CN114078031A - Marketing strategy determination method and device and computer storage medium - Google Patents

Marketing strategy determination method and device and computer storage medium Download PDF

Info

Publication number
CN114078031A
CN114078031A CN202111392823.XA CN202111392823A CN114078031A CN 114078031 A CN114078031 A CN 114078031A CN 202111392823 A CN202111392823 A CN 202111392823A CN 114078031 A CN114078031 A CN 114078031A
Authority
CN
China
Prior art keywords
platform
state information
marketing
marketing strategy
target user
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Pending
Application number
CN202111392823.XA
Other languages
Chinese (zh)
Inventor
杨磊
陈瑜庆
黄磊
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Shanghai Junzheng Network Technology Co Ltd
Original Assignee
Shanghai Junzheng Network Technology Co Ltd
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Shanghai Junzheng Network Technology Co Ltd filed Critical Shanghai Junzheng Network Technology Co Ltd
Priority to CN202111392823.XA priority Critical patent/CN114078031A/en
Publication of CN114078031A publication Critical patent/CN114078031A/en
Pending legal-status Critical Current

Links

Images

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q30/00—Commerce
    • G06Q30/02—Marketing; Price estimation or determination; Fundraising
    • G06Q30/0201—Market modelling; Market analysis; Collecting market data
    • G06Q30/0202—Market predictions or forecasting for commercial activities
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F18/00—Pattern recognition
    • G06F18/20—Analysing
    • G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
    • G06F18/214—Generating training patterns; Bootstrap methods, e.g. bagging or boosting
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q10/00—Administration; Management
    • G06Q10/04—Forecasting or optimisation specially adapted for administrative or management purposes, e.g. linear programming or "cutting stock problem"
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q10/00—Administration; Management
    • G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
    • G06Q10/063—Operations research, analysis or management
    • G06Q10/0637—Strategic management or analysis, e.g. setting a goal or target of an organisation; Planning actions based on goals; Analysis or evaluation of effectiveness of goals
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q10/00—Administration; Management
    • G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
    • G06Q10/067—Enterprise or organisation modelling
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q30/00—Commerce
    • G06Q30/02—Marketing; Price estimation or determination; Fundraising
    • G06Q30/0201—Market modelling; Market analysis; Collecting market data

Landscapes

  • Business, Economics & Management (AREA)
  • Engineering & Computer Science (AREA)
  • Strategic Management (AREA)
  • Human Resources & Organizations (AREA)
  • Entrepreneurship & Innovation (AREA)
  • Development Economics (AREA)
  • Economics (AREA)
  • Theoretical Computer Science (AREA)
  • Finance (AREA)
  • Accounting & Taxation (AREA)
  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • Marketing (AREA)
  • General Business, Economics & Management (AREA)
  • Game Theory and Decision Science (AREA)
  • Data Mining & Analysis (AREA)
  • Tourism & Hospitality (AREA)
  • Quality & Reliability (AREA)
  • Operations Research (AREA)
  • Educational Administration (AREA)
  • Bioinformatics & Computational Biology (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Artificial Intelligence (AREA)
  • Bioinformatics & Cheminformatics (AREA)
  • General Engineering & Computer Science (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Evolutionary Biology (AREA)
  • Evolutionary Computation (AREA)
  • Management, Administration, Business Operations System, And Electronic Commerce (AREA)

Abstract

The invention discloses a marketing strategy determination method, a marketing strategy determination device and a computer storage medium, relates to the technical field of network marketing, and solves the technical problem that a user cannot bring maximized income to a network car booking platform. The marketing strategy determining method comprises the following steps: acquiring target state information of a target user; predicting the accumulated platform income of the target user under different marketing strategies according to the target state information; and determining the maximum platform income brought by the target user under the preset input cost according to the accumulated platform income, and determining a marketing strategy issued to the target user based on the maximum platform income.

