System and method for automatically generating optimal message for each customer in multiple campaign environments

Abstract

A system for automatically generating an optimal message for each customer in multiple campaign environments according to an embodiment of the present invention comprises: a profiling processing module for generating profiling on the basis of action data on a browser and metadata of a customer company; a scenario processing module for generating a plurality of pieces of scenario data on the basis of data on the results of the generated profiling; a scenario selection module for selecting final data for each individual from among the plurality of pieces of scenario data; and a transmission processing module for transmitting the selected final data to each corresponding individual and each corresponding channel.

Description

System and method for automatically generating optimal messages for each customer in a multiple campaign environment

[0001] The present invention relates to a message generation system and method, and more particularly, to a technology related to a system and method for automatically generating and delivering an optimal message for each customer in a multiple campaign environment.

[0002] Many companies operating e-commerce platforms use email, text messages, KakaoTalk channel messages, and app push notifications for customer relationship management (CRM) purposes to increase conversion rates and average purchase price among existing members. To deliver these messages, campaigns must be set up based on the six principles of W and H.

[0003] For example, sending a message requires setting the target recipient conditions and the date and time for sending the message. Furthermore, sending a message requires setting the delivery channel (e.g., email, text message, messenger (notification talk, friend talk), app push, etc.) and configuring the text, image, button name, and button link included in the message (material). Furthermore, sending a message requires setting a target indicator, specifying the quantitative indicator to be achieved, and setting other conditions, such as the number of messages allowed per person per day.

[0004] Message performance can be assessed by setting all six principles (the "W" and "H" principles), creating a campaign, sending the message, and then measuring four indicators: visit rate, click-through rate, conversion rate, and return on ad spend (ROAS). To further improve performance, A / B testing is often used, with variations on one of the six principles. For example, this can compare the four indicators between Group A and Group B. While A / B testing is a powerful way to optimize message performance, it can be cumbersome, requiring marketers to manually set up, conduct, and analyze each experiment. Furthermore, if the number of messages sent is small, only one variation can be tested at a time, which can lead to significant optimization delays.

[0005] Therefore, there is a need for a method that can create and deliver optimized messages for each customer in a short period of time with just simple settings.

[0006] The present invention aims to provide a system and method for automatically generating optimized messages for each customer in a multiple campaign environment, which allows a marketer to automatically generate optimized messages with only a few simple settings.

[0007] A system for automatically generating optimal messages for each customer in a multiple campaign environment according to one embodiment of the present invention may include a profiling processing module that generates profiling based on behavioral data on a browser and metadata of the customer company; a scenario processing module that generates a plurality of scenario data based on the generated profiling result data; a scenario selection module that selects individual final data from among the plurality of scenario data; and a transmission processing module that delivers the selected final data to each individual and channel.

[0008] The behavioral data on the above browser may include at least one of a page URL (uniform resource locator), the number of times an item is displayed, shopping cart information, purchase information, and scroll information.

[0009] The above customer metadata may include at least one of purchase history, member information, and promotional information.

[0010] The above profiling may include at least one of interest in a specific item, interest in a specific category, purchase probability, and return probability.

[0011] The above scenario processing module may include a triggering unit that triggers batch data generation and real-time request processing for scenario data simultaneously.

[0012] The above scenario processing module may include a scenario matching unit that selects a target scenario based on the customer's campaign execution status and personal profiling and performance data.

[0013] The above scenario processing module may include a scenario generation unit that generates multiple scenario data for each individual.

[0014] The above scenario processing module may include an additional information processing unit that additionally generates additional information that is essential to be included in the campaign.

[0015] The above scenario selection module may include a priority evaluation unit that sorts scenario data based on priority information set based on the client's past campaign performance; a channel filtering unit that removes unnecessary data based on the channel status of each client; and a content selection unit that selects one scenario data from the plurality of filtered scenario data.

[0016] The above system may further include a performance measurement module that collects different feedback data according to characteristics of each channel and measures the performance of the campaign.

[0017] A method for automatically generating optimal messages for each customer in a multiple campaign environment according to one embodiment of the present invention may include: generating profiling based on behavioral data on a browser and metadata of the customer; generating a plurality of scenario data based on the generated profiling result data; selecting final data for each individual from among the plurality of scenario data; and delivering the selected final data to each individual and channel.

[0018] The behavioral data on the above browser may include at least one of a page URL (uniform resource locator), the number of times an item is displayed, shopping cart information, purchase information, and scroll information.

[0019] The above customer metadata may include at least one of purchase history, member information, and promotional information.

[0020] The above profiling may include at least one of interest in a specific item, interest in a specific category, purchase probability, and return probability.

