CN114969543A

CN114969543A - Promotion method, promotion system, electronic device and storage medium

Info

Publication number: CN114969543A
Application number: CN202210676425.9A
Authority: CN
Inventors: 杜运辉; 王轶凡; 陈冠霖; 李世雷; 封树超; 陈冠丞; 刘少江; 孔清清; 张钋; 王雪
Original assignee: Beijing Baidu Netcom Science and Technology Co Ltd
Current assignee: Beijing Baidu Netcom Science and Technology Co Ltd
Priority date: 2022-06-15
Filing date: 2022-06-15
Publication date: 2022-08-30
Anticipated expiration: 2042-06-15
Also published as: CN114969543B

Abstract

The application provides a popularization method, a popularization system, electronic equipment and a storage medium, relates to the technical field of computers, and particularly relates to the field of artificial intelligence such as big data and deep learning. The specific implementation scheme is as follows: acquiring user use data corresponding to a target strategy; respectively inputting user use data into a plurality of gain models to obtain a first prediction result output by each gain model; selecting a target gain model from the multiple gain models according to first prediction results corresponding to the multiple gain models respectively; and determining a target crowd corresponding to the target strategy according to the target gain model. Therefore, under the condition of comparing the same input data, the target gain model is selected from the gain models according to the comparison result by comparing the first prediction results of the gain models, so that the accuracy of selecting the target gain model is improved, the target group for popularizing the target strategy is determined based on the selected target gain model, and the accuracy of popularizing the strategy is improved.

Description

Promotion method, promotion system, electronic device and storage medium

Technical Field

The application relates to the technical field of computers, in particular to the field of artificial intelligence such as big data and deep learning, and specifically relates to a popularization method, a popularization system, electronic equipment and a storage medium.

Background

In practical applications, besides the influence of some strategies concerning the product on the target index, different influences of different groups receiving the strategies may also influence the target which needs to be increased finally.

In the related art, the gain evaluation method can effectively position the part of users which are obviously influenced by the strategy actually, but the machine learning models applied under the gain method are more, and the gains brought by adopting different gain model popularization strategies are possibly different.

Therefore, how to improve the accuracy of strategy popularization is an urgent problem to be solved.

Disclosure of Invention

The application provides a popularization method, a popularization system, electronic equipment and a storage medium. The specific scheme is as follows:

according to an aspect of the present application, there is provided a popularization method including:

acquiring user use data corresponding to a target strategy;

inputting the user use data into a plurality of gain models respectively to obtain a first prediction result output by each gain model;

selecting a target gain model from the multiple gain models according to first prediction results corresponding to the multiple gain models respectively;

and determining a target crowd corresponding to the target strategy according to the target gain model.

According to another aspect of the present application, there is provided a promotion system, including:

the model module is used for acquiring user use data corresponding to a target strategy sent by the platform module, inputting the user use data into a plurality of gain models respectively to acquire a first prediction result output by each gain model, and sending the first prediction result output by each gain model to the platform module;

the platform module is used for acquiring user use data corresponding to a target strategy, sending the user use data to the model module, acquiring a first prediction result output by each gain model sent by the model module, selecting a target gain model from the gain models according to the first prediction results respectively corresponding to the gain models, and determining a target group corresponding to the target strategy according to the target gain model.

According to another aspect of the present application, there is provided an electronic device including:

at least one processor; and

a memory communicatively coupled to the at least one processor; wherein the content of the first and second substances,

the memory stores instructions executable by the at least one processor to enable the at least one processor to perform the method of the above embodiments.

According to another aspect of the present application, there is provided a non-transitory computer readable storage medium having stored thereon computer instructions for causing the computer to perform the method according to the above-described embodiments.

According to another aspect of the present application, a computer program product is provided, comprising a computer program which, when being executed by a processor, carries out the steps of the method of the above-mentioned embodiment.

It should be understood that the statements in this section do not necessarily identify key or critical features of the embodiments of the present application, nor do they limit the scope of the present application. Other features of the present application will become apparent from the following description.

Drawings

The drawings are included to provide a better understanding of the present solution and are not intended to limit the present application. Wherein:

fig. 1 is a schematic flow chart of a popularization method according to an embodiment of the present application;

fig. 2 is a schematic flow chart of a popularization method according to another embodiment of the present application;

fig. 3 is a schematic flow chart of a popularization method according to another embodiment of the present application;

fig. 4 is a schematic flowchart of a popularization method according to another embodiment of the present application;

fig. 5 is a schematic structural diagram of a popularization system according to an embodiment of the present application;

fig. 6 is a schematic structural diagram of a promotion system according to another embodiment of the present application;

fig. 7 is a schematic diagram of a framework of a promotion system according to an embodiment of the present application;

FIG. 8 is a schematic overall flow chart provided in accordance with an embodiment of the present application;

fig. 9 is a block diagram of an electronic device for implementing the promotion method of the embodiment of the present application.

Detailed Description

The following description of the exemplary embodiments of the present application, taken in conjunction with the accompanying drawings, includes various details of the embodiments of the application for the understanding of the same, which are to be considered exemplary only. Accordingly, those of ordinary skill in the art will recognize that various changes and modifications of the embodiments described herein can be made without departing from the scope and spirit of the present application. Also, descriptions of well-known functions and constructions are omitted in the following description for clarity and conciseness.

