Information processing device, information processing method, and program
Patent Information
- Authority / Receiving Office
- JP · JP
- Patent Type
- Applications
- Current Assignee / Owner
- THROUGH PASS INC
- Filing Date
- 2025-08-18
- Publication Date
- 2026-08-06
Smart Images
Figure 2026127573000001_ABST
Abstract
Description
Technical Field
[0001] The present invention relates to an information processing apparatus, an information processing method, and a program that can be applied to the consideration or formulation of measures for a target person.
Background Art
[0002] A direct mail creation support device that proposes optimal conditions for direct mail has been proposed (see Patent Document 1).
Prior Art Documents
Patent Documents
[0003]
Patent Document 1
Summary of the Invention
Problems to be Solved by the Invention
[0004] An object of the present invention is to provide an information processing apparatus, an information processing method, and a program that can output information useful for considering or formulating effective measures.
Means for Solving the Problems
[0005] 1. Information Processing Method An information processing method for calculating information for supporting the formulation of a measure that appeals to an effective action or behavior for a predetermined person, or an object of the action or behavior, in consideration of a predetermined event or situation, a step of inputting an action or behavior, or an object of the action or behavior, by an input unit; a step of inputting, by the input unit, information on the implemented measure when the measure is implemented at a plurality of time points based on the time point of a predetermined event or situation; a step of inputting, by the input unit, the response content of the implemented measure; a step of calculating, by a response transition calculation unit, the response transition of the response content of the measure; The impact calculation unit includes the step of extracting and setting feature quantities related to the event or situation and the measures based on the response trends, using machine learning, and calculating the degree to which the feature quantities have an influence on the response content.
[0006] The information processing method of the present invention may include a step of estimating the response rate if a measure were implemented at a predetermined time from the same or similar time of occurrence as the event, based on the degree of influence on the response rate.
[0007] In the above invention, the information processing method may include a step of inputting or deriving the relationships between feature quantities. The information processing device may include an input unit or a derivation unit for inputting the relationships between feature quantities. When calculating the degree to which the feature quantities have an influence on the feedback content, a more accurate degree of influence can be calculated.
[0008] The information processing method of the present invention may include a step of estimating the response rate when a measure is implemented at a predetermined time, based on a correspondence table that associates the feature quantity, the degree of influence on the response rate, and the time from the occurrence of an event identical or of the same type as the reference event with the amount of change in the response rate.
[0009] 2. Information Processing Device The information processing device of the present invention is An information processing device for calculating information to support the formulation of effective actions or behaviors, or strategies for appealing to the target of such actions or behaviors, to a specified person, taking into consideration a specified event or situation, An input section for inputting an action or behavior, or the object of an action or behavior, An input unit for inputting information about the measures implemented when the measures are implemented at multiple points in time based on the time of a predetermined event or situation, An input unit for inputting the response to the measures implemented, A response trend calculation unit that calculates the response trends of the content of the response to the aforementioned measure, Based on the response trends, the system includes an influence calculation unit that uses machine learning to extract and set feature quantities related to the event or situation and the measures, and calculates the degree to which the feature quantities influence the content of the responses.
[0010] 3. Program The program of the present invention, A program that causes a computer to execute an information processing method for calculating information to support the formulation of effective actions or behaviors, or strategies for appealing to the target of such actions or behaviors, to a specified person, taking into consideration a specified event or situation, The input unit inputs an action or behavior, or the object of the action or behavior. The input unit inputs information about the measures taken when the measures were taken at multiple points in time based on the time of a predetermined event or situation. The input unit inputs the content of the response to the measures implemented, The response transition calculation unit calculates the response transition of the response content of the aforementioned measure, The system causes a computer to perform the following steps based on the response trends: the influence calculation unit extracts and sets feature quantities related to the event or situation and the measures using machine learning, and calculates the degree to which the feature quantities influence the content of the responses.
[0011] Multiple points in time, based on the point in time of a specified event or situation, shall include points in time before and after the point in time of the specified event or situation.
[0012] Actions or behaviors include concepts encompassing all actions or behaviors such as participation actions, purchase actions, actions of transfer or lending, borrowing actions, usage actions, viewing actions, actions of providing services, actions of receiving service provisions, movement actions, etc. The objects of actions or behaviors include, for example, transfer or transfer / receipt objects (including purchase objects), usage objects, lending objects, consideration objects, those for whom a given person receives some service provision, and more specifically, concepts including goods and services, real estate, events and gatherings or any meetings, things used in service provisions or things provided for use of services, etc.
[0013] The degree of influence on the response content of the reference event or situation may also be calculated. As a specific example, for instance, the degree of influence can be shown in the form of "Regarding Law Amendment A, Feature Quantity X had this much influence".