[0021] The step of generating the above scenario data may include a step of triggering batch data generation and real-time request processing for the scenario data simultaneously.

[0022] According to the present invention, there is an advantage in that a marketer can automatically create and deliver an optimized message with only a few simple settings, without having to experiment, measure, judge, and adjust all of the elements corresponding to the six principles described above.

[0023] The present invention offers the advantage of allowing marketers to automatically generate and deliver optimized messages with just a few simple settings, without having to experiment, measure, judge, and adjust all the elements corresponding to the six principles described above. For example, with just a few simple settings, marketers can automatically generate and deliver materials (e.g., images, text, etc.) based on individual member interest estimates.

[0024] FIG. 1 is a block diagram showing the detailed configuration of a system for automatically generating optimal messages for each customer in a multiple campaign environment according to one embodiment of the present invention.

[0025] Figure 2 is a block diagram showing a detailed configuration of a scenario processing module according to one embodiment of the present invention.

[0026] FIG. 3 is a block diagram showing a detailed configuration of a scenario selection module according to one embodiment of the present invention.

[0027] FIG. 4 is a flowchart illustrating a method for automatically generating optimal messages for each customer in a multiple campaign environment according to one embodiment of the present invention.

[0028] FIG. 5 is a block diagram illustrating a system for automatically generating optimal messages for each customer in a multiple campaign environment according to one embodiment of the present invention.

[0029] Hereinafter, embodiments of the present invention will be described in detail with reference to the attached drawings and the contents described in the attached drawings, but the present invention is not limited or restricted by the embodiments.

[0030] The terminology used herein is for the purpose of describing embodiments only and is not intended to limit the present invention. In this specification, the singular also includes the plural unless the context clearly dictates otherwise. As used herein, the terms "comprises" and / or "comprising" do not exclude the presence or addition of one or more other components, steps, operations, and / or elements.

[0031] The terms “embodiment,” “example,” “aspect,” and “example” used herein are not to be construed as implying that any aspect or design described is better or advantageous over other aspects or designs.

[0032] Also, the term 'or' means 'inclusive or' rather than 'exclusive or'. That is, unless stated otherwise or clear from context, the expression 'x utilizes a or b' means any one of the natural inclusive permutations.

[0033] Additionally, as used in this specification and claims, the singular forms “a” or “an” should generally be construed to mean “one or more” unless otherwise indicated or clear from the context to be in the singular form.

[0034] Additionally, while the terms "first," "second," etc., used in this specification and claims may be used to describe various components, these components should not be limited by these terms. These terms are used solely to distinguish one component from another.

[0035] Unless otherwise defined, all terms (including technical and scientific terms) used herein may be used in their common sense to those of ordinary skill in the art to which the present invention pertains. Furthermore, terms defined in commonly used dictionaries are not to be interpreted ideally or excessively unless explicitly and specifically defined otherwise.

[0036] Meanwhile, when describing the present invention, if a detailed description of a related known function or configuration is judged to unnecessarily obscure the gist of the present invention, such detailed description will be omitted. Furthermore, the terminology used in this specification is intended to appropriately express embodiments of the present invention and may vary depending on the intent of the user or operator, or the practices of the field to which the present invention pertains. Therefore, the definitions of these terms should be based on the contents throughout this specification.

[0037] In the various embodiments described below, a campaign may be a concept that includes advertisements, but is not limited to specific advertisement data. In one embodiment, campaign information may be referred to as scenario data, and the scenario data may include at least one of text, images, videos, and animations.

[0038] FIG. 1 is a block diagram showing the detailed configuration of a system for automatically generating optimal messages for each customer in a multiple campaign environment according to one embodiment of the present invention.

[0039] Referring to FIG. 1, a system for automatically generating optimal messages for each customer in a multiple campaign environment according to one embodiment of the present invention may include a profiling processing module (10), a scenario processing module (20), a scenario selection module (30), a sending processing module (40), and a performance measurement module (50).

[0040] The profiling processing module (10) may generate profiling based on behavioral data on a browser and metadata of the customer. For example, the behavioral data on the browser may include at least one of a page URL (uniform resource locator), the number of item exposures, shopping cart information, purchase information, and scroll information. The customer metadata may include at least one of purchase history, member information, and promotional information. The profiling processing module (10) may calculate profiling based on information of the customer itself (e.g., customer metadata) and behavioral information for each customer (e.g., behavioral data on a browser). According to one embodiment, the profiling may include at least one of interest in a specific item, interest in a specific category, purchase probability, and revisit probability. The profiling may be calculated according to a known calculation method.