Artificial intelligence is the subject of research on the use of computers to simulate certain mental processes and intelligent behaviors (such as learning, reasoning, thinking, planning, etc.) of humans, both in the hardware and software domain. Artificial intelligence hardware technologies generally include technologies such as sensors, dedicated artificial intelligence chips, cloud computing, distributed storage, big data processing, and the like; the artificial intelligence software technology comprises a computer vision technology, a voice recognition technology, a natural language processing technology, deep learning, a big data processing technology, a knowledge map technology and the like.

Deep learning is a new research direction in the field of machine learning. Deep learning is the intrinsic law and expression level of the learning sample data, and the information obtained in the learning process is very helpful for the interpretation of data such as characters, images and sounds. The final aim of the method is to enable a machine to have analysis and learning capabilities like a human, and to recognize data such as characters, images and sounds.

A popularization method, a system, an electronic device, and a storage medium of the embodiments of the present application are described below with reference to the drawings.

Fig. 1 is a schematic flow chart of a popularization method according to an embodiment of the present application.

The popularization method can be executed by the popularization system, and the device can be configured in electronic equipment to select the target gain model according to the comparison result of the gain models, determine the target crowd of the popularization target strategy based on the target gain model, and improve the accuracy of strategy popularization.

The electronic device may be any device with computing capability, for example, a personal computer, a mobile terminal, a server, and the like, and the mobile terminal may be a hardware device with various operating systems, touch screens, and/or display screens, such as an in-vehicle device, a mobile phone, a tablet computer, a personal digital assistant, a wearable device, and the like.

As shown in fig. 1, the popularization method includes:

step 101, obtaining user usage data corresponding to a target policy.

In the application, after a policy of a product is on-line, the use data of the product by a user can be acquired, so that the use data of the user corresponding to the policy, that is, the use data of the user corresponding to a target policy, is acquired.

The user usage data may include gain targets, user identifications, product identifications, target policy identifications, user characteristics, and the like, among others. The user characteristics may include, among other things, the user's gender, age, preferences, etc.

For example, if the product is an application and the policy is to expose a function of the application, the user usage data may include: goal Y (gain goal, e.g., user age of a product), user id, product id _ policy sid, whether the policy is in effect (e.g., whether a certain product function is presented to the user), user characteristics, etc.

It should be noted that, in the technical solution of the present application, the acquisition, storage, application, and the like of the personal information of the related user all conform to the regulations of the relevant laws and regulations, and do not violate the customs of the public order.

In the present application, the user usage data includes two types of user usage data, one is a user who implements a policy, and the other is a user who does not implement a policy, that is, the user usage data includes experimental group data and control group data.

Step 102, inputting user usage data into a plurality of gain models respectively to obtain a first prediction result output by each gain model.

In the application, the popularization system is integrated with a plurality of gain models, the obtained user use data can be respectively input into the gain models, and a first prediction result output by each gain model can be obtained.

The first prediction result may include a prediction result corresponding to each user. For example, the gain target is the retention of the application program, and the first prediction result may include a retention improvement probability corresponding to each user in the experimental group and the control group.

In the application, a plurality of gain models are obtained by adopting different modeling modes, so that the types of the gain models are enriched.

Step 103, selecting a target gain model from the plurality of gain models according to the first prediction results corresponding to the plurality of gain models respectively.

In the present application, the gain corresponding to each gain model may be determined according to the first prediction result corresponding to each gain model, and the model with the highest gain may be selected from the multiple gain models as the target gain model.

And 104, determining a target crowd corresponding to the target strategy according to the target gain model.

In the application, the use data of some users on the product can be acquired, the use data of the users are input into the target gain model, and the users with the predicted values larger than the preset threshold value can be used as target crowds.

After the target crowd is determined, the target strategy can be popularized to the target crowd, so that the accurate popularization of the target strategy is realized, and the gain is improved. For example, if the target population is women over the age of 25, then the target policy may be implemented for users over the age of 25.

In the embodiment of the application, the user use data corresponding to the obtained target strategy is respectively input into the gain models to obtain a first prediction result output by each gain model, and the target gain models are selected from the gain models according to the comparison results by comparing the first prediction results of the gain models under the condition of the same input data, so that the accuracy of selecting the target gain models is improved, the target population for popularizing the target strategy is determined based on the selected target gain models, and the accuracy of popularizing the strategy is improved and the gain is improved.

Fig. 2 is a schematic flow chart of a popularization method according to another embodiment of the present application.

As shown in fig. 2, the popularization method includes:

step 201, obtaining user usage data corresponding to the target policy.

Step 202, inputting user usage data into a plurality of gain models respectively to obtain a first prediction result output by each gain model.

In the present application, steps 201 to 202 are similar to those described in the above embodiments, and therefore are not described herein again.

Step 203, determining a first evaluation result corresponding to each gain model according to the first prediction result corresponding to each gain model.

In the application, the same evaluation index may be adopted to evaluate the first prediction results corresponding to the plurality of gain models respectively, so as to obtain the first evaluation result corresponding to each gain model.

The evaluation index may include a monotonicity score, a mean causal effect, an individual causal effect, a Qini curve, and the like.

And 204, selecting a target gain model from the multiple gain models according to the first evaluation result corresponding to each gain model.

In the present application, the first evaluation results of the plurality of gain models may be compared to select a gain model with the largest gain from the plurality of gain models, that is, to select a target gain model from the plurality of gain models.

