CN109598542B - Marketing equity throwing method and device and electronic equipment - Google Patents
Marketing equity throwing method and device and electronic equipment Download PDFInfo
- Publication number
- CN109598542B CN109598542B CN201811381203.4A CN201811381203A CN109598542B CN 109598542 B CN109598542 B CN 109598542B CN 201811381203 A CN201811381203 A CN 201811381203A CN 109598542 B CN109598542 B CN 109598542B
- Authority
- CN
- China
- Prior art keywords
- marketing
- user
- target
- rights
- event
- 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.)
- Active
Links
- 238000000034 method Methods 0.000 title claims abstract description 45
- 230000008901 benefit Effects 0.000 claims abstract description 118
- 238000012549 training Methods 0.000 claims description 58
- 239000013598 vector Substances 0.000 claims description 17
- 238000012360 testing method Methods 0.000 claims description 16
- 238000004590 computer program Methods 0.000 claims description 9
- 238000002716 delivery method Methods 0.000 claims description 3
- 230000000694 effects Effects 0.000 description 7
- 238000012545 processing Methods 0.000 description 6
- 238000010586 diagram Methods 0.000 description 5
- 238000011156 evaluation Methods 0.000 description 5
- 230000006870 function Effects 0.000 description 5
- 230000008569 process Effects 0.000 description 5
- 238000013528 artificial neural network Methods 0.000 description 3
- 230000005540 biological transmission Effects 0.000 description 2
- 230000015572 biosynthetic process Effects 0.000 description 2
- 238000013135 deep learning Methods 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 230000002093 peripheral effect Effects 0.000 description 2
- 238000003491 array Methods 0.000 description 1
- 230000006399 behavior Effects 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 239000002131 composite material Substances 0.000 description 1
- 238000010276 construction Methods 0.000 description 1
- 230000001419 dependent effect Effects 0.000 description 1
- 230000008451 emotion Effects 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 238000005065 mining Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 238000011022 operating instruction Methods 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 238000005457 optimization Methods 0.000 description 1
- 230000000750 progressive effect Effects 0.000 description 1
- 230000009467 reduction Effects 0.000 description 1
- 230000003068 static effect Effects 0.000 description 1
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
- 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
- G06Q30/0206—Price or cost determination based on market factors
Landscapes
- Business, Economics & Management (AREA)
- Strategic Management (AREA)
- Engineering & Computer Science (AREA)
- Accounting & Taxation (AREA)
- Development Economics (AREA)
- Finance (AREA)
- Entrepreneurship & Innovation (AREA)
- Game Theory and Decision Science (AREA)
- Data Mining & Analysis (AREA)
- Economics (AREA)
- Marketing (AREA)
- Physics & Mathematics (AREA)
- General Business, Economics & Management (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The embodiment of the application relates to a marketing benefit releasing method and device and electronic equipment. The putting method comprises the following steps: grouping the marketing interests based on the number of target user groups of the marketing interests, wherein each user of the target user groups corresponds to one marketing interest group, and any two marketing interests in the marketing interest groups with the marketing interests greater than 1 are mutually exclusive; selecting a target marketing benefit matched with the user from a marketing benefit group corresponding to each user according to a strategy of maximum total branching rate of the target user group based on the upper limit of marketing cost of the target user group and the predicted branching rate corresponding to each marketing benefit; and respectively throwing matched target marketing benefits to users in the target user group.
Description
Technical Field
The embodiment of the application relates to the technical field of information mining, in particular to a marketing equity throwing method, a marketing equity throwing device and electronic equipment.
Background
With the popularization of electronic commerce, online shopping has become an important consumption mode in daily life of people. To facilitate consumption, online shopping platforms typically promote marketing campaigns to users to ignite the user's consumption emotion.
At present, marketing rights are not targeted. Often, a marketing campaign is supported and engaged by only a portion of the users, resulting in less than good marketing benefits after a cost input.
Disclosure of Invention
The embodiment of the application aims to provide a method, a device and electronic equipment for releasing marketing benefits, which can release the marketing benefits with high utilization rate individually for different users on the premise of limited marketing cost, thereby realizing maximized marketing benefits.
In order to achieve the above object, the embodiment of the present application adopts the following technical scheme:
in a first aspect, an embodiment of the present application provides a method for processing an operation log, including:
grouping the marketing interests based on the number of target user groups of the marketing interests, wherein each user of the target user groups corresponds to one marketing interest group, and any two marketing interests in the marketing interest groups with the marketing interests greater than 1 are mutually exclusive;
selecting a target marketing benefit matched with the user from a marketing benefit group corresponding to each user according to a strategy of maximum total branching rate of the target user group based on the upper limit of marketing cost of the target user group and the predicted branching rate corresponding to each marketing benefit;
and respectively throwing matched target marketing benefits to users in the target user group.
In a second aspect, there is provided a processing apparatus for an operation log, including:
the grouping module is used for grouping the marketing rights based on the number of the target user groups of the marketing rights, each user of the target user groups corresponds to one marketing rights grouping, and any two marketing rights in the marketing rights grouping with the marketing rights greater than 1 are mutually exclusive;
the selection module is used for selecting a target marketing benefit matched with the user from marketing benefit groups corresponding to each user according to a strategy of maximum total branching rate of the target user group based on the upper limit of marketing cost of the target user group and the predicted branching rate corresponding to each marketing benefit;
and the delivery module is used for respectively delivering the matched target marketing rights to the users in the target user group.
In a third aspect, an electronic device is provided, comprising: a memory, a processor, and a computer program stored on the memory and executable on the processor, the computer program being executed by the processor:
grouping the marketing interests based on the number of target user groups of the marketing interests, wherein each user of the target user groups corresponds to one marketing interest group, and any two marketing interests in the marketing interest groups with the marketing interests greater than 1 are mutually exclusive;
selecting a target marketing benefit matched with the user from a marketing benefit group corresponding to each user according to a strategy of maximum total branching rate of the target user group based on the upper limit of marketing cost of the target user group and the predicted branching rate corresponding to each marketing benefit;
and respectively throwing matched target marketing benefits to users in the target user group.
