WO2019165868A1

WO2019165868A1 - Marketing plan determining method and device, and electronic apparatus

Info

Publication number: WO2019165868A1
Application number: PCT/CN2019/073558
Authority: WO
Inventors: 周志超; 熊军; 周峰; 蒋建; 黄国进; 郑岩; 冯健
Original assignee: 阿里巴巴集团控股有限公司
Priority date: 2018-02-28
Filing date: 2019-01-29
Publication date: 2019-09-06
Also published as: CN108510311A; CN108510311B; TW201937429A

Abstract

A marketing plan determining method and device, and an electronic apparatus. The method comprises: allocating, according to an A/B test traffic splitting policy, a preset amount of test traffic to a first marketing plan and a second marketing plan (101); determining, according to a tag of a target user corresponding to target traffic and a preset correspondence, content of a marketing plan to be recommended to the target user (102), wherein the target traffic is the test traffic of the matching first marketing plan or second marketing plan, and the preset correspondence is a correspondence between a tag and a marketing plan; and determining, regarding a conversion rate of the recommended content on the basis of the user corresponding to the test traffic allocated to the first marketing plan and the second marketing plan, a target marketing plan in the first marketing plan and the second marketing plan.

Description

Method, device and electronic device for determining marketing plan

Cross-reference to related applications

The present application claims priority to Chinese Patent Application No. 20110116714, filed on Feb. 28, 2018, the entire disclosure of which is incorporated herein by reference. The way is incorporated in this article.

Technical field

The present application relates to the field of computer technology, and in particular, to a method, an apparatus, and an electronic device for determining a marketing plan.

Background technique

With the development of the Internet and terminal technologies, e-commerce technology has also developed rapidly. In order to attract more users, or to encourage users to make more consumption, e-commerce platforms or online merchants often develop different resource marketing programs (hereinafter referred to as marketing programs), for example, different promotions for a certain festival. Moreover, in order to more effectively motivate users to consume, the e-commerce platform or the online merchant needs to select a more effective marketing plan and recommend the content of the selected marketing plan to the user.

In the prior art, the relative effectiveness of the two schemes is often determined by the AB test (ABtest). However, most of the existing AB tests are style-oriented or algorithm-oriented, for example, for the validity of new and old styles of web pages. The lack of an AB testing solution for resource marketing scenarios, therefore, it is necessary to propose a method to determine the marketing plan to help resource operators to determine a more effective marketing plan.

Summary of the invention

The embodiment of the present application provides a method, an apparatus, and an electronic device for determining a marketing plan to solve the problem of the prior art lacking an AB testing solution for a resource marketing scenario.

To solve the above technical problem, the embodiment of the present application is implemented as follows:

In the first aspect, a method of determining a marketing plan is proposed, including:

According to the AB test diversion strategy, a preset amount of test traffic is allocated to the first marketing plan and the second marketing plan;

Determining, according to the target user's tag and the preset correspondence corresponding to the target traffic, the content of the marketing plan that needs to be recommended to the target user; wherein the target traffic is a test traffic that hits the first marketing plan or the second marketing plan, The preset correspondence relationship is a correspondence between a label and a marketing plan;

The target marketing plan is determined in the first marketing plan and the second marketing plan based on the conversion rate of the recommended content based on the user corresponding to the test traffic assigned to the first marketing plan and the second marketing plan.

In a second aspect, an apparatus for determining a marketing plan is proposed, comprising:

The splitting unit allocates a preset amount of test traffic to the first marketing plan and the second marketing plan according to the AB test shunting strategy;

The recommended content determining unit determines the content of the marketing plan that needs to be recommended to the target user according to the label and the preset correspondence relationship of the target user corresponding to the target traffic; wherein the target traffic is hitting the first marketing plan or the second marketing The test flow of the solution, the preset correspondence relationship is a correspondence between the label and the marketing plan;

The decision unit determines the target marketing plan in the first marketing plan and the second marketing plan based on the conversion rate of the recommended content based on the user corresponding to the test traffic assigned to the first marketing plan and the second marketing plan.

In a third aspect, an electronic device is proposed, comprising:

Processor;

A memory arranged to store computer executable instructions that, when executed, cause the processor to perform the following operations:

In a fourth aspect, a computer readable storage medium is presented, the computer readable storage medium storing one or more programs that, when executed by an electronic device comprising a plurality of applications, cause The electronic device performs the following operations:

The foregoing technical solutions adopt the above technical solutions to achieve at least the following technical effects:

It can be seen from the technical solutions provided by the foregoing embodiments of the present application that the solution of the embodiment of the present application has at least one of the following technical effects:

Determining a predetermined number of test traffic to the first marketing plan and the second marketing plan according to the AB test shunting policy; determining, according to the target user's tag and the preset correspondence corresponding to the offloaded target traffic, that the recommended recommendation is Content of the marketing plan of the target user; and determining the target in the first marketing plan and the second marketing plan based on the user corresponding to the test traffic assigned to the first marketing plan and the second marketing plan, the conversion rate of the recommended content Marketing plan. Therefore, the problem of the AB testing scheme lacking the resource-oriented marketing scenario in the prior art can be solved, and the effect of quickly and effectively helping the resource operator to determine a more effective marketing scheme can be achieved.