[0041] The profiling processing module (10) may generate profiling result data according to the profiling generation process. At this time, the profiling result data may include goal-oriented profiling data. For example, the goal-oriented profiling data may be automatically tuned and generated using profiling parameters based on marketing actions and their performance. The profiling results may be generated by date and / or time. The profiling results may include individual profiling data and may further include targets and information for subsequent marketing actions.

[0042] According to one embodiment, the scenario processing module (20) can generate a plurality of scenario data based on the result data of profiling generated by the profiling processing module (10).

[0043] Hereinafter, the scenario processing module (20) will be described in detail with reference to FIG. 2.

[0044] Figure 2 is a block diagram showing a detailed configuration of a scenario processing module according to one embodiment of the present invention.

[0045] Referring to FIG. 2, a scenario processing module (20) according to one embodiment may include a triggering unit (21), a scenario matching unit (22), a scenario generation unit (23), and an additional information processing unit (24).

[0046] In one embodiment, the triggering unit (21) may be triggered to simultaneously process batch data generation and real-time requests for scenario data. To this end, the triggering unit (21) may have a dual architecture to simultaneously process batch data generation operations and real-time requests.

[0047] The scenario matching unit (22) can select target scenarios based on the client's campaign execution status and personal profiling and performance data. For example, the client's campaign execution status may include activated marketing channels or set times. The personal profiling and performance data may include data reflecting the previous exposure status for each campaign period or the individual's intention (e.g., turning off exposure).

[0048] The above scenario generation unit (23) can generate multiple scenario data for each individual. For example, since scenario data assigned to each individual can be selectively dropped in the future, the above scenario generation unit (23) can generate multiple scenario data.

[0049] The above-mentioned additional information processing unit (24) can additionally generate additional information that is essential to be included in the campaign. The additional information generated by the above-mentioned additional information processing unit (24) can be attached to each of the plurality of scenario data generated by the above-mentioned scenario generation unit (23).

[0050] Referring again to FIG. 1, according to one embodiment, the scenario selection module (30) can select individual final data from among the plurality of scenario data generated by the scenario processing module (20).

[0051] Hereinafter, the scenario selection module (30) will be described in detail with reference to FIG. 3.

[0052] FIG. 3 is a block diagram showing a detailed configuration of a scenario selection module according to one embodiment of the present invention.

[0053] Referring to FIG. 3, the scenario selection module (30) may include a priority evaluation unit (31), a channel filtering unit (32), and a content selection unit (33).

[0054] In one embodiment, the priority evaluation unit (31) can sort multiple scenario data based on priority information derived from the client's past campaign performance. For example, the priority evaluation unit (31) can select and set multiple indicators, such as open rate, click-through rate, and ROAS (Return of Ad Spend), according to the campaign's purpose. The priority evaluation unit (31) may further include response logic for new campaigns (cold starts).

[0055] In one embodiment, the channel filtering unit (32) can filter out unnecessary data (e.g., scenario data) from among the plurality of scenario data according to settings / policies such as channel status and cost control for each customer, thereby eliminating such unnecessary data. In this way, by eliminating unnecessary data from among the plurality of scenario data, charging can be controlled, and erroneous charges and incorrect transmissions can be prevented in advance.

[0056] In one embodiment, the content selection unit (33) may select materials (e.g., scenario data) to be actually exposed to customers and generate final scenario data. The content selection unit (33) may generate personalized scenario data based on previously received customer-specific campaign data. In this case, the content selection unit (33) may employ a tracking means for measuring campaign performance.

[0057] Referring back to FIG. 1, according to one embodiment, the transmission processing module (40) can transmit and process the final scenario data selected by the scenario selection module (30) for each individual and channel. For example, the transmission processing module (40) can transmit and process the final scenario data selected by the scenario selection module (30) by at least one of battery, email, SMS, MMS, notification talk, channel talk, talk provided by a portal site, and app push. At this time, the transmission processing module (4) can transmit a personalized message (e.g., scenario data) in real time or at a preset time. The transmission processing module (40) can check the channel health of the site by collecting indicators of the transmission itself, such as transmission success or exposure success.

[0058] In one embodiment, the performance measurement module (50) can measure the performance of a campaign. For example, the performance measurement module (50) can collect different feedback data according to the characteristics of each channel. In this case, the performance measurement module (50) can collect direct response data from the recipient customer based on the user's open or click behavior. In addition, the performance measurement module (50) can link the on-site behavior data after the recipient customer's response. In addition, the performance measurement module (50) can configure a feedback loop to reflect the performance measurement results back into the customer's profiling. Accordingly, the aforementioned profiling processing module (10) can regenerate the customer's profiling based on the performance measurement results fed back from the performance measurement module (50).