In a fourth aspect, there is provided a computer readable storage medium having stored thereon a computer program which when executed by a processor performs the steps of:
grouping the marketing interests based on the number of target user groups of the marketing interests, wherein each user of the target user groups corresponds to one marketing interest group, and any two marketing interests in the marketing interest groups with the marketing interests greater than 1 are mutually exclusive;
selecting a target marketing benefit matched with the user from a marketing benefit group corresponding to each user according to a strategy of maximum total branching rate of the target user group based on the upper limit of marketing cost of the target user group and the predicted branching rate corresponding to each marketing benefit;
and respectively throwing matched target marketing benefits to users in the target user group.
The above at least one technical scheme adopted by the embodiment of the application can achieve the following beneficial effects:
in the embodiment of the application, on the premise of not exceeding the upper limit of the marketing cost of the target user group, the marketing benefits of high utilization rate are personalized put in aiming at different users, and the maximized marketing benefits are realized. Because the upper limit of the marketing cost of the target user group is used as a constraint condition of delivery, the formation of a similar linear mathematical relationship between the marketing cost and the predicted branch rate is avoided, and therefore, in practical application, the weight parameters do not need to be additionally configured for the target user group and the predicted branch rate, and the marketing cost of a marketing activity is determined, so that the marketing cost of different users can be matched with the proper marketing rights.
Drawings
In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings that are required in the embodiments or the description of the prior art will be briefly described below, and it is obvious that the drawings in the following description are only some embodiments described in the embodiments of the present application, and other drawings may be obtained according to these drawings without inventive effort to a person skilled in the art.
FIG. 1 is a flow chart of a method for delivering marketing benefits provided by an embodiment of the present application;
FIG. 2 is a schematic diagram of a scenario in which a target marketing benefit is delivered to a user according to the method for delivering a marketing benefit provided by the embodiment of the present application;
FIG. 3 is a schematic structural diagram of a support model in a method for delivering a marketing benefit according to an embodiment of the present application;
fig. 4 is a schematic logic structure diagram of a marketing benefit delivering device according to an embodiment of the present application;
fig. 5 is a schematic diagram of a hardware structure of an electronic device according to an embodiment of the present application.
Detailed Description
In order to make the objects, technical solutions and advantages of the embodiments of the present application more clear, the technical solutions of the embodiments of the present application will be clearly and completely described below with reference to specific embodiments of the present specification and corresponding drawings. It will be apparent that the described embodiments are only some, but not all, of the embodiments of the present specification. All other embodiments, which can be made by one of ordinary skill in the art without undue burden from the present disclosure, are intended to be within the scope of the embodiments of the present application.
As mentioned above, the current marketing rights are not targeted, and after the marketing campaign is promoted, a large number of users cannot generate enthusiasm, so that the marketing effect is not ideal.
To ensure that a majority of users are able to support a marketing campaign, it is easy to think of delivering high comprehensive scoring marketing rights to users. The overall score is dependent on the rate of the marketing equity (the rate of equity refers to the probability that the user uses the marketing equity) and the marketing cost of the marketing equity. In this manner, however, the utilization of the marketing equity has an approximately linear relationship with the marketing costs, which is not always true.
For example, in situations where the total cost is insufficient, the user cannot be given high value marketing rights, and then the weight of the marketing cost and the utilization rate in the composite score needs to be adjusted. In weight adjustment, marketing costs and utilization may vary drastically and do not necessarily lead to an ideal compromise.
In view of the above, the present application provides a scheme for delivering marketing rights in a nonlinear relationship from the two viewpoints of controlling marketing cost and user utilization.
In one aspect, an embodiment of the present application provides a method for delivering a marketing benefit, as shown in fig. 1, including:
step S102, marketing benefits are grouped based on the number of target user groups of the marketing benefits, each user of the target user groups corresponds to one marketing benefit group, and any two marketing benefits in the marketing benefit groups with the marketing benefits being more than 1 are mutually exclusive;
for step S102:
marketing benefits are benefits offered to users in marketing campaigns, such as cash packs, rebate packs, coupons, discount coupons, and the like, which are common in online purchases. The utilization rate determines whether the user approves the marketing rights and benefits, and the value of the marketing rights and benefits to the user can be presented.
The target user group contains the promotion object that the user is the marketing campaign. This step may determine a marketing equity group for each user of the target group of users, and the marketing equity group for each user may include marketing equities depending on marketing strategies to include all kinds of marketing equities, and may include some kinds of marketing equities.
As an exemplary introduction, assume that the target user group includes user 1, user 2, and user 3, and the marketing rights and interests of this marketing campaign are ABC.
If the number of each marketing equity is set to infinity, then the marketing equity groups of user 1, user 2, and user 3 may each include three marketing equity ABC;
if the number of each marketing right is set to be a preset value and the number of different marketing rights is the same or different, the number of marketing rights obtained by the user should not exceed the preset value.
For example, the number of marketing rights A is only two, the number of marketing rights B is only one, and the number of marketing rights C is three;
then, as one of the possible implementations, the marketing rights grouping for user 1 may include: marketing equity a, marketing equity C, the marketing equity grouping of user 2 may include: marketing equity C, the marketing equity group of user 3 may include marketing equity a, marketing equity B, marketing equity C;
or the marketing rights grouping of user 1 may include: marketing equity a and marketing equity C, the marketing equity grouping of user 2 may include: marketing equity B and marketing equity C, the marketing equity group of user 3 may include marketing equity a and marketing equity C.
Since the manner is not unique, the description is not repeated here.
Step S104, based on the upper limit of the marketing cost of the target user group and the predicted branch rate corresponding to each marketing equity, selecting the target marketing equity matched with the user from the marketing equity group corresponding to each user according to the strategy of the maximum total branch rate of the target user group.
For step S104:
each marketing benefit corresponds to a respective marketing cost, and in general, the higher the marketing cost of a marketing benefit, the greater the benefit to the user and the higher the corresponding equity. However, the marketing cost of the target user group is limited, and the step is to maximize the total utilization rate of the target user group and ensure the marketing benefit of the marketing activity for each user in the target user group on the premise that the marketing cost of the target user group is not exceeded.
Specifically, this step may be based on a packet knapsack algorithm to select matching target marketing rights for a plurality of users from a plurality of candidate marketing rights, respectively.
The packet backpack algorithm refers to a backpack that assumes N items and a capacity V. The cost of the i-th item is ci and the value is wi. The items are divided into groups, with the items in each group conflicting with each other, at most one piece. Solving which items to load into the backpack allows the sum of the costs of these items to be no more than the backpack capacity and the sum of the values to be maximized.
