Information processing device, information processing method, and information processing program
The information processing device optimizes advertisement distribution by defining customer journeys and using predictive models to enhance conversions and micro-conversions, addressing the limitations of existing technologies in managing the full user funnel from awareness to purchase.
Patent Information
- Application Number
- JP2023083250
- Authority / Receiving Office
- JP · JP
- Patent Type
- Applications
- Current Assignee / Owner
- Filing Date
- 2023-05-19
- Publication Date
- 2024-11-29
AI Technical Summary
Existing advertisement distribution technologies fail to optimize the entire user journey from product awareness to purchase, lacking comprehensive strategies for maximizing conversions and micro-conversions across diverse user actions.
An information processing device that receives customer journey settings defining multiple time-series user actions and performs optimization processing to enhance advertisement distribution, using predictive models to determine optimal strategies based on advertising budget, user attributes, and creative information.
Supports optimized advertisement distribution by predicting user types that maximize conversions and micro-conversions, improving the effectiveness of ad campaigns by aligning strategies with user behaviors and budget constraints.
Smart Images

Figure 2024166863000001_ABST
Abstract
Description
[Technical field]
[0001] The present invention relates to an information processing device, an information processing method, and an information processing program. [Background technology]
[0002] In recent years, with the rapid spread of the Internet, advertisement distribution via the Internet has become popular. As an example of such advertisement distribution, a technology has been proposed that maximizes advertising profits by controlling the bid amount for an advertisement space based on past bidding records (for example, see Patent Document 1). [Prior art documents] [Patent documents]
[0003] [Patent Document 1] JP 2019-220052 A Summary of the Invention [Problem to be solved by the invention]
[0004] However, the user actions that need to be monitored throughout the entire process from when a user becomes aware of an advertised product or service to when they purchase it (hereinafter referred to as the full funnel) are becoming more diverse, making it desirable to optimize ad delivery for at least part of the full funnel.
[0005] The present application has been made in consideration of the above, and aims to provide an information processing device, an information processing method, and an information processing program capable of supporting optimization related to advertisement delivery. [Means for solving the problem]
[0006] The information processing device of the present disclosure includes a reception unit and an optimization unit. The reception unit receives a setting of a customer journey in which a plurality of user actions in a time series related to an advertising target are defined. The optimization unit performs an optimization process for advertisement delivery in the customer journey based on the customer journey setting received by the reception unit. Effect of the Invention
[0007] According to one aspect of the embodiment, it is possible to provide an effect of supporting optimization of advertisement delivery. [Brief description of the drawings]
[0008] [Figure 1] FIG. 1 is a diagram illustrating an example of information processing according to an embodiment. [Diagram 2] FIG. 2 is a diagram illustrating an example of the configuration of an information processing system according to the embodiment. [Diagram 3] FIG. 3 is a diagram illustrating an example of the configuration of the information processing device according to the embodiment. [Figure 4] FIG. 4 is a diagram illustrating an example of a user information table stored in the user information storage unit of the information processing device according to the embodiment. [Diagram 5] FIG. 5 is a diagram showing an example of a customer journey setting screen displayed on a terminal device based on customer journey setting information provided by a providing unit of an information processing device according to the embodiment. [Figure 6] FIG. 6 is a diagram showing an example of optimization-related information provided by the providing unit of the information processing device according to the embodiment and displayed on a terminal device. [Figure 7] FIG. 7 is a diagram showing another example of optimization-related information provided by the providing unit of the information processing device according to the embodiment and displayed on the terminal device. [Figure 8] FIG. 8 is a diagram illustrating an example of a customer journey setting area included in a customer journey setting screen displayed on a terminal device according to the embodiment. [Figure 9]FIG. 9 is a diagram illustrating an example of operation status information provided by the providing unit of the information processing device according to the embodiment and displayed on the terminal device. [Figure 10] FIG. 10 is a flowchart illustrating an example of information processing by the processing unit of the information processing device according to the embodiment. [Figure 11] FIG. 11 is a hardware configuration diagram showing an example of a computer that realizes the functions of the information processing device according to the embodiment. DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS
[0009] Hereinafter, the information processing device, the information processing method, and the information processing program according to the present application (hereinafter, referred to as "embodiments") will be described in detail with reference to the drawings. Note that the information processing device, the information processing method, and the information processing program according to the present application are not limited to these embodiments. In addition, each embodiment can be appropriately combined as long as the processing contents are not contradictory. In addition, the same parts in each of the following embodiments are given the same reference numerals, and duplicated explanations will be omitted.
[0010] [1. An example of information processing] First, an example of information processing according to the embodiment will be described with reference to Fig. 1. Fig. 1 is a diagram showing an example of information processing according to the embodiment, which is executed by an information processing device 1.
[0011] The information processing device 1 shown in Fig. 1 accepts the setting of a customer journey in which multiple time-series user actions related to an advertising target are defined, and performs optimization processing related to advertisement delivery in the customer journey based on the customer journey setting accepted. In this way, the information processing device 1 can support optimization related to advertisement delivery. The information processing executed by the information processing device 1 will be specifically described below.
[0012] 1, the information processing device 1 provides customer journey setting information to the terminal device 2 of the worker O (step S1). The worker O is, for example, an advertiser who wishes to deliver advertisements related to the target of the advertisement (hereinafter, sometimes referred to as the "advertising target") or a business entity entrusted with setting the delivery of advertisements related to the advertising target.
[0013] An advertisement is, for example, content for advertising an advertising target, and is also called advertising content. Examples of such advertisements include, but are not limited to, banner advertisements, listing advertisements, native advertisements, social media advertisements, and video advertisements.
[0014] The customer journey setting information is information for the worker O to set a customer journey using the terminal device 2. For example, when a web browser is installed in the terminal device 2, the customer journey setting information is, for example, information used in the web browser.
[0015] When the customer journey setting information is information used in a web browser, the customer journey setting information includes information written using, for example, HTML (HyperText Markup Language), CSS (Cascading Style Sheets), script (e.g., Javascript (registered trademark)), etc.
[0016] Furthermore, in the case where a customer journey setting app, which is a dedicated application program, is installed in the terminal device 2, the customer journey setting information is, for example, information used in the customer journey setting app.
[0017] When the customer journey setting information is information used in a customer journey setting app, the customer journey setting information includes information written using a format that represents a data structure, such as JSON (JavaScript Object Notation) or XML (eXtension Markup Language).
[0018] The terminal device 2 requests customer journey setting information from the information processing device 1 via an interface such as an API (Application Programming Interface) by processing the customer journey setting app. The terminal device 2 acquires the customer journey setting information transmitted from the information processing device 1 in response to the request.
[0019] Based on the customer journey setting information provided by the information processing device 1, the terminal device 2 displays a customer journey setting screen, which is a screen for setting a customer journey in which multiple user actions in a time series related to the advertising target are defined (step S2).
[0020] On the customer journey setting screen, the worker O can set the customer journey, delivery information, and the like by operating the terminal device 2. The worker O sets the customer journey related to the advertising target, for example, by selecting a plurality of user action parts related to the advertising target, arranging these plurality of user action parts in chronological order, and setting advertising information in at least one of these plurality of user action parts.
[0021] The customer journey setting screen includes, for example, a user action library area, a customer journey setting area, a delivery property setting area, an optimization button, and a trend visualization button.
[0022] In the user action library area, a user action library including multiple types of user action components and multiple types of connection components is arranged. By operating the terminal device 2, the worker O can select the necessary user action components and connection components from the user action library and arrange the selected user action components and connection components in the customer journey setting area.
[0023] The customer journey setting information includes a user action library according to the type of advertising target, and the worker O can use a user action library according to the type of advertisement or the type of advertising target. The type of advertising target is, for example, a type of conversion or a type of conversion target. The user action library according to the type of advertisement or the type of advertising target is selected by the information processing device 1 based on the type of advertisement or the type of advertising target set by the worker O, but the worker O can also select from multiple user action libraries.
[0024] The multiple types of user action components included in the user action library include click action components, view action components, search action components, video playback action components, video click action components, micro conversion components, conversion components, etc., but are not limited to these examples and can include a variety of components.
[0025] Various user action components are, for example, GUI (Graphical User Interface) components, and by selecting a user action component through an operation on the terminal device 2, a property window for setting information related to the user action can be displayed on the terminal device 2.
[0026] The worker O can set information related to a user action in the property window by operating the terminal device 2. In the property window, for example, a UI (User Interface) for setting the contents of each of a plurality of property items is arranged. The worker O can set the contents of the property items in the property window by operating the UI by operating the terminal device 2.