DRAWINGS

The drawings described herein are intended to provide a further understanding of the present application, and are intended to be a part of this application. In the drawing:

FIG. 1 is a schematic diagram of an implementation process of a method for determining a marketing plan provided by an embodiment of the present specification.

FIG. 2 is a schematic flowchart showing a detailed implementation process of step 102 in the method provided in the embodiment shown in FIG.

FIG. 3 is a schematic structural diagram of a system for determining a marketing plan according to an embodiment of the present specification.

FIG. 4 is a schematic structural diagram of an electronic device according to an embodiment of the present specification.

FIG. 5 is a schematic structural diagram of an apparatus for determining a marketing plan according to an embodiment of the present specification.

FIG. 6 is a detailed structural diagram of a unit 502 in the apparatus provided in the embodiment shown in FIG. 5 of the present specification.

Detailed ways

The technical solutions of the present application will be clearly and completely described in the following with reference to the specific embodiments of the present application and the accompanying drawings. It is apparent that the described embodiments are only a part of the embodiments of the present application, and not all of them. All other embodiments obtained by a person of ordinary skill in the art based on the embodiments of the present application without departing from the inventive scope are the scope of the present application.

In order to solve the problem of the lack of an AB testing scheme for a resource-oriented marketing scenario in the prior art, the embodiments of the present specification provide a method for determining a marketing scheme. The execution subject of the method for determining a marketing plan provided by the embodiments of the present specification includes, but is not limited to, at least one of a server, a personal computer, and the like that can be configured to execute the method provided by the embodiment of the present invention.

For convenience of description, an embodiment of the method will be described below by taking an example of the execution of the method as a server capable of executing the method. It can be understood that the execution subject of the method is only an exemplary description of the server, and should not be construed as limiting the method.

1 is a flow chart of a method of determining a marketing plan provided by an embodiment of the present specification. As shown in FIG. 1, the method may include the following steps:

Step 101: Assign a preset amount of test traffic to the first marketing plan and the second marketing plan according to the AB test offloading strategy.

The first marketing plan and the second marketing plan in step 101 can be understood as two plans to be compared in the AB test, which can be referred to as marketing plan A and marketing plan B, respectively, for convenience of understanding.

As stated in the background of the specification, the marketing plan is an abbreviation of the resource marketing plan. The resource marketing plan can include specific content related to resource marketing. Such content may include, for example, but is not limited to, red envelopes, coupons, stores, articles, news, products, merchandise, and the like.

For example, the marketing plan can be a marketing campaign planned by an e-commerce platform or an online merchant's operator, for example, the Watsons Spring Festival in Hong Kong. More specifically, the above marketing plan A can be a Hong Kong Watsons Spring Festival promotion event 1: shopping for 100 yuan discount 10 yuan coupon, the above marketing plan B can be Hong Kong Watsons Spring Festival promotion activities 2: shopping over 200 yuan discount 20 Yuan coupon. And through this program, you can compare the effects of these two big promotion activities, so that the benefits of Hong Kong Watsons in the Spring Festival promotion will be maximized.

It should be noted that, in the embodiment provided in this specification, the first marketing plan and the second marketing plan in step 101 are intended to illustrate different marketing plans that need to be compared, and are not limited to the number of marketing plans to be compared. It is to be understood that, in practical applications, the solution to be compared may be two or more than two, and the embodiments provided in the present specification do not limit this.

In this embodiment, the AB test offloading strategy includes, but is not limited to, splitting by random ratio, splitting by user client, splitting by region, and splitting by member non-members, and the like.

The AB test generally refers to the development of two schemes (A scheme and B scheme) for the same target, so that some users (flow) use the A scheme, and another user uses the B scheme to record the usage of the scheme by the two users. And compare the results of the use to see which program is more in line with the design goals. For example, two or more versions of the Web or App (Application) interface, in the same time dimension, respectively, two or more attributes or the same (similar) group of visitors to visit, collect each group The group's user experience data and business data, and finally analyzed and evaluated the best version officially adopted.

It should be noted that the AB test generally refers to the test of group users in the same time dimension for similar attributes (usually distinguished by the label of the user group), and the uniformity of time can effectively avoid the factors caused by time, season and the like. Impact, and the similarity of attributes minimizes the impact of other factors such as geography, gender, age, etc. on performance statistics.

Step 102: Determine, according to the label of the target user corresponding to the target traffic and the preset correspondence, the content of the marketing plan that needs to be recommended to the target user.

The user's label is the identifier of the user group to which the user belongs. For example, the user's tag can be male, female, high-income, low-income, and the like.