According to the definition, the marketing rights and interests can be used as articles (the number of the articles is infinity or a preset value) in the grouped knapsack algorithm, the marketing cost of the marketing rights and interests is used as the cost in the grouped knapsack algorithm, the predicted support rate corresponding to the marketing rights and interests is used as the price in the grouped knapsack algorithm, the upper limit of the marketing cost of the target user group is used as the knapsack capacity in the grouped knapsack algorithm, and the target marketing rights and interests corresponding to each user in the target user group are solved through the knapsack grouping algorithm.
Step S106, the matched target marketing interests are respectively put in the users in the target user group.
For step 106:
as shown in fig. 2, a targeted marketing benefit may be delivered to a user based on a delivery time decision after a delivery trigger event occurs. The delivery mode is not unique, and as an exemplary introduction, a passive delivery channel, such as a short message, a push, a card, a corner mark, a waist seal, a benefit payment mode and the like, can be used for delivering the target marketing benefits; or an active delivery channel, such as a home page screen flicking mode, can be used for delivering the target marketing benefits.
According to the method for delivering the high-count marketing benefits, the marketing benefits of the high-count utilization rate are delivered individually for different users on the premise that the marketing cost upper limit of the target user group is not exceeded, and the maximized marketing benefits are achieved. Because the upper limit of the marketing cost of the target user group is used as a constraint condition of delivery, the formation of a similar linear mathematical relationship between the marketing cost and the predicted branch rate is avoided, and therefore, in practical application, the weight parameters do not need to be additionally configured for the target user group and the predicted branch rate, and the marketing cost of a marketing activity is determined, so that the marketing cost of different users can be matched with the proper marketing rights.
The application can evaluate the branching behavior of all users on the marketing rights based on the branching data of the historical marketing events so as to obtain the predicted branching rate corresponding to the marketing rights.
As an exemplary introduction, the embodiment of the present application may construct a support model, and when executing step S104, the marketing benefits and the user portrait data of the users in the target user group may be input to a preset support model, so as to obtain the predicted support rate corresponding to the marketing benefits output by the support model.
The branch model is trained based on training sample data, wherein the training sample data can be marked historical marketing events, and the marked historical marketing events comprise user image features and marketing event features. In the training process, the user portrait features and the marketing event features are integrated to be used as feature vectors of the support model. And training the branch model through the marked training sample data to determine the branch weight of the feature vector on the marketing benefits put on the marketing event.
The predicted branch utilization rate of the marketing rights calculated by the trained branch model is related to the marketing event and the factors of the user, so that the method has higher accuracy.
The construction of the support model is described in an exemplary manner in connection with one implementation.
As shown in FIG. 3, the embodiment of the application can firstly establish a deep learning FTRL (Single-machine Single-thread running program) model, and the neural network structure schematic diagram of the model is shown in FIG. 3, and the model comprises an upper function and an embedded layer.
The embedded low-dimensional feature vector may be integrated from, but is not limited to, a user identity portrait feature, a user property portrait feature, a user credit use portrait feature, a marketing event time feature, a marketing event frequency feature, and a marketing equity feature.
The user identity portrayal feature may be user basic information such as age, gender, education, family, religion, occupation, etc.
The user property portrayal feature may be a user's financial information such as savings, consumption, investment, insurance, etc.
The credit use portrait features of the user are information of the loan of the user, such as the bar, the flower bar, the financial lever, the house loan and the like.
The marketing event time characteristic may be a time of release of the marketing event, such as a day of the week, a day of the month, a month of the year, a holiday, a workday, or a time interval and a frequency of release of the marketing event (such as a real-time frequency of the marketing event and an offline frequency of the marketing event), etc.
The marketing event frequency characteristic may be a frequency of placement of marketing events, such as frequent marketing events or intermittent marketing events, and the like.
The marketing equity feature may be a marketing equity related feature such as equity name, content, category, delivery channel, etc.
After the feature vector of the FTRL model is determined, the branch model may be trained based on the training sample data to determine a weight value of the feature vector.
In order to avoid larger deviation between the expected branch rate of the marketing equity determined by the branch model and the actual branch rate of the marketing equity, the embodiment of the application can take the average value of the marketing equity aiming at all training sample data as the predicted branch rate of the marketing equity.
Meanwhile, the accuracy of the support model can be further verified. For example, prior to performing step 104, the test sample data support model is used to perform a test, and the accuracy of the support model is evaluated based on the test result (e.g., an indicator of the area under the AUC curve of the test result) to adjust the parameters of the support model.
As an exemplary introduction, the embodiment of the application can judge whether the branch model is fitted or not based on the accuracy of the test result and the accuracy of the training result obtained after the branch model is trained;
if the accuracy of the training result is higher than that of the test result and the difference value of the training result and the test result exceeds or is equal to a preset threshold value, the test result and the training result are proved to have larger deviation, and the fact that the branch model is fitted is confirmed. At this time, the support model needs to be adjusted to reduce the error of the over-fitting.
Specifically, the present embodiment may solve the overfitting problem in the following manner:
mode one:
and removing the feature vector of the branch model, the occurrence number of which is smaller than or equal to a preset threshold value, in the training sample data, and then training the branch model again based on the training sample data.
The neural network structure of the support model can be simplified, and the problem that the support model is fitted after training due to excessive complexity of the internal neural network structure is avoided.
Mode two:
based on priori knowledge, regularization is performed on the partial feature vectors of the support model (for example, the weights of the partial feature vectors of the support model are directly determined by adopting an L1 regularization method or an L2 regularization method). The training model is then retrained based on the training sample data.
In the second mode, the regularized feature vector is used as a constraint condition for retraining the support model, so that an error function used for training is more prone to selecting a gradient reduction direction meeting the constraint, the training effect of the support model is finally enabled to be closer to priori knowledge, and the problem of over fitting after training is avoided.
Mode three:
retraining the branch model according to a dropout strategy based on training sample data;
in the third mode, under the dropout strategy, the feature vectors of the support model are randomly activated in each training round, so that the influence among the feature vectors in the training process is eliminated to a certain extent, and the support model reduces the fitting error after retraining.
Mode four:
and after the training times are adjusted, retraining the support model based on training sample data.
In general, training can be stopped when the model accuracy cannot be effectively improved after training. Through multiple practices, the optimization benefit starts to be obviously reduced when the training times reach 1.5-2 times of the number of the training sample data, so that the adjusted training times are preferably not more than 1.5-2 times of the number of the training sample data.