[0014] The degree of influence on the response content regarding the content of the implementation measures may also be calculated. As a specific example, for instance, the degree of influence can be shown in the form of "Regarding Measure A, Feature Quantity Y had this much influence".
[0015] In this specification, machine learning is a concept that also includes deep learning
Advantages of the Invention
[0016] According to the present invention, an information processing apparatus, an information processing method, and a program capable of outputting information contributing to the consideration or formulation of effective measures can be realized.
Brief Description of the Drawings
[0017] [Figure 1] A conceptual diagram of information processing according to an embodiment is shown. [Figure 2] An information processing flow according to an embodiment is shown. [Figure 3] An example of the relationship at each time point for grasping the response rate and obtaining the response transition in relation to measure implementation is shown. [Figure 4] It is a display example showing the contribution degree of feature quantities. [Figure 5] This section shows a screen displaying information on the implementation of measures, an example of the output for estimating influencing factors, and an example of how improvement suggestions are displayed. [Figure 6] This is an illustrative diagram of model interpretation technology. [Figure 7] An example of an information processing device is shown. [Figure 8] An example of an information management screen is shown. [Figure 9] An example of the analysis screen is shown. [Figure 10] This is an example of a diagram that organizes candidate features and the relationships between them in a tree format, which is useful when deciding "what features to include" in machine learning. [Modes for carrying out the invention]
[0018] Hereinafter, preferred embodiments of the present invention will be described with reference to the drawings.
[0019] The basic concept of the information processing method according to this embodiment supports, for example, the realization of the following steps 1 to 4. Step 1: Data Formatting and Input Step 2: Model creation using machine learning (feature extraction, etc.) Step 3: Calculation of the degree of influence of each feature through model interpretation. Step 4: Recommending the optimal direct mail strategy
[0020] "At least one step of feature extraction and configuration" is one of the tasks in Step 1. By decomposing information such as the project creative list described later into elements (i.e., features) and applying machine learning, a mathematical model can be created with the features as variables. After reviewing the results of Steps 2 and 3, one can return to Step 1 to create a more accurate model. This process of reviewing the results of Steps 2 and 3 and returning to Step 1 can be repeated. The concept of feature contribution includes those shown by coefficients (so-called mechanical contributions) and those that are visualized and made easy to understand for humans (so-called human-oriented contributions such as SHAP values). The concept of a model formula includes a first model formula shown in terms of features and feature contributions, and a second model formula that uses the first model formula. The second model formula is calculated by returning to Step 1, reviewing the features, and repeatedly inputting and processing to improve the accuracy of the model formula. This is the execution of machine learning for model interpretation to make it visualized and easy to understand. Visualization allows for the consideration of improvement measures using steps of inference and deduction.
[0021] The method for creating machine learning models can be appropriately selected depending on the data and field. In machine learning, for example, there are three ways to use it. The first way to use it is to extract features and set which features to include. The second way to use it is to machine learn from the input data, calculate the contribution, and create a mathematical model (3a + 4d + ...) that can be understood by the machine using the model method. The third way to use it is to machine learn (visualize) so that it can be interpreted by humans. When selecting which features to include, the candidate features shown in Figure 10 and the relationships between each feature can be organized in a tree format to select the features.
[0022] In this specification, "DM" is described as an example of "strategy" and "appeal strategy." Even if it is described as "DM," it is not limited to "DM" and can be interpreted as being broadly applicable to "strategy" and "appeal strategy." Therefore, the use of "DM" does not mean to exclude appeals that are not DMs from the concepts of "strategies" and "appeals," but rather to use "DM" as an example, and descriptions that replace "strategies" and "appeals" are also within the scope of disclosure of this specification.
[0023] As shown in Figure 1, the information processing method according to this embodiment takes information about an event or situation, a sales strategy, and the response to the sales strategy as input, extracts and sets features using machine learning, calculates the degree of influence of the features, and can then calculate an inference model or evaluation model based on that degree of influence.
[0024] As shown in Figure 2, one concrete example of the concept of an information processing method is presented. This information processing method is an example of a series of processing flows and may include a step S1 in which information about an event or situation is entered, a step S2 in which information about each appeal is entered, a step S3 in which the response rate for each appeal is entered, a step S4 in which the trend of the response rate is calculated, a step S5 in which features are extracted or set by machine learning, a step S6 in which a model equation is calculated with the features as variables, a step S7 in which the contribution of each feature to the response rate is calculated, and a step S8 in which the contribution of each feature is displayed. Machine learning can be performed in both the feature extraction and / or setting step S5 and the model equation calculation step S6. Machine learning can also be performed in the feature contribution calculation step S7 and the feature contribution display step S8.