The target traffic may be the test traffic assigned in step 101 that hits the first marketing plan or the second marketing plan. Correspondingly, the target user corresponding to the target traffic may be the user who generates the target traffic.

The preset correspondence may be a correspondence between the label and the marketing plan. In a more specific embodiment, the preset correspondence may be saved in the inverted list to quickly and efficiently determine a marketing plan that matches the target user's tag. On the basis of this, the method for determining a marketing plan provided by the embodiment of the present specification may further include: constructing the inverted list according to a label of a user group to which the marketing plan is directed.

Inverted table, also known as inverted index table. Reverse indexing stems from the fact that in real applications it is necessary to look up records based on the value of the attribute (eg, a tag) (eg, a marketing plan). Each entry in this index table includes an attribute value and the address of each record having the attribute value. Since the attribute value is not determined by the record, but the position of the record is determined by the attribute value, it is called an inverted index. Correspondingly, if the index of the attribute value is determined by the record, it can be called a forward index table, or a positive list.

In the present specification, an inverted list as shown in Table 1 can be established in advance, and in Table 1, key indicates a label, and Value indicates a marketing plan.

Table 1

Key(标签)Key	value(活动)Value
标签1Label 1	营销方案A、营销方案C、营销方案DMarketing Plan A, Marketing Plan C, Marketing Plan D
标签2Label 2	营销方案B、营销方案C、营销方案DMarketing Plan B, Marketing Plan C, Marketing Plan D
标签3Label 3	营销方案A、营销方案B、营销方案CMarketing Plan A, Marketing Plan B, Marketing Plan C
标签4Label 4	营销方案A、营销方案B、营销方案DMarketing Plan A, Marketing Plan B, Marketing Plan D
〃〃〃〃〃〃	〃〃〃〃〃〃

It can be understood that since different traffic represents different users, and different users may belong to different user groups, different users may have different labels, and thus the marketing scheme may be described by corresponding or non-combination of labels. The traffic can represent the perspective of the user, and the marketing solution can represent the operational perspective of the e-commerce platform or the operator of the online merchant, and the two are aligned by the inverted table.

In a specific implementation, the step 102 may include: determining, according to the target user's label and the preset correspondence corresponding to the target traffic, a marketing plan that matches the target user's label, and determining the The content of the target user's tag-matched marketing plan is determined as the content of the marketing plan that needs to be recommended to the target user.

For example, if the target traffic is assumed to be the test traffic assigned to the first marketing plan (marketing plan A), and the target user's tag corresponding to the target traffic is the tag 1 in Table 1, the matching table 1 can be determined to match the tag 1 The marketing plan includes marketing plan A, marketing plan C and marketing plan D. Correspondingly, the contents of the marketing plan A, the marketing plan C, and the marketing plan D can be determined as the content of the marketing plan that needs to be recommended to the target user.

Similarly, if the target traffic is assumed to be the test traffic assigned to the second marketing plan (marketing plan B), and the target user's tag corresponding to the target traffic is the tag 2 in Table 1, the tag 2 can be determined by the search table 1 The matching marketing plan includes marketing plan B, marketing plan C and marketing plan D. Correspondingly, the content of the marketing plan B, the marketing plan C, and the marketing plan D can be determined as the content of the marketing plan that needs to be recommended to the target user.

In another specific implementation, as shown in FIG. 2, the foregoing step 102 may specifically include the following sub-steps:

Sub-step 201: Determine, according to the target user's tag and the preset correspondence corresponding to the target traffic, a candidate marketing plan set that matches the target user's tag.

For example, if the target traffic is assumed to be the test traffic assigned to the first marketing plan (Marketing Plan A), and the target user's tag corresponding to the target traffic is the tag 3 in Table 1, the matching table 1 can be determined to match the tag 3. The candidate marketing plan set includes: marketing plan A, marketing plan B, and marketing plan C.

Similarly, if the target traffic is assumed to be the test traffic assigned to the second marketing plan (marketing plan B), and the target user's tag corresponding to the target traffic is the tag 4 in Table 1, the tag 1 can be determined by the search table 1 The matched candidate marketing plan set includes: three elements: marketing plan A, marketing plan B, and marketing plan D.

In the embodiment of the present description, it is necessary to determine which of the marketing plan A and the marketing plan B is superior and more effective. However, after comparing the above identified candidate marketing plan sets that match Tag 3 and Tag 4, it is not difficult to find that both contain the marketing plan A and the marketing plan B to be compared, at this time, if the tag 3 and the tag are to be 4 The content of the marketing plan in the matching candidate marketing plan set is directly recommended to the corresponding target user, which will make the final comparison effect less accurate.

Therefore, in the other specific implementation manner, the marketing plan in the determined candidate marketing plan set may also be filtered, so that when the target traffic is the test traffic allocated to the marketing plan A, the recommended target traffic is corresponding. The user's content does not include the content of the marketing plan B; when the target traffic is the test traffic assigned to the marketing plan B, the content recommended to the user corresponding to the target traffic does not include the content of the marketing plan A, and the specific filtering method is as follows: 202.

