to the user because the probability of the user making a payment is low when the spending propensity is less than or equal to the first threshold.

[0160] For example, the first event may be a discount promotion, and the second event may be a reward promotion. Since the probability of the user making a payment is low when the spending propensity is below the first threshold, the electronic device (100) may decide to provide the second event, a reward promotion with a high reward rate, to the user. By providing rewards according to the reward promotion to users with a spending propensity below the first threshold, future repurchases by the user can be encouraged.

[0161] As described above, the electronic device (100) can provide a discount promotion with a different discount rate depending on the user's spending habits. Additionally, the electronic device (100) can determine an event that can increase the user's spending amount among a plurality of events of different types.

[0162] The electronic device (100) can receive all events (or multiple events) from the server (10). The electronic device (100) can determine, among the multiple events received from the server (10), an event suitable for the user or an event to increase the user's expenditure.

[0163] For example, the electronic device (100) can perform the operation (340) of FIG. 3 after the operation (420) and operation (430).

[0165] FIG. 6 is a diagram showing the operation of an electronic device (100) according to various embodiments determining a charge amount.

[0166] The operations (610) to (630) illustrated in FIG. 6 can be performed substantially identically by the processor (110) of the electronic device (100).

[0167] The operations (610) to (630) illustrated in FIG. 6 may be performed sequentially, but are not necessarily performed sequentially. For example, the order of the operations may be changed, and at least two operations may be performed in parallel.

[0168] For example, the electronic device (100) can calculate the average expenditure of the management group and the non-management group or the expenditure per user in operation (610).

[0169] For example, all users may be divided into a management group and a non-management group. The electronic device (100) can determine the spending habits of users included in the management group. The electronic device (100) can determine events based on the spending habits of users included in the management group.

[0170] For example, the non-managed group may represent a comparison group for comparing or verifying the increase in sales of the managed group due to the operation of the electronic device (100).

[0171] For example, the electronic device (100) can determine the charge amount based on the difference between the average expenditure of the management group and the non-management group or the average expenditure per user in operation (620).

[0172] For example, the difference between the average expenditure or expenditure per user of the management group and the non-management group may represent the increase in the average expenditure or expenditure per user caused by the operation of the electronic device (100).

[0173] The electronic device (100) can determine the charge amount based on the difference between the average expenditure of the management group and the non-management group or the average expenditure per user. For example, the difference between the average expenditure per user of the management group and the non-management group may be caused by the operation of the electronic device (100). The electronic device (100) can determine the additional expenditure caused by the operation of the electronic device (100) by using the difference between the average expenditure per user of the management group and the non-management group. The electronic device (100) can determine the charge amount by a set percentage of the additional expenditure caused by the operation of the electronic device (100).

[0174] For example, the billing amount may represent the amount charged to the administrator (or user) of the server (10).

[0175] For example, the electronic device (100) can provide sales statistics information in operation (630) by using the average of the expenditures of the management group and the non-management group or the expenditures per user.

[0176] For example, sales statistics information may include information such as the average expenditure of the management group and the non-management group or the expenditure per user, total sales, and additional sales generated due to the operation of the electronic device (100). Sales statistics information may include expenditures, sales, etc., during a set period (e.g., 1 day, 3 days, 1 week).

[0178] FIG. 7 is a diagram showing the operation of an electronic device (100) according to various embodiments for determining the ratio of a management group.

[0179] The operations (710) to (750) illustrated in FIG. 7 can be performed substantially identically by the processor (110) of the electronic device (100).

[0180] The operations (710) to (750) illustrated in FIG. 7 may be performed sequentially, but are not necessarily performed sequentially. For example, the order of the operations may be changed, and at least two operations may be performed in parallel.

[0181] Referring to FIG. 7, an electronic device (100) according to one embodiment can compare the average expenditure per user of a management group with the average expenditure per user of a non-management group in operation (710).

[0182] In operation (710), if it is determined that the average expenditure per user of the management group exceeds the average expenditure per user of the non-management group, the electronic device (100) can compare the ratio of the management group with a first threshold and a second threshold in operation (720).

[0183] For example, the first threshold and the second threshold may represent the minimum and maximum values ​​of the ratio of management groups that can be set.

[0184] In operation (720), if the ratio of the management group exceeds the first threshold and is less than the second threshold, the electronic device (100) can increase the ratio of the management group in operation (750).

[0185] The fact that the average expenditure per user in the management group is greater than the average expenditure per user in the non-management group may indicate that the total sales have increased as users make additional payments according to the operation of the electronic device (100).

[0186] In order to further increase the total sales revenue, the electronic device (100) can increase the proportion of the management group in the operation (750).