The fourth mode can avoid that excessive training aggravates errors caused by fitting.
In addition, the embodiment can also perform offline evaluation on the utilization rate based on the offline evaluation sample data, and optimize parameters of the utilization model according to the offline evaluation result. Since the offline evaluation and the test evaluation principle are the same, the description thereof will not be repeated here.
And after the supporting model is finally constructed, the predicted supporting rate of the marketing rights and interests can be obtained through the supporting model.
And then, selecting a target marketing benefit matched with the user from the marketing benefit groups corresponding to each user by adopting a grouping knapsack algorithm.
By way of exemplary introduction, assuming a total number of users of M, a category of marketing equity of K, a total marketing equity of N, a number of $n per marketing equity regardless of marketing equity inventory i (i=1, 2, … …, K) infinity, cost per equity c i (i＝1,2,……,K)。
Based on the principle of packet knapsack, users can be divided into M groups, namely each user is regarded as a packet, and each packet contains all kinds of marketing rights, namely K different kinds of marketing rights. Then the packet in the packet knapsack algorithm, i.e. user, the item in each packet, i.e. prize (marketing equity), the value of the item in each packet is pij (the rate of the user i corresponding to the marketing equity j), if the upper limit of the average marketing cost of the user is C, the total knapsack capacity is C x M, and if the marketing equity is chosen as x ij (whether user i corresponds to marketing equity j selected);
according to the formulaThe target marketing rights of each user can be obtained.
Wherein, based on the definition of the packet backpack, the above formula needs to obey the following constraints:
the above is an introduction to the delivery method of the present embodiment. It should be noted that, in the embodiment, the deep learning method for branch rate prediction may be replaced by other branch models, so long as the regression models considering the user features and the marketing benefit features of the same dimension can make the prediction in principle, the only difference is the accuracy and stability of the deep model in the big data scene, and the prediction results of the branch models may be the scheme of the embodiment of the present application.
Corresponding to the above method for delivering the marketing rights, as shown in fig. 4, the embodiment of the present application further provides a device 400 for delivering the marketing rights, including:
the grouping module 41 groups the marketing interests based on the number of target user groups of the marketing interests, wherein each user of the target user groups corresponds to one marketing interest group, and any two marketing interests in the marketing interest groups with the marketing interests greater than 1 are mutually exclusive;
a selection module 42, based on the upper limit of the marketing cost of the target user group and the predicted branch rate corresponding to each marketing equity, for selecting a target marketing equity matched with the user from the marketing equity group corresponding to each user according to a policy that the total branch rate of the target user group is the largest;
and the delivering module 43 is used for delivering the matched target marketing rights to the users in the target user group respectively.
The throwing device provided by the embodiment of the application can individually throw the marketing benefits with high utilization rate for different users on the premise of not exceeding the upper limit of the marketing cost, thereby realizing the maximized marketing benefits. Because the upper limit of the marketing cost is used as a constraint condition of release, a similar linear mathematical relationship is avoided between the marketing cost and the predicted branch rate, so that in practical application, the weight parameters are not required to be additionally configured for the upper limit and the predicted branch rate, and the marketing cost of a marketing activity is determined, so that the marketing cost is matched with the proper marketing rights and interests for different users.
The selection module 42 specifically uses the marketing rights as the items in the knapsack algorithm, uses the marketing cost of the marketing rights as the cost in the knapsack algorithm, uses the predicted utilization rate corresponding to the marketing rights as the price in the knapsack algorithm, uses the upper limit of the marketing cost of the target user group as the knapsack capacity in the knapsack algorithm, and solves the target marketing rights corresponding to each user in the target user group through the knapsack grouping algorithm.
Wherein the number of each marketing equity is set to infinity; or, the number of each marketing right is set to be a preset value, and the number of different marketing rights is the same or different.
Optionally, the selection module 42 is further configured to: and inputting the user portrait data of the users in the marketing rights and the target user group into a preset support model to obtain the predicted support rate corresponding to the marketing rights.
Optionally, the support model is trained based on training sample data comprising user image features and marketing event features.
Wherein, the user portrait features include: user identity portrayal features, user property portrayal features, user credit usage portrayal features;
the marketing event feature comprises: marketing event time characteristics and marketing event frequency characteristics.
Optionally, the throwing device of the embodiment of the present application further includes:
the test module is used for inputting test sample data into the support model to obtain a test result;
the judging module is used for judging whether the branch model is fitted or not based on the accuracy of the test result and the accuracy of a training result obtained after the branch model is trained;
and the training module retrains the branch model if the branch model is fitted so as to reduce the error of the fit of the branch model.
The training module specifically comprises any of the following units:
the first training unit is used for removing feature vectors of which the occurrence times of the branch model in training sample data are smaller than or equal to a preset threshold value, and then retraining the branch model based on the training sample data.
And the second training unit is used for regularizing part of the feature vectors of the branch model, and then retraining the branch model based on training sample data.
The third training unit is used for retraining the branch model according to a dropout strategy based on training sample data; under the dropout strategy, the feature vector of the support model is randomly activated in each training round.
Obviously, the throwing device of the embodiment of the application can be used as an execution main body of the throwing method of the marketing rights, so that the technical effect achieved by the throwing method can be achieved, and the throwing device of the embodiment of the application can be achieved as well. For example, the delivery device of the embodiment of the present application may implement the functions of the delivery method shown in fig. 1 to 3.
Fig. 5 is a schematic structural view of an electronic device according to an embodiment of the present application. Referring to fig. 5, at the hardware level, the electronic device includes a processor, and optionally an internal bus, a network interface, and a memory. The Memory may include a Memory, such as a Random-Access Memory (RAM), and may further include a non-volatile Memory (non-volatile Memory), such as at least 1 disk Memory. Of course, the electronic device may also include hardware required for other services.
The processor, network interface, and memory may be interconnected by an internal bus, which may be an ISA (Industry Standard Architecture ) bus, a PCI (Peripheral Component Interconnect, peripheral component interconnect standard) bus, or EISA (Extended Industry Standard Architecture ) bus, among others. The buses may be classified as address buses, data buses, control buses, etc. For ease of illustration, only one bi-directional arrow is shown in FIG. 5, but not only one bus or type of bus.
And the memory is used for storing programs. In particular, the program may include program code including computer-operating instructions. The memory may include memory and non-volatile storage and provide instructions and data to the processor.