Sub-step 202: Removing the same marketing plan as the specified marketing plan in the candidate marketing plan set, and obtaining a target marketing plan set.

Wherein, when the target traffic is a test traffic that hits the first marketing plan (marketing plan A), the specified marketing plan is the second marketing plan (marketing plan B), and the target traffic is hit second. When the marketing plan (marketing plan B) tests the traffic, the specified marketing plan is the first marketing plan (marketing plan A).

According to the example in the sub-step 201, if the target traffic is assumed to be the test traffic allocated to the first marketing plan (marketing plan A), the candidate marketing plan set includes: marketing plan A, marketing plan B, and marketing plan C. element. Then the filtered target marketing plan set includes: marketing plan A and marketing plan C two elements.

Similarly, if the target traffic is assumed to be the test traffic assigned to the second marketing plan (marketing plan B), the candidate marketing plan set includes three elements: marketing plan A, marketing plan B, and marketing plan D. Then the filtered target marketing plan set includes two elements: marketing plan B and marketing plan D.

Sub-step 203: determining content of the marketing plan in the target marketing plan set as content that needs to be recommended to the target user.

According to the analysis in the foregoing sub-step 201, after performing the sub-step 202, when the target traffic is the test traffic allocated to the marketing plan A, the content recommended to the user corresponding to the target traffic does not include the content of the marketing plan B; When the target traffic is the test traffic allocated to the marketing plan B, the content of the user recommended to the target traffic does not include the content of the marketing plan A, which may make the target marketing plan determined by the determined marketing plan provided by the present specification more effective, More in line with the operator's goals.

Step 103: Determine a target marketing plan in the first marketing plan and the second marketing plan based on the conversion rate of the recommended content based on the user corresponding to the test traffic allocated to the first marketing plan and the second marketing plan.

In this step 103, the behaviors of the users corresponding to each test content, such as clicking, receiving, writing off, and the like, may be collected and recorded by the user corresponding to each test flow, and two of the first marketing plan and the second marketing plan are obtained. The conversion rate of the content corresponding to the traffic collection is tested, and then one of the higher conversion rates of the content in the first marketing plan and the second marketing plan is determined as the target marketing plan. The target marketing plan can be understood as a marketing plan that is better, more effective, and more in line with the operator's design goals in the first marketing plan and the second marketing plan.

That is, the above step 103 may specifically include: determining a conversion rate of the recommended content for the user corresponding to the test traffic allocated to the first marketing plan and the second marketing plan; and using the first marketing plan and the second marketing plan The content conversion rate of the higher marketing program is determined as the target marketing program.

For example, suppose that in step 101, 100 test flows are allocated to the first marketing plan and the second marketing plan, and the first marketing plan and the second marketing plan respectively obtain 50 test flows, which can be recommended by comparison The conversion rate of the content of the 50 test traffic corresponding to the first marketing plan, and the conversion rate of the content of the 50 test traffic sets corresponding to the second marketing plan, which one of the first marketing plan and the second marketing plan is obtained Excellent and more effective.

Optionally, after the step 102, before the step 103, the method for determining a marketing plan provided by the embodiment may further include: recommending, to the target user, the content that needs to be recommended determined in step 102. Following the example in step 102, if the target traffic is assumed to be the test traffic assigned to the first marketing plan (marketing plan A), and the filtered target marketing plan set includes: two elements: marketing plan A and marketing plan C. , the content of marketing plan A and marketing plan C can be recommended to the target user.

It can be understood that in step 102, it may be determined that there may be multiple marketing schemes that need to be recommended to the target user, and each marketing scheme may include multiple content, and the content of the marketing plan that needs to be recommended to the target user, with the target user's The tags correspond, so the content recommended for different users may be different. Since the user corresponds to the traffic and operates the corresponding marketing plan, in the method for determining the marketing plan provided by the embodiment of the present specification, although the traffic is diverted, the test is compared with the marketing solution, which is well solved. There is a lack of technology in the AB test program for marketing scenarios.

A method for determining a marketing plan provided by an embodiment of the present specification, by assigning a preset quantity of test traffic to a first marketing plan and a second marketing plan according to the AB test diversion policy; and the target user corresponding to the target traffic after the diversion a label and a preset correspondence, determining content of a marketing plan that needs to be recommended to the target user; and converting the recommended content based on the user corresponding to the test traffic assigned to the first marketing plan and the second marketing plan The target marketing plan is determined in the first marketing plan and the second marketing plan. Therefore, the problem of the AB testing scheme lacking the resource-oriented marketing scenario in the prior art can be solved, and the effect of quickly and effectively helping the resource operator to determine a more effective marketing scheme can be achieved.

Optionally, in another embodiment of the present disclosure, the foregoing recommending the determined content that needs to be recommended to the target user may include: predicting a determined conversion rate of the content that needs to be recommended to the target user. And recommending the predicted content whose conversion rate meets the preset condition to the target user.