Taking the evaluation index as an example of the monotonicity score, for example, if the first prediction result includes the retention and promotion probability after each user policy, the average value of the retention and promotion probabilities corresponding to each user corresponding to each gain model may be used as the overall promotion probability, the ratio between the overall promotion probability and the true promotion probability may be used as the monotonicity score, and the gain model with the highest monotonicity score may be used as the target gain model. Wherein, the true lifting probability may be a difference between the true retention rate of the experimental group and the true retention rate of the control group.

And step 205, determining a target crowd corresponding to the target strategy according to the target gain model.

In the present application, step 205 is similar to the content described in the above embodiments, and therefore, the description thereof is omitted.

In the embodiment of the application, when the target gain model is selected from the plurality of gain models, the first evaluation result of each gain model can be determined according to the first prediction result of each gain model, and the gain model with better gain effect can be selected from the plurality of gain models by comparing the first evaluation results of the plurality of gain models, so that the accuracy of selecting the gain model is improved.

Fig. 3 is a schematic flow chart of a popularization method according to another embodiment of the present application.

As shown in fig. 3, the popularization method includes:

step 301, obtaining user usage data corresponding to the target policy.

Step 302, inputting user usage data into a plurality of gain models respectively to obtain a first prediction result output by each gain model.

Step 303, selecting a target gain model from the plurality of gain models according to the first prediction results corresponding to the plurality of gain models respectively.

In the present application, steps 301 to 303 are similar to those described in the above embodiments, and therefore are not described herein again.

And step 304, generating an explanatory dendrogram corresponding to the target gain model according to the first prediction result corresponding to the target gain model.

In the application, an explanatory tree diagram corresponding to the target gain model can be generated by calling the model according to the first prediction result corresponding to the target gain. For example, a policy learning tree or a decision tree may be invoked to generate an explanatory tree diagram.

In the present application, each tree node in the explanatory tree diagram corresponding to the target model may include a gain corresponding to the user characteristic, whether a policy is adopted, and the like.

And 305, determining a target user characteristic corresponding to the user gain larger than the threshold value according to the user gain corresponding to each user characteristic in the explanatory tree diagram.

In the application, the user gains larger than the threshold value can be determined according to the user gains corresponding to the user characteristics in the explanatory tree diagram, and the user characteristics with the user gains larger than the threshold value are used as the target user characteristics.

For example, the target user may be characterized by an age of 25, 26, 28, 30.

And step 306, determining a target crowd corresponding to the target strategy according to the characteristics of the target user.

According to the target user characteristics, the users meeting the target user characteristics can be determined and used as target crowds corresponding to the target strategy.

For example, the target users are characterized by ages 25, 26, 28, 30, etc., and users older than 25 may be targeted.

In the embodiment of the application, the explanatory tree diagram corresponding to the target gain model can be generated according to the first prediction result corresponding to the target gain model, the target user characteristics corresponding to the user gains larger than the threshold value are determined according to the user gains corresponding to the user characteristics in the explanatory tree diagram, and the target crowd corresponding to the target strategy is determined based on the target user characteristics, so that the target crowd with better gain effect can be determined according to the explanatory tree diagram corresponding to the target gain model, and the method is simple and convenient.

Fig. 4 is a schematic flow chart of a popularization method according to another embodiment of the present application.

As shown in fig. 4, the popularization method further includes:

step 401, obtaining a plurality of candidate gain models and training data corresponding to a target strategy.

In the application, before the target gain model is determined, a plurality of candidate gain models and training data corresponding to the target strategy can be obtained.

The training data corresponding to the target strategy is similar to the user use data corresponding to the target strategy, the training data also comprises control group data and experimental group data, and the training data can be enough for modeling.

In order to facilitate training, in the present application, when training data is acquired, if the acquired data does not meet the standard specification, the data may be processed to ensure that the training data obtained after processing meets the standard specification. For example, the standard specification is that the training data includes information such as target Y, user id, target policy id, and user characteristics.

In practical application, the number of gain models is relatively large, and for convenience of calculation, in the application, a plurality of candidate gain models can be screened from a large number of gain models in advance. In implementation, a plurality of initial gain models may be obtained, the plurality of initial gain models may be trained by using a standard data set to obtain a plurality of trained gain models, and a plurality of models may be selected from the plurality of trained gain models as candidate gain models based on evaluation results of the plurality of trained gain models. Therefore, a plurality of candidate gain models can be screened out by training a plurality of initial gain models, and the subsequent calculation amount is reduced.

Step 402, training the candidate gain models respectively by using the training data to obtain a plurality of gain models.

In the application, each candidate gain model can be trained by using the training data to obtain the corresponding gain model. And the modeling modes of the gain models of the candidate models are different, and the gain models can be obtained by adopting the corresponding modeling modes.

For example, the differential model based on the dual model models the experimental group data and the control group data in the training data separately, or the control group data and the experimental group data may be put together for modeling.

In the application, when the candidate gain model is trained, the candidate gain model can be trained in a deep learning mode, and compared with other machine learning methods, the deep learning method has better performance on a large data set.

And step 403, acquiring test data corresponding to the target strategy.

The test data corresponding to the target strategy is similar to the training data corresponding to the target strategy, and is also the use data of some users on the product, which is obtained after the target strategy of the product is online, and the test data also comprises experimental group data and comparison group data.