The processor reads the corresponding computer program from the nonvolatile memory into the memory and then runs the computer program to form the multimedia playing device on a logic level. The processor is used for executing the programs stored in the memory and is specifically used for executing the following operations:
grouping the marketing interests based on the number of target user groups of the marketing interests, wherein each user of the target user groups corresponds to one marketing interest group, and any two marketing interests in the marketing interest groups with the marketing interests greater than 1 are mutually exclusive;
selecting a target marketing benefit matched with the user from a marketing benefit group corresponding to each user according to a strategy of maximum total branching rate of the target user group based on the upper limit of marketing cost of the target user group and the predicted branching rate corresponding to each marketing benefit;
and respectively throwing matched target marketing benefits to users in the target user group.
The method performed by the electronic device disclosed in the embodiment of fig. 1 of the present application may be applied to a processor or implemented by a processor. The processor may be an integrated circuit chip having signal processing capabilities. In implementation, the steps of the above method may be performed by integrated logic circuits of hardware in a processor or by instructions in the form of software. The processor may be a general-purpose processor, including a central processing unit (Central Processing Unit, CPU), a network processor (Network Processor, NP), etc.; but also digital signal processors (Digital Signal Processor, DSP), application specific integrated circuits (Application Specific Integrated Circuit, ASIC), field programmable gate arrays (Field-Programmable Gate Array, FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components. The disclosed methods, steps, and logic blocks in the embodiments of the present application may be implemented or performed. A general purpose processor may be a microprocessor or the processor may be any conventional processor or the like. The steps of the method disclosed in connection with the embodiments of the present application may be embodied directly in the execution of a hardware decoding processor, or in the execution of a combination of hardware and software modules in a decoding processor. The software modules may be located in a random access memory, flash memory, read only memory, programmable read only memory, or electrically erasable programmable memory, registers, etc. as well known in the art. The storage medium is located in a memory, and the processor reads the information in the memory and, in combination with its hardware, performs the steps of the above method.
The electronic device may also execute the method of fig. 1 and implement the functions of the delivery device in the embodiments shown in fig. 1-3, and the embodiments of the present application are not described herein again.
Of course, other implementations, such as a logic device or a combination of hardware and software, are not excluded from the electronic device of the present application, that is, the execution subject of the following processing flows is not limited to each logic unit, but may be hardware or a logic device.
The embodiments of the present application also provide a computer-readable storage medium storing one or more programs, the one or more programs comprising instructions, which when executed by a portable electronic device comprising a plurality of application programs, enable the portable electronic device to perform the method of the embodiment of fig. 1, and in particular to perform the operations of:
grouping the marketing interests based on the number of target user groups of the marketing interests, wherein each user of the target user groups corresponds to one marketing interest group, and any two marketing interests in the marketing interest groups with the marketing interests greater than 1 are mutually exclusive;
selecting a target marketing benefit matched with the user from a marketing benefit group corresponding to each user according to a strategy of maximum total branching rate of the target user group based on the upper limit of marketing cost of the target user group and the predicted branching rate corresponding to each marketing benefit;
and respectively throwing matched target marketing benefits to users in the target user group.
Computer readable media, including both non-transitory and non-transitory, removable and non-removable media, may implement information storage by any method or technology. The information may be computer readable instructions, data structures, modules of a program, or other data. Examples of storage media for a computer include, but are not limited to, phase change memory (PRAM), static Random Access Memory (SRAM), dynamic Random Access Memory (DRAM), other types of Random Access Memory (RAM), read Only Memory (ROM), electrically Erasable Programmable Read Only Memory (EEPROM), flash memory or other memory technology, compact disc read only memory (CD-ROM), digital Versatile Discs (DVD) or other optical storage, magnetic cassettes, magnetic tape magnetic disk storage or other magnetic storage devices, or any other non-transmission medium, which can be used to store information that can be accessed by a computing device. Computer-readable media, as defined herein, does not include transitory computer-readable media (transmission media), such as modulated data signals and carrier waves.
It should be understood that when the computer program in the computer readable storage medium of the embodiment of the present application is executed by the processor, the method of delivering shown in fig. 1 can be implemented, and the functions of the delivering device shown in fig. 1 to 3 are implemented, which will not be described herein.
In summary, the foregoing description is only of the preferred embodiments of the present application, and is not intended to limit the scope of the present application. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present application should be included in the protection scope of the present application.
It should also be noted that 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 one … …" does not exclude the presence of other like elements in a process, method, article or apparatus that comprises the element.
In this specification, each embodiment is described in a progressive manner, and identical and similar parts of each embodiment are all referred to each other, and each embodiment mainly describes differences from other embodiments. In particular, for system embodiments, since they are substantially similar to method embodiments, the description is relatively simple, as relevant to see a section of the description of method embodiments.
Claims (9)
1. A method of delivering marketing rights, comprising:
grouping marketing benefits based on the number of target user groups of the marketing benefits, wherein each user of the target user groups corresponds to one marketing benefit group, the marketing benefits contained in the marketing benefit groups of each user depend on a marketing strategy, and any two marketing benefits in the marketing benefit groups with the marketing benefits greater than 1 are mutually exclusive;
selecting a target marketing benefit matched with the user from a marketing benefit group corresponding to each user according to a strategy of maximum total branching rate of the target user group based on the upper limit of marketing cost of the target user group and the predicted branching rate corresponding to each marketing benefit;
respectively putting matched target marketing interests to users in the target user group;
based on the upper limit of the marketing cost of the target user group and the predicted branch rate corresponding to each marketing equity, selecting the target marketing equity matched with the user from the marketing equity group corresponding to each user according to the strategy of the maximum total branch rate of the target user group, wherein the method comprises the following steps:
taking the marketing rights and interests as articles in a grouped knapsack algorithm, taking the marketing cost of the marketing rights and interests as the cost in the grouped knapsack algorithm, taking the predicted utilization rate corresponding to the marketing rights and interests as the price value in the grouped knapsack algorithm, taking the upper limit of the marketing cost of the target user group as the knapsack capacity in the knapsack algorithm, and solving the target marketing rights and interests corresponding to each user in the target user group through the knapsack grouping algorithm; and
inputting the user portrait data of the users in the marketing rights and the target user group to a preset support model to obtain a predicted support rate corresponding to the marketing rights; the support model is obtained by training based on training sample data containing user image features and marketing event features; the user portrayal feature comprises: user identity portrayal features, user property portrayal features, user credit usage portrayal features; the marketing event feature comprises: marketing event time characteristics and marketing event frequency characteristics; the marketing event time features include a time of release of a marketing event, an event interval of release of a marketing event, and a frequency of release of a marketing event.