In this embodiment, the existing prediction model may be used to predict the ranking of the conversion rate of each content that needs to be recommended to the target user, and then the content with the highest conversion rate, or the content that will be sorted (descending) in the first few names. Recommended for the target user.

That is to say, the above preset condition may be that the predicted conversion rate is the largest, or the predicted conversion rate is ranked greater than the preset ranking, and the like.

It can be understood that recommending the content with the predicted conversion rate that meets the preset condition to the target user can make the content recommended to the user more consistent with the user's interest, thereby being more easily converted by the user, so that the determined conversion rate is more reliable.

Optionally, in a further embodiment of the present specification, the method for determining a marketing plan provided by the embodiment of the present disclosure may further include:

a non-target marketing plan in the first marketing plan and the second marketing plan;

Monitoring non-test traffic; wherein, the non-test traffic can be the monitored user access traffic after the AB test is completed and the target marketing plan is formally adopted;

Determining, according to the label of the user corresponding to the non-test traffic and the preset correspondence, the content of the third marketing plan that needs to be recommended to the user corresponding to the non-test traffic; wherein the third marketing scheme does not include Non-target marketing plan;

The content of the third marketing plan is recommended to the user corresponding to the non-test traffic.

In this embodiment, after the target marketing plan with better effect is determined, the non-target marketing plan with relatively poor effect is offline, and the target marketing plan with better effect is retained. After the offline non-target marketing plan, you can continue to monitor non-test traffic (because the test process is over, so the non-test traffic is monitored), and determine the need to recommend according to the user's label and inverted table corresponding to the monitored traffic. For the content of the third marketing plan for different users, it should be noted that since the non-target marketing plan has been offline, the non-target marketing plan is not included in the third marketing plan.

In this embodiment, since the target marketing campaign decided based on the embodiment shown in FIG. 1 can continue to recommend content to the non-test traffic, and the recommended content does not include the content of the non-target marketing scheme, the operator can be expected. Maximize revenue.

FIG. 3 is a schematic structural diagram of a system for determining a marketing plan provided by an embodiment of the present specification. As shown in FIG. 3, the system 300 may include: a distribution configuration module 311, a label determination module 312, a content management module 313 of a marketing plan, a first storage module 321, a second storage module 322, a third storage module 323, and a recommendation. System 330, fourth storage module 411, and effect comparison module 412.

The recommendation system 330 specifically includes: a traffic distribution module 331, a marketing solution retrieval module 332, and a marketing solution filtering module 333.

In the system 300, the operator sets the AB test offload policy through the offload configuration module 311 and saves it in the first storage module 321; the operator sets the label of the user group to which the various marketing activities are designed by the tag determination module 312. And saved in the second storage module 322; the operator sets the content of the marketing plan through the content management module 313 of the marketing plan, and saves it in the third storage module 323. Then, the AB test offloading policy saved in the first storage module 321 is imported into the traffic distribution module 321, and the contents stored in the second storage module 322 and the third storage module 323 are imported into the inverted list.

In the recommendation system 330 of the system 300, after the test traffic is monitored, the traffic distribution module 331 determines the destination of the test traffic according to the previously introduced AB test offload policy: assigned to the marketing plan A or the marketing plan B. The marketing plan retrieval module 332 retrieves a marketing plan that matches the user's tag according to the user's tag and the inverted list corresponding to the test flow. The marketing plan filtering module 333 filters or deletes the specified marketing plan in the marketing plan that matches the user's tag, wherein when the test flow is assigned to the marketing plan A, the designated marketing plan is the marketing plan B, when the test When the traffic is assigned to Marketing Plan B, the designated marketing plan is Marketing Plan A. More specifically, the marketing plan A filtering sub-module 3331 in the marketing solution filtering module 333 is configured to filter the specified marketing plan corresponding to the marketing plan A; the marketing plan B filtering sub-module 3332 in the marketing plan filtering module 333 is configured to filter Marketing Plan B corresponds to the designated marketing plan.

The recommendation system 330 recommends the content of the marketing plan filtered by the marketing plan filtering module 333 to the corresponding user, and introduces the feedback behavior of the user to the recommended content into the fourth storage module 411. The effect comparison module 412 compares the marketing plan A and the marketing plan B according to the feedback behavior of the user stored in the fourth storage module 411, thereby helping the operator to make a decision.

FIG. 4 is a schematic structural diagram of an electronic device according to an embodiment of the present specification. Referring to FIG. 4, at the hardware level, the electronic device includes a processor, optionally including an internal bus, a network interface, and a memory. The memory may include a memory, such as a high-speed random access memory (RAM), and may also include a non-volatile memory, such as at least one disk memory. Of course, the electronic device may also include hardware required for other services.