It should be noted that, in the present application, the test data corresponding to the target strategy may be obtained after training the training data corresponding to the target strategy to obtain a plurality of gain models, or after the target strategy of the product is online, the usage data of some users on the product may be obtained, and a part of the obtained usage data of the users is used as the training data, and another part is used as the test data, which is not limited in the present application.

Step 404, inputting the test data into the plurality of gain models respectively to obtain a second prediction result output by each gain model.

After obtaining the plurality of gain models, the plurality of gain models may be evaluated for effectiveness. In the application, test data corresponding to a target strategy are obtained, and the test data are respectively input into a plurality of gain models to obtain a second prediction result output by each gain model.

Step 405, using the same evaluation index, evaluating the second prediction result corresponding to each gain model to determine the second evaluation result corresponding to each gain model.

The evaluation index may include an average causal effect, an individual causal effect, a group causal effect, a Qini curve, a boost curve, a gain curve, and the like.

In the present application, the value of one or more evaluation indexes may be calculated according to the second prediction result of each gain model, so as to obtain the second evaluation result corresponding to each gain model. Thereby, the gain effect of each gain model can be determined from the second evaluation result.

In order to facilitate the visual observation of the gain effect of the model or the visual comparison of the gain effect of each gain model, in the present application, a second evaluation result of one or more gain models may also be displayed. For example, an evaluation index map of the gain model with the best gain effect may be displayed, wherein the evaluation index map includes a grouped causal effect map, a Qini graph, a boosting graph, a gain graph, and the like.

In the embodiment of the application, a plurality of candidate gain models can be trained by using training data corresponding to target strategies to obtain a plurality of gain models, so that training data based on different target strategies can be trained to obtain a plurality of gain models corresponding to different strategies, test data corresponding to the target strategies can be respectively input into the plurality of gain models to obtain second prediction results of the plurality of gain models, and the plurality of gain models are evaluated by adopting unified evaluation indexes, so that the gain effects of the gain models under the same input can be compared conveniently.

In order to implement the foregoing embodiment, the embodiment of the present application further provides a popularization system. Fig. 5 is a schematic structural diagram of a popularization system according to an embodiment of the present application.

As shown in fig. 5, the promotion system 500 includes: a platform module 510 and a model module 520, wherein,

the model module 520 is configured to obtain user usage data corresponding to the target policy sent by the platform module 510, input the user usage data into the plurality of gain models respectively to obtain a first prediction result output by each gain model, and send the first prediction result output by each gain model to the platform module 510.

The platform module 510 is configured to obtain user usage data corresponding to the target policy, send the user usage data to the model module 520, obtain a first prediction result output by each gain model sent by the model module 520, select a target gain model from the multiple gain models according to the first prediction results corresponding to the multiple gain models, and determine a target group corresponding to the target policy according to the target gain model.

In this application, after a policy of a product is on-line, the platform module 510 may obtain the usage data of the product by the user, so as to obtain the usage data of the user corresponding to the policy, that is, the usage data of the user corresponding to the target policy.

The user usage data may include gain targets, user identifications, product identifications, target policy identifications, user characteristics, and the like, among others. The user characteristics may include, among other things, the user's gender, age, preferences, and the like.

In the present application, the promotion system 500 has a plurality of gain models, and the model module 520 may input the user usage data corresponding to the target policy into the plurality of gain models, respectively, and may obtain the first prediction result output by each gain model.

The model module 520 sends the first prediction result output by each gain model to the platform module 510, and the platform module 510 may determine the gain corresponding to each gain model according to the first prediction result corresponding to each gain model, select a model with the highest gain from the multiple gain models as a target gain model, obtain usage data of some users on products, input the usage data of the users into the target gain model, and take users with a prediction value greater than a preset threshold as a target population.

In an embodiment of the present application, based on the popularization system shown in fig. 5, the platform module 510 is configured to determine a first evaluation result corresponding to each gain model according to the first prediction result corresponding to each gain model, and select a target gain model from among the multiple gain models according to the first evaluation result corresponding to each gain model.

In this application, the platform module 510 may evaluate the first prediction results corresponding to the gain models respectively by using the same evaluation index to obtain a first evaluation result corresponding to each gain model, and compare the first evaluation results of the gain models to select a gain model with the largest gain from among the gain models, that is, select a target gain model from the gain models.

In the embodiment of the application, the platform module may determine the first evaluation result corresponding to each gain model according to the first prediction result corresponding to each gain model, select the target gain model from the plurality of gain models according to the first evaluation result corresponding to each gain model, and select the gain model with a better gain effect from the plurality of gain models by comparing the evaluation results of the plurality of gain models, thereby improving the accuracy of selection.

In an embodiment of the present application, based on the popularization system shown in fig. 5, the platform module 510 is configured to generate an explanatory tree diagram corresponding to the target gain model according to the first prediction result corresponding to the target gain model, determine a target user characteristic corresponding to a user gain greater than a threshold value according to a user gain corresponding to each user characteristic in the explanatory tree diagram, and determine a target crowd according to the target user characteristic.

In this application, the platform module 510 may generate an explanatory tree diagram corresponding to the target gain model by calling the tree model according to the first prediction result corresponding to the target gain. The tree model may be a policy learning tree, a decision tree, or the like.

In the present application, each tree node in the explanatory tree diagram corresponding to the target model includes a gain corresponding to the user characteristic, whether a policy is adopted, and the like.