2. The method of delivery according to claim 1,
the number of each marketing benefit is set to infinity; or alternatively
The number of each marketing benefit is set to a preset value, and the number of different marketing benefits is the same or different.
3. The delivery method of claim 1, further comprising, prior to inputting the marketing equity and user portrayal data of the users in the target user group to a pre-set support model:
inputting test sample data into the support model to obtain a test result;
judging whether the branch model is fitted or not based on the accuracy of the test result and the accuracy of a training result obtained after the branch model is trained;
if yes, retraining the support model to reduce the error of overfitting of the support model.
4. The method of claim 3, wherein,
retraining the support model, comprising:
and removing the feature vector of the branch model, the occurrence number of which is smaller than or equal to a preset threshold value, in the training sample data, and then retraining the branch model based on the training sample data.
5. The method of claim 3, wherein,
retraining the support model further includes:
and regularizing partial feature vectors of the branch model, and then retraining the branch model based on training sample data.
6. The method of claim 3, wherein,
retraining the support model further includes:
retraining the branch model according to a dropout strategy based on training sample data; under the dropout strategy, the feature vectors of the support model are randomly activated in each round of training.
7. A marketing rights delivery device comprising:
the grouping module is used for grouping the marketing benefits based on the number of the target user groups of the marketing benefits, each user of the target user groups corresponds to one marketing benefit group, the marketing benefits contained in the marketing benefit groups of each user depend on the marketing strategy, and any two marketing benefits in the marketing benefit groups with the marketing benefits greater than 1 are mutually exclusive;
the selection module is used for selecting a target marketing benefit matched with the user from marketing benefit groups corresponding to each user according to a strategy of maximum total branching rate of the target user group based on the upper limit of marketing cost of the target user group and the predicted branching rate corresponding to each marketing benefit;
the delivery module is used for respectively delivering matched target marketing rights and interests to users in the target user group;
the method comprises the steps that a selection module specifically takes marketing rights and interests as articles in a packet knapsack algorithm, marketing cost of the marketing rights and interests as cost in the packet knapsack algorithm, predicted utilization rate corresponding to the marketing rights and interests as price value in the packet knapsack algorithm, upper limit of marketing cost of a target user group as knapsack capacity in the knapsack algorithm, and target marketing rights and interests corresponding to each user in the target user group are solved through the knapsack packet algorithm; and
inputting the user portrait data of the users in the marketing rights and the target user group to a preset support model to obtain a predicted support rate corresponding to the marketing rights; the support model is obtained by training based on training sample data containing user image features and marketing event features; the user portrayal feature comprises: user identity portrayal features, user property portrayal features, user credit usage portrayal features; the marketing event feature comprises: marketing event time characteristics and marketing event frequency characteristics; the marketing event time features include a time of release of a marketing event, an event interval of release of a marketing event, and a frequency of release of a marketing event.
8. An electronic device includes: a memory, a processor, and a computer program stored on the memory and executable on the processor, the computer program being executed by the processor:
grouping marketing benefits based on the number of target user groups of the marketing benefits, wherein each user of the target user groups corresponds to one marketing benefit group, the marketing benefits contained in the marketing benefit groups of each user depend on a marketing strategy, and any two marketing benefits in the marketing benefit groups with the marketing benefits greater than 1 are mutually exclusive;
selecting a target marketing benefit matched with the user from a marketing benefit group corresponding to each user according to a strategy of maximum total branching rate of the target user group based on the upper limit of marketing cost of the target user group and the predicted branching rate corresponding to each marketing benefit;
respectively putting matched target marketing interests to users in the target user group;
taking the marketing rights and interests as articles in a grouped knapsack algorithm, taking the marketing cost of the marketing rights and interests as the cost in the grouped knapsack algorithm, taking the predicted utilization rate corresponding to the marketing rights and interests as the price value in the grouped knapsack algorithm, taking the upper limit of the marketing cost of the target user group as the knapsack capacity in the knapsack algorithm, and solving the target marketing rights and interests corresponding to each user in the target user group through the knapsack grouping algorithm; and
inputting the user portrait data of the users in the marketing rights and the target user group to a preset support model to obtain a predicted support rate corresponding to the marketing rights; the support model is obtained by training based on training sample data containing user image features and marketing event features; the user portrayal feature comprises: user identity portrayal features, user property portrayal features, user credit usage portrayal features; the marketing event feature comprises: marketing event time characteristics and marketing event frequency characteristics; the marketing event time features include a time of release of a marketing event, an event interval of release of a marketing event, and a frequency of release of a marketing event.