The processor, the network interface, and the memory may be interconnected by an internal bus, which may be an ISA (Industry Standard Architecture) bus, a PCI (Peripheral Component Interconnect) bus, or an EISA (Extended) Industry Standard Architecture, extending the industry standard structure) bus. The bus can be divided into an address bus, a data bus, a control bus, and the like. For ease of representation, only one double-headed arrow is shown in Figure 4, but it does not mean that there is only one bus or one type of bus.

Memory for storing programs. In particular, the program can include program code, the program code including computer operating instructions. The memory can include both memory and non-volatile memory and provides instructions and data to the processor.

The processor reads the corresponding computer program from the non-volatile memory into memory and then runs, forming a device at a logical level that determines the marketing plan. The processor executes the program stored in the memory and is specifically used to perform the following operations:

The method for determining a marketing plan disclosed in the embodiment shown in FIG. 1 of the present specification may be applied to a processor or implemented by a processor. The processor may be an integrated circuit chip with signal processing capabilities. In the implementation process, each step of the above method may be completed by an integrated logic circuit of hardware in a processor or an instruction in a form of software. The above processor may be a general-purpose processor, including a central processing unit (CPU), a network processor (NP), etc.; or may be a digital signal processor (DSP), dedicated integration. Application Specific Integrated Circuit (ASIC), Field-Programmable Gate Array (FPGA) or other programmable logic device, discrete gate or transistor logic device, discrete hardware component. The methods, steps, and logic blocks disclosed in one or more embodiments of the specification can be implemented or executed. The general purpose processor may be a microprocessor or the processor or any conventional processor or the like. The steps of a method disclosed in connection with one or more embodiments of the present specification can be directly embodied as a hardware decoding processor or a combination of hardware and software modules in a decoding processor. The software module can be located in a conventional storage medium such as random access memory, flash memory, read only memory, programmable read only memory or electrically erasable programmable memory, registers, and the like. The storage medium is located in the memory, and the processor reads the information in the memory and combines the hardware to complete the steps of the above method.

The electronic device can also perform the method for determining a marketing plan of FIG. 1, and the description is not repeated herein.

Of course, in addition to the software implementation, the electronic device of the present specification does not exclude other implementation manners, such as a logic device or a combination of software and hardware, etc., that is, the execution body of the following processing flow is not limited to each logical unit. It can also be hardware or logic.

The embodiment of the present application further provides a computer readable storage medium storing one or more programs, the one or more programs including instructions, when the portable electronic device is included in a plurality of applications When executed, the portable electronic device can be configured to perform the method of the embodiment shown in FIG. 1 and specifically for performing the following operations:

FIG. 5 is a schematic structural diagram of an apparatus 500 for determining a marketing plan provided by the present specification. Referring to FIG. 5, in a software implementation, the apparatus 500 for determining a marketing plan may include: a distribution unit 501, a recommendation content determination unit 502, and a decision unit 503, wherein:

The splitting unit 501 can be configured to allocate a preset amount of test traffic to the first marketing plan and the second marketing plan according to the AB test offloading policy.

The recommended content determining unit 502 is configured to determine, according to the target user's label and the preset correspondence corresponding to the target traffic, the content of the marketing plan that needs to be recommended to the target user; wherein the target traffic is hitting the first marketing plan or The test traffic of the second marketing plan, the preset correspondence relationship is a correspondence between the tag and the marketing plan.

In an embodiment, the recommended content determining unit 502 is specifically configured to:

Determining, according to the target user's tag and the preset correspondence corresponding to the target traffic, a marketing plan that matches the target user's tag;

The determined content of the marketing plan that matches the target user's tag is determined as the content of the marketing plan that needs to be recommended to the target user.

In another embodiment, as shown in FIG. 6, the recommended content determining unit 502 may include: a retrieving subunit 601, a filtering subunit 602, and a determining subunit 603, where:

The search sub-unit 601 is configured to determine, according to the target user's tag and the preset correspondence corresponding to the target traffic, a candidate marketing plan set that matches the target user's tag.

The filtering sub-unit 602 is configured to remove the marketing plan of the candidate marketing plan set that is the same as the specified marketing plan, and obtain the target marketing plan set.

The determining subunit 603 is configured to determine content of the marketing plan in the target marketing plan set as content that needs to be recommended to the target user.

The determining unit 503 is configured to determine a target marketing plan in the first marketing plan and the second marketing plan based on the conversion rate of the recommended content based on the user corresponding to the test traffic allocated to the first marketing plan and the second marketing plan.

In an embodiment, the determining unit 503 is specifically configured to:

Determining a conversion rate of the recommended content for the user corresponding to the test traffic assigned to the first marketing plan and the second marketing plan;

The marketing plan with higher conversion rate of the content in the first marketing plan and the second marketing plan is determined as the target marketing plan.

Optionally, in an implementation manner, the apparatus 500 may further include a first recommendation unit, where the first recommendation unit is configured to:

After determining the content of the marketing plan that needs to be recommended to the target user, the conversion rate of the recommended content is based on the user corresponding to the test traffic assigned to the first marketing plan and the second marketing plan, in the first marketing plan Before determining the target marketing plan in the second marketing plan, the content recommended to be recommended in the recommended content determining unit 502 is recommended to the target user.