In the application, the platform module can determine the user gains larger than the threshold value according to the user gains corresponding to the user characteristics in the explanatory dendriform graph, and determine the users according with the target user characteristics according to the user gains larger than the threshold value as the target user characteristics, and determine the users according with the target user characteristics according to the target user characteristics as the target population corresponding to the target strategy.

In this embodiment of the application, the platform module 510 may generate an explanatory tree diagram corresponding to the target gain model according to the first prediction result corresponding to the target gain model, determine a target user characteristic corresponding to a user gain greater than a threshold value according to a user gain corresponding to each user characteristic in the explanatory tree diagram, and determine a target population according to the target user characteristic, so that a target population with a better gain effect may be determined according to the explanatory tree diagram corresponding to the target gain model, which is simple and convenient.

Fig. 6 is a schematic structural diagram of a popularization system according to another embodiment of the present application.

As shown in fig. 6, the promotion system 600 includes: a platform module 610, a model module 620, a data module 630, and an evaluation module 640.

The model module 620 is configured to obtain user usage data corresponding to the target policy sent by the platform module 610, input the user usage data into the plurality of gain models respectively to obtain a first prediction result output by each gain model, and send the first prediction result output by each gain model to the platform module 610.

The platform module 610 is configured to obtain user usage data corresponding to a target policy, send the user usage data to the model module 620, obtain a first prediction result output by each gain model sent by the model module 620, select a target gain model from the multiple gain models according to the first prediction results corresponding to the multiple gain models, and determine a target group corresponding to the target policy according to the target gain model.

In the present application, the functions of the platform module 610 and the model module 620 are similar to those of the platform module 510 and the model module 520 in the above embodiments, and therefore the description is repeated here.

The data module 630 is configured to obtain training data corresponding to the target policy, and send the training data to the model module 620.

The model module 620 is configured to obtain training data sent by the data module 630, obtain a plurality of candidate gain models from the evaluation module 640, and train the plurality of candidate gain models by using the training data, so as to obtain a plurality of gain models.

In this application, the data module 630 may obtain training data corresponding to the target strategy and send the training data to the model module 620, and the model module 620 obtains the training data corresponding to the target strategy sent by the data module 630 and obtains a plurality of candidate gain models from the evaluation module 640, and trains each candidate gain model by using the training data to obtain a corresponding gain model.

For training, the data module 630 may obtain training data according to a standard specification defined in the present application. For example, the standard specification is that the training data includes information such as target Y, user id, target policy id, and user characteristics.

In the application, each candidate model gain model has different modeling modes, and the gain model can be obtained by adopting the corresponding modeling mode. For example, the differential model based on the dual model models the experimental group data and the control group data in the training data separately, or the control group data and the experimental group data may be put together for modeling.

In this application, the data module 630 may support feature data of which input data is in a csv format, support reading of local data and data of a cluster HDFS (Hadoop Distributed File System), and may directly call a data interface with an instruction, for example: -s CSV input FILE, or after setting cluster clients, using-HDFS _ FILE to get data in the cluster.

In addition, the data module 630 may also access generated simulation data, where the simulation data is generated data of various types, such as nonlinear intervention and linear feature data or nonlinear intervention and nonlinear feature data.

In the embodiment of the application, the model module can train a plurality of candidate gain models by using training data corresponding to target strategies to obtain a plurality of gain models, so that training can be performed based on the training data of different target strategies to obtain a plurality of gain models corresponding to different strategies.

In an embodiment of the present application, based on the popularization system shown in fig. 6, the model module 620 may be further configured to obtain test data corresponding to the target policy, input the test data into the multiple gain models respectively, to obtain a second prediction result output by each gain model, and send the second prediction result output by each gain model to the evaluation module 640. The evaluation module 640 is configured to obtain a second prediction result output by each gain model sent by the model module, and evaluate the second prediction result corresponding to each gain model by using the same evaluation index to determine the second evaluation result corresponding to each gain model.

Therefore, the test data are respectively input into the gain models to obtain second prediction results of the gain models, and the gain models are evaluated by adopting a uniform evaluation index, so that the gain effects of the gain models under the same input can be conveniently compared.

After obtaining the multiple gain models, the evaluation module 640 may be used to evaluate the effects of the multiple gain models. In this application, the model module 620 obtains test data corresponding to the target policy, and inputs the test data into the plurality of gain models, respectively, to obtain a second prediction result output by each gain model, and sends the second prediction result output by each gain model to the evaluation module 640.

The test data is similar to the training data and is the use data of the product obtained by the user after the target strategy of the product is on line, and the test data also comprises experimental group data and comparison group data.

The evaluation module 640 may calculate values of one or more evaluation indexes according to the second prediction result of each gain model, so as to obtain a second evaluation result corresponding to each gain model. Thereby, the gain effect of each gain model can be determined based on the second evaluation result.

For visual comparison, the platform module 610 may also display a second evaluation result of one or more gain models. For example, an evaluation index map of the gain model with the best gain effect may be displayed, wherein the evaluation index map includes a grouped causal effect map, a Qini graph, a boosting graph, a gain graph, and the like.

In practical applications, there are many gain models, and based on this, in an embodiment of the present application, based on the popularization system shown in fig. 6, for convenience of calculation, the evaluation module 640 may screen out a plurality of candidate gain models for the model module 620 from a large number of gain models.