[0025] Figure 3 shows an example of the relationship between different time points for understanding the response rate and obtaining the response trend in relation to the implementation of a strategy. Based on the time point at which the event or situation was understood, response rates a, b, and c are obtained when appeal strategies A, B, and C are implemented, respectively. The time points at which the response rate is understood from the date of implementation of the strategy can be arbitrarily determined. Multiple response rates may be understood for a single appeal strategy at different time points.
[0026] The information processing method according to the embodiment may be used to calculate information to support the formulation of effective actions or behaviors, or strategies to appeal to a specific person, taking into consideration a predetermined event or situation. The information processing method may include a step in which an input unit inputs an action or behavior, or the target of an action or behavior; a step in which the input unit inputs information about the implemented strategy when the strategy is implemented at multiple points in time based on the point in time of the predetermined event or situation; a step in which the input unit inputs the content of the response to the implemented strategy; a step in which a response transition calculation unit calculates the response transition of the content of the response to the strategy; and a step in which an influence degree calculation unit extracts and sets feature quantities related to the event or situation and the strategy using machine learning based on the response transition, and calculates the degree of influence of the feature quantities on the content of the response. The information processing method may include a step in which relationships between feature quantities are input or derived. Relationships between feature quantities include, for example, constraints, increases and decreases, denominator effects, and numerator effects between feature quantities, as shown in Figure 10. It is possible to derive or set the following relationships: budget and number of shipments are constraints, shipping method and shipping cost are inversely related, number of shipments and CVR are inversely related, and cost and CPA (Cost per Acquisition) are inversely related. By including a process of inputting or deriving the relationships between features, it is possible to calculate a more accurate degree of influence of the features on the response content, and this is also useful when calculating the model equation.
[0027] (1) Information concerning events or circumstances to be used as reference Information regarding events or situations to consider includes timing, client (=DM issuer), customer information (client's customers), competitor information, economic trends, social trends, political trends, and technological trends. Timing can include, for example, seasons, industry events, and industry peak periods.
[0028] As for the client (=DM issuer), examples include industry, market share, target audience, price, number of employees, sales volume, sales growth rate, and capital relationships. As for customer information, examples include industry, number of employees, sales volume, sales growth rate, and capital relationships. As for competitor information, examples include market share, target audience, price, frequency of DM distribution, and content / design of DM. As for economic trends, examples include industry growth rate, corporate investment intentions, economic fluctuations, inflation / deflation situation, and exchange rates. As for social trends, examples include changes in consumer purchasing behavior and differences in values between generations. As for political trends, examples include changes in laws and regulations, tax reforms, changes in trade relations, government support for the industry, and government subsidies. As for technological trends, examples include the progress of DX, data analysis technology, and AI / automation technology.
[0029] An event or situation can be a concept that includes external factors that affect products, services, or direct mail campaigns, such as legal changes or industry events. The implementation of the promotional strategy itself can also be considered an event or situation.
[0030] Information on a company's willingness to invest can be considered not only in terms of numerical data such as "the target company's total annual investment amount," but also in terms of non-numerical data such as "references to the relevant sector in financial statements."
[0031] (2) Information regarding measures The strategy involves taking some kind of action to ensure that the target audience becomes aware of it. This concept includes persuasive strategies, and more specifically, direct mail (DM) is one example.
[0032] Information regarding the campaign consists of at least one item selected from the group comprising: appeal content, conversion (results), conversion path, rewards, costs incurred from campaign creation to delivery, campaign implementation date (delivery date), number of campaigns implemented (number of deliveries), campaign specifications, campaign content (content published), campaign design information, and a list of recipients. A persuasive strategy refers to, for example, a method of communicating information that can be perceived by the target audience, and is a concept that includes direct mail, printed sales promotion materials, and email.
[0033] To illustrate the information regarding strategies, we will use projects, creatives, and lists as examples.
[0034] The definition of the project creative list managed and analyzed in "Management and Analysis of DM (Direct Mail) Data and Results Data" is as follows:
[0035] A project is defined as information related to initiatives other than the creative list. Examples of project details include the appeal content (e.g., invitation to a management seminar, introduction to a new service), conversions (e.g., inquiries, service applications), conversion channels (e.g., website, email, fax), offers or benefits (e.g., 3 months free, free samples), costs (e.g., costs incurred for producing and sending direct mail), mailing date (e.g., the date the direct mail was sent), and number of mailings (e.g., the number of direct mailings sent).
[0036] Creative refers to information regarding the specifications, content, and design of mailings. Creative specifications can include the type of material (envelope, postcard, OPP bag (transparent envelope), etc.), the number of items (e.g., 3 items enclosed in the envelope, 1 item enclosed), and the size / shape (A4, B5, square, die-cut, etc.). Content can include the structure, content, and amount of text. Design can include the color, font, and motif.
[0037] The list can include information about the shipping destination (area, industry, recipient name, etc.).