[0027] The contents of the property items include, for example, information indicating details of a user action, information indicating a detection condition for the user action, information indicating a value of the user action, and the like, but are not limited to these examples.
[0028] The UI for setting the contents of each of the multiple property items is, for example, a property grid, but is not limited to this example. For example, the UI for setting the contents of the property items may be, for example, an input frame, a combo box, a check box, a check list box, or other UI.
[0029] In addition, the UI for setting the contents of each of the multiple definition items may be, for example, a UI for setting property items in which setting examples are displayed in text or audio, and which can be switched for each property item.
[0030] A click action component is, for example, a component that indicates that a user action is a click on an advertisement other than a video advertisement. The contents of the property items set in the property window of the click action component include, for example, information that identifies the advertisement that is the subject of the click, information that indicates the attributes of the user that is the target of the advertisement, and information that indicates the value of the user action. The information that identifies the advertisement includes, but is not limited to, creative information of the advertisement. Note that in the click action component, "click" information is preset as information that indicates the detection condition of the user action.
[0031] The view action component is, for example, a component that indicates that the user action is viewing. The contents of the property items set in the property window of the view action component are, for example, information indicating the value of the user action, information indicating the minimum display time on the user's terminal device, information specifying the target of the view action, etc. The target of the view action is, for example, a specific advertisement, a specific website, or a specific web page, but is not limited to such examples.
[0032] The search action component is, for example, a component that indicates that the user action is a search. The search is, for example, a search of a website or a web page (web search), but is not limited to such an example and may be, for example, a search using a natural language model.
[0033] The contents of the property items set in the property window of the search action component are, for example, information indicating one or more search keywords, information indicating the value of a user action, etc. The information indicating one or more search keywords is an example of information indicating the detection conditions of a user action.
[0034] The video playback action component is, for example, a component indicating that the user action is the operation of playing a video advertisement. The contents of the property items set in the property window of the video playback action component include, for example, information identifying the video advertisement to be played, information indicating the playback time, information indicating the attributes of the user who is the target of the advertisement, information indicating the value of the user action, etc. In the video playback action component, information on "video advertisement playback operation" is set in advance as information indicating the detection condition of the user action, but is not limited to this example.
[0035] The video click action component is a component that indicates that the user action is a click on a video advertisement. The contents of the property items set in the property window of the video click action component include, for example, information that identifies the video advertisement to be clicked, information that indicates the value of the user action, etc. In the video click action component, information of "click on a video advertisement" is set in advance as information indicating the detection condition of the user action, but is not limited to this example.
[0036] A micro-conversion component is a component that indicates that a user action is a micro-conversion. A micro-conversion is an action that is likely to lead to a final conversion, such as viewing a page that is a transaction target, or adding the transaction target to a shopping cart (if the advertisement target is a transaction target such as a product or service).
[0037] The contents of the property items set in the property window of the micro-conversion component include, for example, information identifying the type of micro-conversion, information indicating the value of the user action, information indicating the detection conditions of the user action, etc. The information indicating the detection conditions of the user action is set with, for example, information on a target corresponding to the type of micro-conversion. The target is, for example, a specific advertisement, a specific website, or a specific webpage, but is not limited to such examples.
[0038] A conversion component is a component that indicates that a user action is a conversion. Conversions include, but are not limited to, the purchase of an advertised transaction object, the use of an advertised transaction object, registration for an advertised membership service, or the viewing (display) of an advertised site. Transaction objects include, for example, products and services.
[0039] For example, a conversion may be signing up for an advertised email distribution, registering an account for an advertised online service, requesting materials for which advertising is being made, visiting a advertised physical store, or sharing on an advertised social networking service (SNS), or it may be some other action.
[0040] The contents of the property items set in the property window of the conversion component are, for example, information indicating the value of the conversion which is a user action, information indicating the type of the conversion which is a user action, information indicating the detection conditions of the user action, etc. The information indicating the value of the conversion is the value per conversion (hereinafter, may be referred to as CV value), for example, the target CPA (Cost Per Action). The information indicating the detection conditions of the user action is, for example, information specifying the target of the conversion, etc.
[0041] Furthermore, the worker O can group a plurality of conversion parts by operating the terminal device 2. In this case, one property window is assigned to the grouped plurality of conversion parts. The contents of the property items set in such one property window include, for example, information for identifying a conversion group, information indicating the value of a conversion which is a user action, information indicating the type of a conversion which is a user action, and the like.
[0042] The customer journey setting information includes a customer journey template according to the type of advertisement or the type of advertising target, and the worker O can use the customer journey template according to the type of advertisement or the type of advertising target.
[0043] A customer journey template according to the type of advertisement or the type of advertising target is selected by the information processing device 1 based on the advertisement information or advertising target information set or input by the operator O, but the operator O can also select from multiple templates. The customer journey setting information may include multiple types of customer journey templates according to the type of advertising target.
[0044] The worker O places user action components corresponding to each of the multiple user actions included in the customer journey to be set in the customer journey setting area by operating the terminal device 2. In the following, the customer journey to be set by the worker O may be referred to as a target customer journey.
[0045] Specifically, the worker O selects a user action component corresponding to a user action included in the target customer journey from among multiple types of user action components included in the user action library, and places it in the customer journey setting area.
[0046] The worker O performs this process for all user actions included in the target customer journey. As a result, all user action parts corresponding to the target customer journey are arranged in the customer journey setting area. The worker O can also group multiple user action parts arranged in the customer journey setting area by operating the terminal device 2.
[0047] After that, the worker O connects two or more user action components arranged in the customer journey setting area with a connection component by operating the terminal device 2. The connection component is a component that determines the time-series position of the user action component, and has, for example, an arrow shape.
[0048] A connection part is, for example, a part whose starting point and ending point each have the shape of an arrow, but may also include a part whose arrow shape branches out from a starting point to two or more ending points. In a connection part, a user action of a user action part connected to the ending point side of the arrow shape is a user action that comes later than a user action of a user action part connected to the starting point side of the arrow shape.
[0049] In the example shown in Figure 1, in the customer journey setting area, a click action component, a search action component, a micro conversion component, and two grouped conversion components are connected in chronological order by connection components.
[0050] Also, in the example shown in Fig. 1, information on advertisement A is set in the click action component as information for identifying the advertisement to be clicked. Also, in the example shown in Fig. 1, "Term X" is set in the search action component as information for indicating a search keyword. "Term X" is, for example, a term for identifying the advertisement target (for example, a term such as the name of the advertisement target or the manufacturer name).
[0051] In the example shown in Fig. 1, the micro conversion component has "site visit" set as information for identifying the type of micro conversion. In the example shown in Fig. 1, the two grouped conversion components have "group 1" set as information for identifying the conversion group, "1000 yen" set as information for indicating the value of the conversion, which is a user action, and "payment" set as information for indicating the type of the conversion, which is a user action.
[0052] Although the example shown in Fig. 1 does not show information on detection settings of user actions, information on detection settings of user actions is set in each user action part. Also, a user action part (e.g., a click action part) in which advertisement information is set may include information on user attributes that are the target of the advertisement.
[0053] In the above example, each property item of the user action component is included in a property window not shown, but this is not limited to such an example. For example, a navigation window may be provided to allow the worker O to set the contents of each property item sequentially by navigation.
[0054] Furthermore, the worker O can set delivery information for the target customer journey in the delivery property setting area by operating the terminal device 2. The delivery information is, for example, information on the advertising budget (hereinafter, may be referred to as "advertising budget"), information on the delivery period of the advertisement, information on the final conversion value, etc., but is not limited to such examples.
[0055] In the example shown in FIG. 1, the advertising budget is set to "200,000 yen," the advertising delivery period is set to "30 days," and the final conversion value is set to "1,000 yen."
[0056] After setting the target customer journey and the delivery information, when the worker O presses the optimization button by operating the terminal device 2, an optimization-related request including the setting information is sent from the terminal device 2 to the information processing device 1 (step S3). The setting information included in the optimization-related request includes, for example, information indicating the setting of the target customer journey and information indicating the setting of the delivery information. In the following, the set target customer journey may be referred to as a set customer journey.
[0057] The information processing device 1 accepts an optimization-related request transmitted from the terminal device 2. In this manner, the information processing device 1 accepts settings of a customer journey in which multiple time-series user actions related to an advertising target are defined.
[0058] The information processing device 1 executes an optimization-related process, which is an optimization process related to advertisement delivery in the set customer journey, based on the setting information included in the received optimization-related request (step S4).