9. A computer readable storage medium having stored thereon a computer program which when executed by a processor performs the steps of:
grouping marketing benefits based on the number of target user groups of the marketing benefits, wherein each user of the target user groups corresponds to one marketing benefit group, the marketing benefits contained in the marketing benefit groups of each user depend on a marketing strategy, and any two marketing benefits in the marketing benefit groups with the marketing benefits greater than 1 are mutually exclusive;
selecting a target marketing benefit matched with the user from a marketing benefit group corresponding to each user according to a strategy of maximum total branching rate of the target user group based on the upper limit of marketing cost of the target user group and the predicted branching rate corresponding to each marketing benefit;
respectively putting matched target marketing interests to users in the target user group;
taking the marketing rights and interests as articles in a grouped knapsack algorithm, taking the marketing cost of the marketing rights and interests as the cost in the grouped knapsack algorithm, taking the predicted utilization rate corresponding to the marketing rights and interests as the price value in the grouped knapsack algorithm, taking the upper limit of the marketing cost of the target user group as the knapsack capacity in the knapsack algorithm, and solving the target marketing rights and interests corresponding to each user in the target user group through the knapsack grouping algorithm; and
inputting the user portrait data of the users in the marketing rights and the target user group to a preset support model to obtain a predicted support rate corresponding to the marketing rights; the support model is obtained by training based on training sample data containing user image features and marketing event features; the user portrayal feature comprises: user identity portrayal features, user property portrayal features, user credit usage portrayal features; the marketing event feature comprises: marketing event time characteristics and marketing event frequency characteristics; the marketing event time features include a time of release of a marketing event, an event interval of release of a marketing event, and a frequency of release of a marketing event.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811381203.4A CN109598542B (en) | 2018-11-20 | 2018-11-20 | Marketing equity throwing method and device and electronic equipment |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811381203.4A CN109598542B (en) | 2018-11-20 | 2018-11-20 | Marketing equity throwing method and device and electronic equipment |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN109598542A CN109598542A (en) | 2019-04-09 |
| CN109598542B true CN109598542B (en) | 2023-10-27 |
Family
ID=65958716
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201811381203.4A Active CN109598542B (en) | 2018-11-20 | 2018-11-20 | Marketing equity throwing method and device and electronic equipment |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109598542B (en) |
Families Citing this family (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110909040B (en) * | 2019-11-08 | 2022-03-04 | 支付宝(杭州)信息技术有限公司 | Business delivery auxiliary method and device and electronic equipment |
| CN111651490A (en) * | 2020-06-04 | 2020-09-11 | 深圳前海微众银行股份有限公司 | Data screening method, device, equipment and computer storage medium |
| CN112581161B (en) * | 2020-12-04 | 2024-01-19 | 上海明略人工智能(集团)有限公司 | Object selection method and device, storage medium and electronic equipment |
| CN112669084B (en) * | 2020-12-31 | 2024-05-14 | 深圳前海微众银行股份有限公司 | Policy determination method, device and computer readable storage medium |
| CN113393269B (en) * | 2021-06-11 | 2024-03-15 | 上海明略人工智能(集团)有限公司 | Method and device for determining conversion rate of contact media, electronic equipment and storage medium |
| CN113902481B (en) * | 2021-10-14 | 2024-07-12 | 平安银行股份有限公司 | Rights and interests determining method, device, storage medium and apparatus |
| CN114266601A (en) * | 2021-12-24 | 2022-04-01 | 深圳前海微众银行股份有限公司 | Marketing strategy determination method and device, terminal equipment and storage medium |
| CN118333671B (en) * | 2024-06-14 | 2024-09-06 | 智者四海（北京）技术有限公司 | Marketing strategy pushing method, device, equipment and medium |
Citations (19)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2004090765A2 (en) * | 2003-04-14 | 2004-10-21 | Sap Ag | Predicting marketing campaigns using customer-specific response probabilities and response values |
| CN102904969A (en) * | 2012-11-13 | 2013-01-30 | 中国电子科技集团公司第二十八研究所 | Method for arranging information processing service in distributed cloud computing environment |
| CN105069662A (en) * | 2015-08-27 | 2015-11-18 | 浙江工业大学 | Network advertisement accurate putting method based on key words |
| CN105160546A (en) * | 2015-08-07 | 2015-12-16 | 北京思特奇信息技术股份有限公司 | Method and system for constructing and analyzing social network |
| KR20160056201A (en) * | 2014-11-11 | 2016-05-19 | 김영준 | Marketing System using User Selection Type Advertising Game Application based on Raising Simulation and Method therefor |
| CN105678580A (en) * | 2016-01-06 | 2016-06-15 | 北京京东尚科信息技术有限公司 | E-commerce platform and method for issuing coupons |
| CN106934646A (en) * | 2015-12-31 | 2017-07-07 | 阿里巴巴集团控股有限公司 | The method and apparatus that electronic coupons are delivered in marketing activity |
| CN107025578A (en) * | 2017-04-13 | 2017-08-08 | 上海艾德韦宣股份有限公司 | A kind of big data intelligent marketing system and marketing method |
| CN107038600A (en) * | 2017-02-23 | 2017-08-11 | 阿里巴巴集团控股有限公司 | The method and apparatus for providing rights and interests |
| CN107481054A (en) * | 2017-08-14 | 2017-12-15 | 携程计算机技术（上海）有限公司 | The push of hotel's favor information and device, electronic equipment, storage medium |
| CN107527232A (en) * | 2017-07-31 | 2017-12-29 | 广州点升信息技术有限公司 | Marketing platform |
| CN107578281A (en) * | 2017-08-31 | 2018-01-12 | 湖南大学 | User preferential certificate behavior prediction method and model building method under e-commerce environment |
| CN107679915A (en) * | 2017-09-30 | 2018-02-09 | 平安科技（深圳）有限公司 | Management method, device, equipment and the computer-readable storage medium of marketing activity |
| CN108305102A (en) * | 2018-01-30 | 2018-07-20 | 阿里巴巴集团控股有限公司 | Electronics red packet distribution method, device and client |
| CN108446984A (en) * | 2018-03-20 | 2018-08-24 | 张家林 | A kind of investment data management method and device |
| CN108550055A (en) * | 2018-04-16 | 2018-09-18 | 清华大学 | Transmitting advertisement information method and system based on geographical location |
| CN108647811A (en) * | 2018-04-26 | 2018-10-12 | 中国联合网络通信集团有限公司 | Predict that user buys method, apparatus, equipment and the storage medium of equity commodity |
| CN108681920A (en) * | 2018-05-14 | 2018-10-19 | 微梦创科网络科技（中国）有限公司 | The method and system launched based on advertising creative optimization advertisement |
| CN108764988A (en) * | 2018-05-21 | 2018-11-06 | 中国联合网络通信有限公司重庆市分公司 | A kind of marketing strategy put-on method and system |