Description

Marketing strategy determination method and device and computer storage medium
Technical Field
The invention relates to the technical field of network marketing, in particular to a marketing strategy determination method, a marketing strategy determination device and a computer storage medium.
Background
At present, the travel by the net car appointment is one of the common travel modes of people. In order to prevent the loss of customers, the online booking platform usually adopts some marketing means to achieve the purposes of renewing, promoting lives, preventing loss and recovering loss.
In the prior art, different marketing means are generally determined by a network car booking platform according to the life cycle of a user, and then the life cycle of the user is artificially designed according to manual experience, so that the user cannot bring maximum benefit to the network car booking platform.
Accordingly, those skilled in the art are directed to developing a marketing strategy determination method, apparatus, and computer storage medium that enables a user to maximize revenue for a networked car booking platform.
Disclosure of Invention
In view of the above-mentioned drawbacks of the prior art, the technical problems to be solved by the present invention are: how to enable a user to bring maximum benefits for a network car booking platform through a marketing strategy.
In order to achieve the purpose, the invention adopts the following technical scheme:
in a first aspect, the present invention provides a marketing strategy determining method, including: acquiring target state information of a target user; predicting the accumulated platform income of the target user under different marketing strategies according to the target state information; and determining the maximum platform income brought by the target user under the preset input cost according to the accumulated platform income, and determining a marketing strategy issued to the target user based on the maximum platform income.
In the embodiment of the invention, the maximum platform profit brought by the target user under the preset input cost can be determined according to the accumulated platform profit of the target user under different marketing strategies, so that the marketing strategy issued to the target user can be determined based on the maximum platform profit, and the maximum platform profit can be ensured to be realized under the preset input cost.
In a preferred embodiment of the present invention, the predicting the accumulated platform revenue of the target user under different marketing strategies according to the target state information includes: and inputting the target state information into a first prediction model to obtain the accumulated platform income of the target user.
In a preferred embodiment of the present invention, the inputting the target state information into a first prediction model to obtain an accumulated platform revenue of the target user includes: inputting the target state information into the first prediction model to obtain M accumulated platform profits of the target user under M marketing strategies; under the condition that the selection probability is larger than a first threshold value, selecting the accumulated platform profit with the maximum profit value from the M accumulated platform profits as an output value of the first prediction model; and under the condition that the selection probability is not greater than the first threshold, randomly selecting one accumulated platform profit from the M accumulated platform profits as an output value of the first prediction model, wherein the selection probability is a randomly generated probability value and is used for determining a mode for selecting one accumulated platform profit from the M accumulated platform profits, and M is an integer greater than 0.
In a preferred embodiment of the present invention, the first predictive model comprises a first network model; before the target state information is input into the first prediction model to obtain the accumulated platform revenue of the target user, the method further includes: acquiring first state information; inputting the first state information into the first network model to determine a training sample; under the condition that the data volume of the training samples is larger than a second threshold value, performing model training on the first network model based on the training samples until a preset training round number is reached; the training sample comprises the first state information, a marketing strategy corresponding to the first state information, platform feedback information corresponding to the first state information and second state information, wherein the second state information is updated state information after the marketing strategy is issued according to the first state information.
In a preferred embodiment of the present invention, the first predictive model further comprises a second network model; the model training of the first network model based on the training samples includes: inputting the first state information into the first network model to obtain first platform benefits; inputting the second state information into the second network model to obtain a second platform benefit; determining a third platform benefit according to the second platform benefit, the marketing strategy corresponding to the second state information and the platform feedback information corresponding to the second state information; updating the first platform gain to the third platform gain, and performing model training on the first network model based on the first state information and the third platform gain.
In a preferred embodiment of the present invention, after the model training of the first network model based on the training samples, the method further includes: copying the model parameters of the second network model into the model parameters of the first network model under the condition of meeting preset conditions; the preset condition includes any one of: reaching the preset time and reaching the preset number of training rounds.
In a preferred embodiment of the present invention, after predicting the accumulated platform revenue of the target user under different marketing strategies according to the target state information, the method further comprises: inputting the target state information and the marketing strategies into a second prediction model to predict the completion probability of the target user under different marketing strategies; the determining the maximum platform profit brought by the target user under the preset input cost according to the accumulated platform profit comprises the following steps: and determining the maximum platform benefit brought by the target user under the preset input cost according to the accumulated platform benefit and the order completion probability.
In a preferred embodiment of the present invention, the determining the maximum platform profit brought by the target user at a preset investment cost according to the accumulated platform profit and the singleton completion probability includes: by marketing models
Figure BDA0003369364750000031
Determining the maximum platform gain brought by the target user under the preset investment cost; the marketing model satisfies the following conditions:
Figure BDA0003369364750000032
Figure BDA0003369364750000033
xij0 or 1; wherein N is the total number of people, M is the total number of marketing strategies, and xijIs to show toi individuals issue jth marketing strategies, C is the preset input cost, couponijFor the investment cost of marketing strategies, probijIs the singleton probability.
In a preferred embodiment of the present invention, the target status information includes at least one of: historical user behavior information, user population attribute information and user future value information; the marketing strategy includes at least one of: issuing a voucher, sending a push message and an empty action; the platform feedback information is reward information determined according to the fact whether the order is finished or not under different marketing strategies.
In a second aspect, the present invention provides a marketing strategy determination apparatus, including: the device comprises an acquisition unit, a prediction unit and a strategy issuing unit; the acquisition unit is used for acquiring target state information of a target user; the prediction unit is used for predicting the accumulated platform income of the target user under different marketing strategies according to the target state information; and the strategy issuing unit is used for determining the maximum platform income brought by the target user under the preset input cost according to the accumulated platform income and determining the marketing strategy issued to the target user based on the maximum platform income.
In a preferred embodiment of the present invention, the prediction unit is specifically configured to: and inputting the target state information into a first prediction model to obtain the accumulated platform income of the target user.