[0038] Relative priorities may be set among the various pieces of information. Information before and after the implementation of the appeal measures may also be entered. Specifically, it may be possible to compare the response rate of measures taken before the appeal measures were implemented with the response rate of measures taken after the appeal measures were implemented. Qualitative information can be indexed using keywords.
[0039] Changes in consumer purchasing behavior can be examined, for example, based on data on the number of keyword searches over a given period (e.g., monthly).
[0040] (3)Reaction content The content of the response can be, for example, the response rate (CVR). The response rate (CVR) can be defined as the number of conversions per unit of mailings for each project (direct mail campaign). The response rate (CVR) is a percentage (%) value calculated based on Equation 1.
[0041] (Formula 1) Number of conversions ÷ Number of copies sent = CVR
[0042] (4) Features Features can be derived using various analytical methods and extracted using known feature extraction methods. When extracting features, a process of quantifying them is performed as needed so that they can be incorporated into machine learning. This quantification process may be done using predefined methods or by calculating them using software.
[0043] (5) Degree of contribution One example of a contribution is the SHAP value. The SHAP value indicates how much each feature contributes to the predicted value. An example of this is shown in Figure 4. The vertical axis shows the features listed, and the horizontal axis shows the distribution of the influence value of each feature in the input data, which in this example is the SHAP value. The content of each strategy can be shown using color coding. SHAP value, for example When calculating a machine learning model based on data from 10 direct mail campaigns, In DM strategy 1, the SHAP value is 100 In DM Strategy_2, the SHAP value was -90 ... In DM Strategy_10, the SHAP value is 30 The values for each direct mail campaign can be plotted using red and blue circles, creating a graph that visualizes the magnitude of their impact.
[0044] 3. Hardware Configuration Figure 7 shows an example of the hardware configuration of an information processing device.
[0045] The information processing device 10 according to this embodiment can be implemented by one or more computers. The input device 20 can be implemented using known input means such as a keyboard, mouse, or touch input device, and is a concept that includes a data acquisition unit that acquires information from hardware resources (such as a server) connected to a communication network (including an internet connection). The input device 20 may include an event or situation input unit 20a, a policy input unit 20b, an echo input unit 20c for inputting echo content, a relevance input unit 20d for setting the degree of relevance of information, and a feature quantity setting unit 20e for setting feature quantities. The input device 20 can be configured by means having one or more input functions.
[0046] Functionally, the processing unit 30 may include a correlation calculation unit 30a that calculates the degree of correlation of information, a response transition calculation unit 30b that calculates the response transition from multiple response contents, a feature extraction unit 30c that extracts feature quantities, a contribution calculation unit 30d that calculates the contribution of feature quantities, a model formula calculation unit 30e that calculates a model formula from the contribution of feature quantities, a response result prediction unit 30f that predicts response results from policies and various information, and an effect verification unit 30g that verifies the effects of the policy implementation and response results, and verifies the model formula. These processes may be implemented by a single arithmetic unit or by multiple arithmetic units. The processing may also be implemented by multiple computers. The processing unit 30 can be implemented by an arithmetic unit such as a CPU. The information processing device 10 may have a storage device 50 that stores various input data and calculated data. The storage device 50 can be stored in a known storage device such as a ROM, a hard disk, or an external storage device (CD, DVD, etc.). The storage device 50 may be configured separately from the arithmetic unit or may be configured within the arithmetic unit. A program that causes the information processing device 10 to perform information processing can be stored in a storage device (for example, ROM, hard disk) included in the information processing device 10. As an example of the processing of the response result prediction unit 30f, it is possible to perform information processing such as calculating a predicted CVR of 0.5% and finding that the feature with the highest contribution is "reward," and then changing the content of "reward" and predicting again with the response result prediction unit 30f, resulting in a predicted CVR of 0.8%. The information processing device can include an input unit or a derivation unit for inputting the relationships between feature quantities.
[0047] The information processing device 10 may include a display device 40 that displays various processing results, such as the degree of contribution of feature quantities. The display device 40 can be a known display such as a liquid crystal display or an organic EL display.
[0048] The information processing device 10 may consist of an input device 20, a processing device 30, a display device 40, and a storage device 50, all of which are part of a single piece of hardware, or they may consist of multiple pieces of hardware that are capable of communication. The information processing device 10 may consist of a single computer or multiple computers. 4. Effects and Examples of Use The effects and usage examples of the information processing method according to this embodiment will be described below.
[0049] (1) According to this embodiment, for example, the strength of the influence of the information on the effectiveness of direct mail can be estimated, and the results of the direct mail response can be analyzed and predicted.
[0050] This embodiment, as an example, serves the following purpose.