[0059] The optimization-related process is, for example, a process of determining an optimization policy for user actions included in a set customer journey, a process of optimizing user actions included in a set customer journey, etc., but is not limited to such examples. In the following, optimization related to advertisement delivery in a set customer journey may also be referred to as optimization of the operation policy of the set customer journey.
[0060] In step S4, the information processing device 1 performs optimization regarding advertisement delivery in the set customer journey, for example, based on the advertisement budget indicated in the delivery information included in the setting information.
[0061] For example, the information processing device 1 determines an optimization policy for user actions included in the set customer journey based on an advertising budget indicated in the delivery information. The optimization policy is, for example, a policy on which user action is to be optimized among multiple user actions included in the set customer journey.
[0062] When the advertising budget indicated in the distribution information is less than a reference amount, the information processing device 1 sets a conversion maximization strategy or a micro-conversion maximization strategy in the distribution period indicated in the distribution information.
[0063] Conversion maximization strategies include strategies that optimize targeting to maximize conversion, for example by predicting user types that will improve conversion.
[0064] The user type is, for example, a type indicated by a user attribute, a type indicated by a user behavior, or a type indicated by a combination of a user attribute and a user behavior. A user attribute is a combination of one or more attribute items of a user. For example, when an attribute item is a combination of gender and age, it may be a female in her 20s, a male in his 20s, a female in her 30s, etc., but the attribute items are not limited to these and may include, for example, the user's occupation, location, annual income, etc., or other attribute items.
[0065] User behavior may be, for example, the number of past clicks on an advertisement by the user, the number of past views by the user, the number of past micro-conversions by the user, etc., where a view is, for example, a viewing of a website or webpage related to the advertised target, and a micro-conversion is a micro-conversion related to the advertised target.
[0066] For example, when a target CPA (conversion value) is set, the information processing device 1 predicts a user type that maximizes conversion. For example, the information processing device 1 can predict a user type that maximizes conversion based on information indicating the target CPA (final conversion value), information indicating the type of conversion, information indicating the advertisement delivery period, and advertisement creative information.
[0067] The information processing device 1 can predict the user type that maximizes the number of conversions by using a prediction model that inputs, for example, information indicating the target CPA, information indicating the type of conversion, information indicating the advertisement delivery period, and advertisement creative information as features and outputs the number of conversions for each user type.
[0068] The types of conversions include, but are not limited to, payment for purchasing a transaction object, account registration, email newsletter registration, download, event registration, etc. The creative information of an advertisement is, for example, creative information of an advertisement, and is, for example, a feature amount obtained from the design, text, etc. of an advertisement.
[0069] Examples of predictive models include, but are not limited to, regression models, decision tree models, random forests, GBDT (Gradient Boosting Decision Tree), and neural networks.
[0070] The prediction model may be a prediction model for each range of target CPA. In this case, the prediction model is a model that inputs, for example, information indicating the type of conversion, information indicating the advertisement delivery period, and advertisement creative information as feature quantities, and outputs the number of conversions for each user type.
[0071] The prediction model may be a model that predicts the number of conversions for each range of the target CPA. Such a prediction model may be a model that inputs, for example, information on the user type, information indicating the type of conversion, information indicating the advertisement delivery period, and advertisement creative information as features, and outputs the number of conversions.
[0072] In this case, the information processing device 1 can predict the user type information contained in the feature that maximizes the predicted value of the number of conversions output from the prediction model as the user type information that maximizes the number of conversions while changing the behavioral information of the user type input into the prediction model.
[0073] In the above example, the feature amount input to the prediction model may include information indicating the type of advertisement, such as a banner advertisement, a listing advertisement, a native advertisement, a social media advertisement, a video advertisement, etc., but is not limited to these examples.
[0074] In addition, the above-mentioned prediction model is a prediction model for each customer journey that predicts the number of conversions that will occur through the route of the set customer journey, but it may also be a model common to all customer journeys.
[0075] In addition, prediction of the user type that maximizes conversion, etc. is not limited to prediction using the prediction model described above, and the information processing device 1 can also make predictions from, for example, statistics or statistical distributions obtained by statistical processing.
[0076] Next, a micro-conversion maximization strategy will be described. The micro-conversion maximization strategy includes a strategy for optimizing targeting so as to maximize micro-conversion. Targeting optimization is performed by predicting a user type that improves the micro-conversion rate.
[0077] For example, the information processing device 1 can predict, for example, a user type that maximizes the micro-conversion rate based on information indicating the type of micro-conversion, information indicating the advertisement delivery period, advertisement creative information, etc. The types of micro-conversion include, for example, site visit, video advertisement viewing, adding to a wishlist, sharing on social media, adding to cart, etc., but are not limited to such examples.
[0078] The information processing device 1 can predict the user type that maximizes the micro-conversion rate by using a prediction model that inputs, for example, information indicating the type of micro-conversion, information indicating the advertisement delivery period, and advertisement creative information as feature quantities and outputs the micro-conversion rate for each user type. Such a prediction model can be, for example, a regression model, a decision tree model, a random forest, GBDT, a neural network, or the like, but is not limited to such examples.
[0079] The feature values input to the prediction model may include information indicating the type of advertisement, such as, but not limited to, banner advertisements, listing advertisements, native advertisements, social media advertisements, and video advertisements.
[0080] The prediction model may also be a model that inputs, for example, information on user type, information indicating the type of conversion, information indicating the advertisement delivery period, and advertisement creative information as features, and outputs a predicted value of the micro-conversion rate.
[0081] In this case, the information processing device 1 can predict, while changing the user type information input to the prediction model, the user type information included in the feature that maximizes the predicted value of the micro-conversion rate output from the prediction model as the user type information that maximizes the micro-conversion rate.
[0082] Furthermore, the above-mentioned predictive model is a predictive model for each customer journey that predicts the micro-conversion rate reached through the route of the set customer journey, but it may also be a model common to all customer journeys.
[0083] The information processing device 1 predicts the conversion rate after the micro-conversion, and predicts the value of the micro-conversion based on the predicted conversion rate and the information of the target CPA. Hereinafter, the predicted value of the conversion rate after the micro-conversion may be referred to as pCVR (MicroCV).
[0084] For example, the information processing device 1 can specify pCVR (MicroCV) using a prediction model that predicts the rate of conversion after a micro-conversion based on information indicating the type of micro-conversion, information indicating the user type, information indicating the advertisement delivery period, advertisement creative information, etc. Then, the information processing device 1 predicts the value of the micro-conversion as a result of multiplying the target CPA by the pCVR (MicroCV).
[0085] When the advertising budget indicated in the distribution information is equal to or larger than a reference amount, the information processing device 1 sets a maximization strategy for a user action before a micro-conversion in the set customer journey.
[0086] For example, in the example shown in FIG. 1, a search maximization strategy is set in the set customer journey. The maximization strategy includes targeting optimization so that the search is maximized.
[0087] In this case, the information processing device 1 can predict, for example, the user type that maximizes the search. For example, the information processing device 1 can predict the user type that maximizes the search by using a prediction model that predicts the search rate. Such a prediction model is, for example, a regression model, a decision tree model, a random forest, a GBDT, a neural network, etc., but is not limited to such examples.
[0088] The feature values input to the prediction model for predicting the search rate include, but are not limited to, information on the search keywords used in the search, information indicating the advertisement distribution period, and advertisement creative information. The information on the search keywords used as the feature values includes, but is not limited to, information indicating the search keyword category and information obtained by vectorizing the search keywords.
[0089] The information processing device 1 predicts the rate of micro-conversions after a search, and predicts the value of the search based on the predicted rate of micro-conversions and pCVR (MicroCV). Hereinafter, the predicted value of the rate of micro-conversions after a search may be referred to as pMicroCVR (Search).
[0090] For example, the information processing device 1 can identify pMicroCVR(Search) using a predictive model that predicts the percentage of micro-conversions after a search based on information on search keywords used in the search, information indicating the user type, information indicating the advertisement delivery period, and advertisement creative information, etc.
[0091] Then, the information processing device 1 predicts the result of multiplying the target CPA by pCVR (MicroCV) as the value of a micro-conversion, and predicts the result of multiplying the predicted value of a micro-conversion by pMicroCVR (Search) as the value of a search.
[0092] In addition, the maximization strategy of the user action before the microconversion is not limited to the maximization of the search, and may be the maximization of the click or other user action. For example, when a view is set as a user action before the microconversion in the set customer journey, the information processing device 1 maximizes the view as a target for optimization.