[0187] In operation (710), if it is determined that the average expenditure per user of the management group is less than or equal to the average expenditure per user of the non-management group, the electronic device (100) can compare the ratio of the management group with a first threshold and a second threshold in operation (730).

[0188] In operation (730), if the ratio of the management group exceeds the first threshold and is less than the second threshold, the electronic device (100) can reduce the ratio of the management group in operation (740).

[0190] Meanwhile, the method according to the present invention is written as a program executable on a computer and can be implemented on various recording media such as magnetic storage media, optical reading media, and digital storage media.

[0191] Implementations of the various technologies described herein may be implemented as digital electronic circuits, or as computer hardware, firmware, software, or combinations thereof. Implementations may be implemented as computer program products, i.e., computer programs tangibly embodied in information carriers, such as machine-readable storage devices (computer-readable media) or radio signals, for processing by the operation of data processing devices, e.g., programmable processors, computers, or multiple computers, or for controlling such operation. Computer programs such as the computer program(s) described above may be written in any form of programming language, including compiled or interpreted languages, and may be deployed in any form, including as a standalone program or as a module, component, subroutine, or other unit suitable for use in a computing environment. Computer programs may be deployed to be processed on one computer or multiple computers at one site, or distributed across multiple sites and interconnected by a communication network.

[0192] Processors suitable for processing computer programs include, for example, both general-purpose and special-purpose microprocessors, and any one or more processors of any type of digital computer. Generally, the processor will receive instructions and data from read-only memory or random access memory, or both. The elements of the computer may include at least one processor that executes instructions and one or more memory devices that store instructions and data. Generally, the computer may include one or more mass storage devices that store data, for example, magnetic, magneto-optical disks, or optical disks, or may be combined to receive data from these, transmit data to these, or both. Information carriers suitable for embodying computer program instructions and data include, for example, semiconductor memory devices, magnetic media such as hard disks, floppy disks, and magnetic tapes; optical media such as CD-ROMs (Compact Disk Read Only Memory) and DVDs (Digital Video Disks); magneto-optical media such as floptical disks; ROMs (Read Only Memory); RAMs (Random Access Memory); flash memory; EPROMs (Erasable Programmable ROM); EEPROMs (Electrically Erasable Programmable ROM); etc. Processors and memory may be supplemented by or included in special-purpose logic circuit organizations.

[0193] Additionally, a computer-readable medium may be any available medium accessible by a computer and may include both computer storage media and transmission media.

[0194] Although this specification contains details of a number of specific embodiments, they should not be understood as limiting the scope of any invention or claimables, but rather as descriptions of features that may be characteristic of a specific embodiment of a specific invention. Specific features described in this specification in the context of individual embodiments may be implemented in combination in a single embodiment. Conversely, various features described in the context of a single embodiment may also be implemented in multiple embodiments individually or in any appropriate sub-combination. Furthermore, while features may operate in a specific combination and be described as initially claimed, one or more features from the claimed combination may be excluded from the combination in some cases, and the claimed combination may be changed to a sub-combination or a variation of the sub-combination.

[0195] Likewise, although operations are depicted in the drawings in a specific order, this should not be understood as requiring that such operations be performed in that specific or sequential order depicted to obtain a desirable result, or that all depicted operations must be performed. In certain cases, multitasking and parallel processing may be advantageous. Furthermore, the separation of the various device components of the embodiments described above should not be understood as requiring such separation in all embodiments, and it should be understood that the described program components and devices can generally be integrated together into a single software product or packaged into multiple software products.

[0196] Meanwhile, the embodiments of the present invention disclosed in this specification and drawings are merely specific examples provided to aid understanding and are not intended to limit the scope of the present invention. It is obvious to those skilled in the art that other variations based on the technical concept of the present invention are possible in addition to the embodiments disclosed herein. Explanation of the symbols

[0198] 10: Server 20: User terminal 100: Electronic device 110: Processor 120: Memory 130: Model 140: Communication circuit