[0051] 1) Management and analysis of DM data and performance data 2) Proposals for improving direct marketing strategies using machine learning models This embodiment has the following effects.
[0052] When implementing a direct mail (DM) campaign, it's often unclear which target audience to send to, when to send it, what content to include, and what type of DM to use for maximum effectiveness. This information processing method allows for the detection of characteristics of highly effective DMs by managing and analyzing information related to past DM campaign projects, creatives, and lists.
[0053] After implementing a direct mail (DM) campaign, it's often difficult to accurately analyze the reasons for high or low effectiveness during the effectiveness evaluation, making it challenging to formulate effective improvement plans. By managing and analyzing information related to past DM campaign projects, creatives, and lists, we can detect the reasons for high or low effectiveness.
[0054] (2) As shown in Figure 5, it is possible to propose improvements to direct mail (DM) strategies using machine learning models. When implementing DM strategies, it is not possible to determine which target audience to send what content to, at what time, and with what type of DM to maximize effectiveness. By performing machine learning and using model interpretation techniques based on the following considerations, it is possible to identify features (≒ elements) that have a large / small impact on DM strategies.
[0055] (Consideration information) • Project Information • Creative information • List information • Other internal information: Sales figures / number of employees of companies sending out direct mail, etc. Other external information: stock prices, legal changes, weather, etc.
[0056] (3) By constructing an inference model using the extracted or defined features, the following can be done, for example: 1) Before implementing a measure, it is possible to calculate the "predicted number of conversions," "predicted conversion rate," and "predicted cost per acquisition (CPA)" by inputting information about the measure. 2) Before the implementation of the measures, by inputting information about the measures, it is possible to submit improvement suggestions and the expected range of improvement resulting from those suggestions. 3) After the implementation of the measures, by inputting information about the measures and the CVR, it is possible to analyze the causes of discrepancies between the "predicted number of conversions / CVR / CPA" and the actual results, and to improve the machine learning model. 4) It is useful in recommending the optimal direct marketing strategy. It contributes to the recommendation process. 5) Because it is possible to calculate the contribution of features, it can play a role as a method for calculating model equations, methods for estimating effects, and methods for calculating support data for formulating measures to improve effectiveness. 6) It can be used to manage and analyze data and performance data of appeals (e.g., direct mail). It can be used to propose improvements to appeals using machine learning models. By applying machine learning to information, it is possible to estimate the strength of the influence of that information on the effectiveness of appeals. It can also be used to analyze and predict the response results of appeals.
[0057] (4) As shown in Figure 6, by inputting data into a machine learning model, it is possible to learn and output complex relationships that humans cannot grasp. The overall process involves inputting data into a machine learning model, identifying the basis for the model's predictions and judgments using model interpretation techniques, updating the machine learning model, and improving the description of relationships, for example, improving a specific level of contribution. It is possible to propose improvements to DM measures using the machine learning model. In other words, as shown in Figure 5, 1) it becomes easy to estimate factors that affect the effectiveness of DM using a machine learning model that has learned from the information on DM measures managed by this system, and 2) it becomes easy to automatically propose areas for improvement in the effectiveness of new DM measures based on the estimated influencing factors and their degree of impact.
[0058] 5. Specific Examples The number of internet searches or information on companies' willingness to invest that can be obtained are examples of events or situations. It is also possible to estimate the relationship between the number of internet searches obtained and the response rate, and the relationship between companies' willingness to invest and the response rate.
[0059] (1) First specific example The first specific example is given below.
[0060] (Premise) This example demonstrates a review and analysis of direct mail (DM) promotional activities for a human resources management tool, conducted monthly from April to June 2024. (Results of direct mail marketing) The details and effects of the direct mail promotion campaign promoting product "X" are assumed to be as follows: <DM sent in April 2024> Number of copies shipped: 10,000 Number of CVs (number of responses): 10 CVR (response rate): 0.1% <DM sent in May 2024> Number of copies shipped: 10,000 Number of CVs (number of responses): 40 CVR (response rate): 0.4% <DM sent in June 2024> Number of copies shipped: 10,000 Number of CVs (number of responses): 120 CVR (response rate): 1.2% (Factor analysis) When analyzing the factors that led to the results of the above direct mail promotion, if we investigate the "number of internet searches for related keywords," which can be considered one of the factors, the analysis results can be presented as follows.
[0061] Assuming that a search server on the internet retrieves keyword search information and found that the number of internet searches for the related keyword "personnel management" during the period was as follows: ·April 2024: 10,000 times / month ·May 2024: 30,000 times / month ·June 2024: 60,000 times / month Based on the above results, and taking into account the influence of other factors, a machine learning analysis was performed to calculate that the influence of "number of internet searches" on the CVR (conversion rate) is ●●●. The nature of the influence varies depending on the program used to calculate the influence. In this way, the influence can be calculated.