[0093] Furthermore, the above-mentioned base amount is a fixed amount set in advance, but it may also be a variable amount that varies depending on one or more of the creative features of the advertisement, the type of conversion, the delivery period, and the conversion value.
[0094] In addition, the optimization-related process in step S4 may be one of multiple processes including a process for determining an optimization policy for user actions included in the set customer journey and a process for performing optimization for user actions included in the set customer journey.
[0095] For example, when information indicating the setting of the target customer journey included in the setting information includes information indicating the user type targeted by the advertisement, the information processing device 1 can only perform processing to determine an optimization policy for user actions included in the set customer journey.
[0096] Next, the information processing device 1 transmits optimization-related information including a result of the optimization-related process performed in step S4 to the terminal device 2 (step S5). The optimization-related information includes, for example, maximization target information including information indicating a maximization target that is the target of maximization, and maximization policy information including information indicating a policy for maximizing the maximization target.
[0097] The maximization target information is, for example, information indicating a micro-conversion in the case of a micro-conversion maximization strategy, information indicating a conversion in the case of a conversion maximization strategy, and information indicating a search in the case of a search maximization strategy.
[0098] For example, in the case of a conversion maximization strategy, the maximization policy information includes information on the type of user for which conversion is maximized. For example, in the case of a micro-conversion maximization strategy, the maximization policy information includes information on the type of user for which micro-conversion is maximized and information on the value of the micro-conversion.
[0099] In addition, in the case of a search maximization strategy, the maximization policy information includes, for example, information on the user type for maximizing the search, information on the value of the search, and information on the value of the microconversion, etc. In the case of a view maximization strategy, the maximization policy information includes, for example, information on the user type for maximizing the view, information on the value of the view, and information on the value of the microconversion, etc.
[0100] When the terminal device 2 receives the optimization-related information transmitted from the information processing device 1, the terminal device 2 displays the received optimization-related information. For example, the terminal device 2 can display the optimization-related information transmitted from the information processing device 1 in a customer journey setting area. This allows the worker O to optimize the set customer journey.
[0101] Next, a case where the worker O presses the optimization button will be described. After the provision of the advertisement set in the set customer journey has started, when the worker O presses the trend visualization button by operating the terminal device 2, a trend visualization request including the setting information is transmitted from the terminal device 2 to the information processing device 1 (step S6). The setting information included in the trend visualization request includes, for example, information indicating the set customer journey.
[0102] When the information processing device 1 receives a trend visualization request sent from the terminal device 2, it performs a trend identification process to identify the operation status of the set customer journey for which advertising provision has begun (hereinafter, sometimes referred to as the set customer journey operation status) based on the setting information included in the trend visualization request (step S7).
[0103] For example, based on information on the behavioral history of a user to whom an advertisement set in the set customer journey has been provided, the information processing device 1 identifies the behavioral changes of a user to whom an advertisement set in the set customer journey has been provided along the route of the set customer journey as the set customer journey operation status.
[0104] For example, in the example shown in Figure 1, the path of the set customer journey is the click on ad A, the search for term X, the micro-conversion of a site visit, and the conversion included in the conversion group.
[0105] In this case, the configured customer journey operation status includes information such as the number of times Ad A was clicked, the number of searches for term X performed after Ad A was clicked, the number of micro-conversions of site visits performed after searches for term X were performed, and the number of conversions included in the conversion group performed after micro-conversions of site visits were performed.
[0106] Next, the information processing device 1 transmits operation status information, which is information indicating the set customer journey operation status identified in step S7, to the terminal device 2, thereby providing the operation status information to the worker O (step S8).
[0107] When the terminal device 2 receives the operation status information transmitted from the information processing device 1, it displays the received operation status information. For example, the terminal device 2 can display the operation status information transmitted from the information processing device 1 in a customer journey setting area. The worker O can easily grasp the operation status of the set customer journey based on the operation status information.
[0108] In this way, the information processing device 1 accepts the setting of the customer journey in which multiple time-series user actions related to the advertising target are defined, and performs optimization of advertisement delivery in the customer journey based on the accepted customer journey. In this way, the information processing device 1 can support optimization of advertisement delivery.
[0109] The configuration of an information processing system including the information processing device 1 that performs such processing will be described in detail below.
[0110] 2. Configuration of the Information Processing System 2 is a diagram showing an example of a configuration of an information processing system according to an embodiment. As shown in FIG. 2, the information processing system 100 according to the embodiment includes an information processing device 1, a terminal device 2, and a plurality of terminal devices 3.
[0111] The terminal device 2 is used by a worker O. The multiple terminal devices 3 are used by different users U. Each of the terminal devices 2, 3 is, for example, a notebook PC (Personal Computer), a desktop PC, a smartphone, a tablet PC, or a wearable device. The wearable device is, for example, smart glasses or a smart watch, but is not limited to such examples. The user U is a user of an online service who performs the above-mentioned user action.
[0112] The information processing device 1, the terminal device 2, and the terminal device 3 are connected to each other so as to be able to communicate with each other by wire or wirelessly via a network N. Note that the information processing system 100 shown in FIG. 2 may include a plurality of information processing devices 1 and the like.
[0113] The network N includes, for example, a Wide Area Network (WAN) such as the Internet and mobile communication networks such as Long Term Evolution (LTE), 4th Generation (4G), and 5th Generation (5G: fifth generation mobile communication system).
[0114] Each of the terminal devices 2 and 3 can connect to the network N via short-range wireless communication such as a mobile communication network, Bluetooth (registered trademark), or a wireless LAN (Local Area Network), and communicate with the information processing device 1.
[0115] 3. Configuration of information processing device 1 3 is a diagram showing an example of the configuration of the information processing device 1 according to the embodiment. As shown in FIG. 3, the information processing device 1 includes a communication unit 10, a storage unit 11, and a processing unit 12.
[0116] [3.1. Communication unit 10] The communication unit 10 is realized by, for example, a communication module or a NIC (Network Interface Card). The communication unit 10 is connected to a network N by wire or wirelessly, and transmits and receives information to and from various other devices. For example, the communication unit 10 transmits and receives information to and from the terminal devices 2 and 3 via the network N.
[0117] [3.2. Storage section 11] The storage unit 11 is realized by, for example, a semiconductor memory element such as a random access memory (RAM) or a flash memory, or a storage device such as a hard disk or an optical disk. The storage unit 11 has a user information storage unit 20 and an optimization-related information storage unit 21.
[0118] 3.2.1. User information storage unit 20 The user information storage unit 20 stores various pieces of information related to the user U. Fig. 4 is a diagram showing an example of a user information table stored in the user information storage unit 20 of the information processing device 1 according to the embodiment.
[0119] 4, the user information table stored in the user information storage unit 20 includes information items such as "User ID (Identifier)," "Attribute Information," and "History Information." The "User ID" is an identifier for identifying a user U, and is information assigned to each user U.
[0120] The "attribute information" is attribute information indicating attributes of the user U associated with the "user ID." The attributes of the user U are, for example, demographic attributes, psychographic attributes, etc. The demographic attributes are demographic attributes, and include a plurality of attribute items such as age, sex, occupation, place of residence, annual income, and family structure.
[0121] The psychographic attributes are psychological attributes, and include, for example, a plurality of attribute items related to lifestyle, values, interests, etc. For example, each of the plurality of attribute items in the psychographic attributes is an object of interest of the user U, such as a car, clothes, travel, games, camping, motorcycle, train, home appliance, or computer.
[0122] "History information" includes information on the behavioral history of user U associated with "user ID." The behavioral history of user U includes, for example, information on the behavioral history of user U in online services. Information on the behavioral history of user U in online services is information on user actions, which are actions of user U in online services, and includes, for example, search history information, browsing history information, delivery history information, and transaction history information.
[0123] The search history information of the user U includes, for example, information on the search history by the user U in a web search service, etc. The browsing history information of the user U includes, for example, information on the browsing history of content by the user U in an online service, etc.
[0124] The delivery history information includes information on the delivery history of delivery content delivered to the terminal device 2 of the user U, the delivery history of advertisements delivered to the terminal device 2 of the user U, and the history of actions (e.g., clicks) of the user U on advertisements delivered to the terminal device 2 of the user U. The transaction history information includes information on the transaction history of products by the user U in online services.
[0125] 3.2.2. Optimization-related information storage unit 21 The optimization-related information storage unit 21 stores various pieces of information related to user actions. For example, the optimization-related information storage unit 21 stores information for setting a customer journey, including information on the above-mentioned user action library. The user action library includes a plurality of user action components.