In a preferred embodiment of the present invention, the prediction unit is specifically configured to: inputting the target state information into the first prediction model to obtain M accumulated platform profits of the target user under M marketing strategies; under the condition that the selection probability is larger than a first threshold value, selecting the accumulated platform profit with the maximum profit value from the M accumulated platform profits as an output value of the first prediction model; and under the condition that the selection probability is not greater than the first threshold, randomly selecting one accumulated platform profit from the M accumulated platform profits as an output value of the first prediction model, wherein the selection probability is a randomly generated probability value and is used for determining a mode for selecting one accumulated platform profit from the M accumulated platform profits, and M is an integer greater than 0.
In a preferred embodiment of the present invention, the first predictive model comprises a first network model; the acquiring unit is further used for acquiring first state information; the prediction unit is further configured to input the first state information into the first network model to determine a training sample; under the condition that the data volume of the training samples is larger than a second threshold value, performing model training on the first network model based on the training samples until a preset training round number is reached; the training sample comprises the first state information, a marketing strategy corresponding to the first state information, platform feedback information corresponding to the first state information and second state information, wherein the second state information is updated state information after the marketing strategy is issued according to the first state information.
In a preferred embodiment of the present invention, the first predictive model further comprises a second network model; the prediction unit is specifically configured to input the first state information into the first network model to obtain a first platform gain; inputting the second state information into the second network model to obtain a second platform benefit; determining a third platform benefit according to the second platform benefit, the marketing strategy corresponding to the second state information and the platform feedback information corresponding to the second state information; updating the first platform gain to the third platform gain, and performing model training on the first network model based on the first state information and the third platform gain.
In a preferred embodiment of the present invention, the prediction unit is further configured to input the target state information and the marketing strategy into a second prediction model to predict the probability of completion of the target user under different marketing strategies; the policy issuing unit is specifically configured to determine, according to the accumulated platform revenue and the order completion probability, a maximum platform revenue brought by the target user at a preset investment cost.
In a preferred embodiment of the present invention, the prediction unit is further configured to copy the model parameters of the second network model into the model parameters of the first network model when a preset condition is met; the preset condition includes any one of: reaching the preset time and reaching the preset number of training rounds.
In a preferred embodiment of the invention, the policy issuing unit is particularly adapted to pass through a marketing model
Figure BDA0003369364750000051
Determining the maximum platform gain brought by the target user under the preset investment cost; the marketing model satisfies the following conditions:
Figure BDA0003369364750000052
Figure BDA0003369364750000053
xij0 or 1; wherein N is the total number of people, M is the total number of marketing strategies, and xijIndicating to issue the jth marketing strategy to the ith person, wherein C is the preset input cost and couponijFor the investment cost of marketing strategies, probijIs the singleton probability.
In a preferred embodiment of the present invention, the target status information includes at least one of: historical user behavior information, user population attribute information and user future value information; the marketing strategy includes at least one of: issuing a voucher, sending a push message and an empty action; the platform feedback information is reward information determined according to the fact whether the order is finished or not under different marketing strategies.
In a third aspect, the present invention provides a marketing strategy determination apparatus comprising a memory and a processor. The memory is used for storing computer execution instructions, and the processor is connected with the memory through a bus. When the marketing strategy determination device is operating, the processor executes computer-executable instructions stored in the memory to cause the marketing strategy determination device to perform the marketing strategy determination method provided by the first aspect and its various possible implementations.
In a fourth aspect, a computer-readable storage medium is provided, which includes computer-executable instructions, which, when executed on a computer, cause a marketing strategy determination apparatus to perform the marketing strategy determination method provided by the first aspect and its various possible implementations.
In a fifth aspect, a computer program product is provided, which comprises computer instructions that, when run on a computer, cause a marketing strategy determination apparatus to perform the marketing strategy determination methods provided by the first aspect and its various possible implementations.
It should be noted that all or part of the computer instructions may be stored on the computer readable storage medium. The computer readable storage medium may be packaged with the processor executing the marketing strategy determination device, or may be packaged separately from the processor executing the marketing strategy determination device, which is not limited in this embodiment of the present invention.
For the description of the second, third, fourth and fifth aspects of the present invention, reference may be made to the detailed description of the first aspect; in addition, for the beneficial effects described in the second aspect, the third aspect, the fourth aspect and the fifth aspect, reference may be made to the beneficial effect analysis of the first aspect, and details are not repeated here.
The conception, the specific structure and the technical effects of the present invention will be further described with reference to the accompanying drawings to fully understand the objects, the features and the effects of the present invention.
Drawings
Fig. 1 is a diagram of a reinforcement learning framework of a marketing strategy determination method according to an embodiment of the present invention;
FIG. 2 is a flow chart of a marketing strategy determination method according to an embodiment of the present invention;
FIG. 3 is a user state transition diagram provided by an embodiment of the present invention;
FIG. 4 is a diagram of a fully-connected neural network architecture for a first predictive model provided by an embodiment of the present invention;
FIG. 5 is a diagram of interaction processing of a first network model and a second network model provided by an embodiment of the invention;
fig. 6 is a schematic structural diagram of a marketing strategy determination device according to an embodiment of the present invention;
fig. 7 is a second schematic structural diagram of a marketing strategy determination device according to an embodiment of the present invention.
Detailed Description
The embodiments of the present invention are described below with reference to specific embodiments, and other advantages and effects of the present invention will be easily understood by those skilled in the art from the disclosure of the present specification. The invention is capable of other and different embodiments and of being practiced or of being carried out in various ways, and its several details are capable of modification in various respects, all without departing from the spirit and scope of the present invention. It is to be noted that the features in the following embodiments and examples may be combined with each other without conflict.
It should be noted that, in the embodiments of the present invention, words such as "exemplary" or "for example" are used to indicate examples, illustrations or explanations. Any embodiment or design described as "exemplary" or "e.g.," an embodiment of the present invention is not necessarily to be construed as preferred or advantageous over other embodiments or designs. Rather, use of the word "exemplary" or "such as" is intended to present concepts related in a concrete fashion.