An apparatus for determining a marketing plan provided by an embodiment of the present specification, by assigning a preset quantity of test traffic to a first marketing plan and a second marketing plan according to an AB test diversion policy; and a target user corresponding to the target traffic after the diversion a label and a preset correspondence, determining content of a marketing plan that needs to be recommended to the target user; and converting the recommended content based on the user corresponding to the test traffic assigned to the first marketing plan and the second marketing plan The target marketing plan is determined in the first marketing plan and the second marketing plan. Therefore, the problem of the AB testing scheme lacking the resource-oriented marketing scenario in the prior art can be solved, and the effect of quickly and effectively helping the resource operator to determine a more effective marketing scheme can be achieved.

Optionally, in another embodiment of the present disclosure, the foregoing first recommending unit may be specifically configured to:

Predicting the conversion rate of the determined content recommended to the target user;

The predicted content whose conversion rate meets the preset condition is recommended to the target user.

It can be understood that recommending the content with the predicted conversion rate that meets the preset condition to the target user can make the content recommended to the user more consistent with the user's interest, thereby being more easily converted by the user, so that the determined content is transformed. The rate is more reliable.

Optionally, in still another embodiment of the present specification, on the basis of the embodiment shown in FIG. 5, the apparatus 500 may further include: a downlink unit, a monitoring unit, a determining unit, and a second recommending unit, where:

The offline unit can be used for the non-target marketing plan in the first marketing plan and the second marketing plan.

The monitoring unit can be used to monitor non-test traffic; wherein, the non-test traffic can be the monitored user access traffic after the AB test is completed and the target marketing plan is formally adopted.

The determining unit is configured to determine, according to the label of the user corresponding to the non-test traffic and the preset correspondence, the content of the third marketing plan that needs to be recommended to the user corresponding to the non-test traffic. Wherein, the third marketing plan does not include the non-target marketing plan.

The second recommendation unit is configured to recommend content of the third marketing plan to a user corresponding to the non-test traffic.

In this embodiment, since the target marketing campaign determined based on the embodiment shown in FIG. 5 can continue to recommend content to the non-test traffic, and the recommended content includes the content of the target marketing scheme but does not include the content of the non-target marketing scheme, This maximizes the expected revenue for the operator.

The device 500 for determining the marketing plan can implement the method of the method embodiment of FIG. 1 . For details, refer to the method for determining the marketing plan of the embodiment shown in FIG. 1 , and details are not described herein.

In conclusion, the above description is only the preferred embodiment of the present specification, and is not intended to limit the scope of the present specification. Any modifications, equivalent substitutions, improvements, etc. within the spirit and scope of the present invention are intended to be included within the scope of the present invention.

The system, device, module or unit illustrated in the above embodiments may be implemented by a computer chip or an entity, or by a product having a certain function. A typical implementation device is a computer. Specifically, the computer can be, for example, a personal computer, a laptop computer, a cellular phone, a camera phone, a smart phone, a personal digital assistant, a media player, a navigation device, an email device, a game console, a tablet computer, a wearable device, or A combination of any of these devices.

Computer readable media includes both permanent and non-persistent, removable and non-removable media. Information storage can be implemented by any method or technology. The information can be computer readable instructions, data structures, modules of programs, or other data. Examples of computer storage media include, but are not limited to, phase change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read only memory. (ROM), electrically erasable programmable read only memory (EEPROM), flash memory or other memory technology, compact disk read only memory (CD-ROM), digital versatile disk (DVD) or other optical storage, Magnetic tape cartridges, magnetic tape storage or other magnetic storage devices or any other non-transportable media can be used to store information that can be accessed by a computing device. As defined herein, computer readable media does not include temporary storage of computer readable media, such as modulated data signals and carrier waves.

It is also to be understood that the terms "comprises" or "comprising" or "comprising" or any other variations are intended to encompass a non-exclusive inclusion, such that a process, method, article, Other elements not explicitly listed, or elements that are inherent to such a process, method, commodity, or equipment. An element defined by the phrase "comprising a ...", without further limitation, does not exclude the presence of additional identical elements in the process, method, item, or device that comprises the element.

The various embodiments in the specification are described in a progressive manner, and the same or similar parts between the various embodiments may be referred to each other, and each embodiment focuses on the differences from the other embodiments. In particular, for the system embodiment, since it is basically similar to the method embodiment, the description is relatively simple, and the relevant parts can be referred to the description of the method embodiment.