[0126] In addition, the optimization-related information storage unit 21 also stores information included in the customer journey setting information other than the user action library. In addition, the optimization-related information storage unit 21 can store information on the set customer journey set by the worker O, delivery information, and the like.
[0127] [3.3. Processing section 12] The processing unit 12 is a controller, and is realized, for example, by a CPU (Central Processing Unit) or an MPU (Micro Processing Unit) executing various programs stored in a storage device inside the information processing device 1 using a RAM as a working area.
[0128] The processing unit 12 may be partially or entirely realized by an integrated circuit such as an application specific integrated circuit (ASIC) or a field programmable gate array (FPGA).
[0129] 3, the processing unit 12 has an acquisition unit 30, a reception unit 31, an optimization unit 32, a specification unit 33, and a provision unit 34, and realizes or executes the functions and actions of information processing described below. Note that the internal configuration of the processing unit 12 is not limited to the configuration shown in FIG. 3, and may be other configurations as long as they perform the information processing described below.
[0130] [3.3.1. Acquisition part 30] The acquisition unit 30 acquires various pieces of information from an external information processing device, the terminal device 2, the terminal device 3, or the like via the communication unit 10, and stores the acquired information in the storage unit 11.
[0131] For example, the acquisition unit 30 acquires user information, which is information about the user U, from an external information processing device or the terminal device 2 via the communication unit 10, and adds the acquired user information to a user information table in the user information storage unit 20.
[0132] Furthermore, the acquisition unit 30 acquires various types of information from the storage unit 11. For example, the acquisition unit 30 acquires user information, which is information on the user U, from the user information storage unit 20 or the like. The user information acquired by the acquisition unit 30 includes, for example, a part or all of at least one of the above-mentioned attribute information and history information.
[0133] In addition, the acquisition unit 30 acquires various pieces of information related to user actions from the optimization-related information storage unit 21, etc. In this case, the information acquired by the acquisition unit 30 is, for example, information of a user action library or information for setting a customer journey, but is not limited to such examples.
[0134] [3.3.2. Reception Unit 31] The reception unit 31 receives various requests and information from the terminal device 2 and the terminal device 3 via the communication unit 10 .
[0135] For example, the requests received by the reception unit 31 include an optimization-related request or a trend visualization request transmitted from the terminal device 2, and an advertisement request transmitted from the terminal device 3, but are not limited to these examples.
[0136] The optimization-related request includes information on the set customer journey, distribution information, etc., and the reception unit 31 receives the optimization-related request, thereby receiving information on the set customer journey, distribution information, etc.
[0137] The reception unit 31 receives information on the set customer journey, thereby receiving the setting of the customer journey in which multiple user actions in time series related to the advertising target are defined.
[0138] The receiving unit 31 receives, as a customer journey setting, information setting in which a plurality of user action parts related to an advertising target are arranged in chronological order and advertising information is set in at least one of the plurality of user action parts. Each of the plurality of user action parts is a user action part selected by the worker O or the like from a plurality of types of user action parts included in a user action library.
[0139] For example, when the reception unit 31 receives an optimization-related request transmitted from the terminal device 2, the reception unit 31 stores information on the set customer journey and delivery information included in the optimization-related request in the optimization-related information storage unit 21.
[0140] [3.3.3. Optimization Unit 32] The optimization unit 32 performs optimization-related processing, which is processing for optimizing advertisement delivery in a set customer journey based on a set customer journey, which is a customer journey whose setting has been accepted by the acceptance unit 31.
[0141] For example, when an optimization-related request sent from a terminal device 2 is accepted by the acceptance unit 31, the optimization unit 32 executes optimization-related processing, which is processing for optimizing advertising delivery in the set customer journey, based on information on the set customer journey and delivery information contained in the optimization-related request.
[0142] Examples of optimization-related processes include processes for determining optimization policies for user actions included in a set customer journey and processes for optimizing user actions included in a set customer journey, but are not limited to such examples.
[0143] The optimization unit 32 optimizes the advertisement delivery in the set customer journey based on, for example, an advertisement budget indicated in the delivery information included in the setting information. For example, the optimization unit 32 determines an optimization policy for user actions included in the set customer journey based on an advertisement budget indicated in the delivery information. The optimization policy is, for example, a policy on which user action is to be optimized among multiple user actions included in the set customer journey.
[0144] When the advertising budget indicated in the distribution information is less than a reference amount, the optimization unit 32 sets a conversion maximization strategy or a micro-conversion maximization strategy for the distribution period indicated in the distribution information.
[0145] For example, if the advertising budget indicated in the distribution information is less than a reference amount and is lower than a preset threshold, the optimization unit 32 sets a conversion maximization strategy, and if not, sets a micro-conversion maximization strategy.
[0146] In addition, when the advertising budget is less than a reference amount, the optimization unit 32 may increase the probability of setting a conversion maximization strategy the lower the advertising budget, and may increase the probability of setting a micro-conversion maximization strategy the higher the advertising budget.
[0147] Conversion maximization strategies include strategies that optimize targeting to maximize conversion, for example by predicting user types that will improve conversion.
[0148] The user type is, for example, a type indicated by a user attribute, a type indicated by a user behavior, or a type indicated by a combination of a user attribute and a user behavior. The user attribute is a combination of one or more attribute items of the user U. For example, when the attribute item is a combination of gender and age, it may be a female in her 20s, a male in his 20s, a female in her 30s, etc., but the attribute items are not limited to these and may include, for example, the user's occupation, location, annual income, etc., or other attribute items.
[0149] User behavior may be, for example, the number of past clicks on an advertisement by user U, the number of past views by user U, the number of past micro-conversions by user U, etc., where a view is, for example, a viewing of a website or webpage related to the advertised target, and a micro-conversion is a micro-conversion related to the advertised target.
[0150] For example, when a target CPA (conversion value) is set, the optimization unit 32 predicts a user type that maximizes conversion. For example, the optimization unit 32 can predict a user type that maximizes conversion based on information indicating the target CPA (final conversion value), information indicating the type of conversion, information indicating the advertisement delivery period, and advertisement creative information.
[0151] The optimization unit 32 can input, for example, information indicating the target CPA, information indicating the type of conversion, information indicating the advertisement delivery period, and advertisement creative information as features, and predict the user type that maximizes the number of conversions using a prediction model that outputs the number of conversions for each user type.
[0152] The types of conversions include, but are not limited to, payment for purchasing a transaction object, account registration, email newsletter registration, download, event registration, etc. The creative information of an advertisement is, for example, creative information of an advertisement, and is, for example, a feature amount obtained from the design, text, etc. of an advertisement.
[0153] Examples of predictive models include, but are not limited to, regression models, decision tree models, random forests, GBDTs, and neural networks.
[0154] The prediction model may be a prediction model for each range of target CPA. In this case, the prediction model is a model that inputs, for example, information indicating the type of conversion, information indicating the advertisement delivery period, and advertisement creative information as feature quantities, and outputs the number of conversions for each user type.
[0155] The prediction model may be a model that predicts the number of conversions for each range of the target CPA. Such a prediction model may be a model that inputs, for example, information on the user type, information indicating the type of conversion, information indicating the advertisement delivery period, and advertisement creative information as features, and outputs the number of conversions.
[0156] In this case, the optimization unit 32 can predict, while changing the behavioral information of the user type input into the prediction model, the information of the user type contained in the feature that maximizes the predicted value of the number of conversions output from the prediction model, as the information of the user type that maximizes the number of conversions.
[0157] In the above example, the feature amount input to the prediction model may include information indicating the type of advertisement, such as a banner advertisement, a listing advertisement, a native advertisement, a social media advertisement, a video advertisement, etc., but is not limited to these examples.
[0158] In addition, the above-mentioned prediction model is a prediction model for each customer journey that predicts the number of conversions that will occur through the route of the set customer journey, but it may also be a model common to all customer journeys.
[0159] In addition, prediction of the user type that maximizes conversion, etc. is not limited to prediction using the prediction model described above, and the optimization unit 32 can also make predictions from, for example, statistics or statistical distributions obtained by statistical processing.
[0160] Next, a micro-conversion maximization strategy will be described. The micro-conversion maximization strategy includes a strategy for optimizing targeting so as to maximize micro-conversion. Targeting optimization is performed by predicting a user type that improves the micro-conversion rate.
[0161] For example, the optimization unit 32 can predict, for example, a user type for which the micro-conversion rate is maximized, based on information indicating the type of micro-conversion, information indicating the advertisement delivery period, advertisement creative information, etc. The types of micro-conversion include, for example, site visit, video advertisement viewing, adding to a wishlist, sharing on social media, adding to cart, etc., but are not limited to such examples.