It should be noted that, in this document, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising an … …" does not exclude the presence of other like elements in a process, method, article, or apparatus that comprises the element. Further, it should be noted that the scope of the methods and apparatus of embodiments of the present invention is not limited to performing functions in the order illustrated or discussed, but may include performing functions in a substantially simultaneous manner or in a reverse order based on the functions involved, e.g., the methods described may be performed in an order different than that described, and various steps may be added, omitted, or combined. In addition, features described with reference to certain examples may be combined in other examples.
For the convenience of clearly describing the technical solutions of the embodiments of the present invention, in the embodiments of the present invention, the words "first", "second", and the like are used for distinguishing the same items or similar items with basically the same functions and actions, and those skilled in the art can understand that the words "first", "second", and the like are not limited in number or execution order.
Some exemplary embodiments of the invention have been described for illustrative purposes, and it is to be understood that the invention may be practiced otherwise than as specifically described.
The above-described implementations are described in detail below with reference to specific embodiments and the accompanying drawings.
Fig. 1 is a diagram of a reinforcement learning framework of a marketing strategy determination method according to an embodiment of the present invention. The marketing platform can acquire the state information of the user, then a certain marketing strategy is adopted for the user according to the state information, and then platform feedback information, namely rewards, is issued to the one-way marketing platform according to whether the user finishes the marketing strategy or not. So as to improve the marketing mechanism of the marketing platform.
As shown in fig. 2, an embodiment of the present invention provides a marketing strategy determination method, which may be applied to a marketing strategy determination apparatus. The marketing strategy determination device can be a component, an integrated circuit or a chip in the terminal, a mobile electronic device such as a notebook computer or a non-mobile electronic device such as a server. The marketing strategy determination method may include: S101-S103:
s101, the marketing strategy determining device obtains target state information of a target user.
Optionally, the target status information may include at least one of: the user historical behavior information, the user demographic attribute information and the user future value information. The user historical behavior information may include the amount of orders completed, the amount of orders issued, the amount of orders found, the number of times of opening the target application, the registration duration of the target application, the duration of the latest order completion until the present, and the like of the user within a preset historical period. The user demographic attribute information may include gender, age, frequent departure address, and the like. The user future value information can be the income which is predicted according to the user historical behavior information and can be brought to the marketing platform of the target application in the future.
Optionally, as shown in fig. 3, the user of the target application may include a new user, a second new user, an active user, and an attrition user according to the user lifecycle partition. The target user may be a user at any stage in the life cycle.
S102, predicting the accumulated platform income of the target user under different marketing strategies according to the target state information by the marketing strategy determining device.
Optionally, the marketing strategy may include at least one of: issuing vouchers, sending push messages and null actions. The voucher with different face value can represent different marketing strategies, the push message with different contents can represent different marketing strategies, and the null action represents that no marketing operation is taken.
Optionally, the marketing strategy determining device may input the target state information into the first prediction model to obtain the accumulated platform revenue of the target user.
Illustratively, as shown in fig. 4, the fully connected neural network structure of the first prediction model is shown, wherein the input is the state information of the user, i.e. the state characteristics of the user, and the output is the accumulated platform profit obtained by different marketing strategies in the state.
Optionally, the marketing strategy determining device may input the target state information into the first prediction model to obtain M accumulated platform profits of the target user under M marketing strategies; the marketing strategy determination means may then randomly generate a selection probability, which is a randomly generated probability value after obtaining the M cumulative platform revenues, that may be used to determine a manner of selecting a cumulative platform revenue from the M cumulative platform revenues. In a case where the selection probability is greater than the first threshold, the marketing strategy determination means may select, as an output value of the first prediction model, an accumulated platform profit having a largest profit value from the M accumulated platform profits; in the case where the selection probability is not greater than the first threshold value, the marketing strategy determination means may randomly select one accumulated platform profit from M accumulated platform profits as the output value of the first prediction model, where M is an integer greater than 0.
Illustratively, M is 5 and the first threshold is 0.9. After the marketing strategy determination device obtains 5 accumulated platform gains, the marketing strategy determination device can randomly generate a selection probability between 0 and 1, and if the selection probability is greater than 0.9, the marketing strategy determination device can select the accumulated platform gain with the maximum gain value from the 5 accumulated platform gains as an output value of the first prediction model; if the selection probability is not greater than 0.9, the marketing strategy determination means may randomly select one accumulated platform profit from the 5 accumulated platform profits as an output value of the first prediction model.
Based on the scheme, the output value of the first prediction model can be the accumulated platform profit with the maximum profit value or the accumulated platform profit selected randomly, so that the balance between model learning exploration and greedy can be strengthened.
Optionally, the first prediction model includes a first network model; the marketing strategy determination means may train the first network model before inputting the target state information into the first predictive model to obtain the cumulative platform revenue for the target user. The specific training process comprises the following steps: the marketing strategy determination device can acquire first state information of the user; and inputting the first state information into the first network model to determine a training sample, where the training sample may include the first state information, a marketing strategy corresponding to the first state information, platform feedback information corresponding to the first state information, and second state information, and the second state information is state information updated after a marketing strategy is issued according to the first state information. For example, if the current state is t steps, the first state information may be represented as stMarketing strategy corresponding to the first state informationCan be represented as atThe platform feedback information corresponding to the first state information may be denoted as rt+1The second state information may be represented as st+1I.e. the training sample is(s)t，at，rt+1，st+1). The marketing strategy corresponding to the first state information is a marketing strategy adopted by the marketing platform under the condition that the state information of the user is the first state information; the platform feedback information corresponding to the first state information is feedback information obtained by the marketing platform after the marketing strategy is adopted for the user under the first state information, and the platform feedback information is reward information determined according to the fact whether the user is finished under different marketing strategies. Then, under the condition that the data volume of the training samples in the storage space is larger than a second threshold, model training can be performed on the first network model based on the training samples until a preset training round number is reached or a loss function tends to be stable.