[0059] FIG. 4 is a flowchart illustrating a method for automatically generating optimal messages for each customer in a multiple campaign environment according to one embodiment of the present invention.

[0060] Referring to FIG. 4, according to one embodiment, a system for automatically generating optimal messages for each customer in a multiple campaign environment may first collect behavioral data and metadata of the customer company on a browser (S410). Then, the system for automatically generating optimal messages for each customer in the multiple campaign environment may perform a step of generating profiling based on the collected behavioral data and metadata (S420).

[0061] Next, the system for automatically generating optimal messages for each customer in the above multiple campaign environment can generate multiple scenario data based on the result data of the above generated profiling. (S430)

[0062] Next, the system for automatically generating optimal messages for each customer in the above multiple campaign environment can select individual final data from among the multiple scenario data. (S440)

[0063] Next, the system for automatically generating optimal messages for each customer in the above multiple campaign environment can deliver the selected final data to each individual and channel (S450).

[0064] Finally, the system for automatically generating optimal messages for each customer in the aforementioned multi-campaign environment can measure campaign performance based on feedback data tailored to channel characteristics (S460). Furthermore, a feedback loop can be configured to reflect the campaign performance measurement results back into customer profiling. Accordingly, the performance measurement results from step S460 can be fed back to regenerate profiling in step S420.

[0065] FIG. 5 is a block diagram illustrating a system for automatically generating optimal messages for each customer in a multiple campaign environment according to one embodiment of the present invention.

[0066] Referring to FIG. 5, a system for automatically generating optimal messages for each customer in a multiple campaign environment according to one embodiment may include a communication unit (110), a display (120), a memory (130), a user input unit (140), and a processor (150).

[0067] According to one embodiment, the communication unit (110) may receive browser-based behavioral data and customer metadata input to the profiling processing module (10) from an external server. The browser-based behavioral data and customer metadata collected through the communication unit (110) may be provided to the processor (150). The memory (130) may store the browser-based behavioral data and customer metadata collected through the communication unit (110).

[0068] According to one embodiment, the processor (150) may process functions performed in the profiling processing module (10) illustrated in FIG. 1 based on data collected through the communication unit (110). For example, the processor (150) may perform functions of each module illustrated in FIG. 1 (e.g., profiling processing module (10), scenario processing module (20), scenario selection module (30), dispatch processing module (40), and performance measurement module (50)).

[0069] According to one embodiment, the processor (150) can transmit selected final data (e.g., scenario data) to each individual and channel through the communication unit (110).

[0070] In one embodiment, the user input unit (140) may receive a scenario triggering request (e.g., a batch data generation request and / or a real-time request) from a user. The display (120) may display data input or generated during the scenario data generation process on the screen. In addition, the display (120) may display performance measurement results measured by the performance measurement module (50) on the screen after the personalized scenario message is delivered.

[0071] The devices described above may be implemented as hardware components, software components, and / or a combination of hardware components and software components. For example, the devices and components described in the embodiments may be implemented using one or more general-purpose computers or special-purpose computers, such as, for example, a processor, a controller, an arithmetic logic unit (ALU), a digital signal processor, a microcomputer, a field programmable array (FPA), a programmable logic unit (PLU), a microprocessor, or any other device capable of executing instructions and responding to them. The processing device may execute an operating system (OS) and one or more software applications running on the operating system. The processing device may also access, store, manipulate, process, and generate data in response to the execution of the software. For ease of understanding, the processing device is sometimes described as being used alone; however, one of ordinary skill in the art will recognize that the processing device may include multiple processing elements and / or multiple types of processing elements. For example, a processing unit may include multiple processors, or a processor and a controller. Other processing configurations, such as parallel processors, are also possible.

[0072] Software may include a computer program, code, instructions, or a combination of one or more of these, which may configure a processing device to perform a desired operation or may, independently or collectively, command the processing device. The software and / or data may be permanently or temporarily embodied in any type of machine, component, physical device, virtual equipment, computer storage medium or device, or transmitted signal wave, for interpretation by the processing device or for providing instructions or data to the processing device. The software may also be distributed over networked computer systems and stored or executed in a distributed manner. The software and data may be stored on one or more computer-readable recording media.