In implementation, the evaluation module 640 may obtain a plurality of initial gain models, may train the plurality of initial gain models respectively by using a standard data set to obtain a plurality of trained gain models, and select a plurality of models from the plurality of trained gain models as a plurality of candidate gain models based on evaluation results of the plurality of trained gain models. Therefore, a plurality of candidate gain models can be screened out by training a plurality of initial gain models, and the subsequent calculation amount is reduced.

In one embodiment of the present application, the promotional system as shown in FIG. 6 may also include a validation module 650.

And an effect module 650 for promoting the target policy to the target group. Therefore, accurate popularization of the target strategy is achieved, and gain is improved.

For example, if the target population is women over the age of 25, then the target policy may be implemented for users over the age of 25.

To facilitate understanding of the foregoing embodiments, the foregoing promotion system is further described below with reference to fig. 7, and fig. 7 is a schematic frame diagram of a promotion system according to an embodiment of the present application.

As shown in fig. 7, the promotion system includes a platform module, a data module, a model module, an evaluation module, and an effect module.

The platform module is responsible for displaying input and output of the whole process; the data module is responsible for effectively importing data of a flow experiment into the model module; the model module is responsible for model training and evaluation; and the validation module is finally responsible for pushing the whole implementation or the strategy online of the target group. The above-described modules are explained below.

A platform module: after the strategy is on line, product use data is collected, an interface of a model module is called, a model comparison result is obtained, and income confirmation can be carried out.

In addition, in the platform module shown in fig. 7, the original policy index and the new policy index may be, for example, a retention rate, a usage time of a product by a user, and the like, a true value required for gain effect comparison, for example, a true retention rate, may be determined based on the policy indexes, a target gain model with an optimal gain effect may be determined according to a result of the gain effect comparison, and then, a benefit is determined by using the target gain model. The gain of the user selected by the profit confirmation method, such as the comparison model, is improved by a certain amount compared with the original strategy. The platform module can also record, display and count the income.

When the gain effect comparison is in accordance with the expectation, the strategy can be directly adopted for the product user, and after the strategy is adopted, a new strategy index can be obtained for the gain effect comparison.

The data module can ensure that the received training data are all in accordance with the standard, support the feature data of which the input data are in the csv format, support the reading of the local data and the cluster HDFS data, and also can access the generated simulation data.

In fig. 7, the data module may obtain service flow data based on policy configuration of the platform module, extract user behavior features from the service flow data through the feature extraction operator, obtain external features from external data (such as a portrait), and synthesize the user behavior features and the external features to obtain user granularity data for model training. The external features may be understood as user features, that is, user granularity data, that is, training data corresponding to the target policy in the above embodiment.

In fig. 7, the evaluation module may perform model training on the algorithms in the candidate algorithm set (i.e., perform model training on the plurality of initial gain models) by using the historical verification data and the generated data, that is, the standard data set, evaluate the model effect by using the evaluation indexes in the evaluation index set, add the models that meet expectations to the formal algorithm set according to the evaluation result, and perform re-research, development, and submission on the gain algorithms that do not meet expectations. The alternative algorithm set is obtained through gain algorithm investigation, development and submission, and the formal algorithm set comprises the multiple candidate gain models.

The model module is responsible for model loading and training, the model module can train the model with a positive algorithm set by using user granularity data, namely train the model screened by the evaluation module, and evaluate the model effect by using the evaluation index set by the evaluation model evaluation index to obtain a model explanatory dendrogram, and the platform module can display the model explanatory dendrogram generalization characteristics or service income evaluation.

In addition, the calculation architecture interface in the model implementation interface realizes single machine training and high concurrency training, and aiming at the high concurrency training, the popularization system can be fused with an open source Fugue distributed technical architecture to decouple the model algorithm logic of the upper layer from the parallel calculation implementation of the lower layer, so that a user only needs to define a candidate gain model without paying attention to the calculation implementation details of the lower layer, and the corresponding model can be ensured to be trained and predicted with higher efficiency in a distributed mode. In terms of local code implementation, the local code can be planted into a computing engine, such as Spark and Dask, to run only by a small amount of change, so that decoupling of algorithm logic and a concurrency framework is achieved, different codes corresponding to various high concurrency frameworks do not need to be developed respectively, and production cost is greatly saved.

And the validation module can carry out one-key derivation validation based on platform display or directly carry out one-key derivation validation based on generalization characteristics or service income evaluation in the model module. The one-key derivation validation comprises the step of directly carrying out real-time strategy on all users of the product or sampling validation, namely, the experimental population is online.

In the embodiment of the application, after various aspects of model comparison and model selection are performed by combining corresponding business targets and product data (for example, product data search, product data recommendation, mobile phone application program product data and the like) through a popularization system, a model with the best gain effect is obtained, a potential optimal profit crowd is defined, product improvement suggestions are provided in a targeted manner, meanwhile, verification can be further performed by combining a small flow experiment, the sample size of the small flow experiment can be modeled sufficiently, the overall process can be shown in fig. 8, the first step is strategy online, the second step is gain model comparison, the third step is determination of the crowd with the best gain effect based on gain model comparison, the fourth step is small flow verification to determine whether to perform completeness or not, and partial user use data can be used for verification.

The popularization system of the embodiment of the application integrates the training, the analysis and the evaluation of the gain model, supports the user gain analysis under the complex scene of the internet products, integrates various gain models, can meet the requirements of the gain analysis of various scenes, adopts unified evaluation indexes, can support the effect comparison and the visual graph expression of various different models, integrates the distributed technical architecture, can realize high-concurrency training, and can effectively solve the performance bottleneck problem of single-point calculation ubiquitous.