Optionally, as shown in fig. 5, the first prediction model may further include a second network model; marketing strategy determination device based on training samples(s)t，at，rt+1，st+1) Performing model training on the first network model, which may specifically include: the first state information stInputting the first network model to obtain a first platform profit Q1; the second state information st+1Inputting the second network model to obtain a second platform profit Q2; according to the second platform profit Q2 and the marketing strategy a corresponding to the second state informationtPlatform feedback information r corresponding to the second state informationt+1Determining a third platform gain; updating the first platform profit to the third platform profit, and performing model training on the first network model based on the first state information and the third platform profit until a preset training round number is reached or a loss function tends to be stable.
Optionally, the calculation model for accumulating platform revenue in the first network model may be:
Figure BDA0003369364750000101
wherein Q represents the accumulated platform revenue, α represents the learning rate, rt+1Is shown in state stAdopting marketing strategy atThe instant prize earned. Gamma represents a discount factor, and the value range of gamma is 0-1.
Optionally, the platform feedback information may be a reward brought by a change of a user behavior after the marketing platform adopts a marketing strategy, for example, a 5-generation voucher is issued to a user, and the system gives the marketing platform a certain feedback reward when the user is finished. The platform feedback information may include the following levels: r1, finishing the idle action; r2, finishing the order after sending the push message; r1, finishing the bill after using the voucher; r1, checking the outstanding coupon; r1, checking the push message is not finished; r1, unchecked voucher unchecked push message and outstanding.
Optionally, with continued reference to fig. 5, after performing model training on the first network model based on the training samples, the marketing strategy determination device may further copy the model parameters of the second network model to the model parameters of the first network model when a preset condition is met; the preset condition includes any one of: reaching the preset time and reaching the preset number of training rounds.
S103, the marketing strategy determining device determines the maximum platform income brought by the target user under the preset input cost according to the accumulated platform income, and determines the marketing strategy issued to the target user based on the maximum platform income.
Optionally, after predicting the accumulated platform revenue of the target user under different marketing strategies according to the target state information, the marketing strategy determining device may further input the target state information and the marketing strategies into the second prediction model to predict the probability of the target user completing the single under different marketing strategies. Then, the marketing strategy determination means may determine the maximum platform profit that the target user brings at the preset investment cost, according to the accumulated platform profit and the completion probability. The second predictive model may be a conventional memory model.
Alternatively to this, the first and second parts may,the marketing strategy determining means may pass through a marketing model
Figure BDA0003369364750000111
Determining the maximum platform gain brought by the target user under the preset investment cost; the marketing model satisfies the following conditions:
Figure BDA0003369364750000112
xij0 or 1; wherein N is the total number of people, M is the total number of marketing strategies, and xijIndicating to issue the jth marketing strategy to the ith person, wherein C is the preset input cost and couponijFor the investment cost of marketing strategies, probijIs the singleton probability. Then, the marketing strategy determination means may determine the marketing strategy to be delivered to the target user based on the maximum platform profit, and deliver the determined marketing strategy to the target user.
In the embodiment of the invention, the maximum platform profit brought by the target user under the preset input cost can be determined according to the accumulated platform profit of the target user under different marketing strategies, so that the marketing strategy issued to the target user can be determined based on the maximum platform profit, and the maximum platform profit can be ensured to be realized under the preset input cost.
The scheme provided by the embodiment of the application is mainly introduced from the perspective of a method. To implement the above functions, it includes hardware structures and/or software modules for performing the respective functions. Those of skill in the art will readily appreciate that the various illustrative elements and algorithm steps described in connection with the embodiments disclosed herein may be implemented as hardware or combinations of hardware and computer software. Whether a function is performed as hardware or computer software drives hardware depends upon the particular application and design constraints imposed on the solution. Skilled artisans may implement the described functionality in varying ways for each particular application, but such implementation decisions should not be interpreted as causing a departure from the scope of the present application.
In the marketing strategy determination method provided by the embodiment of the application, the executive subject may be a marketing strategy determination device, or a control module used for determining a marketing strategy in the marketing strategy determination device. In the embodiment of the present application, a marketing strategy determining apparatus executing a marketing strategy determining method is taken as an example, and the marketing strategy determining apparatus provided in the embodiment of the present application is described.
It should be noted that, in the embodiment of the present application, the marketing strategy determination device may be divided into the functional modules according to the above method examples, for example, each functional module may be divided corresponding to each function, or two or more functions may be integrated into one processing module. The integrated module can be realized in a hardware mode, and can also be realized in a software functional module mode. Optionally, the division of the modules in the embodiment of the present application is schematic, and is only a logic function division, and there may be another division manner in actual implementation.
As shown in fig. 6, an embodiment of the present application provides a marketing strategy determination apparatus 600. The marketing strategy determining apparatus 600 includes: an acquisition unit 601, a prediction unit 602, and a policy issuing unit 603; the acquiring unit 601 is configured to acquire target status information of a target user; the prediction unit 602 is configured to predict, according to the target state information, accumulated platform revenue of the target user under different marketing strategies; the policy issuing unit 603 is configured to determine, according to the accumulated platform revenue, a maximum platform revenue brought by the target user at a preset investment cost, and determine, based on the maximum platform revenue, a marketing policy issued to the target user.
Optionally, the prediction unit 602 is specifically configured to: and inputting the target state information into a first prediction model to obtain the accumulated platform income of the target user.
Optionally, the prediction unit 602 is specifically configured to: inputting the target state information into the first prediction model to obtain M accumulated platform profits of the target user under M marketing strategies; under the condition that the selection probability is larger than a first threshold value, selecting the accumulated platform profit with the maximum profit value from the M accumulated platform profits as an output value of the first prediction model; and under the condition that the selection probability is not greater than the first threshold, randomly selecting one accumulated platform profit from the M accumulated platform profits as an output value of the first prediction model, wherein the selection probability is a randomly generated probability value and is used for determining a mode for selecting one accumulated platform profit from the M accumulated platform profits, and M is an integer greater than 0.