Claims

Claim 1 In electronic devices, a processor; The processor includes a memory electrically connected to the processor and storing instructions executed by the processor, wherein when the instructions are executed, the processor causes the electronic device to receive data regarding user activity from a server connected via communication; determine the user’s spending propensity based on the data; determine an event to be provided to the user based on the spending propensity and provide the event to the server, wherein the user is included in the management group among all users classified into a management group and a non-management group, the spending propensity includes the probability that the user will make a payment, and the event includes one or more of a discount promotion or a reward promotion, wherein the processor determines the spending propensity using a model trained to input the data and output the spending propensity, and determines to provide the event to a user whose spending propensity is lower than a first threshold, and if it is determined to provide the event as a discount promotion, determines to provide the discount promotion with a higher discount rate as the spending propensity is lower, calculates the user’s spending propensity according to the discount rate, and among the discount rates where the user’s spending propensity according to the discount rate exceeds a second threshold, the discount promotion to be provided to the user If it is determined that a discount rate is determined and the above event is provided as the above accumulation promotion, it is determined that the above accumulation promotion with a higher accumulation rate is provided as the spending propensity is lower, and (i) if the amount of change in total sales is greater than a third threshold, or (ii) if the change in the sales ratio of a product or product category is greater than a fourth threshold, the possibility of a change in the activity pattern of the entire user is identified, and in response to the identification of the possibility of a change, the entire data regarding the activity of the entire user is received, and the change in the activity pattern of the entire user is identified using the entire data.An electronic device that, based on a change in the activity pattern, retrains the model to output the spending propensity using the entire data for a set period from the point in time when the activity pattern changed, compares the average spending per user of the management group with the average spending per user of the non-management group, and if the average spending per user of the management group exceeds the average spending per user of the non-management group and the proportion of the management group exceeds a fifth threshold—wherein the fifth threshold represents the minimum value of the proportion of the management group—and is less than a sixth threshold—wherein the sixth threshold represents the maximum value of the proportion of the management group—increases the proportion of the management group, and if the average spending per user of the management group is less than or equal to the average spending per user of the non-management group and the proportion of the management group exceeds the fifth threshold and is less than the sixth threshold, decreases the proportion of the management group. Claim 2 delete Claim 3 In paragraph 1, the processor is an electronic device that calculates the average expenditure of the management group and the non-management group or the expenditure per user. Claim 4 In paragraph 3, the processor is an electronic device that determines a charge amount based on the difference between the expenditures of the management group and the non-management group. Claim 5 In claim 1, the processor is an electronic device that determines the event to increase the user's expenditure amount according to the user's spending propensity. Claim 6 delete Claim 7 delete Claim 8 In claim 1, the processor receives all events from the server; and among the all events, the electronic device determines the event. Claim 9 A method for providing an event performed by an electronic device comprising a processor and a memory electrically connected to the processor and storing instructions executed by the processor, the method comprising: receiving data regarding a user’s activity from a communication-connected server; determining the user’s spending propensity based on the data; determining an event to be provided to the user based on the spending propensity; and providing the event to the server, wherein the user is included in the management group among all users classified into a management group and a non-management group, the spending propensity includes the probability that the user will make a payment, and the event includes one or more of a discount promotion or a reward promotion, the operation of determining the spending propensity includes determining the spending propensity using a model trained to input the data and output the spending propensity, and the operation of determining the event includes determining to provide the event to a user whose spending propensity is lower than a first threshold. If it is decided to provide the above event as the above discount promotion, the operation of determining to provide the above discount promotion with a higher discount rate as the spending propensity is lower, calculating the user's spending propensity according to the discount rate, and determining the discount rate of the above discount promotion to be provided to the user among the discount rates where the user's spending propensity according to the discount rate exceeds a second threshold; if it is decided to provide the above event as the above accumulation promotion, the operation of determining to provide the above accumulation promotion with a higher accumulation rate as the spending propensity is lower; (i) if the amount of change in total sales is greater than a third threshold, or (ii) if the change in the sales ratio of a product or product category is greater than a fourth threshold, the operation of identifying the possibility of change in the activity pattern of the entire user; and in response to the identification of the possibility of change, the operation of receiving all data regarding the activity of the entire user.An event providing method comprising: an operation of identifying a change in the activity pattern of all users using the entire data; an operation of retraining the model to output the spending propensity using the entire data for a set period from the time when the activity pattern changed, based on the change in the activity pattern; an operation of comparing the average expenditure per user of the management group with the average expenditure per user of the non-management group; an operation of increasing the ratio of the management group when the average expenditure per user of the management group exceeds the average expenditure per user of the non-management group and the ratio of the management group exceeds a fifth threshold—where the fifth threshold represents the minimum value of the ratio of the management group—and is less than a sixth threshold—where the sixth threshold represents the maximum value of the ratio of the management group—; and an operation of decreasing the ratio of the management group when the average expenditure per user of the management group is less than or equal to the average expenditure per user of the non-management group and the ratio of the management group exceeds the fifth threshold and is less than the sixth threshold. Claim 10 delete Claim 11 In claim 9, an event providing method further comprising the operation of calculating the average expenditure or expenditure per user of the management group and the non-management group. Claim 12 An event providing method according to claim 11, further comprising the operation of determining a charge amount based on the difference in expenditure between the management group and the non-management group. Claim 13 In claim 9, the operation of determining the event includes the operation of determining the event to increase the user's expenditure amount according to the user's expenditure tendency, an event providing method. Claim 14 delete Claim 15 delete Claim 16 In claim 9, the operation of determining the event comprises: the operation of receiving all events from the server; and the operation of determining the event among all events, an event providing method.

Images