[0062] (2) Second specific example The following information processing flow is also acceptable. In direct mail promoting "Product X," the number of internet searches for related keywords was highly relevant to the legal amendment A (effective date: mid-July). ·April: 10,000 times ·May: 30,000 times ·June: 60,000 times Let's assume that this was known. In April, we sent out 10,000 direct mail pieces, resulting in 10 conversions (response rate of 0.1%). The direct mail campaign sent out in May consisted of 10,000 copies, resulting in 40 conversions (response rate of 0.4%). The direct mail campaign sent out in June consisted of 10,000 copies, resulting in 120 conversions (response rate of 1.2%). Let's assume this is the result. Based on the above results, we can conclude that the impact of legal amendment A on the direct mail response rate for product X is XXX, and that the response rate will change by △△% as the implementation date approaches. On the other hand, the impact of internet searches is □□□.
[0063] The expression "degree of impact" can have several different meanings depending on the "event" being input. For example, in the case of a legal amendment, the degree of impact would be calculated in terms of a causal relationship, such as "the implementation of this legal amendment increases the need for introducing this service, and thus its introduction progresses." In the case of internet search volume, the degree of impact would be calculated in terms of a correlation, such as "sending direct mail during periods when the number of searches for the related keyword 'human resources management' is high tends to result in a higher conversion rate (CVR)."
[0064] From the first and second specific examples, it is possible to calculate the degree of influence using internet search volume and CVR as input information. It is also possible to calculate the degree of influence such as, "Sending direct mail during periods of high search volume tends to increase the CVR (response rate) of that direct mail."
[0065] (3) A third specific example This method can also be used to determine the extent to which the response rate of each direct mail campaign was affected by various legal revisions and the dates of those revisions.
[0066] The following is an example of a specification when a legal amendment is considered an event. Step 1: Set the degree of relevance between the "product / service to be promoted in the direct mail" and the "legal amendment" in question for each case (e.g., very high / high / medium / low / very low). Step 2: Classify the "products / services to be promoted in the direct mail" and various "legal amendments" for each project (e.g., [products / services: medical / construction / IT...], [legal amendments: laws / government ordinances / ministerial ordinances / regulations / written laws]). Step 3: Group items based on their classification and relevance, then calculate the response trend by aggregating the "interval between dispatch date and revision date" and the "response rate for each item" within each group. Step 4: Using machine learning, the accuracy of the prediction model is improved by taking into account the influence (contribution) of other features on the calculated response trends. As a grouping method, "amendments to the Labor Standards Act" can be divided into five categories: "1. Laws related to the Labor Standards Act / 2. Cabinet Orders / 3. Ministerial Ordinances / 4. Regulations / 5. Written Laws and Regulations related to the Labor Standards Act," and a degree of relevance can be assigned to each category. For example, in relation to goods or services, "1. Laws related to the Labor Standards Act" could be considered to have a "very high" degree of relevance, while "4. Regulations related to the Labor Standards Act" could be considered to have a "low" degree of relevance.
[0067] In the case of legal revisions, it is possible to calculate the degree of impact in terms of causal relationships, such as "the implementation of this legal revision will increase the need for introducing this service, and thus promote its adoption." In the case of internet search volume, it is also possible to calculate the degree of impact in terms of correlations, such as "sending direct mail during periods when the number of searches for the related keyword 'human resources management' is high tends to result in a higher conversion rate (CVR)."
[0068] Legal amendment A has an impact of XX, and the response rate will change by □□% as the implementation date approaches. On the other hand, it is also acceptable to output that internet search volume has an impact of △△. It is also possible to output that "In a project (DM campaign) with a response rate of 0.3%, legal amendment A has an impact of ●●●." Changes in laws and regulations can be referenced from government legal amendments and regulatory information databases, and the response rate can be estimated by aggregating the trend of reactions before and after the legal amendment from past data.
[0069] "A compilation of trends in reactions before and after a legal amendment" can be illustrated by the following example: By aggregating data such as the response rates of direct mail sent one year, six months, three months, one month, and one month after legal amendment A, the response rates of direct mail sent one year, six months, three months, one month, one month, and three months after legal amendment B, and the response rates of direct mail sent one year, six months, three months, and three months after legal amendment C, it is possible to quantitatively present a prediction that the conversion rate (CVR) will increase by approximately +10% month-on-month until three months before the legal amendment, but will surge by +80% month-on-month from three months before to the amendment date, and then decline sharply after the amendment date. This method can be used to identify "how much the response rate of each direct mail campaign was affected by various legal revisions and the dates of those revisions." It can also be used to construct a model of response trends.