[0162] The optimization unit 32 can predict the user type that maximizes the micro-conversion rate by using a prediction model that inputs, for example, information indicating the type of micro-conversion, information indicating the advertisement delivery period, and advertisement creative information as feature quantities and outputs the micro-conversion rate for each user type. Such a prediction model can be, for example, a regression model, a decision tree model, a random forest, GBDT, a neural network, or the like, but is not limited to these examples.
[0163] The feature values input to the prediction model may include information indicating the type of advertisement, such as, but not limited to, banner advertisements, listing advertisements, native advertisements, social media advertisements, and video advertisements.
[0164] The prediction model may also be a model that inputs, for example, information on user type, information indicating the type of conversion, information indicating the advertisement delivery period, and advertisement creative information as features, and outputs a predicted value of the micro-conversion rate.
[0165] In this case, the optimization unit 32 can predict, while changing the user type information input to the prediction model, the user type information included in the feature that maximizes the predicted value of the micro-conversion rate output from the prediction model as the user type information that maximizes the micro-conversion rate.
[0166] Furthermore, the above-mentioned predictive model is a predictive model for each customer journey that predicts the micro-conversion rate reached through the route of the set customer journey, but it may also be a model common to all customer journeys.
[0167] The optimization unit 32 predicts the conversion rate after the micro-conversion, and predicts the value of the micro-conversion based on the predicted conversion rate and information on the target CPA.
[0168] For example, the optimization unit 32 can identify pCVR (MicroCV) using a prediction model that predicts the rate of conversion after a micro-conversion based on information indicating the type of micro-conversion, information indicating the user type, information indicating the advertisement delivery period, advertisement creative information, etc. Then, the optimization unit 32 predicts the value of the micro-conversion as the result of multiplying the target CPA by the pCVR (MicroCV).
[0169] When the advertising budget indicated in the distribution information is equal to or greater than a reference amount, the optimization unit 32 sets a maximization strategy for user actions prior to micro-conversions in the set customer journey.
[0170] In this case, the optimization unit 32 can predict, for example, the user type for which the search is maximized. For example, the optimization unit 32 can predict the user type for which the search is maximized using a prediction model for predicting the search rate. Such a prediction model is, for example, a regression model, a decision tree model, a random forest, a GBDT, a neural network, etc., but is not limited to such examples.
[0171] The feature values input to the prediction model for predicting the search rate include, but are not limited to, information on the search keywords used in the search, information indicating the advertisement distribution period, and advertisement creative information. The information on the search keywords used as the feature values includes, but is not limited to, information indicating the search keyword category and information obtained by vectorizing the search keywords.
[0172] The optimization unit 32 predicts the rate of micro-conversions after a search, and predicts the value of the search based on the predicted rate of micro-conversions and pCVR (MicroCV).
[0173] For example, the optimization unit 32 can identify pMicroCVR(Search) using a predictive model that predicts the percentage of micro-conversions after a search based on information on the search keywords used in the search, information indicating the user type, information indicating the advertisement delivery period, and advertisement creative information, etc.
[0174] Then, the optimization unit 32 predicts the value of a micro-conversion by multiplying the target CPA by pCVR (MicroCV), and predicts the value of a search by multiplying the predicted value of a micro-conversion by pMicroCVR (Search).
[0175] In addition, the maximization strategy of the user action before the microconversion is not limited to the maximization of the search, and may be the maximization of the click or other user action. For example, when a view is set as a user action before the microconversion in the set customer journey, the optimization unit 32 performs maximization of the view as an optimization target.
[0176] Furthermore, the above-mentioned base amount is a fixed amount set in advance, but it may also be a variable amount that varies depending on one or more of the creative features of the advertisement, the type of conversion, the delivery period, and the conversion value.
[0177] In addition, the optimization-related processing performed by the optimization unit 32 may be one of multiple processing including a processing for determining an optimization policy for user actions included in the set customer journey and a processing for performing optimization for user actions included in the set customer journey.
[0178] For example, when information indicating the setting of the target customer journey included in the setting information includes information indicating the user type targeted by the advertisement, the optimization unit 32 can only perform processing to determine an optimization policy for user actions included in the set customer journey.
[0179] In addition, when the information indicating the setting of the target customer journey included in the setting information does not include information indicating the user type targeted by the advertisement, the optimization unit 32 performs multiple processes including a process of determining an optimization policy for user actions included in the set customer journey and a process of optimizing user actions included in the set customer journey.
[0180] [3.3.4. Specification part 33] The identification unit 33 identifies a behavioral transition of the user U on the route of the set customer journey, which is a customer journey whose setting has been accepted by the reception unit 31. For example, when a trend visualization request is accepted by the reception unit 31, the identification unit 33 identifies a behavioral transition of the user U on the route of the set customer journey as the set customer journey operation status.
[0181] The identification unit 33, for example, based on information on the behavior history of the user U to whom the advertisement set in the set customer journey was provided, identifies the behavioral transition along the route of the set customer journey of the user U to whom the advertisement set in the set customer journey was provided as the set customer journey operation status. The information on the behavior history of the user U to whom the advertisement set in the set customer journey was provided is acquired from the user information storage unit 20 by the acquisition unit 30, for example.
[0182] The set customer journey operation status includes, for example, information such as the number of users U who performed each user action in the set customer journey. The set customer journey operation status may be, for example, information per unit period on the number of users U who performed each user action in the set customer journey, or information on the number of users U from the start of the advertisement delivery period to the latest time.
[0183] The identification unit 33 can also acquire the behavior of user U along the route of the set customer journey by setting tags for detecting user actions on websites or web pages corresponding to user actions based on information indicating detection conditions for user actions contained in the information of the set customer journey received by the reception unit 31.
[0184] [3.3.5.Providing Department 34] The providing unit 34 provides various kinds of information via the communication unit 10. For example, the providing unit 34 provides the worker O with the information in response to the request transmitted from the terminal device 2 by transmitting the information in response to the request transmitted from the terminal device 2 to the terminal device 2.
[0185] For example, when a specified access from the terminal device 2 is accepted by the accepting unit 31, the providing unit 34 provides the customer journey setting information to the worker O by sending the customer journey setting information to the terminal device 2.
[0186] Based on the customer journey setting information provided by the providing unit 34, the terminal device 2 displays a customer journey setting screen, which is a screen for setting a customer journey in which multiple user actions in a time series related to the advertising target are defined.
[0187] FIG. 5 is a diagram showing an example of a customer journey setting screen displayed on the terminal device 2 based on the customer journey setting information provided by the providing unit 34 of the information processing device 1 according to the embodiment.
[0188] The customer journey setting screen 50 shown in FIG. 5 includes a user action library area 51, a customer journey setting area 52, a delivery property setting area 53, an optimization button 54, a trend visualization button 55, and the like.
[0189] A user action library including a plurality of types of user action components and a plurality of types of connection components is arranged in the user action library area 51. For example, the user action library area 51 arranges user action libraries according to the type of advertisement or the type of advertisement target.
[0190] Based on the type of advertisement or the type of advertisement target set or input by the worker O, the providing unit 34 can include a user action library corresponding to the type of advertisement or the type of advertisement target in the customer journey setting information.
[0191] The customer journey setting area 52 is configured by arranging user action components and connection components selected by the worker O from multiple types of user action components included in the user action library, thereby setting the customer journey desired by the worker O.
[0192] In the customer journey setting area 52 shown in FIG. 5, a customer journey is set by connecting a click action component, a search action component, a micro conversion component, and two grouped conversion components in chronological order with connection components.
[0193] In the delivery property setting area 53, delivery information in the customer journey desired by the worker O is set. In the example shown in Fig. 5, the delivery information includes "200,000 yen" as the advertising budget, "30 days" as the advertising delivery period, and "1,000 yen" as the final conversion value.
[0194] The optimization button 54 is a button for transmitting an optimization-related request to the information processing device 1, and the trend visualization button 55 is a button for transmitting a trend visualization request to the information processing device 1.
[0195] When an optimization-related request is accepted by the accepting unit 31, the providing unit 34 provides the optimization-related information to the worker O by transmitting the optimization-related information, including information indicating the results of the optimization processing by the optimizing unit 32, to the terminal device 2.