Optionally, the first prediction model comprises a first network model; the acquiring unit 601 is further configured to acquire first state information; the prediction unit 602 is further configured to input the first state information into the first network model to determine a training sample; under the condition that the data volume of the training samples is larger than a second threshold value, performing model training on the first network model based on the training samples until a preset training round number is reached; the training sample comprises the first state information, a marketing strategy corresponding to the first state information, platform feedback information corresponding to the first state information and second state information, wherein the second state information is updated state information after the marketing strategy is issued according to the first state information.
Optionally, the first prediction model further comprises a second network model; the predicting unit 602 is specifically configured to input the first state information into the first network model to obtain a first platform benefit; inputting the second state information into the second network model to obtain a second platform benefit; determining a third platform benefit according to the second platform benefit, the marketing strategy corresponding to the second state information and the platform feedback information corresponding to the second state information; updating the first platform gain to the third platform gain, and performing model training on the first network model based on the first state information and the third platform gain.
Optionally, the predicting unit 602 is further configured to copy the model parameters of the second network model into the model parameters of the first network model when a preset condition is met; the preset condition includes any one of: reaching the preset time and reaching the preset number of training rounds.
Optionally, the predicting unit 602 is further configured to input the target state information and the marketing strategy into a second prediction model to predict the probability of completing the target user under different marketing strategies; the policy issuing unit 603 is specifically configured to determine, according to the accumulated platform revenue and the order completion probability, a maximum platform revenue brought by the target user at a preset investment cost.
Optionally, the policy issuing unit 603 is specifically configured to pass through a marketing model
Figure BDA0003369364750000131
Determining the maximum platform gain brought by the target user under the preset investment cost; the marketing model satisfies the following conditions:
Figure BDA0003369364750000132
xij0 or 1; wherein N is the total number of people, M is the total number of marketing strategies, and xijIndicating to issue the jth marketing strategy to the ith person, wherein C is the preset input cost and couponijFor the investment cost of marketing strategies, probijIs the singleton probability.
Optionally, the target status information includes at least one of: historical user behavior information, user population attribute information and user future value information; the marketing strategy includes at least one of: issuing a voucher, sending a push message and an empty action; the platform feedback information is reward information determined according to the fact whether the order is finished or not under different marketing strategies.
Of course, the marketing strategy determination device 600 provided by the embodiment of the present application includes, but is not limited to, the above units.
According to the marketing strategy determining device provided by the embodiment of the invention, the maximum platform profit brought by the target user under the preset input cost can be determined according to the accumulated platform profit and the order completion probability of the target user under different marketing strategies, so that the marketing strategy issued to the target user can be determined based on the maximum platform profit, and the maximum platform profit can be ensured to be realized under the preset input cost.
The embodiment of the present application further provides a marketing strategy determination device as shown in fig. 7, which includes a processor 11, a memory 12, a communication interface 13, and a bus 14. The processor 11, the memory 12 and the communication interface 13 may be connected by a bus 14.
The processor 11 is a control center of the marketing strategy determination device, and may be a single processor or a collective term for a plurality of processing elements. For example, the processor 11 may be a general-purpose Central Processing Unit (CPU), or may be another general-purpose processor. Wherein a general purpose processor may be a microprocessor or any conventional processor or the like.
For one embodiment, processor 11 may include one or more CPUs, such as CPU 0 and CPU 1 shown in FIG. 7.
The memory 12 may be, but is not limited to, a read-only memory (ROM) or other type of static storage device that may store static information and instructions, a Random Access Memory (RAM) or other type of dynamic storage device that may store information and instructions, an electrically erasable programmable read-only memory (EEPROM), a magnetic disk storage medium or other magnetic storage device, or any other medium that can be used to carry or store desired program code in the form of instructions or data structures and that can be accessed by a computer.
In a possible implementation, the memory 12 may be present separately from the processor 11, and the memory 12 may be connected to the processor 11 via a bus 14 for storing instructions or program code. The deployment method of the service function chain provided by the embodiment of the present application can be implemented when the processor 11 calls and executes the instructions or program codes stored in the memory 12.
In another possible implementation, the memory 12 may also be integrated with the processor 11.
And a communication interface 13 for connecting with other devices through a communication network. The communication network may be an ethernet network, a radio access network, a Wireless Local Area Network (WLAN), or the like. The communication interface 13 may comprise a receiving unit for receiving data and a transmitting unit for transmitting data.
The bus 14 may be an Industry Standard Architecture (ISA) bus, a Peripheral Component Interconnect (PCI) bus, an Extended ISA (EISA) bus, or the like. The bus may be divided into an address bus, a data bus, a control bus, etc. For ease of illustration, only one thick line is shown in FIG. 7, but this is not intended to represent only one bus or type of bus.
It is to be noted that the structure shown in fig. 7 does not constitute a limitation of the marketing strategy determination means. In addition to the components shown in fig. 7, the marketing strategy determination means may include more or fewer components than shown, or some components may be combined, or a different arrangement of components.
Embodiments of the present invention also provide a computer-readable storage medium, which includes computer-executable instructions. When the computer executes the instructions to run on the computer, the computer executes the steps executed by the marketing strategy determination device in the marketing strategy determination method provided by the above embodiment.
The embodiment of the present invention further provides a computer program product, which can be directly loaded into the memory and contains software codes, and after the computer program product is loaded and executed by the computer, the marketing strategy determining method provided by the above embodiment can be implemented, and the steps executed by the marketing strategy determining apparatus are executed.
Through the above description of the embodiments, those skilled in the art will clearly understand that the method of the above embodiments can be implemented by software plus a necessary general hardware platform, and certainly can also be implemented by hardware, but in many cases, the former is a better implementation manner. Based on such understanding, the technical solutions of the present invention may be embodied in the form of a software product, which is stored in a storage medium (e.g., ROM/RAM, magnetic disk, optical disk) and includes instructions for causing a terminal to execute the methods according to the embodiments of the present invention.
The foregoing embodiments are merely illustrative of the principles and utilities of the present invention and are not intended to limit the invention. Any person skilled in the art can modify or change the above-mentioned embodiments without departing from the spirit and scope of the present invention. Accordingly, it is intended that all equivalent modifications or changes which can be made by those skilled in the art without departing from the spirit and technical spirit of the present invention be covered by the claims of the present invention.