[0070] 6. Examples of the administration screen and analytics screen You may manage and analyze DM data and performance data on the information management screen (see Figure 8) and the analysis screen (see Figure 9). You may also register and manage information and effects (results) of past DM campaigns. Based on the managed data, you may aggregate and analyze campaign attributes (project, creative, list) and time series. You may refine future DM campaigns based on the aggregation and analysis.
[0071] 7. Regarding the period related to the progression of responses The following is an example of how to consider the time period assumed when deriving the trend of responses. (1) The period until the deadline (e.g., the effective date) (2) The period elapsed from the start date (e.g., product release date) (3) The period before and after a specified period (e.g., the peak season for the industry) (4) Period from the initial implementation date of the measure to the most recent implementation date
[0072] The periods (1) to (3) above are set assuming that a specific event will occur. Period (1) is specifically the period applied when considering the trend of responses to measures taken before the deadline. Period (2) has a fixed start date and is the period applied when considering the trend of responses to measures taken after that start date. Period (3) is a period during which an event occurs and is applied when considering the trend of responses to measures taken before and after that event. Period (4) is a period during which no specific event occurs, for example, when you want to purely examine a measure for six months or a year. When setting the period in (1) to (3), the degree of influence can be shown, for example, in the form of "Regarding legal amendment A, feature X had this much influence," or "Regarding policy A, feature Y had this much influence." In the case of setting the period in (4), the degree of influence can be shown, for example, in the form of "Policy A had this much influence on feature Y."
[0073] (1) The period will be explained using legal amendments as an example. As a prerequisite, since companies will need to take prescribed measures in accordance with this amendment, a preparation period of approximately two years will be provided from the date of notification to the date of enforcement. When promoting software services to support compliance with this amendment using direct mail, the response is expected to change as follows depending on the implementation date of the measure. First phase: Within one month of the announcement date (approximately two years until the implementation date): Many responses are received from companies that are quick to respond, such as those with a significant business impact. Medium-term: Approximately one year from the announcement date (approximately one year until the enforcement date): Companies that respond early have already started, and even companies that are late still have about a year until the deadline, so there is not much response. Later period: Approximately two years from the announcement date (just a short time until the implementation date): A large response is generated due to a "last-minute demand" from companies that were slow to respond.
[0074] As described above, by inputting and calculating the response trends for each day the measure is implemented, it is possible to estimate the appropriate implementation date, as well as calculate the appropriate conditions such as creatives and lists for each implementation date, and the degree of influence of each feature. By calculating the degree of influence of each feature in this way, we can obtain evaluations such as the following. Example 1: In the previous period, the conversion rate (CVR) was increased by narrowing the mailing list to listed companies that had a high business impact and required a rapid response. Example 2: In the medium term, when the number of responses tends to decrease, the strategy is to reduce the cost per measure and increase the number of measures, resulting in "fewer missed opportunities within the same budget." Example 3: In the later stages, a surge in demand is anticipated, and many competing services will also be promoting their services. Therefore, offer incentives to increase the conversion rate (CVR).
[0075] (2) The period will be explained using the release of a new product as an example. As a premise, this product is novel and meets market needs, but the barriers to entry are not high, and competitors are entering the market one after another. When promoting this service using direct mail, the response is expected to change as follows depending on the date the campaign is implemented. Early stage (within one year of product release date, no competitors): Receives significant feedback from innovators and early adopters. Mid-term: 1-3 years after product release (several competitors enter the market): The growth in response gradually slows down as companies compete for early majority market share. Late Stage: More than 3 years have passed since product release (many competitors have entered the market): Many competitors are working to acquire the late majority and encourage brand switching from other companies, resulting in stagnant response.
[0076] As described above, by inputting and calculating the response trends for each day of implementation of a measure, it is possible to estimate the appropriate implementation date and cost allocation, as well as calculate the appropriate conditions such as creatives and lists for each implementation date, and the degree of influence of each feature. By calculating the degree of influence of each feature in this way, we can obtain evaluations such as the following. Example 1: In the first half of the year, we increased the conversion rate (CVR) by narrowing the target recipients (list) to companies that are highly interested in innovative services. Example 2: In the mid-term, the focus is on improving the product based on customer feedback and differentiating it from competitors. Therefore, creative content that highlights functional differences will increase the conversion rate (CVR). Example 3: In the later stages, the market matures and the products of each company become standardized. Therefore, the strategy is to increase the number of responses by highlighting achievements and increasing customer touchpoints through the frequency of the measures.
[0077] Regarding the period in (3), we will explain it using the peak season of a certain industry as an example. As a premise, a certain industry has its peak season in December, and a certain product targeted at that industry tends to see increased demand during this peak season in December. When promoting this service using direct mail, the response is expected to change as follows depending on the date the campaign is implemented. Early period. Three months before the peak: This is a preparation period for the peak and is likely to generate a lot of feedback. Mid-term. Peak period: There is a moderate response as it replenishes products that were in short supply during the peak period. Later period. Three months after the peak: The response calms down as the off-season begins.