There is also provided, in accordance with an embodiment of the present application, an electronic device, a readable storage medium, and a computer program product.

FIG. 9 illustrates a schematic block diagram of an example electronic device 900 that can be used to implement embodiments of the present application. Electronic devices are intended to represent various forms of digital computers, such as laptops, desktops, workstations, personal digital assistants, servers, blade servers, mainframes, and other appropriate computers. The electronic device may also represent various forms of mobile devices, such as personal digital processing, cellular phones, smart phones, wearable devices, and other similar computing devices. The components shown herein, their connections and relationships, and their functions, are meant to be examples only, and are not meant to limit implementations of the present application that are described and/or claimed herein.

As shown in fig. 9, the apparatus 900 includes a computing unit 901 that can perform various appropriate actions and processes in accordance with a computer program stored in a ROM (Read-Only Memory) 902 or a computer program loaded from a storage unit 908 into a RAM (Random Access Memory) 903. In the RAM 903, various programs and data required for the operation of the device 900 can also be stored. The calculation unit 901, ROM902, and RAM 903 are connected to each other via a bus 904. An I/O (Input/Output) interface 905 is also connected to the bus 904.

A number of components in the device 900 are connected to the I/O interface 905, including: an input unit 906 such as a keyboard, a mouse, and the like; an output unit 907 such as various types of displays, speakers, and the like; a storage unit 908 such as a magnetic disk, optical disk, or the like; and a communication unit 909 such as a network card, a modem, a wireless communication transceiver, and the like. The communication unit 909 allows the device 900 to exchange information/data with other devices through a computer network such as the internet and/or various telecommunication networks.

The computing unit 901 may be a variety of general and/or special purpose processing components having processing and computing capabilities. Some examples of the computing Unit 901 include, but are not limited to, a CPU (Central Processing Unit), a GPU (graphics Processing Unit), various dedicated AI (Artificial Intelligence) computing chips, various computing Units running machine learning model algorithms, a DSP (Digital Signal Processor), and any suitable Processor, controller, microcontroller, and the like. The calculation unit 901 performs the respective methods and processes described above, such as the popularization method. For example, in some embodiments, the promotion method may be implemented as a computer software program tangibly embodied in a machine-readable medium, such as storage unit 908. In some embodiments, part or all of a computer program may be loaded onto and/or installed onto device 900 via ROM902 and/or communications unit 909. When the computer program is loaded into RAM 703 and executed by the computing unit 901, one or more steps of the promotional method described above may be performed. Alternatively, in other embodiments, the computing unit 901 may be configured to perform the promotion method by any other suitable means (e.g., by means of firmware).

Various implementations of the systems and techniques described here above may be realized in digital electronic circuitry, Integrated circuitry, FPGAs (Field Programmable Gate arrays), ASICs (Application-Specific Integrated circuits), ASSPs (Application Specific Standard products), SOCs (System On Chip, System On a Chip), CPLDs (Complex Programmable Logic devices), computer hardware, firmware, software, and/or combinations thereof. These various embodiments may include: implemented in one or more computer programs that are executable and/or interpretable on a programmable system including at least one programmable processor, which may be special or general purpose, receiving data and instructions from, and transmitting data and instructions to, a storage system, at least one input device, and at least one output device.

Program code for implementing the methods of the present application may be written in any combination of one or more programming languages. These program codes may be provided to a processor or controller of a general purpose computer, special purpose computer, or other programmable data processing apparatus, such that the program codes, when executed by the processor or controller, cause the functions/operations specified in the flowchart and/or block diagram to be performed. The program code may execute entirely on the machine, partly on the machine, as a stand-alone software package partly on the machine and partly on a remote machine or entirely on the remote machine or server.

In the context of this application, a machine-readable medium may be a tangible medium that can contain, or store a program for use by or in connection with an instruction execution system, apparatus, or device. The machine-readable medium may be a machine-readable signal medium or a machine-readable storage medium. A machine-readable medium may include, but is not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any suitable combination of the foregoing. More specific examples of a machine-readable storage medium would include an electrical connection based on one or more wires, a portable computer diskette, a hard disk, a RAM, a ROM, an EPROM (Electrically Programmable Read-Only-Memory) or flash Memory, an optical fiber, a CD-ROM (Compact Disc Read-Only-Memory), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

To provide for interaction with a user, the systems and techniques described here can be implemented on a computer having: a Display device (e.g., a CRT (Cathode Ray Tube) or LCD (Liquid Crystal Display) monitor) for displaying information to a user; and a keyboard and a pointing device (e.g., a mouse or a trackball) by which a user can provide input to the computer. Other kinds of devices may also be used to provide for interaction with a user; for example, feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user may be received in any form, including acoustic, speech, or tactile input.

The systems and techniques described here can be implemented in a computing system that includes a back-end component (e.g., as a data server), or that includes a middleware component (e.g., an application server), or that includes a front-end component (e.g., a user computer having a graphical user interface or a web browser through which a user can interact with an implementation of the systems and techniques described here), or any combination of such back-end, middleware, or front-end components. The components of the system can be interconnected by any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include: LAN (Local Area Network), WAN (Wide Area Network), internet, and blockchain Network.