Family Cites Families (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20020032629A1 (en) * | 2000-04-26 | 2002-03-14 | Siegel John M. | Ranking-based screening system and method for equity analysis |
| US20040204975A1 (en) * | 2003-04-14 | 2004-10-14 | Thomas Witting | Predicting marketing campaigns using customer-specific response probabilities and response values |
| US20040204973A1 (en) * | 2003-04-14 | 2004-10-14 | Thomas Witting | Assigning customers to activities in marketing campaigns |
-
2018
- 2018-11-20 CN CN201811381203.4A patent/CN109598542B/en active Active
Patent Citations (19)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2004090765A2 (en) * | 2003-04-14 | 2004-10-21 | Sap Ag | Predicting marketing campaigns using customer-specific response probabilities and response values |
| CN102904969A (en) * | 2012-11-13 | 2013-01-30 | 中国电子科技集团公司第二十八研究所 | Method for arranging information processing service in distributed cloud computing environment |
| KR20160056201A (en) * | 2014-11-11 | 2016-05-19 | 김영준 | Marketing System using User Selection Type Advertising Game Application based on Raising Simulation and Method therefor |
| CN105160546A (en) * | 2015-08-07 | 2015-12-16 | 北京思特奇信息技术股份有限公司 | Method and system for constructing and analyzing social network |
| CN105069662A (en) * | 2015-08-27 | 2015-11-18 | 浙江工业大学 | Network advertisement accurate putting method based on key words |
| CN106934646A (en) * | 2015-12-31 | 2017-07-07 | 阿里巴巴集团控股有限公司 | The method and apparatus that electronic coupons are delivered in marketing activity |
| CN105678580A (en) * | 2016-01-06 | 2016-06-15 | 北京京东尚科信息技术有限公司 | E-commerce platform and method for issuing coupons |
| CN107038600A (en) * | 2017-02-23 | 2017-08-11 | 阿里巴巴集团控股有限公司 | The method and apparatus for providing rights and interests |
| CN107025578A (en) * | 2017-04-13 | 2017-08-08 | 上海艾德韦宣股份有限公司 | A kind of big data intelligent marketing system and marketing method |
| CN107527232A (en) * | 2017-07-31 | 2017-12-29 | 广州点升信息技术有限公司 | Marketing platform |
| CN107481054A (en) * | 2017-08-14 | 2017-12-15 | 携程计算机技术（上海）有限公司 | The push of hotel's favor information and device, electronic equipment, storage medium |
| CN107578281A (en) * | 2017-08-31 | 2018-01-12 | 湖南大学 | User preferential certificate behavior prediction method and model building method under e-commerce environment |
| CN107679915A (en) * | 2017-09-30 | 2018-02-09 | 平安科技（深圳）有限公司 | Management method, device, equipment and the computer-readable storage medium of marketing activity |
| CN108305102A (en) * | 2018-01-30 | 2018-07-20 | 阿里巴巴集团控股有限公司 | Electronics red packet distribution method, device and client |
| CN108446984A (en) * | 2018-03-20 | 2018-08-24 | 张家林 | A kind of investment data management method and device |
| CN108550055A (en) * | 2018-04-16 | 2018-09-18 | 清华大学 | Transmitting advertisement information method and system based on geographical location |
| CN108647811A (en) * | 2018-04-26 | 2018-10-12 | 中国联合网络通信集团有限公司 | Predict that user buys method, apparatus, equipment and the storage medium of equity commodity |
| CN108681920A (en) * | 2018-05-14 | 2018-10-19 | 微梦创科网络科技（中国）有限公司 | The method and system launched based on advertising creative optimization advertisement |
| CN108764988A (en) * | 2018-05-21 | 2018-11-06 | 中国联合网络通信有限公司重庆市分公司 | A kind of marketing strategy put-on method and system |
Non-Patent Citations (4)
| Title |
|---|
| Bohyung Han ; .BranchOut: Regularization for Online Ensemble Tracking with Convolutional Neural Networks.《2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)》.2017, * |
| 汪长喜.贪心算法.《信息学、语言学、数学与逻辑一本通》.2018, * |
| 社会网络营销中基于成本控制的影响最大化问题研究;杨鸿超;《中国优秀硕士学位论文全文数据库经济与管理科学辑》;20130815;J157-46 * |
| 黄孝平.更好的优化和正则化.《当代机器深度学习方法与应用研究》.2017, * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN109598542A (en) | 2019-04-09 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109598542B (en) | Marketing equity throwing method and device and electronic equipment | |
| US20190035015A1 (en) | Method and apparatus for obtaining a stable credit score | |
| CN105975483A (en) | User preference-based message pushing method and platform | |
| CN110874491B (en) | Privacy data processing method and device based on machine learning and electronic equipment | |
| CN109493113A (en) | A kind of providing method and device of favor information | |
| Zhao et al. | Pricing decisions with reference price effect and risk preference customers | |
| US20140101012A1 (en) | Online catalogs and collaborative financial planning | |
| US20210192618A1 (en) | Fractional share system | |
| CN107679856A (en) | Service control method and device based on transaction | |
| CN108550046A (en) | A kind of resource and market recommendation method, apparatus and electronic equipment | |
| US20150178749A1 (en) | Methods, systems and computer readable media for predicting consumer purchase behavior | |
| CN106600415A (en) | Method and apparatus for determining business credit | |
| CN109697668A (en) | A kind of pricing method of credit product, device, equipment and storage medium | |
| US20170193596A1 (en) | System and Method for Providing a Financial Product Using a Customer Product Criteria | |
| US10304070B2 (en) | Systems and methods for reward prediction and offer selection | |
| US20160267499A1 (en) | Website personalization based on real-time visitor behavior | |
| CN111582872A (en) | Abnormal account detection model training method, abnormal account detection device and abnormal account detection equipment | |
| WO2019144808A1 (en) | Method and apparatus for determining false resource transfer, method and apparatus for determining false trading, and electronic device | |
| WO2020177477A1 (en) | Credit service recommendation method, apparatus, and device | |
| US20220044258A1 (en) | Initiating cardswap based on analytic model indicating third party card reissuance | |
| Dong et al. | Real-time Fraud Detection in e-Market Using Machine Learning Algorithms. | |
| US20240177184A1 (en) | Self-learning valuation and access to digital content | |
| CN114119168A (en) | Information pushing method and device | |
| CN110232150A (en) | A kind of Users'Data Analysis method, apparatus, readable storage medium storing program for executing and terminal device | |
| CN110060188B (en) | Nuclear body mode recommendation method and device and electronic equipment |
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 | ||
| TA01 | Transfer of patent application right | ||
| TA01 | Transfer of patent application right |
Effective date of registration: 20200923 Address after: Cayman Enterprise Centre, 27 Hospital Road, George Town, Grand Cayman, British Islands Applicant after: Innovative advanced technology Co.,Ltd. Address before: Cayman Enterprise Centre, 27 Hospital Road, George Town, Grand Cayman, British Islands Applicant before: Advanced innovation technology Co.,Ltd. Effective date of registration: 20200923 Address after: Cayman Enterprise Centre, 27 Hospital Road, George Town, Grand Cayman, British Islands Applicant after: Advanced innovation technology Co.,Ltd. Address before: A four-storey 847 mailbox in Grand Cayman Capital Building, British Cayman Islands Applicant before: Alibaba Group Holding Ltd. |
|
| GR01 | Patent grant | ||
| GR01 | Patent grant |