[0196] The optimization related information includes, for example, maximization target information including information indicating a maximization target that is a target of maximization, maximization policy information including information indicating a policy for maximizing the maximization target, etc. The maximization target information is, for example, information indicating a micro-conversion in the case of a micro-conversion maximization strategy, information indicating a conversion in the case of a conversion maximization strategy, and information indicating a search in the case of a search maximization strategy.
[0197] For example, in the case of a conversion maximization strategy, the maximization policy information includes information on the type of user for which conversion is maximized. For example, in the case of a micro-conversion maximization strategy, the maximization policy information includes information on the type of user for which micro-conversion is maximized and information on the value of the micro-conversion.
[0198] In addition, in the case of a search maximization strategy, the maximization policy information includes, for example, information on the user type for maximizing the search, information on the value of the search, and information on the value of the microconversion, etc. In the case of a view maximization strategy, the maximization policy information includes, for example, information on the user type for maximizing the view, information on the value of the view, and information on the value of the microconversion, etc.
[0199] When the terminal device 2 receives the optimization-related information transmitted from the information processing device 1, the terminal device 2 displays the received optimization-related information. For example, the terminal device 2 can display the optimization-related information transmitted from the information processing device 1 in a customer journey setting area. This allows the worker O to optimize the set customer journey.
[0200] Fig. 6 is a diagram showing an example of optimization-related information provided by the providing unit 34 of the information processing device 1 according to the embodiment and displayed on the terminal device 2. In the example shown in Fig. 6, target information 61, which is information indicating that the user action to be optimized is "search", and targeting information 62 indicating that the user type, which is targeting for maximizing "search", is "male in his 20s", are displayed as optimization-related information in the customer journey setting area 52.
[0201] In addition, when an optimization-related request is received by the reception unit 31 after targeting information is set by the worker O in the customer journey setting area 52, the optimization-related information provided by the provision unit 34 does not need to include the targeting information 62.
[0202] When the receiving unit 31 receives a trend visualization request, the providing unit 34 transmits operation status information, which is information indicating the set customer journey operation status identified by the identifying unit 33, to the terminal device 2, thereby providing the operation status information to the worker O. The operation status information is an example of the identification result by the identifying unit 33.
[0203] When the terminal device 2 receives the operation status information transmitted from the providing unit 34, the terminal device 2 displays the received operation status information. For example, the terminal device 2 can display the operation status information transmitted from the providing unit 34 in the customer journey setting area 52.
[0204] Fig. 7 is a diagram showing another example of optimization-related information provided by the providing unit 34 of the information processing device 1 according to the embodiment and displayed on the terminal device 2. In the example shown in Fig. 7, a video playback action component, a video click action component, and a conversion component are arranged in chronological order in the customer journey setting area 52, and the user actions of the set customer journey are video playback, video click, and conversion, in that order. Advertisement B, which is a 10-second video advertisement, is set in the video playback and video click of the set customer journey.
[0205] In the example shown in Figure 7, target information 61, which is information indicating that the user action to be optimized is "video click," and targeting information 62, which indicates that the user type, which is the targeting for maximizing "video click," is "teenage female," are displayed in the customer journey setting area 52 as optimization-related information.
[0206] In the set customer journey, conversion does not have to be included in the user action. Fig. 8 is a diagram showing an example of a customer journey setting area 52 included in a customer journey setting screen 50 displayed on the terminal device 2 according to the embodiment.
[0207] In the set customer journey shown in the customer journey setting area 52 shown in Fig. 8, "view" is set as the final user action, and "search" is set as the final user action. This makes it possible to maximize the user actions included in the set customer journey, even when linking with other ad tech or media from which conversions cannot be obtained.
[0208] Advertisement C is set in the user action "view", and "term Y" and "term Z" are set as search keywords in the user action "search". "Term Y" and "term Z" are, for example, terms for identifying the advertising target (for example, terms such as the name of the advertising target or the manufacturer name).
[0209] In this case, the optimization unit 32 predicts the user type for maximizing either the user action "search" or the user action "view." The optimization unit 32 can determine whether to maximize the user action "search" or the user action "view" based on whether the advertising budget is less than a reference amount, and can also determine based on the type of other ad tech media that are targets of the conversion action.
[0210] 9 is a diagram showing an example of operation status information provided by the providing unit 34 of the information processing device 1 according to the embodiment and displayed on the terminal device 2. In the example shown in FIG. 9, the operation status information is displayed in the customer journey setting area 52.
[0211] Specifically, the operational status information displayed in the customer journey setting area 52 shown in FIG. 9 includes information such as the number of clicks on advertisement A ("1000"), the number of searches for term X performed after advertisement A was clicked ("100"), the number of micro-conversions of site visits performed after a search for term X ("50"), and the number of conversions included in a conversion group performed after a micro-conversion of a site visit ("7").
[0212] In addition, the operational status information displayed in the customer journey setting area 52 also includes information such as the number of conversions 1 that were performed in the conversion group ("5") and the number of conversions 2 that were performed in the conversion group ("2").
[0213] The providing unit 34 can also provide a customer journey template according to the type of advertising target. The type of advertising target is, for example, a type of conversion, but is not limited to such an example. The customer journey template is a group of parts in a state in which a plurality of time-series user action parts related to the advertising target are connected by one or more connection parts.
[0214] The providing unit 34 can also provide a customer journey template according to the type of advertisement. The types of advertisements are, for example, banner advertisements, listing advertisements, native advertisements, social media advertisements, video advertisements, etc., but are not limited to these examples. For example, the types of advertisements may be classified based on creative information of the advertisements (design and text content of the advertisements).
[0215] In the above-described example, the optimization unit 32 performs optimization-related processing before the provision of the advertisement set in the set customer journey begins, but it can also perform optimization-related processing after the provision of the advertisement set in the set customer journey begins.
[0216] For example, the optimization unit 32 performs optimization-related processing when the conversion rate in the set customer journey operation state does not satisfy a predetermined condition. The predetermined condition is, for example, a condition that the conversion rate is n% (n is, for example, an integer) or less than the CVR predicted in the optimization-related processing before the provision of the advertisement set in the set customer journey is started.
[0217] In addition, the optimization unit 32 can perform optimization-related processing at predetermined intervals after the provision of the advertisement set in the set customer journey has begun.
[0218] 4. Processing Procedure Next, a procedure of information processing by the processing unit 12 of the information processing device 1 according to the embodiment will be described. Fig. 10 is a flowchart showing an example of information processing by the processing unit 12 of the information processing device 1 according to the embodiment.
[0219] 10, the processing unit 12 of the information processing device 1 determines whether or not a specific access has been received from the terminal device 2 (step S10). When the processing unit 12 determines that a specific access has been received (step S10: Yes), the processing unit 12 provides the customer journey setting information to the worker O by transmitting the customer journey setting information to the terminal device 2 (step S11).
[0220] When the processing of step S11 is completed, or when it is determined that a predetermined access has not been received (step S10: No), the processing unit 12 determines whether or not an optimization-related processing request has been received (step S12).
[0221] If the processing unit 12 determines that it has received an optimization-related processing request (step S12: Yes), it performs the optimization-related processing (step S13) and provides the optimization-related information including the results of the optimization-related processing to the terminal device 2 (step S14).
[0222] When the processing of step S14 is completed, or when it is determined that an optimization-related process request has not been received (step S12: No), the processing unit 12 determines whether or not a trend visualization request has been received (step S15).
[0223] If the processing unit 12 determines that the trend visualization request has been received (step S15: Yes), it performs trend identification processing (step S16) and provides operation status information including the results of the trend identification processing to the terminal device 2, thereby providing the operation status information to the worker O (step S17).
[0224] When the processing of step S17 is completed or when it is determined that the trend visualization request has not been received (step S15: No), the processing unit 12 determines whether or not the operation end timing has arrived (step S18). The processing unit 12 determines that the operation end timing has arrived when, for example, the power supply of the information processing device 1 is turned off.
[0225] If the processing unit 12 determines that the operation end time has not arrived (step S18: No), it transitions to step S10, and if it determines that the operation end time has arrived (step S18: Yes), it terminates the processing shown in Figure 10.
[0226] 5. Modifications The above-mentioned prediction model may be a model in which information of an advertising channel is input as a feature. The advertising channel may be, but is not limited to, a search engine, a social media platform, a display network, a video hosting platform, email, etc. The search engine may be, for example, Google (registered trademark) or Bing (registered trademark).
[0227] Display networks are, for example, websites, blogs, and other digital platforms. Video hosting platforms are, for example, YouTube®, TilTok®, etc.