Claims (12)

1. A marketing strategy determination method, comprising:
acquiring target state information of a target user;
predicting the accumulated platform income of the target user under different marketing strategies according to the target state information;
and determining the maximum platform income brought by the target user under the preset input cost according to the accumulated platform income, and determining a marketing strategy issued to the target user based on the maximum platform income.
2. The marketing strategy of claim 1, wherein predicting the cumulative platform revenue for the targeted user under different marketing strategies based on the targeted state information comprises:
and inputting the target state information into a first prediction model to obtain the accumulated platform income of the target user.
3. The marketing strategy determination method of claim 2, wherein said entering the target status information into a first predictive model yields a cumulative platform revenue for the target user, comprising:
inputting the target state information into the first prediction model to obtain M accumulated platform profits of the target user under M marketing strategies;
under the condition that the selection probability is larger than a first threshold value, selecting the accumulated platform profit with the maximum profit value from the M accumulated platform profits as an output value of the first prediction model;
randomly selecting one accumulated platform gain from the M accumulated platform gains as an output value of the first prediction model under the condition that the selection probability is not greater than the first threshold;
the selection probability is a randomly generated probability value and is used for determining a mode of selecting one accumulated platform profit from the M accumulated platform profits, and M is an integer larger than 0.
4. The marketing strategy determination method of claim 3, wherein the first predictive model comprises a first network model; before the target state information is input into the first prediction model to obtain the accumulated platform revenue of the target user, the method further includes:
acquiring first state information;
inputting the first state information into the first network model to determine a training sample;
under the condition that the data volume of the training samples is larger than a second threshold value, performing model training on the first network model based on the training samples until a preset training round number is reached;
the training sample comprises the first state information, a marketing strategy corresponding to the first state information, platform feedback information corresponding to the first state information and second state information, wherein the second state information is updated state information after the marketing strategy is issued according to the first state information.
5. The marketing strategy determination method of claim 4, wherein the first predictive model further comprises a second network model; the model training of the first network model based on the training samples includes:
inputting the first state information into the first network model to obtain first platform benefits;
inputting the second state information into the second network model to obtain a second platform benefit;
determining a third platform benefit according to the second platform benefit, the marketing strategy corresponding to the second state information and the platform feedback information corresponding to the second state information;
updating the first platform gain to the third platform gain, and performing model training on the first network model based on the first state information and the third platform gain.
6. The marketing strategy determination method of claim 5, wherein after the model training of the first network model based on the training samples, the method further comprises:
copying the model parameters of the second network model into the model parameters of the first network model under the condition of meeting preset conditions; the preset condition includes any one of: reaching the preset time and reaching the preset number of training rounds.
7. The marketing strategy determination method of any of claims 1-6, wherein after predicting the cumulative platform revenue for the targeted user under different marketing strategies based on the targeted state information, the method further comprises:
inputting the target state information and the marketing strategies into a second prediction model to predict the completion probability of the target user under different marketing strategies;
the determining the maximum platform profit brought by the target user under the preset input cost according to the accumulated platform profit comprises the following steps:
and determining the maximum platform benefit brought by the target user under the preset input cost according to the accumulated platform benefit and the order completion probability.
8. The marketing strategy of claim 7, wherein said determining a maximum platform revenue for the target user at a preset investment cost based on the cumulative platform revenue and the probability of completion comprises:
by marketing models
Figure FDA0003369364740000031
Determining the maximum platform gain brought by the target user under the preset investment cost; the marketing model satisfies the following conditions:
Figure FDA0003369364740000032
Figure FDA0003369364740000033
xij0 or 1;
wherein N is the total number of people, M is the total number of marketing strategies, and xijIndicating to issue the jth marketing strategy to the ith person, wherein C is the preset input cost and couponijFor the investment cost of marketing strategies, probijIs the singleton probability.
9. The marketing strategy determination method of any of claims 4-6, wherein the target status information comprises at least one of: historical user behavior information, user population attribute information and user future value information; the marketing strategy includes at least one of: issuing a voucher, sending a push message and an empty action; the platform feedback information is reward information determined according to the fact whether the order is finished or not under different marketing strategies.
10. A marketing strategy determination apparatus, comprising: the device comprises an acquisition unit, a prediction unit and a strategy issuing unit;
the acquisition unit is used for acquiring target state information of a target user;
the prediction unit is used for predicting the accumulated platform income of the target user under different marketing strategies according to the target state information;
and the strategy issuing unit is used for determining the maximum platform income brought by the target user under the preset input cost according to the accumulated platform income and determining the marketing strategy issued to the target user based on the maximum platform income.
11. A marketing strategy determination device comprising a memory and a processor; the memory is used for storing computer execution instructions, and the processor is connected with the memory through a bus;
the processor executes the computer-executable instructions stored by the memory to cause the marketing strategies determination device to perform the marketing strategies determination method of any of claims 1-9 when the marketing strategies determination device is operating.
12. A computer-readable storage medium comprising computer-executable instructions that, when executed on a computer, cause the computer to perform the marketing strategy determination method of any of claims 1-9.
CN202111392823.XA 2021-11-23 2021-11-23 Marketing strategy determination method and device and computer storage medium Pending CN114078031A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202111392823.XA CN114078031A (en) 2021-11-23 2021-11-23 Marketing strategy determination method and device and computer storage medium