The computer system may include clients and servers. A client and server are generally remote from each other and typically interact through a communication network. The relationship of client and server arises by virtue of computer programs running on the respective computers and having a client-server relationship to each other. The Server may be a cloud Server, which is also called a cloud computing Server or a cloud host, and is a host product in a cloud computing service system, so as to solve the defects of high management difficulty and weak service expansibility in a conventional physical host and a VPS (Virtual Private Server). The server may also be a server of a distributed system, or a server incorporating a blockchain.

According to an embodiment of the present application, there is also provided a computer program product, which when executed by an instruction processor in the computer program product, performs the promotion method proposed by the foregoing embodiment of the present application.

It should be understood that various forms of the flows shown above may be used, with steps reordered, added, or deleted. For example, the steps described in the present application may be executed in parallel, sequentially, or in different orders, as long as the desired results of the technical solutions disclosed in the present application can be achieved, and the present invention is not limited herein.

The above-described embodiments should not be construed as limiting the scope of the present application. It should be understood by those skilled in the art that various modifications, combinations, sub-combinations and substitutions may be made in accordance with design requirements and other factors. Any modification, equivalent replacement, and improvement made within the spirit and principle of the present application shall be included in the protection scope of the present application.

Claims

1. A promotional method, comprising:

acquiring user use data corresponding to a target strategy;

2. The method of claim 1, the selecting a target gain model from among the plurality of gain models, comprising:

determining a first evaluation result corresponding to each gain model according to a first prediction result corresponding to each gain model;

and selecting the target gain model from the plurality of gain models according to the first evaluation result corresponding to each gain model.

3. The method of claim 1, wherein the determining a target population corresponding to the target strategy according to the target gain model comprises:

generating an explanatory tree diagram corresponding to the target gain model according to a first prediction result corresponding to the target gain model;

determining a target user characteristic corresponding to the user gain larger than a threshold value according to the user gain corresponding to each user characteristic in the explanatory tree diagram;

and determining the target crowd according to the target user characteristics.

4. The method of claim 1, wherein the method further comprises:

obtaining a plurality of candidate gain models and training data corresponding to the target strategy;

and training the candidate gain models respectively by using the training data to obtain the gain models.

5. The method of claim 4, wherein after said deriving the plurality of gain models, further comprising:

acquiring test data corresponding to the target strategy;

inputting the test data into the gain models respectively to obtain a second prediction result output by each gain model;

and evaluating the second prediction result corresponding to each gain model by using the same evaluation index so as to determine the second evaluation result corresponding to each gain model.

6. The method of claim 5, wherein the method further comprises:

and displaying a second evaluation result of one or more gain models in the plurality of gain models.

7. The method of claim 4, wherein the obtaining a plurality of candidate gain models comprises:

obtaining a plurality of initial gain models;

respectively training the plurality of initial gain models to obtain a plurality of trained gain models;

selecting the plurality of candidate gain models from among the plurality of trained gain models.

8. The method of claim 1, wherein after determining the target population corresponding to the target strategy according to the target gain model, further comprising:

and popularizing the target strategy to the target crowd.

9. The method of claim 1, wherein the plurality of gain models are modeled differently.

10. A promotional system, comprising: a platform module and a model module, wherein,

11. The system of claim 10, wherein,

the platform module is configured to determine a first evaluation result corresponding to each gain model according to a first prediction result corresponding to each gain model, and select the target gain model from the multiple gain models according to the first evaluation result corresponding to each gain model.

12. The system of claim 10, wherein,

the platform module is used for generating an explanatory tree diagram corresponding to the target gain model according to a first prediction result corresponding to the target gain model, determining a target user characteristic corresponding to a user gain larger than a threshold value according to a user gain corresponding to each user characteristic in the explanatory tree diagram, and determining the target crowd according to the target user characteristic.

13. The system of claim 10, further comprising: a data module and an evaluation module, wherein,

the data module is used for acquiring training data corresponding to the target strategy and sending the training data to the model module;

the model module is configured to obtain the training data sent by the data module, obtain a plurality of candidate gain models from the evaluation module, and train the plurality of candidate gain models by using the training data, respectively, to obtain the plurality of gain models.

14. The system of claim 13, wherein,

the model module is used for acquiring test data corresponding to the target strategy, inputting the test data into the gain models respectively to acquire a second prediction result output by each gain model, and sending the second prediction result output by each gain model to the evaluation module;

the evaluation module is configured to obtain a second prediction result output by each gain model sent by the model module, and evaluate the second prediction result corresponding to each gain model by using the same evaluation index to determine the second evaluation result corresponding to each gain model.

15. The system of claim 14, wherein,

the platform module is further configured to display a second evaluation result of one or more gain models of the plurality of gain models.

16. The system of claim 13, wherein,

the evaluation module is configured to obtain a plurality of initial gain models, train the plurality of initial gain models respectively to obtain a plurality of trained gain models, and select the plurality of candidate gain models from the plurality of trained gain models.

17. The system of claim 10, further comprising: a validation module that, in turn,

the validation module is used for popularizing the target strategy to the target crowd.

18. The system of claim 10, wherein the plurality of gain models are modeled differently.

19. An electronic device, comprising:

at least one processor; and

the memory stores instructions executable by the at least one processor to enable the at least one processor to perform the method of any one of claims 1-9.

20. A non-transitory computer readable storage medium having stored thereon computer instructions for causing the computer to perform the method of any one of claims 1-9.

21. A computer program product comprising a computer program which, when executed by a processor, carries out the steps of the method of any one of claims 1-9.