Claims

A method of determining a marketing plan, including:

According to the AB test diversion strategy, a preset amount of test traffic is allocated to the first marketing plan and the second marketing plan;

Determining, according to the target user's tag and the preset correspondence corresponding to the target traffic, the content of the marketing plan that needs to be recommended to the target user; wherein the target traffic is a test traffic that hits the first marketing plan or the second marketing plan, The preset correspondence relationship is a correspondence between a label and a marketing plan;

The target marketing plan is determined in the first marketing plan and the second marketing plan based on the conversion rate of the recommended content based on the user corresponding to the test traffic assigned to the first marketing plan and the second marketing plan.
The method of claim 1, the determining, according to the target user's label and the preset correspondence corresponding to the target traffic, the content of the marketing plan that needs to be recommended to the target user, including:

Determining, according to the target user's tag and the preset correspondence corresponding to the target traffic, a candidate marketing plan set that matches the target user's tag;

Removing the marketing plan of the candidate marketing plan set that is the same as the specified marketing plan, and obtaining the target marketing plan set; wherein, when the target traffic is the test traffic that hits the first marketing plan, the designated marketing plan is the second marketing The solution, when the target traffic is a test traffic that hits the second marketing plan, the designated marketing plan is a first marketing plan;

The content of the marketing plan in the target marketing plan set is determined as the content that needs to be recommended to the target user.
The method of claim 1, after the determining the content of the marketing plan that needs to be recommended to the target user, before determining the target marketing plan in the first marketing plan and the second marketing plan, the method Also includes:

The determined content that needs to be recommended is recommended to the target user.
The method of claim 3, the recommending the determined content that needs to be recommended to the target user comprises:

Predicting the conversion rate of the determined content recommended to the target user;

The predicted content whose conversion rate meets the preset condition is recommended to the target user.
The method of claim 1, wherein the preset correspondence is saved in an inverted list,

Before determining the content of the marketing plan that needs to be recommended to the target user according to the label and the preset correspondence corresponding to the target user corresponding to the target traffic, the method further includes:

The inverted list is constructed according to the label of the user group to which the marketing plan is directed.
The method according to any one of claims 1 to 5, wherein the user corresponding to the test traffic assigned to the first marketing plan and the second marketing plan, the conversion rate of the recommended content, in the first marketing plan and Identify the target marketing plan in the second marketing plan, including:

Determining a conversion rate of the recommended content for the user corresponding to the test traffic assigned to the first marketing plan and the second marketing plan;

The marketing plan with higher conversion rate of the content in the first marketing plan and the second marketing plan is determined as the target marketing plan.
The method according to any one of claims 1-5, wherein the AB test offloading strategy comprises: splitting according to a random ratio, diverting according to a proportion of a user client, diverting by region, and shunting by a member non-member.
The method of any of claims 1-5, the solution further comprising:

a non-target marketing plan in the first marketing plan and the second marketing plan;

Monitor non-test traffic;

Determining, according to the label of the user corresponding to the non-test traffic and the preset correspondence, the content of the third marketing plan that needs to be recommended to the user corresponding to the non-test traffic; wherein the third marketing scheme does not include Non-target marketing plan;

The content of the third marketing plan is recommended to the user corresponding to the non-test traffic.
A device for determining a marketing plan, comprising:

The splitting unit allocates a preset amount of test traffic to the first marketing plan and the second marketing plan according to the AB test shunting strategy;

The recommended content determining unit determines the content of the marketing plan that needs to be recommended to the target user according to the label and the preset correspondence relationship of the target user corresponding to the target traffic; wherein the target traffic is hitting the first marketing plan or the second marketing The test flow of the solution, the preset correspondence relationship is a correspondence between the label and the marketing plan;

The decision unit determines the target marketing plan in the first marketing plan and the second marketing plan based on the conversion rate of the recommended content based on the user corresponding to the test traffic assigned to the first marketing plan and the second marketing plan.
An electronic device comprising:

Processor;

A memory arranged to store computer executable instructions that, when executed, cause the processor to perform the following operations:

According to the AB test diversion strategy, a preset amount of test traffic is allocated to the first marketing plan and the second marketing plan;

Determining, according to the target user's tag and the preset correspondence corresponding to the target traffic, the content of the marketing plan that needs to be recommended to the target user; wherein the target traffic is a test traffic that hits the first marketing plan or the second marketing plan, The preset correspondence relationship is a correspondence between a label and a marketing plan;

The target marketing plan is determined in the first marketing plan and the second marketing plan based on the conversion rate of the recommended content based on the user corresponding to the test traffic assigned to the first marketing plan and the second marketing plan.
A computer readable storage medium storing one or more programs, the one or more programs, when executed by an electronic device including a plurality of applications, causing the electronic device to perform the following operations :

According to the AB test diversion strategy, a preset amount of test traffic is allocated to the first marketing plan and the second marketing plan;

Determining, according to the target user's tag and the preset correspondence corresponding to the target traffic, the content of the marketing plan that needs to be recommended to the target user; wherein the target traffic is a test traffic that hits the first marketing plan or the second marketing plan, The preset correspondence relationship is a correspondence between a label and a marketing plan;

The target marketing plan is determined in the first marketing plan and the second marketing plan based on the conversion rate of the recommended content based on the user corresponding to the test traffic assigned to the first marketing plan and the second marketing plan.