[0228] Furthermore, when the optimization request does not include information on the target CPA, the optimization unit 32 can predict the user type for which the target CPA will be the smallest based on the information on the set customer journey and the information on the delivery period. In this case, the optimization unit 32 predicts the CPA predicted when the user type predicted in this way is targeted as the target CPA.
[0229] Some or all of the functions of the information processing device 1 described above may be included in the functions of the terminal device 2. That is, the terminal device 2 may have some or all of the functions of the acquisition unit 30, the reception unit 31, the optimization unit 32, the identification unit 33, and the provision unit 34.
[0230] [6. Hardware Configuration] The information processing device 1 according to the embodiment described above is realized by a computer 80 having a configuration as shown in Fig. 11. Fig. 11 is a hardware configuration diagram showing an example of the computer 80 that realizes the functions of the information processing device 1 according to the embodiment. The computer 80 has a CPU 81, a RAM 82, a ROM (Read Only Memory) 83, a HDD (Hard Disk Drive) 84, a communication interface (I / F) 85, an input / output interface (I / F) 86, and a media interface (I / F) 87.
[0231] The CPU 81 operates and controls each part based on a program stored in the ROM 83 or the HDD 84. The ROM 83 stores a boot program executed by the CPU 81 when the computer 80 is started up, and programs that depend on the hardware of the computer 80.
[0232] The HDD 84 stores programs executed by the CPU 81, data used by such programs, etc. The communication interface 85 receives data from other devices via the network N (see FIG. 2) and sends it to the CPU 81, and transmits data generated by the CPU 81 to other devices via the network N.
[0233] The CPU 81 controls output devices such as a display and a printer, and input devices such as a keyboard and a mouse, via the input / output interface 86. The CPU 81 acquires data from the input devices via the input / output interface 86. The CPU 81 also outputs data generated via the input / output interface 86 to the output devices.
[0234] The media interface 87 reads a program or data stored in a recording medium 88 and provides it to the CPU 81 via the RAM 82. The CPU 81 loads the program from the recording medium 88 onto the RAM 82 via the media interface 87 and executes the loaded program. The recording medium 88 is, for example, an optical recording medium such as a DVD (Digital Versatile Disc) or a PD (Phase change rewritable Disc), a magneto-optical recording medium such as an MO (Magneto-Optical disk), a tape medium, a magnetic recording medium, or a semiconductor memory.
[0235] For example, when the computer 80 functions as the information processing device 1 according to the embodiment, the CPU 81 of the computer 80 executes a program loaded onto the RAM 82 to realize the function of the processing unit 12. In addition, the HDD 84 stores data in the storage unit 11. The CPU 81 of the computer 80 reads and executes these programs from a recording medium 88, but as another example, these programs may be obtained from another device via the network N.
[0236] [7. Other] In addition, among the processes described in the above embodiments, all or part of the processes described as being performed automatically can be performed manually, or all or part of the processes described as being performed manually can be performed automatically by a known method. In addition, the information including the processing procedures, specific names, various data and parameters shown in the above documents and drawings can be changed arbitrarily unless otherwise specified. For example, the various information shown in each drawing is not limited to the illustrated information.
[0237] In addition, each component of each device shown in the figure is a functional concept, and does not necessarily have to be physically configured as shown in the figure. In other words, the specific form of distribution and integration of each device is not limited to that shown in the figure, and all or part of them can be functionally or physically distributed and integrated in any unit according to various loads, usage conditions, etc.
[0238] For example, the above-mentioned information processing device 1 may be realized by a terminal device and a server computer, or may be realized by multiple server computers. Also, depending on the functions, the configuration can be flexibly changed, such as by calling an external platform using an API or network computing.
[0239] Furthermore, the above-described embodiments and modifications can be appropriately combined as long as the processing contents are not contradictory.
[0240] 8. Effects As described above, the information processing device 1 according to the embodiment includes the reception unit 31 and the optimization unit 32. The reception unit 31 receives settings of a customer journey in which multiple time-series user actions related to an advertising target are defined. The optimization unit 32 performs optimization processing related to advertisement delivery in the customer journey based on the customer journey settings received by the reception unit 31. This allows the information processing device 1 to support optimization related to advertisement delivery.
[0241] The receiving unit 31 also receives, as a customer journey setting, information settings in which a plurality of user action parts related to the advertising target are arranged in chronological order and advertising information is set in at least one of the plurality of user action parts. This allows the information processing device 1 to further support optimization of advertising delivery.
[0242] Each of the plurality of user action components is selected from among a plurality of types of user action components included in the user action library. This allows the information processing device 1 to better support optimization of advertisement delivery.
[0243] Furthermore, the reception unit 31 receives settings of delivery information in a customer journey, and the optimization unit 32 performs optimization related to advertisement delivery based on the customer journey and the delivery information whose settings are received by the reception unit 31. This allows the information processing device 1 to further support optimization related to advertisement delivery.
[0244] The delivery information also includes information on the advertising budget, and the optimization unit 32 determines which user actions are to be optimized among multiple user actions included in the customer journey based on the advertising budget. This allows the information processing device 1 to better support optimization related to advertisement delivery.
[0245] Moreover, the information processing device 1 includes a providing unit 34 that provides optimization-related information including information indicating a result of the optimization-related process performed by the optimization unit 32. This allows the information processing device 1 to better support optimization related to advertisement delivery.
[0246] Moreover, the information processing device 1 includes an identification unit 33 that identifies a behavioral transition of the user U on the route of the customer journey whose setting has been accepted by the acceptance unit 31, and the provision unit 34 provides information indicating the identification result by the identification unit 33. This allows the information processing device 1 to further support optimization related to advertisement delivery.
[0247] The above describes the embodiment of the present application in detail based on the drawings, but this is merely an example, and the present invention can be implemented in other forms that include various modifications and improvements based on the knowledge of those skilled in the art, including the forms described in the Disclosure of the Invention section.
[0248] Furthermore, the above-mentioned "section, module, unit" can be read as "means" or "circuit", etc. For example, an acquisition section can be read as an acquisition means or an acquisition circuit. [Explanation of symbols]
[0249] 1. Information processing device 2,3 Terminal Equipment 10. Communications Department 11 Storage section 12 Processing section 20 User information storage unit 21 Optimization related information storage unit 30 Acquisition Department 31 Reception 32 Optimization Section 33 Specific part 34 Providing Department 100 Information Processing Systems N Network
Claims
1. A reception unit that receives a setting of a customer journey in which a plurality of time-series user actions related to an advertising target are defined; An optimization unit that performs optimization processing regarding advertisement delivery in the customer journey based on the customer journey whose setting is accepted by the acceptance unit.
23. An information processing apparatus comprising:
2. The reception unit is A setting of information in which a plurality of user action components related to the advertising target are arranged in chronological order and advertising information is set in at least one of the plurality of user action components is accepted as a setting of the customer journey.
2. The information processing apparatus according to claim 1,
3. Each of the plurality of user action components includes: A user action component selected from multiple types of user action components included in the user action library.
3. The information processing apparatus according to claim 2.
4. The reception unit is Accepting settings for delivery information in the customer journey; The optimization unit is Optimizing the advertisement delivery based on the customer journey and the delivery information, the settings of which are accepted by the accepting unit.
4. The information processing apparatus according to claim 1, wherein the information processing apparatus is a computer.
5. The distribution information includes: Contains advertising budget information, The optimization unit is Based on the advertising budget, a user action to be optimized is determined from among the plurality of user actions included in the customer journey.
5. The information processing apparatus according to claim 4.
6. a providing unit that provides optimization-related information including information indicating a result of a process related to optimization by the optimization unit; 4. The information processing apparatus according to claim 1, wherein the information processing apparatus is a computer.
7. An identification unit that identifies a behavioral transition of a user along a route of the customer journey whose setting has been accepted by the acceptance unit, The providing unit is Provide information indicating the result of the identification by the identification unit 7. The information processing apparatus according to claim 6,
8. 1. A computer-implemented information processing method, comprising: A receiving step of receiving a setting of a customer journey in which a plurality of time-series user actions related to an advertising target are defined; and an optimization process for performing optimization processing regarding advertisement delivery in the customer journey based on the customer journey whose setting has been accepted by the acceptance process.
23. An information processing method comprising:
9. An acceptance procedure for accepting a customer journey setting in which multiple chronological user actions related to an advertising target are defined; an optimization procedure for performing optimization processing related to advertisement delivery in the customer journey based on the customer journey, the setting of which is accepted by the acceptance procedure, 23. An information processing program comprising:
Citation Information
Patent Citations
Information processing device, information processing method and information processing program
JP2019220052A