[0073] The method according to the embodiment may be implemented in the form of program commands that can be executed through various computer means and recorded on a computer-readable medium. The computer-readable medium may include program commands, data files, data structures, etc., alone or in combination. The program commands recorded on the medium may be those specially designed and configured for the embodiment or may be those known and available to those skilled in the art of computer software. Examples of the computer-readable recording medium include magnetic media such as hard disks, floppy disks, and magnetic tapes, optical media such as CD-ROMs and DVDs, magneto-optical media such as floptical disks, and hardware devices specially configured to store and execute program commands, such as ROMs, RAMs, and flash memories. Examples of the program commands include not only machine language codes generated by a compiler, but also high-level language codes that can be executed by a computer using an interpreter, etc. The hardware devices described above may be configured to operate as one or more software modules to perform the operations of the embodiment, and vice versa.

[0074] Although the embodiments described above have been described by way of limited examples and drawings, those skilled in the art will appreciate that various modifications and variations can be made based on the above teachings. For example, appropriate results can still be achieved even if the described techniques are performed in a different order than described, and / or components of the described systems, structures, devices, circuits, etc. are combined or combined in a different manner than described, or are replaced or substituted with other components or equivalents.

[0075] Therefore, other implementations, other embodiments, and equivalents to the claims also fall within the scope of the claims described below.

Claims

1. In a system for automatically generating optimal messages for each customer in a multiple campaign environment, A profiling processing module that generates profiling based on behavioral data on the browser and metadata of the customer; A scenario processing module that generates multiple scenario data based on the result data of the above-mentioned generated profiling; A scenario selection module for selecting individual final data from among the above multiple scenario data; and A system for automatically generating optimal messages for each customer in a multi-campaign environment, comprising a sending processing module that delivers the selected final data to each individual and channel.

2. In paragraph 1, the behavioral data on the browser is: A system for automatically generating optimal messages for each customer in a multi-campaign environment, including at least one of a page URL (uniform resource locator), number of item exposures, shopping cart information, purchase information, and scroll information.

3. In paragraph 1, the customer metadata is: A system for automatically generating optimal messages for each customer in a multi-campaign environment, including at least one of purchase history, member information, and promotional information.

4. In paragraph 1, the profiling, A system for automatically generating optimal messages for each customer in a multi-campaign environment, including at least one of interest in a specific item, interest in a specific category, purchase probability, and return probability.

5. In paragraph 1, the scenario processing module, A system for automatically generating optimal messages for each customer in a multiple campaign environment, comprising a triggering unit that triggers batch data generation and real-time request processing for scenario data simultaneously.

6. In paragraph 1, the scenario processing module, A system for automatically generating optimal messages for each customer in a multiple campaign environment, including a scenario matching unit that selects target scenarios based on the customer's campaign execution status and personal profiling and performance data.

7. In paragraph 1, the scenario processing module, A system for automatically generating optimal messages for each customer in a multiple campaign environment, comprising a scenario generation unit that generates multiple scenario data for each individual.

8. In paragraph 1, the scenario processing module, A system for automatically generating optimal messages for each customer in a multiple campaign environment, comprising: an additional information processing unit for additionally generating additional information that is essential to be included in a campaign; 9. In paragraph 1, the scenario selection module, A priority evaluation unit that sorts scenario data based on priority information established based on the client's past campaign performance; Channel filtering unit that removes unnecessary data based on channel status by customer; and A system for automatically generating optimal messages for each customer in a multiple campaign environment, comprising a content selection unit for selecting one scenario data from the above filtered multiple scenario data.

10. In paragraph 1, the system, A system for automatically generating optimal messages for each customer in a multi-campaign environment, further including a performance measurement module that measures the performance of a campaign by collecting different feedback data according to the characteristics of each channel.

11. In a method for automatically generating optimal messages for each customer in a multiple campaign environment, A step of generating profiling based on behavioral data on the browser and metadata of the customer; A step of generating multiple scenario data based on the result data of the above-mentioned generated profiling; A step of selecting individual final data from the above multiple scenario data; and A method for automatically generating optimal messages for each customer in a multi-campaign environment, comprising the step of delivering the selected final data to each individual and channel.

12. In paragraph 11, the behavioral data on the browser is: A method for automatically generating optimal messages for each customer in a multiple campaign environment, the method including at least one of a page URL (uniform resource locator), number of item exposures, shopping cart information, purchase information, and scroll information.

13. In clause 11, the customer metadata is: A method for automatically generating customer-specific optimal messages in a multi-campaign environment, wherein the optimized messages include at least one of purchase history, member information, and promotional information.

14. In paragraph 11, the profiling is: A method for automatically generating optimal messages for customers in a multi-campaign environment, comprising at least one of interest in a specific item, interest in a specific category, probability of purchase, and probability of return visit.

15. In paragraph 11, the step of generating the scenario data comprises: A method for automatically generating customer-specific optimal messages in a multi-campaign environment, comprising: a step of triggering batch data generation and real-time request processing for scenario data simultaneously;

Images