[0078] As described above, by inputting and calculating the response trends for each day of implementation of a measure, it is possible to estimate the appropriate implementation date and cost allocation, as well as calculate the appropriate conditions such as creatives and lists for each implementation date, and the degree of influence of each feature. By calculating the degree of influence of each feature in this way, we can obtain evaluations such as the following. Example 1: In the previous period, we increased the conversion rate (CVR) by differentiating ourselves from competitors through incentives and other means. Example 2: In the medium term, it is anticipated that there will be an urgent need to replenish the product, so the creative should emphasize the ability to respond quickly. Example 3: In the later stages, segments and costs are allocated according to the expected number of purchases and total purchase amount for each company, and different measures are taken for each segment.
[0079] Regarding the period in (4), we will explain using new measures for existing products as an example. As a premise, we will implement two types of strategies (Strategy A and Strategy B) with new appeals to a market that already has a certain level of awareness of this product. When implementing strategies A and B using direct mail, and conducting each strategy three times with intervals in between, the response is expected to change as follows depending on the implementation date of the strategy. First implementation date in the first semester: Strategy A received a large number of responses, while strategy B received a moderate number of responses. Mid-term, second implementation date (6 months after the first implementation): Moderate response was obtained with Strategy A, and moderate response was also obtained with Strategy B. Late period, 3rd implementation date (1 year after the 1st implementation): Strategy A received a small amount of feedback, while strategy B received a moderate amount of feedback.
[0080] As described above, by inputting and calculating the response trends for each day of implementation of a measure, it is possible to estimate the appropriate number of times to implement each measure, as well as to calculate the conditions such as creatives and lists that can suppress the reduction in the number of responses for each measure, and the degree of influence of each feature. Example 1: Strategy A shows a significant decrease in the number of responses with repeated implementations. Therefore, the number of implementations should be limited to two, and the recipient list for the second mailing should be narrowed down based on the characteristics of customers who responded in the first mailing to increase the conversion rate (CVR). Example 2: Since Strategy B shows only a slight decrease in response rates with repeated implementations, the number of implementations will be limited to 7 times, and the response rate will be increased by only changing the content of the rewards.
[0081] The above embodiments can be modified in various ways within the scope of the gist of the present invention. [Explanation of Symbols]
[0082] 10 Information Processing Devices 20 Input devices 30 Processing Unit 40 Display device 50 Storage device
Claims
1. An information processing method for calculating information to support the formulation of effective actions or behaviors, or strategies for appealing to the target of such actions or behaviors, to a specified person, taking into consideration a specified event or situation, The input unit inputs an action or behavior, or the object of the action or behavior. The input unit inputs information about the measures taken when the measures were taken at multiple points in time based on the time of a predetermined event or situation. The input unit inputs the content of the response to the measures implemented, The response transition calculation unit performs the step of calculating the response transition of the response content of the aforementioned measure, An information processing method comprising the steps of: an impact calculation unit extracting and setting feature quantities related to the event or situation and the measure based on the response trends, using machine learning, and calculating the degree to which the feature quantities have an influence on the response content.
2. An information processing device for calculating information to support the formulation of effective actions or behaviors, or strategies for appealing to the target of such actions or behaviors, to a specified person, taking into consideration a specified event or situation, An input section for inputting an action or behavior, or the object of an action or behavior, An input unit for inputting information about the measures implemented when the measures are implemented at multiple points in time based on the time of a predetermined event or situation, An input unit for inputting the response to the measures implemented, A response trend calculation unit that calculates the response trends of the content of the response to the aforementioned measure, An information processing device including an influence calculation unit that, based on the response trends, extracts and sets at least one of the feature quantities related to the event or situation and the measures using machine learning, and calculates the degree to which the feature quantities have an influence on the response content.
3. A program that causes a computer to execute an information processing method for calculating information to support the formulation of effective actions or behaviors, or strategies for appealing to the target of such actions or behaviors, to a specified person, taking into consideration a specified event or situation, The input unit inputs an action or behavior, or the object of the action or behavior. The input unit inputs information about the measures taken when the measures were taken at multiple points in time based on the time of a predetermined event or situation. The input unit inputs the content of the response to the measures implemented, The response transition calculation unit calculates the response transition of the response content of the aforementioned measure, A program that causes a computer to perform the following steps: an impact calculation unit extracts and sets feature quantities related to the event or situation and the measure based on the response trends, using machine learning, and calculates the degree to which the feature quantities have an influence on the response content.
Citation Information
Patent Citations
Direct mail creation support device, direct mail creation support method, and program
JP2021184212A