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202111392823.XA CN114078031A (en) 2021-11-23 2021-11-23 Marketing strategy determination method and device and computer storage medium

Publications (1)

Publication Number Publication Date
CN114078031A true CN114078031A (en) 2022-02-22

Family

ID=80284790

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202111392823.XA Pending CN114078031A (en) 2021-11-23 2021-11-23 Marketing strategy determination method and device and computer storage medium

Country Status (1)

Country Link
CN (1) CN114078031A (en)

Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
WO2012103290A1 (en) * 2011-01-26 2012-08-02 Google Inc. Dynamic predictive modeling platform
CN110675183A (en) * 2019-08-30 2020-01-10 阿里巴巴集团控股有限公司 Marketing object determining method, marketing promotion method and related device
CN110914856A (en) * 2018-07-10 2020-03-24 北京嘀嘀无限科技发展有限公司 System and method for determining marketing strategies for online-to-offline services
CN112669084A (en) * 2020-12-31 2021-04-16 深圳前海微众银行股份有限公司 Policy determination method, device and computer-readable storage medium

Patent Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
WO2012103290A1 (en) * 2011-01-26 2012-08-02 Google Inc. Dynamic predictive modeling platform
CN110914856A (en) * 2018-07-10 2020-03-24 北京嘀嘀无限科技发展有限公司 System and method for determining marketing strategies for online-to-offline services
CN110675183A (en) * 2019-08-30 2020-01-10 阿里巴巴集团控股有限公司 Marketing object determining method, marketing promotion method and related device
CN112669084A (en) * 2020-12-31 2021-04-16 深圳前海微众银行股份有限公司 Policy determination method, device and computer-readable storage medium

Similar Documents

Publication Publication Date Title
Hancock et al. Decision field theory: Improvements to current methodology and comparisons with standard choice modelling techniques
Berbeglia et al. Dynamic pickup and delivery problems
CN111242752B (en) Method and system for determining recommended object based on multi-task prediction
Li et al. Dynamic booking control for car rental revenue management: A decomposition approach
US20150371252A1 (en) Portfolio modeling and campaign optimization
US20150100526A1 (en) Online temporal difference learning from incomplete customer interaction histories
US11861643B2 (en) Reinforcement learning method for driver incentives: generative adversarial network for driver-system interactions
KR102453582B1 (en) Method and system for ai demand forcasting
CN110020662B (en) Training method and device for user classification model
CN110543947B (en) Rewarding resource issuing method and device based on reinforcement learning model
JP2022509384A (en) Reinforcement learning system and reinforcement learning method for inventory management and optimization
CN111292122A (en) Method and apparatus for facilitating user to perform target behavior for target object
Branchi et al. Learning to act: a reinforcement learning approach to recommend the best next activities
JP2001357189A (en) Decision-making support device for market participation
US8255316B2 (en) Integrated business decision-making system and method
KR102554135B1 (en) Method for providing product discount coupons based on store demand forecasting and system thereof
CN111445032B (en) Method and device for decision processing by using business decision model
CN116468109B (en) Training method, using method and related device of prediction model
CN112819507A (en) Service pushing method and device, electronic equipment and readable storage medium
CN114078031A (en) Marketing strategy determination method and device and computer storage medium
CN116611499A (en) Method and apparatus for training reinforcement learning system for automatic bidding
Michalewicz et al. Parameter control in practice
CN115049433A (en) Model training method and device, storage medium and electronic equipment
US20060059030A1 (en) Method and decision support system for optimal allocation of expendable resources in internet marketing with resource-dependant effectiveness and use of a-posteriori information
Horner et al. Increasing driver flexibility through personalized menus and incentives in ridesharing and crowdsourced delivery platforms

Legal Events

Date Code Title Description
PB01 Publication
PB01 Publication
SE01 Entry into force of request for substantive examination
SE01 Entry into force of request for substantive examination